To avoid the laborious annotation process for dense prediction tasks like semantic segmentation,unsupervised domain adaptation(UDA)methods have been proposed to leverage the abundant annotations from a source domain,s...To avoid the laborious annotation process for dense prediction tasks like semantic segmentation,unsupervised domain adaptation(UDA)methods have been proposed to leverage the abundant annotations from a source domain,such as virtual world(e.g.,3D games),and adapt models to the target domain(the real world)by narrowing the domain discrepancies.However,because of the large domain gap,directly aligning two distinct domains without considering the intermediates leads to inefficient alignment and inferior adaptation.To address this issue,we propose a novel learnable evolutionary Category Intermediates(CIs)guided UDA model named Leci,which enables the information transfer between the two domains via two processes,i.e.,Distilling and Blending.Starting from a random initialization,the CIs learn shared category-wise semantics automatically from two domains in the Distilling process.Then,the learned semantics in the CIs are sent back to blend the domain features through a residual attentive fusion(RAF)module,such that the categorywise features of both domains shift towards each other.As the CIs progressively and consistently learn from the varying feature distributions during training,they are evolutionary to guide the model to achieve category-wise feature alignment.Experiments on both GTA5 and SYNTHIA datasets demonstrate Leci's superiority over prior representative methods.展开更多
Heart rate variability(HRV),as a key indicator for evaluating autonomic nervous system function,has significant value in areas such as cardiovascular disease screening and emotion monitoring.Although traditional conta...Heart rate variability(HRV),as a key indicator for evaluating autonomic nervous system function,has significant value in areas such as cardiovascular disease screening and emotion monitoring.Although traditional contact-based measurement methods offer high precision,they suffer from issues such as poor comfort and low user compliance.This paper proposes a non-contact HRV monitoring method using frequency modulated continuous wave(FMCW)radar,highlighting adaptive cycle segmentation and peak extraction as core innovations.Key advantages of this method include:1)effective suppression of motion artifacts and respiratory harmonics by leveraging cardiac energy concentration;2)precise heartbeat cycle identification across physiological states via adaptive segmentation,addressing time-varying differences;3)adaptive threshold adjustment using discrete energy signals and a support vector machine(SVM)model based on morphological-temporal-spectral characteristics,reducing complexity while maintaining precision.Previous approaches predominantly process radar signals holistically through algorithms to uniformly extract inter-beat intervals(IBIs),which may result in high computational complexity and inadequate dynamic adaptability.In contrast,our method achieved higher precision than conventional holistic processing approaches,while maintaining comparable precision with lower computational complexity than previous optimization algorithms.Experimental results demonstrate that the system achieves an average IBI error of 8.28 ms(RMSE of 15.3 ms),which is reduced by about 66%compared with the traditional holistically peak seeking method.The average errors of SDNN and RMSSD are 2.65 ms and 4.33 ms,respectively.More than 92%of the IBI errors are controlled within 20 ms.The distance adaptability test showed that although the accuracy of long-distance measurement decreased slightly(<6 ms),the overall detection performance remained robust at different distances.This study provided a novel estimation algorithm for non-contact HRV detection,offering new perspectives for future health monitoring.展开更多
Indoor visual localization relies heavily on image retrieval to ascertain location information.However,the widespread presence and high consistency of floor patterns across different images of-ten lead to the extracti...Indoor visual localization relies heavily on image retrieval to ascertain location information.However,the widespread presence and high consistency of floor patterns across different images of-ten lead to the extraction of numerous repetitive features,thereby reducing the accuracy of image retrieval.This article proposes an indoor visual localization method based on semantic segmentation and adaptive weight fusion to address the issue of ground texture interference with retrieval results.During the positioning process,an indoor semantic segmentation model is established.Semantic segmentation technology is applied to accurately delineate the ground portion of the images.Fea-ture extraction is performed on both the original database and the ground-segmented database.The vector of locally aggregated descriptors(VLAD)algorithm is then used to convert image features into a fixed-length feature representation,which improves the efficiency of image retrieval.Simul-taneously,a method for adaptive weight optimization in similarity calculation is proposed,using a-daptive weights to compute similarity for different regional features,thereby improving the accuracy of image retrieval.The experimental results indicate that this method significantly reduces ground interference and effectively utilizes ground information,thereby improving the accuracy of image retrieval.展开更多
In order to extract froth morphological feature,a bubble image adaptive segmentation method was proposed.Considering the image's low contrast and weak froth edges,froth image was coarsely segmented by using fuzzy ...In order to extract froth morphological feature,a bubble image adaptive segmentation method was proposed.Considering the image's low contrast and weak froth edges,froth image was coarsely segmented by using fuzzy c means(FCM) algorithm. Through the attributes of size and shape pattern spectrum,the optimal morphological structuring element was determined.According to the optimal parameters,some image noises were removed with an improved area opening and closing by reconstruction operation,which consist of image regional markers,and the bubbles were finely separated from each other by watershed transform.The experimental results show that the structural element can be determined adaptively by shape and size pattern spectrum,and the froth image is segmented accurately.Compared with other froth image segmentation method,the proposed method achieves much high accuracy,based on which,the bubble size and shape features are extracted effectively.展开更多
