Accurate detection of fashion design attributes is essential for trend analyses and recommendation systems.Among these attributes,the neckline style plays a key role in shaping garment aesthetics.However,the presence ...Accurate detection of fashion design attributes is essential for trend analyses and recommendation systems.Among these attributes,the neckline style plays a key role in shaping garment aesthetics.However,the presence of complex backgrounds and varied body postures in real-world fashion images presents challenges for reliable neckline detection.To address this problem,this research builds a comprehensive fashion neckline database from online shop images and proposes an efficient fashion neckline detection model based on the YOLOv8 architecture(FN-YOLO).First,the proposed model incorporates a BiFormer attention mechanism into the backbone,enhancing its feature extraction capability.Second,a lightweight multi-level asymmetry detector head(LADH)is designed to replace the original head,effectively reducing the computational complexity and accelerating the detection speed.Last,the original loss function is replaced with Wise-IoU,which improves the localization accuracy of the detection box.The experimental results demonstrate that FN-YOLO achieves a mean average precision(mAP)of 81.7%,showing an absolute improvement of 3.9%over the original YOLOv8 model,and a detection speed of 215.6 frame/s,confirming its suitability for real-time applications in fashion neckline detection.展开更多
Recently,there has been a widespread application of deep learning in object detection with Synthetic Aperture Radar(SAR).The current algorithms based on Convolutional Neural Networks(CNN)often achieve good accuracy at...Recently,there has been a widespread application of deep learning in object detection with Synthetic Aperture Radar(SAR).The current algorithms based on Convolutional Neural Networks(CNN)often achieve good accuracy at the expense of more complex model structures and huge parameters,which poses a great challenge for real-time and accurate detection of multi-scale targets.To address these problems,we propose a lightweight real-time SAR ship object detector based on detection transformer(LSD-DETR)in this study.First,a lightweight backbone network LCNet containing a stem module and inverted residual structure is constructed to balance the inference speed and detection accuracy of model.Second,we design a transformer encoder with Cascaded Group Attention(CGA Encoder)to enrich the feature information of small targets in SAR images,which makes detection of small-sized ships more precise.Third,an efficient cross-scale feature fusion pyramid module(C3Het-FPN)is proposed through the lightweight units(C3Het)and the introduction of the weighted bidirectional feature pyramid(BiFPN)structure,which realizes the adaptive fusion of multi-scale features with fewer parameters.Ablation experiments and comparative experiments demonstrate the effectiveness of LSD-DETR.The model parameter of LSD-DETR is 8.8 M(only 20.6%of DETR),the model’s FPS reached 43.1,the average detection accuracy mAP50 on the SSDD and HRSID datasets reached 97.3%and 93.4%.Compared to advanced methods,the LSD-DETR can attain superior precision with fewer parameters,which enables accurate real-time object detection of multi-scale ships in SAR images.展开更多
In recent years,the country has spent significant workforce and material resources to prevent traffic accidents,particularly those caused by fatigued driving.The current studies mainly concentrate on driver physiologi...In recent years,the country has spent significant workforce and material resources to prevent traffic accidents,particularly those caused by fatigued driving.The current studies mainly concentrate on driver physiological signals,driving behavior,and vehicle information.However,most of the approaches are computationally intensive and inconvenient for real-time detection.Therefore,this paper designs a network that combines precision,speed and lightweight and proposes an algorithm for facial fatigue detection based on multi-feature fusion.Specifically,the face detection model takes YOLOv8(You Only Look Once version 8)as the basic framework,and replaces its backbone network with MobileNetv3.To focus on the significant regions in the image,CPCA(Channel Prior Convolution Attention)is adopted to enhance the network’s capacity for feature extraction.Meanwhile,the network training phase employs the Focal-EIOU(Focal and Efficient Intersection Over Union)loss function,which makes the network lightweight and increases the accuracy of target detection.Ultimately,the Dlib toolkit was employed to annotate 68 facial feature points.This study established an evaluation metric for facial fatigue and developed a novel fatigue detection algorithm to assess the driver’s condition.A series of comparative experiments were carried out on the self-built dataset.The suggested method’s mAP(mean Average Precision)values for object detection and fatigue detection are 96.71%and 95.75%,respectively,as well as the detection speed is 47 FPS(Frames Per Second).This method can balance the contradiction between computational complexity and model accuracy.Furthermore,it can be transplanted to NVIDIA Jetson Orin NX and quickly detect the driver’s state while maintaining a high degree of accuracy.It contributes to the development of automobile safety systems and reduces the occurrence of traffic accidents.展开更多
[Objective]The accurate identification of maize tassels is critical for the production of hybrid seed.Existing object detection models in complex farmland scenarios face limitations such as restricted data diversity,i...[Objective]The accurate identification of maize tassels is critical for the production of hybrid seed.Existing object detection models in complex farmland scenarios face limitations such as restricted data diversity,insufficient feature extraction,high computational load,and low detection efficiency.To address these challenges,a real-time field maize tassel detection model,LightTassel-YOLO(You Only Look Once)based on an improved YOLOv11n is proposed.The model is designed to quickly and accurately identify maize tassels,enabling efficient operation of detasseling unmanned aerial vehicles(UAVs)and reducing the impact of manual intervention.[Methods]Data was continuously collected during the tasseling stage of maize from 2023 to 2024 using UAVs,establishing a large-scale,high-quality maize tassel dataset that covered different maize tasseling stages,multiple varieties,varying altitudes,and diverse meteorological conditions.First,EfficientViT(Efficient vision transformer)was applied as the backbone network to enhance the ability to perceive information across multi-scale features.Second,the C2PSA-CPCA(Convolutional block with parallel spatial attention with channel prior convolutional attention)module was designed to dynamically assign attention weights to the channel and spatial dimensions of feature maps,effectively enhancing the network's capability to extract target features while reducing computational complexity.Finally,the C3k2-SCConv module was constructed to facilitate representative feature learning and achieve low-cost spatial feature reconstruction,thereby improving the model's detection accuracy.[Results and Discussions]The results demonstrated that LightTassel-YOLO provided a reliable method for maize tassel detection.The final model achieved an accuracy of 92.6%,a recall of 89.1%,and an AP@0.5 of 94.7%,representing improvements of 2.5,3.8 and 4.0 percentage points over the baseline model YOLOv11n,respectively.The model had only 3.23 M parameters and a computational cost of 6.7 GFLOPs.In addition,LightTassel-YOLO was compared with mainstream object detection algorithms such as Faster R-CNN,SSD,and multiple versions of the YOLO series.The results demonstrated that the proposed method outperformed these algorithms in overall performance and exhibits excellent adaptability in typical field scenarios.[Conclusions]The proposed method provides an effective theoretical framework for precise maize tassel monitoring and holds significant potential for advancing intelligent field management practices.展开更多
