In global navigation satellite system denial environment,cross-view geo-localization based on image retrieval presents an exceedingly critical visual localization solution for Unmanned Aerial Vehicle(UAV)systems.The e...In global navigation satellite system denial environment,cross-view geo-localization based on image retrieval presents an exceedingly critical visual localization solution for Unmanned Aerial Vehicle(UAV)systems.The essence of cross-view geo-localization resides in matching images containing the same geographical targets from disparate platforms,such as UAV-view and satellite-view images.However,images of the same geographical targets may suffer from occlusions and geometric distortions due to variations in the capturing platform,view,and timing.The existing methods predominantly extract features by segmenting feature maps,which overlook the holistic semantic distribution and structural information of objects,resulting in loss of image information.To address these challenges,dilated neighborhood attention Transformer is employed as the feature extraction backbone,and Multi-feature representations based on Multi-scale Hierarchical Contextual Aggregation(MMHCA)is proposed.In the proposed MMHCA method,the multiscale hierarchical contextual aggregation method is utilized to extract contextual information from local to global across various granularity levels,establishing feature associations of contextual information with global and local information in the image.Subsequently,the multi-feature representations method is utilized to obtain rich discriminative feature information,bolstering the robustness of model in scenarios characterized by positional shifts,varying distances,and scale ambiguities.Comprehensive experiments conducted on the extensively utilized University-1652 and SUES-200 benchmarks indicate that the MMHCA method surpasses the existing techniques.showing outstanding results in UAV localization and navigation.展开更多
This study proposes a learner profile framework based on multi-feature fusion,aiming to enhance the precision of personalized learning recommendations by integrating learners’static attributes(e.g.,demographic data a...This study proposes a learner profile framework based on multi-feature fusion,aiming to enhance the precision of personalized learning recommendations by integrating learners’static attributes(e.g.,demographic data and historical academic performance)with dynamic behavioral patterns(e.g.,real-time interactions and evolving interests over time).The research employs Term Frequency-Inverse Document Frequency(TF-IDF)for semantic feature extraction,integrates the Analytic Hierarchy Process(AHP)for feature weighting,and introduces a time decay function inspired by Newton’s law of cooling to dynamically model changes in learners’interests.Empirical results demonstrate that this framework effectively captures the dynamic evolution of learners’behaviors and provides context-aware learning resource recommendations.The study introduces a novel paradigm for learner modeling in educational technology,combining methodological innovation with a scalable technical architecture,thereby laying a foundation for the development of adaptive learning systems.展开更多
The traditional EnFCM(Enhanced fuzzy C-means)algorithm only considers the grey-scale features in image segmentation,resulting in less than satisfactory results when the algorithm is used for remote sensing woodland im...The traditional EnFCM(Enhanced fuzzy C-means)algorithm only considers the grey-scale features in image segmentation,resulting in less than satisfactory results when the algorithm is used for remote sensing woodland image segmentation and extraction.An EnFCM remote sensing forest land extraction method based on PCA multi-feature fusion was proposed.Firstly,histogram equalization was applied to improve the image contrast.Secondly,the texture and edge features of the image were extracted,and a multi-feature fused pixel image was generated using the PCA technique.Moreover,the fused feature was used as a feature constraint to measure the difference of pixels instead of a single grey-scale feature.Finally,an improved feature distance metric calculated the similarity between the pixel points and the cluster center to complete the cluster segmentation.The experimental results showed that the error was between 1.5%and 4.0%compared with the forested area counted by experts’hand-drawing,which could obtain a high accuracy segmentation and extraction result.展开更多
Chinese Clinical Named Entity Recognition(CNER)is a crucial step in extracting medical information and is of great significance in promoting medical informatization.However,CNER poses challenges due to the specificity...Chinese Clinical Named Entity Recognition(CNER)is a crucial step in extracting medical information and is of great significance in promoting medical informatization.However,CNER poses challenges due to the specificity of clinical terminology,the complexity of Chinese text semantics,and the uncertainty of Chinese entity boundaries.To address these issues,we propose an improved CNER model,which is based on multi-feature fusion and multi-scale local context enhancement.The model simultaneously fuses multi-feature representations of pinyin,radical,Part of Speech(POS),word boundary with BERT deep contextual representations to enhance the semantic representation of text for more effective entity recognition.Furthermore,to address the model’s limitation of focusing just on global features,we incorporate Convolutional Neural Networks(CNNs)with various kernel sizes to capture multi-scale local features of the text and enhance the model’s comprehension of the text.Finally,we integrate the obtained global and local features,and employ multi-head attention mechanism(MHA)extraction to enhance the model’s focus on characters associated with medical entities,hence boosting the model’s performance.We obtained 92.74%,and 87.80%F1 scores on the two CNER benchmark datasets,CCKS2017 and CCKS2019,respectively.The results demonstrate that our model outperforms the latest models in CNER,showcasing its outstanding overall performance.It can be seen that the CNER model proposed in this study has an important application value in constructing clinical medical knowledge graph and intelligent Q&A system.展开更多
Multimodal lung tumor medical images can provide anatomical and functional information for the same lesion.Such as Positron Emission Computed Tomography(PET),Computed Tomography(CT),and PET-CT.How to utilize the lesio...Multimodal lung tumor medical images can provide anatomical and functional information for the same lesion.Such as Positron Emission Computed Tomography(PET),Computed Tomography(CT),and PET-CT.How to utilize the lesion anatomical and functional information effectively and improve the network segmentation performance are key questions.To solve the problem,the Saliency Feature-Guided Interactive Feature Enhancement Lung Tumor Segmentation Network(Guide-YNet)is proposed in this paper.Firstly,a double-encoder single-decoder U-Net is used as the backbone in this model,a single-coder single-decoder U-Net is used to generate the saliency guided feature using PET image and transmit it into the skip connection of the backbone,and the high sensitivity of PET images to tumors is used to guide the network to accurately locate lesions.Secondly,a Cross Scale Feature Enhancement Module(CSFEM)is designed to extract multi-scale fusion features after downsampling.Thirdly,a Cross-Layer Interactive Feature Enhancement Module(CIFEM)is designed in the encoder to enhance the spatial position information and semantic information.Finally,a Cross-Dimension Cross-Layer Feature Enhancement Module(CCFEM)is proposed in the decoder,which effectively extractsmultimodal image features through global attention and multi-dimension local attention.The proposed method is verified on the lung multimodal medical image datasets,and the results showthat theMean Intersection overUnion(MIoU),Accuracy(Acc),Dice Similarity Coefficient(Dice),Volumetric overlap error(Voe),Relative volume difference(Rvd)of the proposed method on lung lesion segmentation are 87.27%,93.08%,97.77%,95.92%,89.28%,and 88.68%,respectively.It is of great significance for computer-aided diagnosis.展开更多