The active contour model based on local image fitting （LIF） energy is an effective method to deal with intensity inhomo- geneities, but it always conflicts with the local minimum problem because LIF has a nonconvex ...The active contour model based on local image fitting （LIF） energy is an effective method to deal with intensity inhomo- geneities, but it always conflicts with the local minimum problem because LIF has a nonconvex energy function form. At the same time, the parameters of LIF are hard to be chosen for better per- formance. A global minimization of the adaptive LIF energy model is proposed. The regularized length term which constrains the zero level set is introduced to improve the accuracy of the bound- aries, and a global minimization of the active contour model is presented, in addition, based on the statistical information of the intensity histogram, the standard deviation σ with respect to the truncated Gaussian window is automatically computed according to images. Consequently, the proposed method improves the performance and adaptivity to deal with the intensity inhomo- geneities. Experimental results for synthetic and real images show desirable performance and efficiency of the proposed method.展开更多
Remote sensing image segmentation is the basis of image understanding and analysis. However,the precision and the speed of segmentation can not meet the need of image analysis,due to strong uncertainty and rich textur...Remote sensing image segmentation is the basis of image understanding and analysis. However,the precision and the speed of segmentation can not meet the need of image analysis,due to strong uncertainty and rich texture details of remote sensing images. We proposed a new segmentation method based on Adaptive Genetic Algorithm(AGA) and Alternative Fuzzy C-Means(AFCM) . Segmentation thresholds were identified by AGA. Then the image was segmented by AFCM. The results indicate that the precision and the speed of segmentation have been greatly increased,and the accuracy of threshold selection is much higher compared with traditional Otsu and Fuzzy C-Means(FCM) segmentation methods. The segmentation results also show that multi-thresholds segmentation has been achieved by combining AGA with AFCM.展开更多
Enormousmethods have been proposed for the detection and segmentation of blur and non-blur regions of the images.Due to the limited available information about blur type,scenario and the level of blurriness,detection ...Enormousmethods have been proposed for the detection and segmentation of blur and non-blur regions of the images.Due to the limited available information about blur type,scenario and the level of blurriness,detection and segmentation is a challenging task.Hence,the performance of the blur measure operator is an essential factor and needs improvement to attain perfection.In this paper,we propose an effective blur measure based on local binary pattern(LBP)with adaptive threshold for blur detection.The sharpness metric developed based on LBP used a fixed threshold irrespective of the type and level of blur,that may not be suitable for images with variations in imaging conditions,blur amount and type.Contrarily,the proposed measure uses an adaptive threshold for each input image based on the image and blur properties to generate improved sharpness metric.The adaptive threshold is computed based on the model learned through support vector machine(SVM).The performance of the proposed method is evaluated using two different datasets and is compared with five state-of-the-art methods.Comparative analysis reveals that the proposed method performs significantly better qualitatively and quantitatively against all of the compared methods.展开更多
The use of visible and infrared remote sensing images to calculate the water area is an effective means to grasp the basic situation of water resources,and water segmentation is the premise of statistics.Generally,the...The use of visible and infrared remote sensing images to calculate the water area is an effective means to grasp the basic situation of water resources,and water segmentation is the premise of statistics.Generally,the edge features of the water in the remote sensing images are complex.When the traditional morphology is used for image segmentation,it is easy to change the image edge and affect the accuracy of image segmentation because the fixed structuring elements are used to perform morphological operations on the image.To segment water in the remote sensing image accurately,a remote sensing image water segmentation method based on adaptive morphological elliptical structuring elements is proposed.Firstly,the eigenvalue and eigenvector of the image are estimated by linear structure tensor,and the elliptical structuring elements are constructed by the eigenvalue and eigenvector.Then adaptive morphological operations are defined,combining the close operation to eliminate the influence of dark detail noise on water without overstretching the water edge,so that the water edge can be maintained more accurately.Finally,on this basis,the water area can be segmented by gray slice.The experimental results show that the proposed method has higher segmentation accuracy and the average segmentation error is less than 1.43%.展开更多
A fast image segmentation algorithm based on salient features model and spatial-frequency domain adaptive kernel is proposed to solve the accurate discriminate objects problem of online visual detection in such scenes...A fast image segmentation algorithm based on salient features model and spatial-frequency domain adaptive kernel is proposed to solve the accurate discriminate objects problem of online visual detection in such scenes of variable sample morphological characteristics,low contrast and complex background texture.Firstly,by analyzing the spectral component distribution and spatial contour feature of the image,a salient feature model is established in spatial-frequency domain.Then,the salient object detection method based on Gaussian band-pass filter and the design criterion of adaptive convolution kernel are proposed to extract the salient contour feature of the target in spatial and frequency domain.Finally,the selection and growth rules of seed points are improved by integrating the gray level and contour features of the target,and the target is segmented by seeded region growing.Experiments have been performed on Berkeley Segmentation Data Set,as well as sample images of online detection,to verify the effectiveness of the algorithm.The experimental results show that the Jaccard Similarity Coefficient of the segmentation is more than 90%,which indicates that the proposed algorithm can availably extract the target feature information,suppress the background texture and resist noise interference.Besides,the Hausdorff Distance of the segmentation is less than 10,which infers that the proposed algorithm obtains a high evaluation on the target contour preservation.The experimental results also show that the proposed algorithm significantly improves the operation efficiency while obtaining comparable segmentation performance over other algorithms.展开更多
