In this paper, we propose a depth image generation method by stereo matching on super-pixel (SP) basis. In the proposed method, block matching is performed only at the center of the SP, and the obtained disparity is a...In this paper, we propose a depth image generation method by stereo matching on super-pixel (SP) basis. In the proposed method, block matching is performed only at the center of the SP, and the obtained disparity is applied to all pixels of the SP. Next, in order to improve the disparity, a new SP-based cost filter is introduced. This filter multiplies the matching cost of the surrounding SP by a weight based on reliability and similarity and sums the weighted costs of neighbors. In addition, we propose two new error checking methods. One-way check uses only a unidirectional disparity estimation with a small amount of calculation to detect errors. Cross recovery uses cross checking and error recovery to repair lacks of objects that are problematic with SP-based matching. As a result of the experiment, the execution time of the proposed method using the one-way check was about 1/100 of the full search, and the accuracy was almost equivalent. The accuracy using cross recovery exceeded the full search, and the execution time was about 1/60. Speeding up while maintaining accuracy increases the application range of depth images.展开更多
Conferring to the American Association of Neurological Surgeons(AANS)survey,85%to 99%of people are affected by spinal cord tumors.The symptoms are varied depending on the tumor’s location and size.Up-to-the-min-ute,b...Conferring to the American Association of Neurological Surgeons(AANS)survey,85%to 99%of people are affected by spinal cord tumors.The symptoms are varied depending on the tumor’s location and size.Up-to-the-min-ute,back pain is one of the essential symptoms,but it does not have a specific symptom to recognize at the earlier stage.Numerous significant research studies have been conducted to improve spine tumor recognition accuracy.Nevertheless,the traditional systems are consuming high time to extract the specific region and features.Improper identification of the tumor region affects the predictive tumor rate and causes the maximum error-classification problem.Consequently,in this work,Super-pixel analytics Numerical Characteristics Disintegration Model(SNCDM)is used to segment the tumor affected region.Estimating the super-pix-els of the affected region by this method reduces the variance between the iden-tified pixels.Further,the super-pixels are selected according to the optimized convolution network that effectively extracts the vertebral super-pixels features.Derived super-pixels improve the network learning and training process,which minimizes the maximum error classification problem also the efficiency of the system was evaluated using experimental results and analysis.展开更多
Automatic segmentation and recognition of content and element information in color geological map are of great significance for researchers to analyze the distribution of mineral resources and predict disaster informa...Automatic segmentation and recognition of content and element information in color geological map are of great significance for researchers to analyze the distribution of mineral resources and predict disaster information.This article focuses on color planar raster geological map(geological maps include planar geological maps,columnar maps,and profiles).While existing deep learning approaches are often used to segment general images,their performance is limited due to complex elements,diverse regional features,and complicated backgrounds for color geological map in the domain of geoscience.To address the issue,a color geological map segmentation model is proposed that combines the Felz clustering algorithm and an improved SE-UNet deep learning network(named GeoMSeg).Firstly,a symmetrical encoder-decoder structure backbone network based on UNet is constructed,and the channel attention mechanism SENet has been incorporated to augment the network’s capacity for feature representation,enabling the model to purposefully extract map information.The SE-UNet network is employed for feature extraction from the geological map and obtain coarse segmentation results.Secondly,the Felz clustering algorithm is used for super pixel pre-segmentation of geological maps.The coarse segmentation results are refined and modified based on the super pixel pre-segmentation results to obtain the final segmentation results.This study applies GeoMSeg to the constructed dataset,and the experimental results show that the algorithm proposed in this paper has superior performance compared to other mainstream map segmentation models,with an accuracy of 91.89%and a MIoU of 71.91%.展开更多