Drogue detection is one of the challenging tasks in autonomous aerial refueling due to the requirement for accuracy and rapidity.Saliency detection based on image intrinsic cues can achieve fast detection,but with poo...Drogue detection is one of the challenging tasks in autonomous aerial refueling due to the requirement for accuracy and rapidity.Saliency detection based on image intrinsic cues can achieve fast detection,but with poor accuracy.Recent studies reveal that optimization-based methods provide accurate and quick solutions for saliency detection.This paper presents a hybrid pigeon-inspired optimization method,the optimized color opponent,that aims to adjust the weight of color opponent channels to detect the drogue region.It can optimize the weights in the selected aerial refueling scene offline,and the results are applied for drogue detection in the scene.A novel algorithm aggregated by the optimized color opponent and robust background detection is presented to provide better precision and robustness.Experimental results on benchmark datasets and aerial refueling images show that the proposed method successfully extracts the saliency region or drogue and exhibits superior performance against the other saliency detection methods with intrinsic cues.The algorithm designed in this paper is competent for the drogue detection task of autonomous aerial refueling.展开更多
Most ground faults in distribution network are caused by insulation deterioration of power equipment.It is difficult to find the insulation deterioration of the distribution network in time,and the development trend o...Most ground faults in distribution network are caused by insulation deterioration of power equipment.It is difficult to find the insulation deterioration of the distribution network in time,and the development trend of the initial insulation fault is unknown,which brings difficulties to the distribution inspection.In order to solve the above problems,a situational awareness method of the initial insulation fault of the distribution network based on a multi-feature index comprehensive evaluation is proposed.Firstly,the insulation situation evaluation index is selected by analyzing the insulation fault mechanism of the distribution network,and the relational database of the distribution network is designed based on the data and numerical characteristics of the existing distribution management system.Secondly,considering all kinds of fault factors of the distribution network and the influence of the power supply region,the evaluation method of the initial insulation fault situation of the distribution network is proposed,and the development situation of the distribution network insulation fault is classified according to the evaluation method.Then,principal component analysis was used to reduce the dimension of the training samples and test samples of the distribution network data,and the support vector machine(SVM)was trained.The optimal parameter combination of the SVM model was found by the grid search method,and a multi-class SVM model based on 1-v-1 method was constructed.Finally,the trained multi-class SVM was used to predict 6 kinds of situation level prediction samples.The results of simulation examples show that the average prediction accuracy of 6 situation levels is above 95%,and the perception accuracy of 4 situation levels is above 96%.In addition,the insulation maintenance decision scheme under different situation levels is able to be given when no fault occurs or the insulation fault is in the early stage,which can meet the needs of power distribution and inspection for accurately sensing the insulation fault situation.The correctness and effectiveness of this method are verified.展开更多
In challenging situations,such as low illumination,rain,and background clutter,the stability of the thermal infrared(TIR)spectrum can help red,green,blue(RGB)visible spectrum to improve tracking performance.However,th...In challenging situations,such as low illumination,rain,and background clutter,the stability of the thermal infrared(TIR)spectrum can help red,green,blue(RGB)visible spectrum to improve tracking performance.However,the high-level image information and the modality-specific features have not been sufficiently studied.The proposed correlation filter uses the fused saliency content map to improve filter training and extracts different features of modalities.The fused content map is intro-duced into the spatial regularization term of correlation filter to highlight the training samples in the content region.Furthermore,the fused content map can avoid the incompleteness of the con-tent region caused by challenging situations.Additionally,differ-ent features are extracted according to the modality characteris-tics and are fused by the designed response-level fusion stra-tegy.The alternating direction method of multipliers(ADMM)algorithm is used to solve the tracker training efficiently.Experi-ments on the large-scale benchmark datasets show the effec-tiveness of the proposed tracker compared to the state-of-the-art traditional trackers and the deep learning based trackers.展开更多
This paper analyzes the progress of handwritten Chinese character recognition technology,from two perspectives:traditional recognition methods and deep learning-based recognition methods.Firstly,the complexity of Chin...This paper analyzes the progress of handwritten Chinese character recognition technology,from two perspectives:traditional recognition methods and deep learning-based recognition methods.Firstly,the complexity of Chinese character recognition is pointed out,including its numerous categories,complex structure,and the problem of similar characters,especially the variability of handwritten Chinese characters.Subsequently,recognition methods based on feature optimization,model optimization,and fusion techniques are highlighted.The fusion studies between feature optimization and model improvement are further explored,and these studies further enhance the recognition effect through complementary advantages.Finally,the article summarizes the current challenges of Chinese character recognition technology,including accuracy improvement,model complexity,and real-time problems,and looks forward to future research directions.展开更多
Neutron radiographic images(NRIs)typically suffer from multiple distortions,including various types of noise,geometric unsharpness,and white spots.Image quality assessment(IQA)can guide on-site image screening and eve...Neutron radiographic images(NRIs)typically suffer from multiple distortions,including various types of noise,geometric unsharpness,and white spots.Image quality assessment(IQA)can guide on-site image screening and even provide metrics for subsequent image processing.However,existing IQA methods for NRIs cannot effectively evaluate the quality of real NRIs with a specific distortion of white spots,limiting their practical application.In this paper,a novel no-reference IQA method is proposed to comprehensively evaluate the quality of real NRIs with multiple distortions.First,we construct large-scale NRI datasets with more than 20,000 images,including high-quality original NRIs and synthetic NRIs with various distortions.Next,an image quality calibration method based on visual salience and a local quality map is introduced to label the NRI dataset with quality scores.Finally,a lightweight convolutional neural network(CNN)model is designed to learn the abstract relationship between the NRIs and quality scores using the constructed NRI training dataset.Extensive experimental results demonstrate that the proposed method exhibits good consistency with human visual perception when evaluating both real NRIs and processed NRIs using enhancement and restoration algorithms,highlighting its application potential.展开更多