An approach based on reinfocement learning for the automated segmentation is presented. The approach consists of two modules:segmentation module and learning module. The segmentation module uses the region-growing alg...An approach based on reinfocement learning for the automated segmentation is presented. The approach consists of two modules:segmentation module and learning module. The segmentation module uses the region-growing algorithm combined with the smooth filtering and the morphological filtering to segment mammograms. The learning module uses the segmentation output as the feedback to learn to select the optimal parameter settings of the segmentation algorithm according to the image properties using reinforcement learning techniques. The approach can adapt itself to various kinds of mammograms through training and therefore obviates the tedious and error-prone tuning of parameter settings manually. Quantitative test results show that the approach is accurate for several kinds of mammograms. Compared to previously proposed approaches,the approach is more adaptable to different mammograms.展开更多
Segmentation of pulmonary nodules in chest radiographs is a particularly challenging task due to heavy noise and superposition of ribs,vessels,and other complicated anatomical structures in lung field. In this paper,a...Segmentation of pulmonary nodules in chest radiographs is a particularly challenging task due to heavy noise and superposition of ribs,vessels,and other complicated anatomical structures in lung field. In this paper,an adaptive order polynomial fitting based raycasting algorithm is proposed for pulmonary nodule segmentation in chest radiographs. Instead of detecting nodule edge points directly,the nodule intensity profiles are first fitted by using the polynomials with adaptively determined orders. Then,the edge positions are identified through analyzing the local minimum of the fitted curves.The performance of the proposed algorithm was evaluated over an image database with 148 nodule cases in chest radiographs that were collected from a variety of digital radiograph modalities. The preliminary results show the proposed algorithm can obtain a high rate of successful segmentations.展开更多
The problem of automatic threshold selection is considered.After a brief discussion of several available techniques,an adaptive thresholding technique is proposed.It is based on the local edge information which can be...The problem of automatic threshold selection is considered.After a brief discussion of several available techniques,an adaptive thresholding technique is proposed.It is based on the local edge information which can be computed without histogramming the gray level value of the image.This method is specifically designed to deal with gradual shading situation.The effectiveness of the method is shown on a practical example.展开更多
Aim: Neurovascular abnormalities are extremely complex, due to the multitude of factors acting simultaneously on cerebral hemodynamics. Cerebral Arteriovenous Malformation (CAVM) hemo-dynamic in one of the vascular ab...Aim: Neurovascular abnormalities are extremely complex, due to the multitude of factors acting simultaneously on cerebral hemodynamics. Cerebral Arteriovenous Malformation (CAVM) hemo-dynamic in one of the vascular abnormality condition results changes in the vessels structures and hemodynamics in blood vessels. The challenge is segmenting accurate vessel region to measure hemodynamics of CAVM patients. The clinical procedure is in-vivo method to measure hemodynamics. The catheter-based procedure is difficult, as it is sometimes difficult to reach vessels sub-structures. Methods: In this paper, we have proposed adaptive vessel segmentation based on threshold technique for CAVM patients. We have compared different adaptive methods for vessel segmentation of CAVM structures. The sub-structures are modeled using lumped model to measure hemodynamics non-invasively. Results: Twenty-three CAVM patients with 150 different vessel locations of DSA datasets were studied as part of the adaptive segmentation. 30 simulated data has been evaluated for more than 150 vessels locations for sub-segmentation of vessels. The segmentation results are evaluated with accuracy of 93%. The computed p-value is smaller than the significance level 0.05. Conclusion: The adaptive segmentation using threshold based produces accurate vessel segmentation, results in better accuracy of hemodynamic measurements for DSA images for CAVM patients. The proposed adaptive segmentation helps clinicians to measure hemodynamic non-invasively for the segmented sub-structures of vessels.展开更多
A new hierarchical approach called bintree energy segmentation was presented for color image segmentation. The image features are extracted by adaptive clustering on multi-channel data at each level and used as the cr...A new hierarchical approach called bintree energy segmentation was presented for color image segmentation. The image features are extracted by adaptive clustering on multi-channel data at each level and used as the criteria to dynamically select the best chromatic channel, where the segmentation is carried out. In this approach, an extended direct energy computation method based on the Chan-Vese model was proposed to segment the selected channel, and the segmentation outputs are then fused with other channels into new images, from which a new channel with better features is selected for the second round segmentation. This procedure is repeated until the preset condition is met. Finally, a binary segmentation tree is formed, in which each leaf represents a class of objects with a distinctive color. To facilitate the data organization, image background is employed in segmentation and channels fusion. The bintree energy segmentation exploits color information involved in all channels data and tries to optimize the global segmentation result by choosing the 'best' channel for segmentation at each level. The experiments show that the method is effective in speed, accuracy and flexibility.展开更多
Road accident detection plays an important role in abnormal scene reconstruction for Intelligent Transportation Systems and abnormal events warning for autonomous driving.This paper presents a novel 3D object detector...Road accident detection plays an important role in abnormal scene reconstruction for Intelligent Transportation Systems and abnormal events warning for autonomous driving.This paper presents a novel 3D object detector and adaptive space partitioning algorithm to infer traffic accidents quantitatively.Using 2D region proposals in an RGB image,this method generates deformable frustums based on point cloud for each 2D region proposal and then frustum-wisely extracts features based on the farthest point sampling network(FPS-Net)and feature extraction network(FE-Net).Subsequently,the encoder-decoder network(ED-Net)implements 3D-oriented bounding box(OBB)regression.Meanwhile,the adaptive least square regression(ALSR)method is proposed to split 3D OBB.Finally,the reduced OBB intersection test is carried out to detect traffic accidents via separating surface theorem(SST).In the experiments of KITTI benchmark,our proposed 3D object detector outperforms other state-of-theartmethods.Meanwhile,collision detection algorithm achieves the satisfactory performance of 91.8%accuracy on our SHTA dataset.展开更多