In the field of neutronics analysis, it is imperative to develop computer-aided modeling technology for Monte Carlo codes to address the increasing complexity of reactor core components by converting 3D CAD model(boun...In the field of neutronics analysis, it is imperative to develop computer-aided modeling technology for Monte Carlo codes to address the increasing complexity of reactor core components by converting 3D CAD model(boundary representation, BREP) to MC model(constructive solid geometry, CSG). Separation-based conversion from BREP to CSG is widely used in computer-aided modeling MC codes because of its high efficiency, reliability, and easy implementation. However, the current separation-based BREP-CSG conversion is poor for processing complex CAD models, and it is necessary to divide a complex model into several simple models before applying the separation-based conversion algorithm, which is time-consuming and tedious. To avoid manual segmentation, this study proposed a MeshCNN-based 3D-shape segmentation algorithm to automatically separate a complex model. The proposed 3D-shape segmentation algorithm was combined with separation-based BREP-CSG conversion algorithms to directly convert complex models.The proposed algorithm was integrated into the computeraided modeling software cosVMPT and validated using the Chinese fusion engineering testing reactor model. The results demonstrate that the MeshCNN-based BREP-CSG conversion algorithm has a better performance and higher efficiency, particularly in terms of CPU time, and the conversion result is more intuitive and consistent with the intention of the modeler.展开更多
To segment the tumor region precisely is a prerequisite for ultrasound navigation and treatment. In this paper, a normalized cut method to segment tumor ultrasound image is proposed by means of simple linear iterative...To segment the tumor region precisely is a prerequisite for ultrasound navigation and treatment. In this paper, a normalized cut method to segment tumor ultrasound image is proposed by means of simple linear iterative clustering for presegmentation procedure. The first step, we use simple linear iterative clustering algorithm to divide the image into a number of homogeneous over-segmented regions. Then, these regions are regarded as nodes, and a similarity matrix is constructed by comparing the histograms of each two regions. Finally, we apply the Ncut method to merging the over-segmented regions, then the image segmentation process is completed. The results show that the proposed segmentation scheme handles the strong speckle noise, low contrast, and weak edges well in ultrasound image. Our method has high segmentation precision and computation efficiency than the pixel-based Ncut method.展开更多
Digital holography has high potentials for future 3D imaging and display technology.We present a method for a dynamic full-color digital holographic 3D display on single digital micro-mirror device(DMD)with full-color...Digital holography has high potentials for future 3D imaging and display technology.We present a method for a dynamic full-color digital holographic 3D display on single digital micro-mirror device(DMD)with full-color,high-speed and high-fidelity characteristics.We combine the square regions of adjacent micro-mirrors into super-pixels that can modulate amplitude and phase independently.Gray images are achieved by amplitude modulation and precise positioning of each color is achieved by phase modulation.The proposed method realizes a full-color imaging based on the three primary colors and achieves measured structural similarity of more than 88%and color similarity of more than 98%,while retaining the high switch speed of 9 kHz,thus achieving dynamic full-color 3D display on charge-coupled device(CCD).展开更多
Super-pixel algorithms based on convolutional neural networks with fuzzy C-means clustering are widely used for high-spatial-resolution remote sensing images segmentation.However,this model requires the number of clus...Super-pixel algorithms based on convolutional neural networks with fuzzy C-means clustering are widely used for high-spatial-resolution remote sensing images segmentation.However,this model requires the number of clusters to be set manually,resulting in a low automation degree due to the complexity of the iterative clustering process.To address this problem,a segmentation method based on a self-learning super-pixel network(SLSP-Net)and modified automatic fuzzy clustering(MAFC)is proposed.SLSP-Net performs feature extraction,non-iterative clustering,and gradient reconstruction.A lightweight feature embedder is adopted for feature extraction,thus expanding the receiving range and generating multi-scale features.Automatic matching is used for non-iterative clustering,and the overfitting of the network model is overcome by adaptively adjusting the gradient weight parameters,providing a better irregular super-pixel neighborhood structure.An optimized density peak algorithm is adopted for MAFC.Based on the obtained super-pixel image,this maximizes the robust decision-making interval,which enhances the automation of regional clustering.Finally,prior entropy fuzzy C-means clustering is applied to optimize the robust decision-making and obtain the final segmentation result.Experimental results show that the proposed model offers reduced experimental complexity and achieves good performance,realizing not only automatic image segmentation,but also good segmentation results.展开更多