The paper puts forward a variance-time plots method based on slide-window mechanism tocalculate the Hurst parameter to detect Distribute Denial of Service(DDoS)attack in real time.Basedon fuzzy logic technology that c...The paper puts forward a variance-time plots method based on slide-window mechanism tocalculate the Hurst parameter to detect Distribute Denial of Service(DDoS)attack in real time.Basedon fuzzy logic technology that can adjust itself dynamically under the fuzzy rules,an intelligent DDoSjudgment mechanism is designed.This new method calculates the Hurst parameter quickly and detectsDDoS attack in real time.Through comparing the detecting technologies based on statistics andfeature-packet respectively under different experiments,it is found that the new method can identifythe change of the Hurst parameter resulting from DDoS attack traffic with different intensities,andintelligently judge DDoS attack self-adaptively in real time.展开更多
The real-time detection and instance segmentation of strawberries constitute fundamental components in the development of strawberry harvesting robots.Real-time identification of strawberries in an unstructured envi-r...The real-time detection and instance segmentation of strawberries constitute fundamental components in the development of strawberry harvesting robots.Real-time identification of strawberries in an unstructured envi-ronment is a challenging task.Current instance segmentation algorithms for strawberries suffer from issues such as poor real-time performance and low accuracy.To this end,the present study proposes an Efficient YOLACT(E-YOLACT)algorithm for strawberry detection and segmentation based on the YOLACT framework.The key enhancements of the E-YOLACT encompass the development of a lightweight attention mechanism,pyramid squeeze shuffle attention(PSSA),for efficient feature extraction.Additionally,an attention-guided context-feature pyramid network(AC-FPN)is employed instead of FPN to optimize the architecture’s performance.Furthermore,a feature-enhanced model(FEM)is introduced to enhance the prediction head’s capabilities,while efficient fast non-maximum suppression(EF-NMS)is devised to improve non-maximum suppression.The experimental results demonstrate that the E-YOLACT achieves a Box-mAP and Mask-mAP of 77.9 and 76.6,respectively,on the custom dataset.Moreover,it exhibits an impressive category accuracy of 93.5%.Notably,the E-YOLACT also demonstrates a remarkable real-time detection capability with a speed of 34.8 FPS.The method proposed in this article presents an efficient approach for the vision system of a strawberry-picking robot.展开更多
Lightning is a typical example of an instantaneous random point source target. It has close connection with severe convective phenomena such as a thunderstorm, whose distribution, variation, position and forecasting c...Lightning is a typical example of an instantaneous random point source target. It has close connection with severe convective phenomena such as a thunderstorm, whose distribution, variation, position and forecasting can be acquired through lightning observation. In this paper, we discuss the way to achieve instantaneous lightning signal intensification and detection from geostationary orbit by using the differences between the lightning signal and the slowly changing background noise such as that of cloud, land and ocean, combining three methods, spectral filtering, spatial filtering and background noise, enabling removal between frames. After six months of operation in orbit, lightning within the coverage of the Geostationary Lightning Imager was effectively detected, strongly supporting the case for shorttime and real-time early warning, forecasting and tracking of severe convective phenomena in China.展开更多
This paper presents a vision-based crack detection approach for concrete bridge decks using an integrated one-dimensional convolutional neural network(1D-CNN)and long short-term memory(LSTM)method in the image frequen...This paper presents a vision-based crack detection approach for concrete bridge decks using an integrated one-dimensional convolutional neural network(1D-CNN)and long short-term memory(LSTM)method in the image frequency domain.The so-called 1D-CNN-LSTM algorithm is trained using thousands of images of cracked and non-cracked concrete bridge decks.In order to improve the training efficiency,images are first transformed into the frequency domain during a preprocessing phase.The algorithm is then calibrated using the flattened frequency data.LSTM is used to improve the performance of the developed network for long sequence data.The accuracy of the developed model is 99.05%,98.9%,and 99.25%,respectively,for training,validation,and testing data.An implementation framework is further developed for future application of the trained model for large-scale images.The proposed 1D-CNN-LSTM method exhibits superior performance in comparison with existing deep learning methods in terms of accuracy and computation time.The fast implementation of the 1D-CNN-LSTM algorithm makes it a promising tool for real-time crack detection.展开更多
Implantable bioelectronics for analyzing physiological biomarkers has recently been recognized as a promising technique in medical treatment or diagnostics. In this study, we developed a self-powered implantable skinl...Implantable bioelectronics for analyzing physiological biomarkers has recently been recognized as a promising technique in medical treatment or diagnostics. In this study, we developed a self-powered implantable skinlike glucometer for real-time detection of blood glucose level in vivo. Based on the piezo-enzymatic-reaction coupling effect of GOx@ZnO nanowire, the device under an applied deformation can actively output piezoelectric signal containing the glucose-detecting information. No external electricity power source or battery is needed for this device, and the outputting piezoelectric voltage acts as both the biosensing signal and electricity power. A practical application of the skin-like glucometer implanted in mouse body for detecting blood glucose level has been simply demonstrated. These results provide a new technique path for diabetes prophylaxis and treatment.展开更多
Mercury(Hg^(2+)),one of the most dangerous toxins in water,is a heavy metal that causes organ damage from both short-term and chronic exposure.Conventional methods for detecting mercury such as atomic absorption spect...Mercury(Hg^(2+)),one of the most dangerous toxins in water,is a heavy metal that causes organ damage from both short-term and chronic exposure.Conventional methods for detecting mercury such as atomic absorption spectrometry or Raman spectroscopy require bulky equipment with complicated procedures.In this work,we fabricated a highly sensitive,real-time thin-film sensor based on vertically aligned rhenium disulfide(ReS_(2)).Its outstanding large surface area and the unique electronic appearance of its layered architecture make a ReS_(2) nanosheet a strong contender for such an application.The sensor exhibited a fast response speed(<2 s)to Hg^(2+)and an ultralow detection limit of 4 nM,which is significantly less than that of the U.S.Environmental Protection Agency's(U.S.EPA)allowed utmost contamination limit for Hg^(2+)in drinking water(10 nM).It also exhibited strong selectivity for Hg^(2+)against other metal ions such as Na^(+),Zn^(2+),Fe^(3+),Cu^(2+),Ca^(2+),Ni^(2+),Ag+,Cd^(2+),Fe^(2+),and Pb^(2+).Because this nanosheet can be replaced with any secondary substrate and possibly patterned into a microscale size,the sensor can be integrated into multiple platforms such as portable devices or sensor nodes in a grid network.展开更多