In this paper, we propose a restricted, adaptive threshold approach for the segmentation of images of the glottis acquired from high speed video-endoscopy (HSV). The approach involves first, identifying a region of in...In this paper, we propose a restricted, adaptive threshold approach for the segmentation of images of the glottis acquired from high speed video-endoscopy (HSV). The approach involves first, identifying a region of interest (ROI) that encloses the vocal-fold motion extent for each image frame as estimated by the different image sequences. This procedure is then followed by threshold segmentation restricted within the identified ROI for each image frame of the original image sequences, or referred to as sub-image sequences. The threshold value is adapted for each sub-image frame and determined by respective minimum gray-scale value that typically corresponds to a spatial location within the glottis. The proposed approach is practical and highly efficient for segmenting a vast amount of image frames since simple threshold method is adapted. Results obtained from the segmentation of representative clinical image sequences are presented to verify the proposed method.展开更多
Neuronal soma segmentation plays a crucial role in neuroscience applications.However,the fine structure,such as boundaries,small-volume neuronal somata and fibers,are commonly present in cell images,which pose a chall...Neuronal soma segmentation plays a crucial role in neuroscience applications.However,the fine structure,such as boundaries,small-volume neuronal somata and fibers,are commonly present in cell images,which pose a challenge for accurate segmentation.In this paper,we propose a 3D semantic segmentation network for neuronal soma segmentation to address this issue.Using an encoding-decoding structure,we introduce a Multi-Scale feature extraction and Adaptive Weighting fusion module(MSAW)after each encoding block.The MSAW module can not only emphasize the fine structures via an upsampling strategy,but also provide pixel-wise weights to measure the importance of the multi-scale features.Additionally,a dynamic convolution instead of normal convolution is employed to better adapt the network to input data with different distributions.The proposed MSAW-based semantic segmentation network(MSAW-Net)was evaluated on three neuronal soma images from mouse brain and one neuronal soma image from macaque brain,demonstrating the efficiency of the proposed method.It achieved an F1 score of 91.8%on Fezf2-2A-CreER dataset,97.1%on LSL-H2B-GFP dataset,82.8%on Thy1-EGFP-Mline dataset,and 86.9%on macaque dataset,achieving improvements over the 3D U-Net model by 3.1%,3.3%,3.9%,and 2.3%,respectively.展开更多
Despite its remarkable performance on natural images,the segment anything model(SAM)lacks domain-specific information in medical imaging.and faces the challenge of losing local multi-scale information in the encoding ...Despite its remarkable performance on natural images,the segment anything model(SAM)lacks domain-specific information in medical imaging.and faces the challenge of losing local multi-scale information in the encoding phase.This paper presents a medical image segmentation model based on SAM with a local multi-scale feature encoder(LMSFE-SAM)to address the issues above.Firstly,based on the SAM,a local multi-scale feature encoder is introduced to improve the representation of features within local receptive field,thereby supplying the Vision Transformer(ViT)branch in SAM with enriched local multi-scale contextual information.At the same time,a multiaxial Hadamard product module(MHPM)is incorporated into the local multi-scale feature encoder in a lightweight manner to reduce the quadratic complexity and noise interference.Subsequently,a cross-branch balancing adapter is designed to balance the local and global information between the local multi-scale feature encoder and the ViT encoder in SAM.Finally,to obtain smaller input image size and to mitigate overlapping in patch embeddings,the size of the input image is reduced from 1024×1024 pixels to 256×256 pixels,and a multidimensional information adaptation component is developed,which includes feature adapters,position adapters,and channel-spatial adapters.This component effectively integrates the information from small-sized medical images into SAM,enhancing its suitability for clinical deployment.The proposed model demonstrates an average enhancement ranging from 0.0387 to 0.3191 across six objective evaluation metrics on BUSI,DDTI,and TN3K datasets compared to eight other representative image segmentation models.This significantly enhances the performance of the SAM on medical images,providing clinicians with a powerful tool in clinical diagnosis.展开更多
Since the problems of branch loss and fracture in retinal blood vessel segmentation algorithms,an image segmentation method is proposed based on improved pulse coupled neural network(PCNN)and gray wolf optimization al...Since the problems of branch loss and fracture in retinal blood vessel segmentation algorithms,an image segmentation method is proposed based on improved pulse coupled neural network(PCNN)and gray wolf optimization algorithm(GWO).Simplifying the neuron input domain and neuron connection domain of the PCNN network,increasing the gradient information factor in the internal activity items,reducing the model parameters,enhancing the pulse issuing ability,and the optimal parameters of the network are automatically obtained based on multiple feature evaluation criteria and the GWO algorithm.The test in the public data set drive shows that the sensitivity,accuracy,precision,and specificity of the algorithm are 0.799549,0.962789,0.889163,and 0.986552,respectively.The accuracy and specificity are better than the classical segmentation algorithm.It solved the influence of low illumination,optic disc highlight,and foveal shadow on vascular segmentation,and showed excellent performance of vessel connectivity and terminal sensitivity.展开更多
The segmentation of unlabeled medical images is troublesome due to the high cost of annotation, and unsupervised domain adaptation is one solution to this. In this paper, an improved unsupervised domain adaptation met...The segmentation of unlabeled medical images is troublesome due to the high cost of annotation, and unsupervised domain adaptation is one solution to this. In this paper, an improved unsupervised domain adaptation method was proposed. The proposed method considered both global alignment and category-wise alignment. First, we aligned the appearance of two domains by image transformation. Second, we aligned the output maps of two domains in a global way. Then, we decomposed the semantic prediction map by category, aligning the prediction maps in a category-wise manner. Finally, we evaluated the proposed method on the 2017 Multi-Modality Whole Heart Segmentation Challenge dataset, and obtained 82.1 on the dice similarity coefficient and 4.6 on the average symmetric surface distance, demonstrating the effectiveness of the combination of global alignment and category-wise alignment.展开更多
基金Australian Research Council Project(FL-170100117).