In this paper, the problem of moving object detection in aerial video is addressed. While motion cues have been extensively exploited in the literature, how to use spatial information is still an open problem. To deal...In this paper, the problem of moving object detection in aerial video is addressed. While motion cues have been extensively exploited in the literature, how to use spatial information is still an open problem. To deal with this issue, we propose a novel hierarchical moving target detection method based on spatiotemporal saliency. Temporal saliency is used to get a coarse segmentation, and spatial saliency is extracted to obtain the object＇s appearance details in candidate motion regions. Finally, by combining temporal and spatial saliency information, we can get refined detection results. Additionally, in order to give a full description of the object distribution, spatial saliency is detected in both pixel and region levels based on local contrast. Experiments conducted on the VIVID dataset show that the proposed method is efficient and accurate.展开更多
Vehicle re-identification(ReID)aims to retrieve the target vehicle in an extensive image gallery through its appearances from various views in the cross-camera scenario.It has gradually become a core technology of int...Vehicle re-identification(ReID)aims to retrieve the target vehicle in an extensive image gallery through its appearances from various views in the cross-camera scenario.It has gradually become a core technology of intelligent transportation system.Most existing vehicle re-identification models adopt the joint learning of global and local features.However,they directly use the extracted global features,resulting in insufficient feature expression.Moreover,local features are primarily obtained through advanced annotation and complex attention mechanisms,which require additional costs.To solve this issue,a multi-feature learning model with enhanced local attention for vehicle re-identification(MFELA)is proposed in this paper.The model consists of global and local branches.The global branch utilizes both middle and highlevel semantic features of ResNet50 to enhance the global representation capability.In addition,multi-scale pooling operations are used to obtain multiscale information.While the local branch utilizes the proposed Region Batch Dropblock(RBD),which encourages the model to learn discriminative features for different local regions and simultaneously drops corresponding same areas randomly in a batch during training to enhance the attention to local regions.Then features from both branches are combined to provide a more comprehensive and distinctive feature representation.Extensive experiments on VeRi-776 and VehicleID datasets prove that our method has excellent performance.展开更多
Urban land provides a suitable location for various economic activities which affect the development of surrounding areas. With rapid industrialization and urbanization, the contradictions in land-use become more noti...Urban land provides a suitable location for various economic activities which affect the development of surrounding areas. With rapid industrialization and urbanization, the contradictions in land-use become more noticeable. Urban administrators and decision-makers seek modern methods and technology to provide information support for urban growth. Recently, with the fast development of high-resolution sensor technology, more relevant data can be obtained, which is an advantage in studying the sustainable development of urban land-use. However, these data are only information sources and are a mixture of ＂information＂ and ＂noise＂. Processing, analysis and information extraction from remote sensing data is necessary to provide useful information. This paper extracts urban land-use information from a high-resolution image by using the multi-feature information of the image objects, and adopts an object-oriented image analysis approach and multi-scale image segmentation technology. A classification and extraction model is set up based on the multi-features of the image objects, in order to contribute to information for reasonable planning and effective management. This new image analysis approach offers a satisfactory solution for extracting information quickly and efficiently.展开更多
Reliable saliency detection can be used to quickly and effectively locate objects in images. In this paper, a novel algorithm for saliency detection based on superpixels clustering and stereo disparity （SDC） is prop...Reliable saliency detection can be used to quickly and effectively locate objects in images. In this paper, a novel algorithm for saliency detection based on superpixels clustering and stereo disparity （SDC） is proposed. Firstly, we use an improved superpixels clustering method to decompose the given image. Then, the disparity of each superpixel is computed by a modified stereo correspondence algorithm. Finally, a new measure which combines stereo disparity with color contrast and spatial coherence is defined to evaluate the saliency of each superpixel. From the experiments we can see that regions with high disparity can get higher saliency value, and the saliency maps have the same resolution with the source images, objects in the map have clear boundaries. Due to the use of superpixel and stereo disparity information, the proposed method is computationally efficient and outperforms some state-of-the-art color- based saliency detection methods.展开更多
Craters are salient terrain features on planetary surfaces, and provide useful information about the relative dating of geological unit of planets. In addition, they are ideal landmarks for spacecraft navigation. Due ...Craters are salient terrain features on planetary surfaces, and provide useful information about the relative dating of geological unit of planets. In addition, they are ideal landmarks for spacecraft navigation. Due to low contrast and uneven illumination, automatic extraction of craters remains a challenging task. This paper presents a saliency detection method for crater edges and a feature matching algorithm based on edges informa- tion. The craters are extracted through saliency edges detection, edge extraction and selection, feature matching of the same crater edges and robust ellipse fitting. In the edges matching algorithm, a crater feature model is proposed by analyzing the relationship between highlight region edges and shadow region ones. Then, crater edges are paired through the effective matching algorithm. Experiments of real planetary images show that the proposed approach is robust to different lights and topographies, and the detection rate is larger than 90%.展开更多