Cervical cancer remains a critically important problem for women, especially those women in the developing world where the case-fatality rate is high. There are an estimated 528,000 cases and 266,000 deaths worldwide....Cervical cancer remains a critically important problem for women, especially those women in the developing world where the case-fatality rate is high. There are an estimated 528,000 cases and 266,000 deaths worldwide. Established screening and detection programs in the developed world have lowered the mortality from 40/100,000 to 2/100,000 over the last 60 years. The standard of care has been and continues to be: a screening Papanicolaou smear with or without Human Papilloma Virus (HPV) testing;followed by colposcopy and biopsies and if the smear is abnormal;and followed by treatment if the biopsies show high grade disease (cervical intraepithelial neoplasia (CIN) grades 2 and 3 and Carcinoma-in-situ). Low grade lesions (Pap smears with Atypical Cells of Uncertain Significance (ASCUS), Low Grade Squamous Intraepithelial Lesions (LGSIL), biopsies showing HPV changes or showing CIN 1);are usually followed for two years and then treated if persistent. Treatment can be performed with loop excision, LASER, or cryotherapy. Loop excision yields a specimen which can be reviewed to establish the diagnosis more accurately. LASER vaporizes the lesion and cryotherapy leads to tissue destruction. Under long term study;loop excision, LASER, and cryotherapy have the same rate of cure. The standard of care is expensive and takes 6 - 12 weeks for the individual patient. During the last twenty years, new technologies that can view the cervix and even image the cervix with cellular resolution have been developed. These technologies could lead to a new paradigm in which diagnosis and treatment occurs at a single visit. These technologies include fluorescence and reflectance spectroscopy (probe or wide-field, whole cervix scanning approaches) and fluorescence confocal endomicroscopy or high resolution micro-endoscopy. Both technologies have received Federal Drug Administration (FDA) and have been commercialized. Research trials continue to show their remarkable performance. These technologies are reviewed and clinical trials are summarized. Emerging technologies are coming along that may compete with those already approved and include optical coherence tomography, optical coherence tomography with autofluorescence, diffuse optical microscopy, and dual mode micro-endoscopy. These technologies are also reviewed and where available, clinical data is reported. Optical technologies are ready to diffuse into clinical practice because they will save money and 3 or 4 visits in the developed world and offer the same standard of care to the developing world where more cervical cancer exists.展开更多
An approach to detection of moving objects in video sequences, with application to video surveillance is presented. The algorithm combines two kinds of change points, which are detected from the region-based frame dif...An approach to detection of moving objects in video sequences, with application to video surveillance is presented. The algorithm combines two kinds of change points, which are detected from the region-based frame difference and adjusted background subtraction. An adaptive threshold technique is employed to automatically choose the threshold value to segment the moving objects from the still background. And experiment results show that the algorithm is effective and efficient in practical situations. Furthermore, the algorithm is robust to the effects of the changing of lighting condition and can be applied for video surveillance system.展开更多
Active noise controls are used in a wide field of applications to cancel out unwanted surrounding noise. Control systems based on the feedback structure however have the disadvantage that they may become unstable duri...Active noise controls are used in a wide field of applications to cancel out unwanted surrounding noise. Control systems based on the feedback structure however have the disadvantage that they may become unstable during run-time due to changes in the control path—in this context including the listener’s ear. Especially when applied to active noise cancellation (ANC) headphones, the risk of instability is associated with the risk of harmful influence on the listener’s ear, which is exposed to the speaker in striking distance. This paper discusses several methods to enable the analysis of a feedback ANC system during run-time to immediately detect instability. Finally, a solution is proposed, which identifies the open loop behavior parametrically by means of an adaptive filter to subsequently evaluate the coefficients regarding stability.展开更多
In this paper, we proposed a new concept: depth of drowsiness, which can more precisely describe the drowsiness than existing binary description. A set of effective markers for drowsiness: normalized band norm was suc...In this paper, we proposed a new concept: depth of drowsiness, which can more precisely describe the drowsiness than existing binary description. A set of effective markers for drowsiness: normalized band norm was successfully developed. These markers are invariant from voltage amplitude of brain waves, eliminating the need for calibrating the voltage output of the brain-computer interface devices. A new polling algorithm was designed and implemented for computing the depth of drowsiness. The time cost of data acquisition and processing for each estimate is about one second, which is well suited for real-time applications. Test results with a portable brain-computer interface device show that the depth of drowsiness computed by the method in this paper is generally invariant from ages of test subjects and sensor channels (P3 and C4). The comparison between experiment and computing results indicate that the new method is noticeably better than one of the recent methods in terms of accuracy for predicting the drowsiness.展开更多
As a fundamental component in computer vision,edges can be categorized into four types based on discontinuities in reflectance,illumination,surface normal,or depth.While deep CNNs have significantly advanced generic e...As a fundamental component in computer vision,edges can be categorized into four types based on discontinuities in reflectance,illumination,surface normal,or depth.While deep CNNs have significantly advanced generic edge detection,real-time multi-class semantic edge detection under resource constraints remains challenging.To address this,we propose a lightweight framework based on PiDiNet that enables fine-grained semantic edge detection.Our model simultaneously predicts background and four edge categories from full-resolution inputs,balancing accuracy and efficiency.Key contributions include:a multi-channel output structure expanding binary edge prediction to five classes,supported by a deep supervision mechanism;a dynamic class-balancing strategy combining adaptive weighting with physical priors to handle extreme class imbalance;and maintained architectural efficiency enabling real-time inference.Extensive evaluations on BSDS-RIND show our approach achieves accuracy competitive with state-of-the-art methods while operating in real time.展开更多
Online examinations have become a dominant assessment mode,increasing concerns over academic integrity.To address the critical challenge of detecting cheating behaviours,this study proposes a hybrid deep learning appr...Online examinations have become a dominant assessment mode,increasing concerns over academic integrity.To address the critical challenge of detecting cheating behaviours,this study proposes a hybrid deep learning approach that combines visual detection and temporal behaviour classification.The methodology utilises object detection models—You Only Look Once(YOLOv12),Faster Region-based Convolutional Neural Network(RCNN),and Single Shot Detector(SSD)MobileNet—integrated with classification models such as Convolutional Neural Networks(CNN),Bidirectional Gated Recurrent Unit(Bi-GRU),and CNN-LSTM(Long Short-Term Memory).Two distinct datasets were used:the Online Exam Proctoring(EOP)dataset from Michigan State University and the School of Computer Science,Duy Tan Unievrsity(SCS-DTU)dataset collected in a controlled classroom setting.A diverse set of cheating behaviours,including book usage,unauthorised interaction,internet access,and mobile phone use,was categorised.Comprehensive experiments evaluated the models based on accuracy,precision,recall,training time,inference speed,and memory usage.We evaluate nine detector-classifier pairings under a unified budget and score them via a calibrated harmonic mean of detection and classification accuracies,enabling deployment-oriented selection under latency and memory constraints.Macro-Precision/Recall/F1 and Receiver Operating Characteristic-Area Under the Curve(ROC-AUC)are reported for the top configurations,revealing consistent advantages of object-centric pipelines for fine-grained cheating cues.The highest overall score is achieved by YOLOv12+CNN(97.15%accuracy),while SSD-MobileNet+CNN provides the best speed-efficiency trade-off for edge devices.This research provides valuable insights into selecting and deploying appropriate deep learning models for maintaining exam integrity under varying resource constraints.展开更多