文摘To avoid the laborious annotation process for dense prediction tasks like semantic segmentation,unsupervised domain adaptation(UDA)methods have been proposed to leverage the abundant annotations from a source domain,such as virtual world(e.g.,3D games),and adapt models to the target domain(the real world)by narrowing the domain discrepancies.However,because of the large domain gap,directly aligning two distinct domains without considering the intermediates leads to inefficient alignment and inferior adaptation.To address this issue,we propose a novel learnable evolutionary Category Intermediates(CIs)guided UDA model named Leci,which enables the information transfer between the two domains via two processes,i.e.,Distilling and Blending.Starting from a random initialization,the CIs learn shared category-wise semantics automatically from two domains in the Distilling process.Then,the learned semantics in the CIs are sent back to blend the domain features through a residual attentive fusion(RAF)module,such that the categorywise features of both domains shift towards each other.As the CIs progressively and consistently learn from the varying feature distributions during training,they are evolutionary to guide the model to achieve category-wise feature alignment.Experiments on both GTA5 and SYNTHIA datasets demonstrate Leci's superiority over prior representative methods.
基金supported by National Natural Science Foundation of China(Nos.62320106002,U22A2014)National Key Research and Development Program of China(No.2021YFA1401103)+2 种基金2022 Wuxi Taihu Talent Program:Innovative Leading Talent Team(No.1096010241230120)Fundamental Research Funds for Central Universities(No.1322050205250910)Wuxi Municipal Basic Research Project(No.K20241026).
文摘Heart rate variability(HRV),as a key indicator for evaluating autonomic nervous system function,has significant value in areas such as cardiovascular disease screening and emotion monitoring.Although traditional contact-based measurement methods offer high precision,they suffer from issues such as poor comfort and low user compliance.This paper proposes a non-contact HRV monitoring method using frequency modulated continuous wave(FMCW)radar,highlighting adaptive cycle segmentation and peak extraction as core innovations.Key advantages of this method include:1)effective suppression of motion artifacts and respiratory harmonics by leveraging cardiac energy concentration;2)precise heartbeat cycle identification across physiological states via adaptive segmentation,addressing time-varying differences;3)adaptive threshold adjustment using discrete energy signals and a support vector machine(SVM)model based on morphological-temporal-spectral characteristics,reducing complexity while maintaining precision.Previous approaches predominantly process radar signals holistically through algorithms to uniformly extract inter-beat intervals(IBIs),which may result in high computational complexity and inadequate dynamic adaptability.In contrast,our method achieved higher precision than conventional holistic processing approaches,while maintaining comparable precision with lower computational complexity than previous optimization algorithms.Experimental results demonstrate that the system achieves an average IBI error of 8.28 ms(RMSE of 15.3 ms),which is reduced by about 66%compared with the traditional holistically peak seeking method.The average errors of SDNN and RMSSD are 2.65 ms and 4.33 ms,respectively.More than 92%of the IBI errors are controlled within 20 ms.The distance adaptability test showed that although the accuracy of long-distance measurement decreased slightly(<6 ms),the overall detection performance remained robust at different distances.This study provided a novel estimation algorithm for non-contact HRV detection,offering new perspectives for future health monitoring.
基金Supported by the National Natural Science Foundation of China(No.61971162,61771186)the Natural Science Foundation of Heilongjiang Province(No.PL2024F025)+2 种基金the Open Research Fund of National Mobile Communications Research Laboratory Southeast University(No.2023D07)the Outstanding Youth Program of Natural Science Foundation of Heilongjiang Province(No.YQ2020F012)the Funda-mental Scientific Research Funds of Heilongjiang Province(No.2022-KYYWF-1050).
文摘Indoor visual localization relies heavily on image retrieval to ascertain location information.However,the widespread presence and high consistency of floor patterns across different images of-ten lead to the extraction of numerous repetitive features,thereby reducing the accuracy of image retrieval.This article proposes an indoor visual localization method based on semantic segmentation and adaptive weight fusion to address the issue of ground texture interference with retrieval results.During the positioning process,an indoor semantic segmentation model is established.Semantic segmentation technology is applied to accurately delineate the ground portion of the images.Fea-ture extraction is performed on both the original database and the ground-segmented database.The vector of locally aggregated descriptors(VLAD)algorithm is then used to convert image features into a fixed-length feature representation,which improves the efficiency of image retrieval.Simul-taneously,a method for adaptive weight optimization in similarity calculation is proposed,using a-daptive weights to compute similarity for different regional features,thereby improving the accuracy of image retrieval.The experimental results indicate that this method significantly reduces ground interference and effectively utilizes ground information,thereby improving the accuracy of image retrieval.
基金Projects(60634020,60874069) supported by the National Natural Science Foundation of ChinaProject(2009AA04Z137) supported by the National High-Tech Research and Development Program of China
文摘In order to extract froth morphological feature,a bubble image adaptive segmentation method was proposed.Considering the image's low contrast and weak froth edges,froth image was coarsely segmented by using fuzzy c means(FCM) algorithm. Through the attributes of size and shape pattern spectrum,the optimal morphological structuring element was determined.According to the optimal parameters,some image noises were removed with an improved area opening and closing by reconstruction operation,which consist of image regional markers,and the bubbles were finely separated from each other by watershed transform.The experimental results show that the structural element can be determined adaptively by shape and size pattern spectrum,and the froth image is segmented accurately.Compared with other froth image segmentation method,the proposed method achieves much high accuracy,based on which,the bubble size and shape features are extracted effectively.