The detection range of underwater laser imaging technology achieves 4—6 times of detection range of conventional camera in intervening water medium, which makes it very promising in oceanic research, deep sea explora...The detection range of underwater laser imaging technology achieves 4—6 times of detection range of conventional camera in intervening water medium, which makes it very promising in oceanic research, deep sea exploration and robotic works. However, the special features in underwater laser images, such as speckle noise and non-uniform illumination, bring great difficulty for image segmentation. In this paper, a novel saliency motivated pulse coupled neural network(SM-PCNN) is proposed for underwater laser image segmentation. The pixel saliency is used as external stimulus of neurons. For improvement of convergence speed to optimal segmentation, a gradient descent method based on maximum two-dimensional Renyi entropy criterion is utilized to determine the dynamic threshold. On the basis of region contrast in each iteration step, the real object regions are effectively distinguished,and the robustness against speckle noise and non-uniform illumination is improved by region selection. The proposed method is compared with four other state-of-the-art methods which are watershed, fuzzy C-means, meanshift and normalized cut methods. Experimental results demonstrate the superiority of our proposed method to allow more accurate segmentation and higher robustness.展开更多
Visual attention is a mechanism that enables the visual system to detect potentially important objects in complex environment.Most computational visual attention models are designed with inspirations from mammalian vi...Visual attention is a mechanism that enables the visual system to detect potentially important objects in complex environment.Most computational visual attention models are designed with inspirations from mammalian visual systems.However,electrophysiological and behavioral evidences indicate that avian species are animals with high visual capability that can process complex information accurately in real time.Therefore,the visual system of the avian species,especially the nuclei related to the visual attention mechanism,are investigated in this paper.Afterwards,a hierarchical visual attention model is proposed for saliency detection.The optic tectum neuron responses are computed and the self-information is used to compute primary saliency maps in the first hierarchy.The"winner-takeall"network in the tecto-isthmal projection is simulated and final saliency maps are estimated with the regularized random walks ranking in the second hierarchy.Comparison results verify that the proposed model,which can define the focus of attention accurately,outperforms several state-of-the-art models.This study provides insights into the relationship between the visual attention mechanism and the avian visual pathways.The computational visual attention model may reveal the underlying neural mechanism of the nuclei for biological visual attention.展开更多
Most image saliency detection models are dependent on prior knowledge and demand high computational cost. However, spectral residual（SR） and phase spectrum of the Fourier transform（PFT） models are simple and fast ...Most image saliency detection models are dependent on prior knowledge and demand high computational cost. However, spectral residual（SR） and phase spectrum of the Fourier transform（PFT） models are simple and fast saliency detection approaches based on two-dimensional Fourier transform without the prior knowledge. For seismic data, the geological structure of the underground rock formation changes more obviously in the time direction. Therefore, one-dimensional Fourier transform is more suitable for seismic saliency detection. Fractional Fourier transform（FrFT） is an improved algorithm for Fourier transform, therefore we propose the seismic SR and PFT models in one-dimensional FrF T domain to obtain more detailed saliency maps. These two models use the amplitude and phase information in FrFT domain to construct the corresponding saliency maps in spatial domain. By means of these two models, several saliency maps at different fractional orders can be obtained for seismic attribute analysis. These saliency maps can characterize the detailed features and highlight the object areas, which is more conducive to determine the location of reservoirs. The performance of the proposed method is assessed on both simulated and real seismic data. The results indicate that our method is effective and convenient for seismic attribute extraction with good noise immunity.展开更多
The knowledge of flow regime is very important for quantifying the pressure drop, the stability and safety of two-phase flow systems. Based on image multi-feature fusion and support vector machine, a new method to ide...The knowledge of flow regime is very important for quantifying the pressure drop, the stability and safety of two-phase flow systems. Based on image multi-feature fusion and support vector machine, a new method to identify flow regime in two-phase flow was presented. Firstly, gas-liquid two-phase flow images including bub- bly flow, plug flow, slug flow, stratified flow, wavy flow, annular flow and mist flow were captured by digital high speed video systems in the horizontal tube. The image moment invariants and gray level co-occurrence matrix texture features were extracted using image processing techniques. To improve the performance of a multiple classifier system, the rough sets theory was used for reducing the inessential factors. Furthermore, the support vector machine was trained by using these eigenvectors to reduce the dimension as flow regime samples, and the flow regime intelligent identification was realized. The test results showed that image features which were reduced with the rough sets theory could excellently reflect the difference between seven typical flow regimes, and successful training the support vector machine could quickly and accurately identify seven typical flow regimes of gas-liquid two-phase flow in the horizontal tube. Image multi-feature fusion method provided a new way to identify the gas-liquid two-phase flow, and achieved higher identification ability than that of single characteristic. The overall identification accuracy was 100%, and an estimate of the image processing time was 8 ms for online flow regime identification.展开更多
Pests detecting is an important research subject in grain storage field.In the past decades,many edge detection methods have been applied to the edge detection of stored grain pests.Although some of them can realize t...Pests detecting is an important research subject in grain storage field.In the past decades,many edge detection methods have been applied to the edge detection of stored grain pests.Although some of them can realize the stored grain pests detecting,precision and robustness are not good enough.Spectral residual(SR)saliency edge detection defines the logarithmic spectrumof image as novelty part of the image information.The remaining spectrumis converted to the airspace to obtain edge detection results.SR algorithm is completely based on frequency domain processing.It not only can effectively simplify the target detection algorithm,but also can improve the effectiveness of target recognition.The experimental results show that the edge results of stored grain pests detected by SR method are effective and stable.展开更多
基金supported by the National Natural Science Foundation of China(Nos.12072027,62103052,61603346 and 62103379)the Henan Key Laboratory of General Aviation Technology,China(No.ZHKF-230201)+3 种基金the Funding for the Open Research Project of the Rotor Aerodynamics Key Laboratory,China(No.RAL20200101)the Key Research and Development Program of Henan Province,China(Nos.241111222000 and 241111222900)the Key Science and Technology Program of Henan Province,China(No.232102220067)the Scholarship Funding from the China Scholarship Council(No.202206030079).