Superpixel as an important pre-processing technique has been successfully used in many vision applications. In this paper, we proposed a region merging method to improve superpixel segmentation accuracy with low compu...Superpixel as an important pre-processing technique has been successfully used in many vision applications. In this paper, we proposed a region merging method to improve superpixel segmentation accuracy with low computational cost. We first segmented the image into many accurate small regions, and then progressively agglomerated them until the desired region number was reached. The region merging weight was derived from a novel energy function, which encourages the superpixel with color consistency and similar size. Experimental results on the Berkeley BSDS500 data set showed that our region merging method can significantly improve the accuracy of superpixel segmentation. Moreover, the region merging method only need 50ms to process a 481x321 image on a single Intel i3 CPU at 2.5 GHz.展开更多
文摘In this paper, we propose a depth image generation method by stereo matching on super-pixel (SP) basis. In the proposed method, block matching is performed only at the center of the SP, and the obtained disparity is applied to all pixels of the SP. Next, in order to improve the disparity, a new SP-based cost filter is introduced. This filter multiplies the matching cost of the surrounding SP by a weight based on reliability and similarity and sums the weighted costs of neighbors. In addition, we propose two new error checking methods. One-way check uses only a unidirectional disparity estimation with a small amount of calculation to detect errors. Cross recovery uses cross checking and error recovery to repair lacks of objects that are problematic with SP-based matching. As a result of the experiment, the execution time of the proposed method using the one-way check was about 1/100 of the full search, and the accuracy was almost equivalent. The accuracy using cross recovery exceeded the full search, and the execution time was about 1/60. Speeding up while maintaining accuracy increases the application range of depth images.
文摘Conferring to the American Association of Neurological Surgeons(AANS)survey,85%to 99%of people are affected by spinal cord tumors.The symptoms are varied depending on the tumor’s location and size.Up-to-the-min-ute,back pain is one of the essential symptoms,but it does not have a specific symptom to recognize at the earlier stage.Numerous significant research studies have been conducted to improve spine tumor recognition accuracy.Nevertheless,the traditional systems are consuming high time to extract the specific region and features.Improper identification of the tumor region affects the predictive tumor rate and causes the maximum error-classification problem.Consequently,in this work,Super-pixel analytics Numerical Characteristics Disintegration Model(SNCDM)is used to segment the tumor affected region.Estimating the super-pix-els of the affected region by this method reduces the variance between the iden-tified pixels.Further,the super-pixels are selected according to the optimized convolution network that effectively extracts the vertebral super-pixels features.Derived super-pixels improve the network learning and training process,which minimizes the maximum error classification problem also the efficiency of the system was evaluated using experimental results and analysis.
基金financially supported by the Natural Science Foundation of China(42301492)the Open Fund of Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering(2022SDSJ04,2024SDSJ03)+1 种基金the Opening Fund of Key Laboratory of Geological Survey and Evaluation of Ministry of Education(GLAB 2023ZR01,GLAB2024ZR08)the Fundamental Research Funds for the Central Universities.
文摘Automatic segmentation and recognition of content and element information in color geological map are of great significance for researchers to analyze the distribution of mineral resources and predict disaster information.This article focuses on color planar raster geological map(geological maps include planar geological maps,columnar maps,and profiles).While existing deep learning approaches are often used to segment general images,their performance is limited due to complex elements,diverse regional features,and complicated backgrounds for color geological map in the domain of geoscience.To address the issue,a color geological map segmentation model is proposed that combines the Felz clustering algorithm and an improved SE-UNet deep learning network(named GeoMSeg).Firstly,a symmetrical encoder-decoder structure backbone network based on UNet is constructed,and the channel attention mechanism SENet has been incorporated to augment the network’s capacity for feature representation,enabling the model to purposefully extract map information.The SE-UNet network is employed for feature extraction from the geological map and obtain coarse segmentation results.Secondly,the Felz clustering algorithm is used for super pixel pre-segmentation of geological maps.The coarse segmentation results are refined and modified based on the super pixel pre-segmentation results to obtain the final segmentation results.This study applies GeoMSeg to the constructed dataset,and the experimental results show that the algorithm proposed in this paper has superior performance compared to other mainstream map segmentation models,with an accuracy of 91.89%and a MIoU of 71.91%.