基金supported by the National Natural Science Foundation of China(6100317061372142+2 种基金61103121)the Fundamental Research Funds for the Central Universities SCUT(2014ZG0037)the China Postdoctoral Science Foundation(2012M511561)
文摘The active contour model based on local image fitting （LIF） energy is an effective method to deal with intensity inhomo- geneities, but it always conflicts with the local minimum problem because LIF has a nonconvex energy function form. At the same time, the parameters of LIF are hard to be chosen for better per- formance. A global minimization of the adaptive LIF energy model is proposed. The regularized length term which constrains the zero level set is introduced to improve the accuracy of the bound- aries, and a global minimization of the active contour model is presented, in addition, based on the statistical information of the intensity histogram, the standard deviation σ with respect to the truncated Gaussian window is automatically computed according to images. Consequently, the proposed method improves the performance and adaptivity to deal with the intensity inhomo- geneities. Experimental results for synthetic and real images show desirable performance and efficiency of the proposed method.
基金Under the auspices of National Natural Science Foundation of China (No. 30370267)Key Project of Jilin Provincial Science & Technology Department (No. 20075014)
文摘Remote sensing image segmentation is the basis of image understanding and analysis. However,the precision and the speed of segmentation can not meet the need of image analysis,due to strong uncertainty and rich texture details of remote sensing images. We proposed a new segmentation method based on Adaptive Genetic Algorithm(AGA) and Alternative Fuzzy C-Means(AFCM) . Segmentation thresholds were identified by AGA. Then the image was segmented by AFCM. The results indicate that the precision and the speed of segmentation have been greatly increased,and the accuracy of threshold selection is much higher compared with traditional Otsu and Fuzzy C-Means(FCM) segmentation methods. The segmentation results also show that multi-thresholds segmentation has been achieved by combining AGA with AFCM.
基金This work is supported by the BK-21 FOUR program and by the Creative Challenge Research Program(2021R1I1A1A01052521)through National Research Foundation of Korea(NRF)under Ministry of Education,Korea.
文摘Enormousmethods have been proposed for the detection and segmentation of blur and non-blur regions of the images.Due to the limited available information about blur type,scenario and the level of blurriness,detection and segmentation is a challenging task.Hence,the performance of the blur measure operator is an essential factor and needs improvement to attain perfection.In this paper,we propose an effective blur measure based on local binary pattern(LBP)with adaptive threshold for blur detection.The sharpness metric developed based on LBP used a fixed threshold irrespective of the type and level of blur,that may not be suitable for images with variations in imaging conditions,blur amount and type.Contrarily,the proposed measure uses an adaptive threshold for each input image based on the image and blur properties to generate improved sharpness metric.The adaptive threshold is computed based on the model learned through support vector machine(SVM).The performance of the proposed method is evaluated using two different datasets and is compared with five state-of-the-art methods.Comparative analysis reveals that the proposed method performs significantly better qualitatively and quantitatively against all of the compared methods.
基金National Natural Science Foundation of China(No.61761027)Graduate Education Reform Project of Lanzhou Jiaotong University(No.1600120101)。
文摘The use of visible and infrared remote sensing images to calculate the water area is an effective means to grasp the basic situation of water resources,and water segmentation is the premise of statistics.Generally,the edge features of the water in the remote sensing images are complex.When the traditional morphology is used for image segmentation,it is easy to change the image edge and affect the accuracy of image segmentation because the fixed structuring elements are used to perform morphological operations on the image.To segment water in the remote sensing image accurately,a remote sensing image water segmentation method based on adaptive morphological elliptical structuring elements is proposed.Firstly,the eigenvalue and eigenvector of the image are estimated by linear structure tensor,and the elliptical structuring elements are constructed by the eigenvalue and eigenvector.Then adaptive morphological operations are defined,combining the close operation to eliminate the influence of dark detail noise on water without overstretching the water edge,so that the water edge can be maintained more accurately.Finally,on this basis,the water area can be segmented by gray slice.The experimental results show that the proposed method has higher segmentation accuracy and the average segmentation error is less than 1.43%.
基金supported by National Natural Science Foundation of China[grant numbers 61573233]Natural Science Foundation of Guangdong,China[grant numbers 2021A1515010661]+1 种基金Special projects in key fields of colleges and universities in Guangdong Province[grant numbers 2020ZDZX2005]Innovation Team Project of University in Guangdong Province[grant numbers 2015KCXTD018].
文摘A fast image segmentation algorithm based on salient features model and spatial-frequency domain adaptive kernel is proposed to solve the accurate discriminate objects problem of online visual detection in such scenes of variable sample morphological characteristics,low contrast and complex background texture.Firstly,by analyzing the spectral component distribution and spatial contour feature of the image,a salient feature model is established in spatial-frequency domain.Then,the salient object detection method based on Gaussian band-pass filter and the design criterion of adaptive convolution kernel are proposed to extract the salient contour feature of the target in spatial and frequency domain.Finally,the selection and growth rules of seed points are improved by integrating the gray level and contour features of the target,and the target is segmented by seeded region growing.Experiments have been performed on Berkeley Segmentation Data Set,as well as sample images of online detection,to verify the effectiveness of the algorithm.The experimental results show that the Jaccard Similarity Coefficient of the segmentation is more than 90%,which indicates that the proposed algorithm can availably extract the target feature information,suppress the background texture and resist noise interference.Besides,the Hausdorff Distance of the segmentation is less than 10,which infers that the proposed algorithm obtains a high evaluation on the target contour preservation.The experimental results also show that the proposed algorithm significantly improves the operation efficiency while obtaining comparable segmentation performance over other algorithms.