To address critical challenges in nighttime ship detection—high small-target missed detection(over 20%),insufficient lightweighting,and limited generalization due to scarce,low-quality datasets—this study proposes a...To address critical challenges in nighttime ship detection—high small-target missed detection(over 20%),insufficient lightweighting,and limited generalization due to scarce,low-quality datasets—this study proposes a systematic solution.First,a high-quality Night-Ships dataset is constructed via CycleGAN-based day-night transfer,combined with a dual-threshold cleaning strategy(Laplacian variance sharpness filtering and brightness-color deviation screening).Second,a Cross-stage Lightweight Fusion-You Only Look Once version 8(CLF-YOLOv8)is proposed with key improvements:the Neck network is reconstructed by replacing Cross Stage Partial(CSP)structure with the Cross Stage Partial Multi-Scale Convolutional Block(CSP-MSCB)and integrating Bidirectional Feature Pyramid Network(BiFPN)for weighted multi-scale fusion to enhance small-target detection;a Lightweight Shared Convolutional and Separated Batch Normalization Detection-Head(LSCSBD-Head)with shared convolutions and layer-wise Batch Normalization(BN)reduces parameters to 1.8M(42% fewer than YOLOv8n);and the FocalMinimum Point Distance Intersection over Union(Focal-MPDIoU)loss combines Minimum Point Distance Intersection over Union(MPDIoU)geometric constraints and Focal weighting to optimize low-overlap targets.Experiments show CLFYOLOv8 achieves 97.6%mAP@0.5(0.7% higher than YOLOv8n)with 1.8 M parameters,outperforming mainstream models in small-target detection,overlapping target discrimination,and adaptability to complex lighting.展开更多
Ensuring the reliability of power transmission networks depends heavily on the early detection of faults in key components such as insulators,which serve both mechanical and electrical functions.Even a single defectiv...Ensuring the reliability of power transmission networks depends heavily on the early detection of faults in key components such as insulators,which serve both mechanical and electrical functions.Even a single defective insulator can lead to equipment breakdown,costly service interruptions,and increased maintenance demands.While unmanned aerial vehicles(UAVs)enable rapid and cost-effective collection of high-resolution imagery,accurate defect identification remains challenging due to cluttered backgrounds,variable lighting,and the diverse appearance of faults.To address these issues,we introduce a real-time inspection framework that integrates an enhanced YOLOv10 detector with a Hybrid Quantum-Enhanced Graph Neural Network(HQGNN).The YOLOv10 module,fine-tuned on domainspecific UAV datasets,improves detection precision,while the HQGNN ensures multi-object tracking and temporal consistency across video frames.This synergy enables reliable and efficient identification of faulty insulators under complex environmental conditions.Experimental results show that the proposed YOLOv10-HQGNN model surpasses existing methods across all metrics,achieving Recall of 0.85 and Average Precision(AP)of 0.83,with clear gains in both accuracy and throughput.These advancements support automated,proactive maintenance strategies that minimize downtime and contribute to a safer,smarter energy infrastructure.展开更多
In fire rescue scenarios,traditional manual operations are highly dangerous,as dense smoke,low visibility,extreme heat,and toxic gases not only hinder rescue efficiency but also endanger firefighters’safety.Although ...In fire rescue scenarios,traditional manual operations are highly dangerous,as dense smoke,low visibility,extreme heat,and toxic gases not only hinder rescue efficiency but also endanger firefighters’safety.Although intelligent rescue robots can enter hazardous environments in place of humans,smoke poses major challenges for human detection algorithms.These challenges include the attenuation of visible and infrared signals,complex thermal fields,and interference frombackground objects,all ofwhichmake it difficult to accurately identify trapped individuals.To address this problem,we propose VIF-YOLO,a visible–infrared fusion model for real-time human detection in dense smoke environments.The framework introduces a lightweight multimodal fusion(LMF)module based on learnable low-rank representation blocks to end-to-end integrate visible and infrared images,preserving fine details while enhancing salient features.In addition,an efficient multiscale attention(EMA)mechanism is incorporated into the YOLOv10n backbone to improve feature representation under low-light conditions.Extensive experiments on our newly constructedmultimodal smoke human detection(MSHD)dataset demonstrate thatVIF-YOLOachievesmAP50 of 99.5%,precision of 99.2%,and recall of 99.3%,outperforming YOLOv10n by a clear margin.Furthermore,when deployed on the NVIDIA Jetson Xavier NX,VIF-YOLO attains 40.6 FPS with an average inference latency of 24.6 ms,validating its real-time capability on edge-computing platforms.These results confirm that VIF-YOLO provides accurate,robust,and fast detection across complex backgrounds and diverse smoke conditions,ensuring reliable and rapid localization of individuals in need of rescue.展开更多
Object detection,a major challenge in computer vision and pattern recognition,plays a significant part in many applications,crossing artificial intelligence,face recognition,and autonomous driving.It involves focusing...Object detection,a major challenge in computer vision and pattern recognition,plays a significant part in many applications,crossing artificial intelligence,face recognition,and autonomous driving.It involves focusing on identifying the detection,localization,and categorization of targets in images.A particularly important emerging task is distinguishing real animals from toy replicas in real-time,mostly for smart camera systems in both urban and natural environments.However,that difficult task is affected by factors such as showing angle,occlusion,light intensity,variations,and texture differences.To tackle these challenges,this paper recommends Group Sparse YOLOv8(You Only Look Once version 8),an improved real-time object detection algorithm that improves YOLOv8 by integrating group sparsity regularization.This adjustment improves efficiency and accuracy while utilizing the computational costs and power consumption,including a frame selection approach.And a hybrid parallel processing method that merges pipelining with dataflow strategies to improve the performance.Established using a custom dataset of toy and real animal images along with well-known datasets,namely ImageNet,MSCOCO,and CIFAR-10/100.The combination of Group Sparsity with YOLOv8 shows high detection accuracy with lower latency.Here provides a real and resource-efficient solution for intelligent camera systems and improves real-time object detection and classification in environments,differentiating between real and toy animals.展开更多
基金Fundamental Research Funds for the Central Universities,China(Nos.2232020G-08 and 2232020E-03)Shanghai University Knowledge Service Platform,China(No.13S107024)。
文摘Accurate detection of fashion design attributes is essential for trend analyses and recommendation systems.Among these attributes,the neckline style plays a key role in shaping garment aesthetics.However,the presence of complex backgrounds and varied body postures in real-world fashion images presents challenges for reliable neckline detection.To address this problem,this research builds a comprehensive fashion neckline database from online shop images and proposes an efficient fashion neckline detection model based on the YOLOv8 architecture(FN-YOLO).First,the proposed model incorporates a BiFormer attention mechanism into the backbone,enhancing its feature extraction capability.Second,a lightweight multi-level asymmetry detector head(LADH)is designed to replace the original head,effectively reducing the computational complexity and accelerating the detection speed.Last,the original loss function is replaced with Wise-IoU,which improves the localization accuracy of the detection box.The experimental results demonstrate that FN-YOLO achieves a mean average precision(mAP)of 81.7%,showing an absolute improvement of 3.9%over the original YOLOv8 model,and a detection speed of 215.6 frame/s,confirming its suitability for real-time applications in fashion neckline detection.