文摘In global navigation satellite system denial environment,cross-view geo-localization based on image retrieval presents an exceedingly critical visual localization solution for Unmanned Aerial Vehicle(UAV)systems.The essence of cross-view geo-localization resides in matching images containing the same geographical targets from disparate platforms,such as UAV-view and satellite-view images.However,images of the same geographical targets may suffer from occlusions and geometric distortions due to variations in the capturing platform,view,and timing.The existing methods predominantly extract features by segmenting feature maps,which overlook the holistic semantic distribution and structural information of objects,resulting in loss of image information.To address these challenges,dilated neighborhood attention Transformer is employed as the feature extraction backbone,and Multi-feature representations based on Multi-scale Hierarchical Contextual Aggregation(MMHCA)is proposed.In the proposed MMHCA method,the multiscale hierarchical contextual aggregation method is utilized to extract contextual information from local to global across various granularity levels,establishing feature associations of contextual information with global and local information in the image.Subsequently,the multi-feature representations method is utilized to obtain rich discriminative feature information,bolstering the robustness of model in scenarios characterized by positional shifts,varying distances,and scale ambiguities.Comprehensive experiments conducted on the extensively utilized University-1652 and SUES-200 benchmarks indicate that the MMHCA method surpasses the existing techniques.showing outstanding results in UAV localization and navigation.
基金This work is supported by the Ministry of Education of Humanities and Social Science projects in China(No.20YJCZH124)Guangdong Province Education and Teaching Reform Project No.640:Research on the Teaching Practice and Application of Online Peer Assessment Methods in the Context of Artificial Intelligence.
文摘This study proposes a learner profile framework based on multi-feature fusion,aiming to enhance the precision of personalized learning recommendations by integrating learners’static attributes(e.g.,demographic data and historical academic performance)with dynamic behavioral patterns(e.g.,real-time interactions and evolving interests over time).The research employs Term Frequency-Inverse Document Frequency(TF-IDF)for semantic feature extraction,integrates the Analytic Hierarchy Process(AHP)for feature weighting,and introduces a time decay function inspired by Newton’s law of cooling to dynamically model changes in learners’interests.Empirical results demonstrate that this framework effectively captures the dynamic evolution of learners’behaviors and provides context-aware learning resource recommendations.The study introduces a novel paradigm for learner modeling in educational technology,combining methodological innovation with a scalable technical architecture,thereby laying a foundation for the development of adaptive learning systems.
基金supported by National Natural Science Foundation of China(No.61761027)Gansu Young Doctor’s Fund for Higher Education Institutions(No.2021QB-053)。
文摘The traditional EnFCM(Enhanced fuzzy C-means)algorithm only considers the grey-scale features in image segmentation,resulting in less than satisfactory results when the algorithm is used for remote sensing woodland image segmentation and extraction.An EnFCM remote sensing forest land extraction method based on PCA multi-feature fusion was proposed.Firstly,histogram equalization was applied to improve the image contrast.Secondly,the texture and edge features of the image were extracted,and a multi-feature fused pixel image was generated using the PCA technique.Moreover,the fused feature was used as a feature constraint to measure the difference of pixels instead of a single grey-scale feature.Finally,an improved feature distance metric calculated the similarity between the pixel points and the cluster center to complete the cluster segmentation.The experimental results showed that the error was between 1.5%and 4.0%compared with the forested area counted by experts’hand-drawing,which could obtain a high accuracy segmentation and extraction result.
基金This study was supported by the National Natural Science Foundation of China(61911540482 and 61702324).
文摘Chinese Clinical Named Entity Recognition(CNER)is a crucial step in extracting medical information and is of great significance in promoting medical informatization.However,CNER poses challenges due to the specificity of clinical terminology,the complexity of Chinese text semantics,and the uncertainty of Chinese entity boundaries.To address these issues,we propose an improved CNER model,which is based on multi-feature fusion and multi-scale local context enhancement.The model simultaneously fuses multi-feature representations of pinyin,radical,Part of Speech(POS),word boundary with BERT deep contextual representations to enhance the semantic representation of text for more effective entity recognition.Furthermore,to address the model’s limitation of focusing just on global features,we incorporate Convolutional Neural Networks(CNNs)with various kernel sizes to capture multi-scale local features of the text and enhance the model’s comprehension of the text.Finally,we integrate the obtained global and local features,and employ multi-head attention mechanism(MHA)extraction to enhance the model’s focus on characters associated with medical entities,hence boosting the model’s performance.We obtained 92.74%,and 87.80%F1 scores on the two CNER benchmark datasets,CCKS2017 and CCKS2019,respectively.The results demonstrate that our model outperforms the latest models in CNER,showcasing its outstanding overall performance.It can be seen that the CNER model proposed in this study has an important application value in constructing clinical medical knowledge graph and intelligent Q&A system.
基金supported in part by the National Natural Science Foundation of China(Grant No.62062003)Natural Science Foundation of Ningxia(Grant No.2023AAC03293).
文摘Multimodal lung tumor medical images can provide anatomical and functional information for the same lesion.Such as Positron Emission Computed Tomography(PET),Computed Tomography(CT),and PET-CT.How to utilize the lesion anatomical and functional information effectively and improve the network segmentation performance are key questions.To solve the problem,the Saliency Feature-Guided Interactive Feature Enhancement Lung Tumor Segmentation Network(Guide-YNet)is proposed in this paper.Firstly,a double-encoder single-decoder U-Net is used as the backbone in this model,a single-coder single-decoder U-Net is used to generate the saliency guided feature using PET image and transmit it into the skip connection of the backbone,and the high sensitivity of PET images to tumors is used to guide the network to accurately locate lesions.Secondly,a Cross Scale Feature Enhancement Module(CSFEM)is designed to extract multi-scale fusion features after downsampling.Thirdly,a Cross-Layer Interactive Feature Enhancement Module(CIFEM)is designed in the encoder to enhance the spatial position information and semantic information.Finally,a Cross-Dimension Cross-Layer Feature Enhancement Module(CCFEM)is proposed in the decoder,which effectively extractsmultimodal image features through global attention and multi-dimension local attention.The proposed method is verified on the lung multimodal medical image datasets,and the results showthat theMean Intersection overUnion(MIoU),Accuracy(Acc),Dice Similarity Coefficient(Dice),Volumetric overlap error(Voe),Relative volume difference(Rvd)of the proposed method on lung lesion segmentation are 87.27%,93.08%,97.77%,95.92%,89.28%,and 88.68%,respectively.It is of great significance for computer-aided diagnosis.