文摘An approach based on reinfocement learning for the automated segmentation is presented. The approach consists of two modules:segmentation module and learning module. The segmentation module uses the region-growing algorithm combined with the smooth filtering and the morphological filtering to segment mammograms. The learning module uses the segmentation output as the feedback to learn to select the optimal parameter settings of the segmentation algorithm according to the image properties using reinforcement learning techniques. The approach can adapt itself to various kinds of mammograms through training and therefore obviates the tedious and error-prone tuning of parameter settings manually. Quantitative test results show that the approach is accurate for several kinds of mammograms. Compared to previously proposed approaches,the approach is more adaptable to different mammograms.
基金Innovation Program of Shanghai Municipal Education Commission,China(No.13YZ136)
文摘Segmentation of pulmonary nodules in chest radiographs is a particularly challenging task due to heavy noise and superposition of ribs,vessels,and other complicated anatomical structures in lung field. In this paper,an adaptive order polynomial fitting based raycasting algorithm is proposed for pulmonary nodule segmentation in chest radiographs. Instead of detecting nodule edge points directly,the nodule intensity profiles are first fitted by using the polynomials with adaptively determined orders. Then,the edge positions are identified through analyzing the local minimum of the fitted curves.The performance of the proposed algorithm was evaluated over an image database with 148 nodule cases in chest radiographs that were collected from a variety of digital radiograph modalities. The preliminary results show the proposed algorithm can obtain a high rate of successful segmentations.
文摘The problem of automatic threshold selection is considered.After a brief discussion of several available techniques,an adaptive thresholding technique is proposed.It is based on the local edge information which can be computed without histogramming the gray level value of the image.This method is specifically designed to deal with gradual shading situation.The effectiveness of the method is shown on a practical example.
文摘Aim: Neurovascular abnormalities are extremely complex, due to the multitude of factors acting simultaneously on cerebral hemodynamics. Cerebral Arteriovenous Malformation (CAVM) hemo-dynamic in one of the vascular abnormality condition results changes in the vessels structures and hemodynamics in blood vessels. The challenge is segmenting accurate vessel region to measure hemodynamics of CAVM patients. The clinical procedure is in-vivo method to measure hemodynamics. The catheter-based procedure is difficult, as it is sometimes difficult to reach vessels sub-structures. Methods: In this paper, we have proposed adaptive vessel segmentation based on threshold technique for CAVM patients. We have compared different adaptive methods for vessel segmentation of CAVM structures. The sub-structures are modeled using lumped model to measure hemodynamics non-invasively. Results: Twenty-three CAVM patients with 150 different vessel locations of DSA datasets were studied as part of the adaptive segmentation. 30 simulated data has been evaluated for more than 150 vessels locations for sub-segmentation of vessels. The segmentation results are evaluated with accuracy of 93%. The computed p-value is smaller than the significance level 0.05. Conclusion: The adaptive segmentation using threshold based produces accurate vessel segmentation, results in better accuracy of hemodynamic measurements for DSA images for CAVM patients. The proposed adaptive segmentation helps clinicians to measure hemodynamic non-invasively for the segmented sub-structures of vessels.
基金The National Basic Research Program (973) of China (No. 2003CB716103) The Key Lab of Image Processing & Intelligent control of National Education Ministry (No. TKLJ0306)
文摘A new hierarchical approach called bintree energy segmentation was presented for color image segmentation. The image features are extracted by adaptive clustering on multi-channel data at each level and used as the criteria to dynamically select the best chromatic channel, where the segmentation is carried out. In this approach, an extended direct energy computation method based on the Chan-Vese model was proposed to segment the selected channel, and the segmentation outputs are then fused with other channels into new images, from which a new channel with better features is selected for the second round segmentation. This procedure is repeated until the preset condition is met. Finally, a binary segmentation tree is formed, in which each leaf represents a class of objects with a distinctive color. To facilitate the data organization, image background is employed in segmentation and channels fusion. The bintree energy segmentation exploits color information involved in all channels data and tries to optimize the global segmentation result by choosing the 'best' channel for segmentation at each level. The experiments show that the method is effective in speed, accuracy and flexibility.
基金National Natural Science Foundation of China(No.51805312)in part by Shanghai Sailing Program(No.18YF1409400)+4 种基金in part by Training and Funding Program of Shanghai College young teachers(No.ZZGCD15102)in part by Scientific Research Project of Shanghai University of Engineering Science(No.2016-19)in part by Science and Technology Commission of Shanghai Municipality(No.19030501100)in part by the Shanghai University of Engineering Science Innovation Fund for Graduate Students(No.18KY0613)in part by National Key R&D Program of China(No.2016YFC0802900).
文摘Road accident detection plays an important role in abnormal scene reconstruction for Intelligent Transportation Systems and abnormal events warning for autonomous driving.This paper presents a novel 3D object detector and adaptive space partitioning algorithm to infer traffic accidents quantitatively.Using 2D region proposals in an RGB image,this method generates deformable frustums based on point cloud for each 2D region proposal and then frustum-wisely extracts features based on the farthest point sampling network(FPS-Net)and feature extraction network(FE-Net).Subsequently,the encoder-decoder network(ED-Net)implements 3D-oriented bounding box(OBB)regression.Meanwhile,the adaptive least square regression(ALSR)method is proposed to split 3D OBB.Finally,the reduced OBB intersection test is carried out to detect traffic accidents via separating surface theorem(SST).In the experiments of KITTI benchmark,our proposed 3D object detector outperforms other state-of-theartmethods.Meanwhile,collision detection algorithm achieves the satisfactory performance of 91.8%accuracy on our SHTA dataset.