基金National Nature Science Foundation of China(No.U24A20589)National Key Research and Development Program of China(No.2023YFB3905504)+1 种基金Innovation Team of the Ministry of Education of China(No.8091B042227)Innovation Group of Sichuan Natural Science Foundation(No.2023NSFSC1974).
文摘Recently,there has been a widespread application of deep learning in object detection with Synthetic Aperture Radar(SAR).The current algorithms based on Convolutional Neural Networks(CNN)often achieve good accuracy at the expense of more complex model structures and huge parameters,which poses a great challenge for real-time and accurate detection of multi-scale targets.To address these problems,we propose a lightweight real-time SAR ship object detector based on detection transformer(LSD-DETR)in this study.First,a lightweight backbone network LCNet containing a stem module and inverted residual structure is constructed to balance the inference speed and detection accuracy of model.Second,we design a transformer encoder with Cascaded Group Attention(CGA Encoder)to enrich the feature information of small targets in SAR images,which makes detection of small-sized ships more precise.Third,an efficient cross-scale feature fusion pyramid module(C3Het-FPN)is proposed through the lightweight units(C3Het)and the introduction of the weighted bidirectional feature pyramid(BiFPN)structure,which realizes the adaptive fusion of multi-scale features with fewer parameters.Ablation experiments and comparative experiments demonstrate the effectiveness of LSD-DETR.The model parameter of LSD-DETR is 8.8 M(only 20.6%of DETR),the model’s FPS reached 43.1,the average detection accuracy mAP50 on the SSDD and HRSID datasets reached 97.3%and 93.4%.Compared to advanced methods,the LSD-DETR can attain superior precision with fewer parameters,which enables accurate real-time object detection of multi-scale ships in SAR images.
基金supported by the Science and Technology Bureau of Xi’an project(24KGDW0049)the Key Research and Development Programof Shaanxi(2023-YBGY-264)the Key Research and Development Program of Guangxi(GK-AB20159032).
文摘In recent years,the country has spent significant workforce and material resources to prevent traffic accidents,particularly those caused by fatigued driving.The current studies mainly concentrate on driver physiological signals,driving behavior,and vehicle information.However,most of the approaches are computationally intensive and inconvenient for real-time detection.Therefore,this paper designs a network that combines precision,speed and lightweight and proposes an algorithm for facial fatigue detection based on multi-feature fusion.Specifically,the face detection model takes YOLOv8(You Only Look Once version 8)as the basic framework,and replaces its backbone network with MobileNetv3.To focus on the significant regions in the image,CPCA(Channel Prior Convolution Attention)is adopted to enhance the network’s capacity for feature extraction.Meanwhile,the network training phase employs the Focal-EIOU(Focal and Efficient Intersection Over Union)loss function,which makes the network lightweight and increases the accuracy of target detection.Ultimately,the Dlib toolkit was employed to annotate 68 facial feature points.This study established an evaluation metric for facial fatigue and developed a novel fatigue detection algorithm to assess the driver’s condition.A series of comparative experiments were carried out on the self-built dataset.The suggested method’s mAP(mean Average Precision)values for object detection and fatigue detection are 96.71%and 95.75%,respectively,as well as the detection speed is 47 FPS(Frames Per Second).This method can balance the contradiction between computational complexity and model accuracy.Furthermore,it can be transplanted to NVIDIA Jetson Orin NX and quickly detect the driver’s state while maintaining a high degree of accuracy.It contributes to the development of automobile safety systems and reduces the occurrence of traffic accidents.
文摘[Objective]The accurate identification of maize tassels is critical for the production of hybrid seed.Existing object detection models in complex farmland scenarios face limitations such as restricted data diversity,insufficient feature extraction,high computational load,and low detection efficiency.To address these challenges,a real-time field maize tassel detection model,LightTassel-YOLO(You Only Look Once)based on an improved YOLOv11n is proposed.The model is designed to quickly and accurately identify maize tassels,enabling efficient operation of detasseling unmanned aerial vehicles(UAVs)and reducing the impact of manual intervention.[Methods]Data was continuously collected during the tasseling stage of maize from 2023 to 2024 using UAVs,establishing a large-scale,high-quality maize tassel dataset that covered different maize tasseling stages,multiple varieties,varying altitudes,and diverse meteorological conditions.First,EfficientViT(Efficient vision transformer)was applied as the backbone network to enhance the ability to perceive information across multi-scale features.Second,the C2PSA-CPCA(Convolutional block with parallel spatial attention with channel prior convolutional attention)module was designed to dynamically assign attention weights to the channel and spatial dimensions of feature maps,effectively enhancing the network's capability to extract target features while reducing computational complexity.Finally,the C3k2-SCConv module was constructed to facilitate representative feature learning and achieve low-cost spatial feature reconstruction,thereby improving the model's detection accuracy.[Results and Discussions]The results demonstrated that LightTassel-YOLO provided a reliable method for maize tassel detection.The final model achieved an accuracy of 92.6%,a recall of 89.1%,and an AP@0.5 of 94.7%,representing improvements of 2.5,3.8 and 4.0 percentage points over the baseline model YOLOv11n,respectively.The model had only 3.23 M parameters and a computational cost of 6.7 GFLOPs.In addition,LightTassel-YOLO was compared with mainstream object detection algorithms such as Faster R-CNN,SSD,and multiple versions of the YOLO series.The results demonstrated that the proposed method outperformed these algorithms in overall performance and exhibits excellent adaptability in typical field scenarios.[Conclusions]The proposed method provides an effective theoretical framework for precise maize tassel monitoring and holds significant potential for advancing intelligent field management practices.