基金This work was partially supported by Science and Technology Innovation 2030-Key Project of“New Generation Artificial Intelligence”,China(No.2018AAA0102403)the National Natural Science Foundation of China(Nos.U1913602,T2121003,91948204,62103040,and U20B2071)the Open Fund/Postdoctoral Fund of the Laboratory of Cognition and Decision Intelligence for Complex Systems,Institute of Automation,Chinese Academy of Sciences(No.CASIA-KFKT-08).
文摘Drogue detection is one of the challenging tasks in autonomous aerial refueling due to the requirement for accuracy and rapidity.Saliency detection based on image intrinsic cues can achieve fast detection,but with poor accuracy.Recent studies reveal that optimization-based methods provide accurate and quick solutions for saliency detection.This paper presents a hybrid pigeon-inspired optimization method,the optimized color opponent,that aims to adjust the weight of color opponent channels to detect the drogue region.It can optimize the weights in the selected aerial refueling scene offline,and the results are applied for drogue detection in the scene.A novel algorithm aggregated by the optimized color opponent and robust background detection is presented to provide better precision and robustness.Experimental results on benchmark datasets and aerial refueling images show that the proposed method successfully extracts the saliency region or drogue and exhibits superior performance against the other saliency detection methods with intrinsic cues.The algorithm designed in this paper is competent for the drogue detection task of autonomous aerial refueling.
基金funded by the Science and Technology Project of China Southern Power Grid(YNKJXM20210175)the National Natural Science Foundation of China(52177070).
文摘Most ground faults in distribution network are caused by insulation deterioration of power equipment.It is difficult to find the insulation deterioration of the distribution network in time,and the development trend of the initial insulation fault is unknown,which brings difficulties to the distribution inspection.In order to solve the above problems,a situational awareness method of the initial insulation fault of the distribution network based on a multi-feature index comprehensive evaluation is proposed.Firstly,the insulation situation evaluation index is selected by analyzing the insulation fault mechanism of the distribution network,and the relational database of the distribution network is designed based on the data and numerical characteristics of the existing distribution management system.Secondly,considering all kinds of fault factors of the distribution network and the influence of the power supply region,the evaluation method of the initial insulation fault situation of the distribution network is proposed,and the development situation of the distribution network insulation fault is classified according to the evaluation method.Then,principal component analysis was used to reduce the dimension of the training samples and test samples of the distribution network data,and the support vector machine(SVM)was trained.The optimal parameter combination of the SVM model was found by the grid search method,and a multi-class SVM model based on 1-v-1 method was constructed.Finally,the trained multi-class SVM was used to predict 6 kinds of situation level prediction samples.The results of simulation examples show that the average prediction accuracy of 6 situation levels is above 95%,and the perception accuracy of 4 situation levels is above 96%.In addition,the insulation maintenance decision scheme under different situation levels is able to be given when no fault occurs or the insulation fault is in the early stage,which can meet the needs of power distribution and inspection for accurately sensing the insulation fault situation.The correctness and effectiveness of this method are verified.
基金supported by the National Natural Science Foundation of China(62073036,62076031)Beijing Natural Science Foundation(4242049).
文摘In challenging situations,such as low illumination,rain,and background clutter,the stability of the thermal infrared(TIR)spectrum can help red,green,blue(RGB)visible spectrum to improve tracking performance.However,the high-level image information and the modality-specific features have not been sufficiently studied.The proposed correlation filter uses the fused saliency content map to improve filter training and extracts different features of modalities.The fused content map is intro-duced into the spatial regularization term of correlation filter to highlight the training samples in the content region.Furthermore,the fused content map can avoid the incompleteness of the con-tent region caused by challenging situations.Additionally,differ-ent features are extracted according to the modality characteris-tics and are fused by the designed response-level fusion stra-tegy.The alternating direction method of multipliers(ADMM)algorithm is used to solve the tracker training efficiently.Experi-ments on the large-scale benchmark datasets show the effec-tiveness of the proposed tracker compared to the state-of-the-art traditional trackers and the deep learning based trackers.
文摘This paper analyzes the progress of handwritten Chinese character recognition technology,from two perspectives:traditional recognition methods and deep learning-based recognition methods.Firstly,the complexity of Chinese character recognition is pointed out,including its numerous categories,complex structure,and the problem of similar characters,especially the variability of handwritten Chinese characters.Subsequently,recognition methods based on feature optimization,model optimization,and fusion techniques are highlighted.The fusion studies between feature optimization and model improvement are further explored,and these studies further enhance the recognition effect through complementary advantages.Finally,the article summarizes the current challenges of Chinese character recognition technology,including accuracy improvement,model complexity,and real-time problems,and looks forward to future research directions.
基金supported by the National Natural Science Foundation of China(Nos.11905028 and 12105040)Scientific Research Project of the Education Department of Jilin Province(No.JJKH20231294KJ)the Youth Growth Technology Project of the Science and Technology Department of Jilin Province(No.20210508027RQ).