文摘In this paper, we propose a restricted, adaptive threshold approach for the segmentation of images of the glottis acquired from high speed video-endoscopy (HSV). The approach involves first, identifying a region of interest (ROI) that encloses the vocal-fold motion extent for each image frame as estimated by the different image sequences. This procedure is then followed by threshold segmentation restricted within the identified ROI for each image frame of the original image sequences, or referred to as sub-image sequences. The threshold value is adapted for each sub-image frame and determined by respective minimum gray-scale value that typically corresponds to a spatial location within the glottis. The proposed approach is practical and highly efficient for segmenting a vast amount of image frames since simple threshold method is adapted. Results obtained from the segmentation of representative clinical image sequences are presented to verify the proposed method.
基金supported by the STI2030-Major-Projects(No.2021ZD0200104)the National Natural Science Foundations of China under Grant 61771437.
文摘Neuronal soma segmentation plays a crucial role in neuroscience applications.However,the fine structure,such as boundaries,small-volume neuronal somata and fibers,are commonly present in cell images,which pose a challenge for accurate segmentation.In this paper,we propose a 3D semantic segmentation network for neuronal soma segmentation to address this issue.Using an encoding-decoding structure,we introduce a Multi-Scale feature extraction and Adaptive Weighting fusion module(MSAW)after each encoding block.The MSAW module can not only emphasize the fine structures via an upsampling strategy,but also provide pixel-wise weights to measure the importance of the multi-scale features.Additionally,a dynamic convolution instead of normal convolution is employed to better adapt the network to input data with different distributions.The proposed MSAW-based semantic segmentation network(MSAW-Net)was evaluated on three neuronal soma images from mouse brain and one neuronal soma image from macaque brain,demonstrating the efficiency of the proposed method.It achieved an F1 score of 91.8%on Fezf2-2A-CreER dataset,97.1%on LSL-H2B-GFP dataset,82.8%on Thy1-EGFP-Mline dataset,and 86.9%on macaque dataset,achieving improvements over the 3D U-Net model by 3.1%,3.3%,3.9%,and 2.3%,respectively.
基金supported by Natural Science Foundation Programme of Gansu Province(No.24JRRA231)National Natural Science Foundation of China(No.62061023)Gansu Provincial Science and Technology Plan Key Research and Development Program Project(No.24YFFA024).
文摘Despite its remarkable performance on natural images,the segment anything model(SAM)lacks domain-specific information in medical imaging.and faces the challenge of losing local multi-scale information in the encoding phase.This paper presents a medical image segmentation model based on SAM with a local multi-scale feature encoder(LMSFE-SAM)to address the issues above.Firstly,based on the SAM,a local multi-scale feature encoder is introduced to improve the representation of features within local receptive field,thereby supplying the Vision Transformer(ViT)branch in SAM with enriched local multi-scale contextual information.At the same time,a multiaxial Hadamard product module(MHPM)is incorporated into the local multi-scale feature encoder in a lightweight manner to reduce the quadratic complexity and noise interference.Subsequently,a cross-branch balancing adapter is designed to balance the local and global information between the local multi-scale feature encoder and the ViT encoder in SAM.Finally,to obtain smaller input image size and to mitigate overlapping in patch embeddings,the size of the input image is reduced from 1024×1024 pixels to 256×256 pixels,and a multidimensional information adaptation component is developed,which includes feature adapters,position adapters,and channel-spatial adapters.This component effectively integrates the information from small-sized medical images into SAM,enhancing its suitability for clinical deployment.The proposed model demonstrates an average enhancement ranging from 0.0387 to 0.3191 across six objective evaluation metrics on BUSI,DDTI,and TN3K datasets compared to eight other representative image segmentation models.This significantly enhances the performance of the SAM on medical images,providing clinicians with a powerful tool in clinical diagnosis.
基金The 2019 Guangdong Province General College Youth Innovation Talent Project(2019GKQNCX009)。
文摘Since the problems of branch loss and fracture in retinal blood vessel segmentation algorithms,an image segmentation method is proposed based on improved pulse coupled neural network(PCNN)and gray wolf optimization algorithm(GWO).Simplifying the neuron input domain and neuron connection domain of the PCNN network,increasing the gradient information factor in the internal activity items,reducing the model parameters,enhancing the pulse issuing ability,and the optimal parameters of the network are automatically obtained based on multiple feature evaluation criteria and the GWO algorithm.The test in the public data set drive shows that the sensitivity,accuracy,precision,and specificity of the algorithm are 0.799549,0.962789,0.889163,and 0.986552,respectively.The accuracy and specificity are better than the classical segmentation algorithm.It solved the influence of low illumination,optic disc highlight,and foveal shadow on vascular segmentation,and showed excellent performance of vessel connectivity and terminal sensitivity.
文摘The segmentation of unlabeled medical images is troublesome due to the high cost of annotation, and unsupervised domain adaptation is one solution to this. In this paper, an improved unsupervised domain adaptation method was proposed. The proposed method considered both global alignment and category-wise alignment. First, we aligned the appearance of two domains by image transformation. Second, we aligned the output maps of two domains in a global way. Then, we decomposed the semantic prediction map by category, aligning the prediction maps in a category-wise manner. Finally, we evaluated the proposed method on the 2017 Multi-Modality Whole Heart Segmentation Challenge dataset, and obtained 82.1 on the dice similarity coefficient and 4.6 on the average symmetric surface distance, demonstrating the effectiveness of the combination of global alignment and category-wise alignment.