基金the Six Heights of Talent in Jiangsu Prov-ince(No.06-E-044).
文摘The paper puts forward a variance-time plots method based on slide-window mechanism tocalculate the Hurst parameter to detect Distribute Denial of Service(DDoS)attack in real time.Basedon fuzzy logic technology that can adjust itself dynamically under the fuzzy rules,an intelligent DDoSjudgment mechanism is designed.This new method calculates the Hurst parameter quickly and detectsDDoS attack in real time.Through comparing the detecting technologies based on statistics andfeature-packet respectively under different experiments,it is found that the new method can identifythe change of the Hurst parameter resulting from DDoS attack traffic with different intensities,andintelligently judge DDoS attack self-adaptively in real time.
基金funded by Anhui Provincial Natural Science Foundation(No.2208085ME128)the Anhui University-Level Special Project of Anhui University of Science and Technology(No.XCZX2021-01)+1 种基金the Research and the Development Fund of the Institute of Environmental Friendly Materials and Occupational Health,Anhui University of Science and Technology(No.ALW2022YF06)Anhui Province New Era Education Quality Project(Graduate Education)(No.2022xscx073).
文摘The real-time detection and instance segmentation of strawberries constitute fundamental components in the development of strawberry harvesting robots.Real-time identification of strawberries in an unstructured envi-ronment is a challenging task.Current instance segmentation algorithms for strawberries suffer from issues such as poor real-time performance and low accuracy.To this end,the present study proposes an Efficient YOLACT(E-YOLACT)algorithm for strawberry detection and segmentation based on the YOLACT framework.The key enhancements of the E-YOLACT encompass the development of a lightweight attention mechanism,pyramid squeeze shuffle attention(PSSA),for efficient feature extraction.Additionally,an attention-guided context-feature pyramid network(AC-FPN)is employed instead of FPN to optimize the architecture’s performance.Furthermore,a feature-enhanced model(FEM)is introduced to enhance the prediction head’s capabilities,while efficient fast non-maximum suppression(EF-NMS)is devised to improve non-maximum suppression.The experimental results demonstrate that the E-YOLACT achieves a Box-mAP and Mask-mAP of 77.9 and 76.6,respectively,on the custom dataset.Moreover,it exhibits an impressive category accuracy of 93.5%.Notably,the E-YOLACT also demonstrates a remarkable real-time detection capability with a speed of 34.8 FPS.The method proposed in this article presents an efficient approach for the vision system of a strawberry-picking robot.
文摘Lightning is a typical example of an instantaneous random point source target. It has close connection with severe convective phenomena such as a thunderstorm, whose distribution, variation, position and forecasting can be acquired through lightning observation. In this paper, we discuss the way to achieve instantaneous lightning signal intensification and detection from geostationary orbit by using the differences between the lightning signal and the slowly changing background noise such as that of cloud, land and ocean, combining three methods, spectral filtering, spatial filtering and background noise, enabling removal between frames. After six months of operation in orbit, lightning within the coverage of the Geostationary Lightning Imager was effectively detected, strongly supporting the case for shorttime and real-time early warning, forecasting and tracking of severe convective phenomena in China.
文摘This paper presents a vision-based crack detection approach for concrete bridge decks using an integrated one-dimensional convolutional neural network(1D-CNN)and long short-term memory(LSTM)method in the image frequency domain.The so-called 1D-CNN-LSTM algorithm is trained using thousands of images of cracked and non-cracked concrete bridge decks.In order to improve the training efficiency,images are first transformed into the frequency domain during a preprocessing phase.The algorithm is then calibrated using the flattened frequency data.LSTM is used to improve the performance of the developed network for long sequence data.The accuracy of the developed model is 99.05%,98.9%,and 99.25%,respectively,for training,validation,and testing data.An implementation framework is further developed for future application of the trained model for large-scale images.The proposed 1D-CNN-LSTM method exhibits superior performance in comparison with existing deep learning methods in terms of accuracy and computation time.The fast implementation of the 1D-CNN-LSTM algorithm makes it a promising tool for real-time crack detection.
基金supported by the National Natural Science Foundation of China (11674048)the Fundamental Research Funds for the Central Universities (N160502002)Liaoning BaiQianWan Talents Program (2014921017)
文摘Implantable bioelectronics for analyzing physiological biomarkers has recently been recognized as a promising technique in medical treatment or diagnostics. In this study, we developed a self-powered implantable skinlike glucometer for real-time detection of blood glucose level in vivo. Based on the piezo-enzymatic-reaction coupling effect of GOx@ZnO nanowire, the device under an applied deformation can actively output piezoelectric signal containing the glucose-detecting information. No external electricity power source or battery is needed for this device, and the outputting piezoelectric voltage acts as both the biosensing signal and electricity power. A practical application of the skin-like glucometer implanted in mouse body for detecting blood glucose level has been simply demonstrated. These results provide a new technique path for diabetes prophylaxis and treatment.
基金supported by the Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(No.2018R1A6A1A03025708)a study on an integrated multifunctional sensor platform based on autonomous energy).
文摘Mercury(Hg^(2+)),one of the most dangerous toxins in water,is a heavy metal that causes organ damage from both short-term and chronic exposure.Conventional methods for detecting mercury such as atomic absorption spectrometry or Raman spectroscopy require bulky equipment with complicated procedures.In this work,we fabricated a highly sensitive,real-time thin-film sensor based on vertically aligned rhenium disulfide(ReS_(2)).Its outstanding large surface area and the unique electronic appearance of its layered architecture make a ReS_(2) nanosheet a strong contender for such an application.The sensor exhibited a fast response speed(<2 s)to Hg^(2+)and an ultralow detection limit of 4 nM,which is significantly less than that of the U.S.Environmental Protection Agency's(U.S.EPA)allowed utmost contamination limit for Hg^(2+)in drinking water(10 nM).It also exhibited strong selectivity for Hg^(2+)against other metal ions such as Na^(+),Zn^(2+),Fe^(3+),Cu^(2+),Ca^(2+),Ni^(2+),Ag+,Cd^(2+),Fe^(2+),and Pb^(2+).Because this nanosheet can be replaced with any secondary substrate and possibly patterned into a microscale size,the sensor can be integrated into multiple platforms such as portable devices or sensor nodes in a grid network.