文摘Neutron radiographic images(NRIs)typically suffer from multiple distortions,including various types of noise,geometric unsharpness,and white spots.Image quality assessment(IQA)can guide on-site image screening and even provide metrics for subsequent image processing.However,existing IQA methods for NRIs cannot effectively evaluate the quality of real NRIs with a specific distortion of white spots,limiting their practical application.In this paper,a novel no-reference IQA method is proposed to comprehensively evaluate the quality of real NRIs with multiple distortions.First,we construct large-scale NRI datasets with more than 20,000 images,including high-quality original NRIs and synthetic NRIs with various distortions.Next,an image quality calibration method based on visual salience and a local quality map is introduced to label the NRI dataset with quality scores.Finally,a lightweight convolutional neural network(CNN)model is designed to learn the abstract relationship between the NRIs and quality scores using the constructed NRI training dataset.Extensive experimental results demonstrate that the proposed method exhibits good consistency with human visual perception when evaluating both real NRIs and processed NRIs using enhancement and restoration algorithms,highlighting its application potential.
基金co-supported by the National Natural Science Foundation of China (Nos.61005028,61175032,and 61101222)
文摘In this paper, the problem of moving object detection in aerial video is addressed. While motion cues have been extensively exploited in the literature, how to use spatial information is still an open problem. To deal with this issue, we propose a novel hierarchical moving target detection method based on spatiotemporal saliency. Temporal saliency is used to get a coarse segmentation, and spatial saliency is extracted to obtain the object＇s appearance details in candidate motion regions. Finally, by combining temporal and spatial saliency information, we can get refined detection results. Additionally, in order to give a full description of the object distribution, spatial saliency is detected in both pixel and region levels based on local contrast. Experiments conducted on the VIVID dataset show that the proposed method is efficient and accurate.
基金This work was supported,in part,by the National Nature Science Foundation of China under Grant Numbers 61502240,61502096,61304205,61773219in part,by the Natural Science Foundation of Jiangsu Province under grant numbers BK20201136,BK20191401+1 种基金in part,by the Postgraduate Research&Practice Innovation Program of Jiangsu Province under Grant Numbers SJCX21_0363in part,by the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)fund.
文摘Vehicle re-identification(ReID)aims to retrieve the target vehicle in an extensive image gallery through its appearances from various views in the cross-camera scenario.It has gradually become a core technology of intelligent transportation system.Most existing vehicle re-identification models adopt the joint learning of global and local features.However,they directly use the extracted global features,resulting in insufficient feature expression.Moreover,local features are primarily obtained through advanced annotation and complex attention mechanisms,which require additional costs.To solve this issue,a multi-feature learning model with enhanced local attention for vehicle re-identification(MFELA)is proposed in this paper.The model consists of global and local branches.The global branch utilizes both middle and highlevel semantic features of ResNet50 to enhance the global representation capability.In addition,multi-scale pooling operations are used to obtain multiscale information.While the local branch utilizes the proposed Region Batch Dropblock(RBD),which encourages the model to learn discriminative features for different local regions and simultaneously drops corresponding same areas randomly in a batch during training to enhance the attention to local regions.Then features from both branches are combined to provide a more comprehensive and distinctive feature representation.Extensive experiments on VeRi-776 and VehicleID datasets prove that our method has excellent performance.
基金The paper is supported by the Research Foundation for OutstandingYoung Teachers , China University of Geosciences ( Wuhan) ( No .CUGQNL0616) Research Foundationfor State Key Laboratory of Geo-logical Processes and Mineral Resources ( No . MGMR2002-02)Hubei Provincial Depart ment of Education (B) .
文摘Urban land provides a suitable location for various economic activities which affect the development of surrounding areas. With rapid industrialization and urbanization, the contradictions in land-use become more noticeable. Urban administrators and decision-makers seek modern methods and technology to provide information support for urban growth. Recently, with the fast development of high-resolution sensor technology, more relevant data can be obtained, which is an advantage in studying the sustainable development of urban land-use. However, these data are only information sources and are a mixture of ＂information＂ and ＂noise＂. Processing, analysis and information extraction from remote sensing data is necessary to provide useful information. This paper extracts urban land-use information from a high-resolution image by using the multi-feature information of the image objects, and adopts an object-oriented image analysis approach and multi-scale image segmentation technology. A classification and extraction model is set up based on the multi-features of the image objects, in order to contribute to information for reasonable planning and effective management. This new image analysis approach offers a satisfactory solution for extracting information quickly and efficiently.
基金supported by NSFC Joint Fund with Guangdong under Key Project(U1201258)National Natural Science foundation of China(61402261+3 种基金6130308861572286)the scientific research foundation of Shandong Province of Outstanding Young Scientist Award(BS2013DX048)Shandong Ji’nan Science and Technology Development Project(201202015)
文摘Reliable saliency detection can be used to quickly and effectively locate objects in images. In this paper, a novel algorithm for saliency detection based on superpixels clustering and stereo disparity （SDC） is proposed. Firstly, we use an improved superpixels clustering method to decompose the given image. Then, the disparity of each superpixel is computed by a modified stereo correspondence algorithm. Finally, a new measure which combines stereo disparity with color contrast and spatial coherence is defined to evaluate the saliency of each superpixel. From the experiments we can see that regions with high disparity can get higher saliency value, and the saliency maps have the same resolution with the source images, objects in the map have clear boundaries. Due to the use of superpixel and stereo disparity information, the proposed method is computationally efficient and outperforms some state-of-the-art color- based saliency detection methods.
基金supported by the National Natural Science Foundation of China(61210012)
文摘Craters are salient terrain features on planetary surfaces, and provide useful information about the relative dating of geological unit of planets. In addition, they are ideal landmarks for spacecraft navigation. Due to low contrast and uneven illumination, automatic extraction of craters remains a challenging task. This paper presents a saliency detection method for crater edges and a feature matching algorithm based on edges informa- tion. The craters are extracted through saliency edges detection, edge extraction and selection, feature matching of the same crater edges and robust ellipse fitting. In the edges matching algorithm, a crater feature model is proposed by analyzing the relationship between highlight region edges and shadow region ones. Then, crater edges are paired through the effective matching algorithm. Experiments of real planetary images show that the proposed approach is robust to different lights and topographies, and the detection rate is larger than 90%.