文摘Cervical cancer remains a critically important problem for women, especially those women in the developing world where the case-fatality rate is high. There are an estimated 528,000 cases and 266,000 deaths worldwide. Established screening and detection programs in the developed world have lowered the mortality from 40/100,000 to 2/100,000 over the last 60 years. The standard of care has been and continues to be: a screening Papanicolaou smear with or without Human Papilloma Virus (HPV) testing;followed by colposcopy and biopsies and if the smear is abnormal;and followed by treatment if the biopsies show high grade disease (cervical intraepithelial neoplasia (CIN) grades 2 and 3 and Carcinoma-in-situ). Low grade lesions (Pap smears with Atypical Cells of Uncertain Significance (ASCUS), Low Grade Squamous Intraepithelial Lesions (LGSIL), biopsies showing HPV changes or showing CIN 1);are usually followed for two years and then treated if persistent. Treatment can be performed with loop excision, LASER, or cryotherapy. Loop excision yields a specimen which can be reviewed to establish the diagnosis more accurately. LASER vaporizes the lesion and cryotherapy leads to tissue destruction. Under long term study;loop excision, LASER, and cryotherapy have the same rate of cure. The standard of care is expensive and takes 6 - 12 weeks for the individual patient. During the last twenty years, new technologies that can view the cervix and even image the cervix with cellular resolution have been developed. These technologies could lead to a new paradigm in which diagnosis and treatment occurs at a single visit. These technologies include fluorescence and reflectance spectroscopy (probe or wide-field, whole cervix scanning approaches) and fluorescence confocal endomicroscopy or high resolution micro-endoscopy. Both technologies have received Federal Drug Administration (FDA) and have been commercialized. Research trials continue to show their remarkable performance. These technologies are reviewed and clinical trials are summarized. Emerging technologies are coming along that may compete with those already approved and include optical coherence tomography, optical coherence tomography with autofluorescence, diffuse optical microscopy, and dual mode micro-endoscopy. These technologies are also reviewed and where available, clinical data is reported. Optical technologies are ready to diffuse into clinical practice because they will save money and 3 or 4 visits in the developed world and offer the same standard of care to the developing world where more cervical cancer exists.
文摘An approach to detection of moving objects in video sequences, with application to video surveillance is presented. The algorithm combines two kinds of change points, which are detected from the region-based frame difference and adjusted background subtraction. An adaptive threshold technique is employed to automatically choose the threshold value to segment the moving objects from the still background. And experiment results show that the algorithm is effective and efficient in practical situations. Furthermore, the algorithm is robust to the effects of the changing of lighting condition and can be applied for video surveillance system.
文摘Active noise controls are used in a wide field of applications to cancel out unwanted surrounding noise. Control systems based on the feedback structure however have the disadvantage that they may become unstable during run-time due to changes in the control path—in this context including the listener’s ear. Especially when applied to active noise cancellation (ANC) headphones, the risk of instability is associated with the risk of harmful influence on the listener’s ear, which is exposed to the speaker in striking distance. This paper discusses several methods to enable the analysis of a feedback ANC system during run-time to immediately detect instability. Finally, a solution is proposed, which identifies the open loop behavior parametrically by means of an adaptive filter to subsequently evaluate the coefficients regarding stability.
文摘In this paper, we proposed a new concept: depth of drowsiness, which can more precisely describe the drowsiness than existing binary description. A set of effective markers for drowsiness: normalized band norm was successfully developed. These markers are invariant from voltage amplitude of brain waves, eliminating the need for calibrating the voltage output of the brain-computer interface devices. A new polling algorithm was designed and implemented for computing the depth of drowsiness. The time cost of data acquisition and processing for each estimate is about one second, which is well suited for real-time applications. Test results with a portable brain-computer interface device show that the depth of drowsiness computed by the method in this paper is generally invariant from ages of test subjects and sensor channels (P3 and C4). The comparison between experiment and computing results indicate that the new method is noticeably better than one of the recent methods in terms of accuracy for predicting the drowsiness.
基金supported by the National Natural Science Foundation of China 62402171.
文摘As a fundamental component in computer vision,edges can be categorized into four types based on discontinuities in reflectance,illumination,surface normal,or depth.While deep CNNs have significantly advanced generic edge detection,real-time multi-class semantic edge detection under resource constraints remains challenging.To address this,we propose a lightweight framework based on PiDiNet that enables fine-grained semantic edge detection.Our model simultaneously predicts background and four edge categories from full-resolution inputs,balancing accuracy and efficiency.Key contributions include:a multi-channel output structure expanding binary edge prediction to five classes,supported by a deep supervision mechanism;a dynamic class-balancing strategy combining adaptive weighting with physical priors to handle extreme class imbalance;and maintained architectural efficiency enabling real-time inference.Extensive evaluations on BSDS-RIND show our approach achieves accuracy competitive with state-of-the-art methods while operating in real time.
文摘Online examinations have become a dominant assessment mode,increasing concerns over academic integrity.To address the critical challenge of detecting cheating behaviours,this study proposes a hybrid deep learning approach that combines visual detection and temporal behaviour classification.The methodology utilises object detection models—You Only Look Once(YOLOv12),Faster Region-based Convolutional Neural Network(RCNN),and Single Shot Detector(SSD)MobileNet—integrated with classification models such as Convolutional Neural Networks(CNN),Bidirectional Gated Recurrent Unit(Bi-GRU),and CNN-LSTM(Long Short-Term Memory).Two distinct datasets were used:the Online Exam Proctoring(EOP)dataset from Michigan State University and the School of Computer Science,Duy Tan Unievrsity(SCS-DTU)dataset collected in a controlled classroom setting.A diverse set of cheating behaviours,including book usage,unauthorised interaction,internet access,and mobile phone use,was categorised.Comprehensive experiments evaluated the models based on accuracy,precision,recall,training time,inference speed,and memory usage.We evaluate nine detector-classifier pairings under a unified budget and score them via a calibrated harmonic mean of detection and classification accuracies,enabling deployment-oriented selection under latency and memory constraints.Macro-Precision/Recall/F1 and Receiver Operating Characteristic-Area Under the Curve(ROC-AUC)are reported for the top configurations,revealing consistent advantages of object-centric pipelines for fine-grained cheating cues.The highest overall score is achieved by YOLOv12+CNN(97.15%accuracy),while SSD-MobileNet+CNN provides the best speed-efficiency trade-off for edge devices.This research provides valuable insights into selecting and deploying appropriate deep learning models for maintaining exam integrity under varying resource constraints.
基金the Shandong Provincial Key Research and Development Program(Grant No.2024SFGC0201).
文摘To address critical challenges in nighttime ship detection—high small-target missed detection(over 20%),insufficient lightweighting,and limited generalization due to scarce,low-quality datasets—this study proposes a systematic solution.First,a high-quality Night-Ships dataset is constructed via CycleGAN-based day-night transfer,combined with a dual-threshold cleaning strategy(Laplacian variance sharpness filtering and brightness-color deviation screening).Second,a Cross-stage Lightweight Fusion-You Only Look Once version 8(CLF-YOLOv8)is proposed with key improvements:the Neck network is reconstructed by replacing Cross Stage Partial(CSP)structure with the Cross Stage Partial Multi-Scale Convolutional Block(CSP-MSCB)and integrating Bidirectional Feature Pyramid Network(BiFPN)for weighted multi-scale fusion to enhance small-target detection;a Lightweight Shared Convolutional and Separated Batch Normalization Detection-Head(LSCSBD-Head)with shared convolutions and layer-wise Batch Normalization(BN)reduces parameters to 1.8M(42% fewer than YOLOv8n);and the FocalMinimum Point Distance Intersection over Union(Focal-MPDIoU)loss combines Minimum Point Distance Intersection over Union(MPDIoU)geometric constraints and Focal weighting to optimize low-overlap targets.Experiments show CLFYOLOv8 achieves 97.6%mAP@0.5(0.7% higher than YOLOv8n)with 1.8 M parameters,outperforming mainstream models in small-target detection,overlapping target discrimination,and adaptability to complex lighting.
基金supported by Ho Chi Minh City Open University,Vietnam and Suan Sunandha Rajabhat Univeristy,Thailand.
文摘Ensuring the reliability of power transmission networks depends heavily on the early detection of faults in key components such as insulators,which serve both mechanical and electrical functions.Even a single defective insulator can lead to equipment breakdown,costly service interruptions,and increased maintenance demands.While unmanned aerial vehicles(UAVs)enable rapid and cost-effective collection of high-resolution imagery,accurate defect identification remains challenging due to cluttered backgrounds,variable lighting,and the diverse appearance of faults.To address these issues,we introduce a real-time inspection framework that integrates an enhanced YOLOv10 detector with a Hybrid Quantum-Enhanced Graph Neural Network(HQGNN).The YOLOv10 module,fine-tuned on domainspecific UAV datasets,improves detection precision,while the HQGNN ensures multi-object tracking and temporal consistency across video frames.This synergy enables reliable and efficient identification of faulty insulators under complex environmental conditions.Experimental results show that the proposed YOLOv10-HQGNN model surpasses existing methods across all metrics,achieving Recall of 0.85 and Average Precision(AP)of 0.83,with clear gains in both accuracy and throughput.These advancements support automated,proactive maintenance strategies that minimize downtime and contribute to a safer,smarter energy infrastructure.
基金funded by the National Natural Science Foundation of China under Grant 62306128the Leading Innovation Project of Changzhou Science and Technology Bureau underGrant CQ20230072+2 种基金the Basic Science Research Project of Jiangsu Provincial Department of Education under Grant 23KJD520003the Science and Technology Development Plan Project of Jilin Provinceunder Grant 20240101382JCthe National KeyR esearch and Development Program of China under Grant 2023YFF1105102.
文摘In fire rescue scenarios,traditional manual operations are highly dangerous,as dense smoke,low visibility,extreme heat,and toxic gases not only hinder rescue efficiency but also endanger firefighters’safety.Although intelligent rescue robots can enter hazardous environments in place of humans,smoke poses major challenges for human detection algorithms.These challenges include the attenuation of visible and infrared signals,complex thermal fields,and interference frombackground objects,all ofwhichmake it difficult to accurately identify trapped individuals.To address this problem,we propose VIF-YOLO,a visible–infrared fusion model for real-time human detection in dense smoke environments.The framework introduces a lightweight multimodal fusion(LMF)module based on learnable low-rank representation blocks to end-to-end integrate visible and infrared images,preserving fine details while enhancing salient features.In addition,an efficient multiscale attention(EMA)mechanism is incorporated into the YOLOv10n backbone to improve feature representation under low-light conditions.Extensive experiments on our newly constructedmultimodal smoke human detection(MSHD)dataset demonstrate thatVIF-YOLOachievesmAP50 of 99.5%,precision of 99.2%,and recall of 99.3%,outperforming YOLOv10n by a clear margin.Furthermore,when deployed on the NVIDIA Jetson Xavier NX,VIF-YOLO attains 40.6 FPS with an average inference latency of 24.6 ms,validating its real-time capability on edge-computing platforms.These results confirm that VIF-YOLO provides accurate,robust,and fast detection across complex backgrounds and diverse smoke conditions,ensuring reliable and rapid localization of individuals in need of rescue.
文摘Object detection,a major challenge in computer vision and pattern recognition,plays a significant part in many applications,crossing artificial intelligence,face recognition,and autonomous driving.It involves focusing on identifying the detection,localization,and categorization of targets in images.A particularly important emerging task is distinguishing real animals from toy replicas in real-time,mostly for smart camera systems in both urban and natural environments.However,that difficult task is affected by factors such as showing angle,occlusion,light intensity,variations,and texture differences.To tackle these challenges,this paper recommends Group Sparse YOLOv8(You Only Look Once version 8),an improved real-time object detection algorithm that improves YOLOv8 by integrating group sparsity regularization.This adjustment improves efficiency and accuracy while utilizing the computational costs and power consumption,including a frame selection approach.And a hybrid parallel processing method that merges pipelining with dataflow strategies to improve the performance.Established using a custom dataset of toy and real animal images along with well-known datasets,namely ImageNet,MSCOCO,and CIFAR-10/100.The combination of Group Sparsity with YOLOv8 shows high detection accuracy with lower latency.Here provides a real and resource-efficient solution for intelligent camera systems and improves real-time object detection and classification in environments,differentiating between real and toy animals.