基金the National High Technology Research and Development Program(863)of China(No.2011AA09A106)the National Natural Science Foundation of China(No.51009040)and the Fundamental Research Funds for Central Universities of China(No.HEUCF140113)
文摘The detection range of underwater laser imaging technology achieves 4—6 times of detection range of conventional camera in intervening water medium, which makes it very promising in oceanic research, deep sea exploration and robotic works. However, the special features in underwater laser images, such as speckle noise and non-uniform illumination, bring great difficulty for image segmentation. In this paper, a novel saliency motivated pulse coupled neural network(SM-PCNN) is proposed for underwater laser image segmentation. The pixel saliency is used as external stimulus of neurons. For improvement of convergence speed to optimal segmentation, a gradient descent method based on maximum two-dimensional Renyi entropy criterion is utilized to determine the dynamic threshold. On the basis of region contrast in each iteration step, the real object regions are effectively distinguished,and the robustness against speckle noise and non-uniform illumination is improved by region selection. The proposed method is compared with four other state-of-the-art methods which are watershed, fuzzy C-means, meanshift and normalized cut methods. Experimental results demonstrate the superiority of our proposed method to allow more accurate segmentation and higher robustness.
基金supported by Natural Science Foundation of China(61425008,61333004,61273054)
文摘Visual attention is a mechanism that enables the visual system to detect potentially important objects in complex environment.Most computational visual attention models are designed with inspirations from mammalian visual systems.However,electrophysiological and behavioral evidences indicate that avian species are animals with high visual capability that can process complex information accurately in real time.Therefore,the visual system of the avian species,especially the nuclei related to the visual attention mechanism,are investigated in this paper.Afterwards,a hierarchical visual attention model is proposed for saliency detection.The optic tectum neuron responses are computed and the self-information is used to compute primary saliency maps in the first hierarchy.The"winner-takeall"network in the tecto-isthmal projection is simulated and final saliency maps are estimated with the regularized random walks ranking in the second hierarchy.Comparison results verify that the proposed model,which can define the focus of attention accurately,outperforms several state-of-the-art models.This study provides insights into the relationship between the visual attention mechanism and the avian visual pathways.The computational visual attention model may reveal the underlying neural mechanism of the nuclei for biological visual attention.
基金supported by the National Natural Science Foundation of China (Nos.61571096,61775030,41274127,41301460,and 40874066)
文摘Most image saliency detection models are dependent on prior knowledge and demand high computational cost. However, spectral residual（SR） and phase spectrum of the Fourier transform（PFT） models are simple and fast saliency detection approaches based on two-dimensional Fourier transform without the prior knowledge. For seismic data, the geological structure of the underground rock formation changes more obviously in the time direction. Therefore, one-dimensional Fourier transform is more suitable for seismic saliency detection. Fractional Fourier transform（FrFT） is an improved algorithm for Fourier transform, therefore we propose the seismic SR and PFT models in one-dimensional FrF T domain to obtain more detailed saliency maps. These two models use the amplitude and phase information in FrFT domain to construct the corresponding saliency maps in spatial domain. By means of these two models, several saliency maps at different fractional orders can be obtained for seismic attribute analysis. These saliency maps can characterize the detailed features and highlight the object areas, which is more conducive to determine the location of reservoirs. The performance of the proposed method is assessed on both simulated and real seismic data. The results indicate that our method is effective and convenient for seismic attribute extraction with good noise immunity.
基金Supported by the National Natural Science Foundation of China （50706006） and the Science and Technology Development Program of Jilin Province （20040513）.
文摘The knowledge of flow regime is very important for quantifying the pressure drop, the stability and safety of two-phase flow systems. Based on image multi-feature fusion and support vector machine, a new method to identify flow regime in two-phase flow was presented. Firstly, gas-liquid two-phase flow images including bub- bly flow, plug flow, slug flow, stratified flow, wavy flow, annular flow and mist flow were captured by digital high speed video systems in the horizontal tube. The image moment invariants and gray level co-occurrence matrix texture features were extracted using image processing techniques. To improve the performance of a multiple classifier system, the rough sets theory was used for reducing the inessential factors. Furthermore, the support vector machine was trained by using these eigenvectors to reduce the dimension as flow regime samples, and the flow regime intelligent identification was realized. The test results showed that image features which were reduced with the rough sets theory could excellently reflect the difference between seven typical flow regimes, and successful training the support vector machine could quickly and accurately identify seven typical flow regimes of gas-liquid two-phase flow in the horizontal tube. Image multi-feature fusion method provided a new way to identify the gas-liquid two-phase flow, and achieved higher identification ability than that of single characteristic. The overall identification accuracy was 100%, and an estimate of the image processing time was 8 ms for online flow regime identification.
基金financially supported by National Natural Science Foundation of China(No.61871176)Key Scientific and Technological Project of Science and Technology Department of Henan Province(No.172102210030,182102110099)+2 种基金Key Scientific Research Project Program of Universities of Henan Province(No.18B520025)Open Fund of Key Laboratory of Grain Information Processing and Control(No.KFJJ-2018-102)supported by Collaborative Innovation Center of Grain Storage and Security of Henan Province
文摘Pests detecting is an important research subject in grain storage field.In the past decades,many edge detection methods have been applied to the edge detection of stored grain pests.Although some of them can realize the stored grain pests detecting,precision and robustness are not good enough.Spectral residual(SR)saliency edge detection defines the logarithmic spectrumof image as novelty part of the image information.The remaining spectrumis converted to the airspace to obtain edge detection results.SR algorithm is completely based on frequency domain processing.It not only can effectively simplify the target detection algorithm,but also can improve the effectiveness of target recognition.The experimental results show that the edge results of stored grain pests detected by SR method are effective and stable.