基金supported by the National Key R&D Program of China(Nos.2019YFE03110000 and 2017YFE0300501)the Chinese National Natural Science Foundation(No.11775256)。
文摘In the field of neutronics analysis, it is imperative to develop computer-aided modeling technology for Monte Carlo codes to address the increasing complexity of reactor core components by converting 3D CAD model(boundary representation, BREP) to MC model(constructive solid geometry, CSG). Separation-based conversion from BREP to CSG is widely used in computer-aided modeling MC codes because of its high efficiency, reliability, and easy implementation. However, the current separation-based BREP-CSG conversion is poor for processing complex CAD models, and it is necessary to divide a complex model into several simple models before applying the separation-based conversion algorithm, which is time-consuming and tedious. To avoid manual segmentation, this study proposed a MeshCNN-based 3D-shape segmentation algorithm to automatically separate a complex model. The proposed 3D-shape segmentation algorithm was combined with separation-based BREP-CSG conversion algorithms to directly convert complex models.The proposed algorithm was integrated into the computeraided modeling software cosVMPT and validated using the Chinese fusion engineering testing reactor model. The results demonstrate that the MeshCNN-based BREP-CSG conversion algorithm has a better performance and higher efficiency, particularly in terms of CPU time, and the conversion result is more intuitive and consistent with the intention of the modeler.
基金Supported by the National Basic Research Program ofChina(2011CB707900)
文摘To segment the tumor region precisely is a prerequisite for ultrasound navigation and treatment. In this paper, a normalized cut method to segment tumor ultrasound image is proposed by means of simple linear iterative clustering for presegmentation procedure. The first step, we use simple linear iterative clustering algorithm to divide the image into a number of homogeneous over-segmented regions. Then, these regions are regarded as nodes, and a similarity matrix is constructed by comparing the histograms of each two regions. Finally, we apply the Ncut method to merging the over-segmented regions, then the image segmentation process is completed. The results show that the proposed segmentation scheme handles the strong speckle noise, low contrast, and weak edges well in ultrasound image. Our method has high segmentation precision and computation efficiency than the pixel-based Ncut method.
基金This work was supported by National Natural Science Foundation of China(91850202,61775085,11774256)Natural Science Foundation of Guangdong Province(2016A030312010,2020A1515010958)Science and Technology Innovation Commission of Shenzhen(KQTD2017033011044403,ZDSYS201703031605029).
文摘Digital holography has high potentials for future 3D imaging and display technology.We present a method for a dynamic full-color digital holographic 3D display on single digital micro-mirror device(DMD)with full-color,high-speed and high-fidelity characteristics.We combine the square regions of adjacent micro-mirrors into super-pixels that can modulate amplitude and phase independently.Gray images are achieved by amplitude modulation and precise positioning of each color is achieved by phase modulation.The proposed method realizes a full-color imaging based on the three primary colors and achieves measured structural similarity of more than 88%and color similarity of more than 98%,while retaining the high switch speed of 9 kHz,thus achieving dynamic full-color 3D display on charge-coupled device(CCD).
基金funded by Scientific and Technological Innovation Team of Universities in Henan Province,grant number 22IRTSTHN008Innovative Research Team(in Philosophy and Social Science)in University of Henan Province grant number 2022-CXTD-02the National Natural Science Foundation of China,grant number 41371524.
文摘Super-pixel algorithms based on convolutional neural networks with fuzzy C-means clustering are widely used for high-spatial-resolution remote sensing images segmentation.However,this model requires the number of clusters to be set manually,resulting in a low automation degree due to the complexity of the iterative clustering process.To address this problem,a segmentation method based on a self-learning super-pixel network(SLSP-Net)and modified automatic fuzzy clustering(MAFC)is proposed.SLSP-Net performs feature extraction,non-iterative clustering,and gradient reconstruction.A lightweight feature embedder is adopted for feature extraction,thus expanding the receiving range and generating multi-scale features.Automatic matching is used for non-iterative clustering,and the overfitting of the network model is overcome by adaptively adjusting the gradient weight parameters,providing a better irregular super-pixel neighborhood structure.An optimized density peak algorithm is adopted for MAFC.Based on the obtained super-pixel image,this maximizes the robust decision-making interval,which enhances the automation of regional clustering.Finally,prior entropy fuzzy C-means clustering is applied to optimize the robust decision-making and obtain the final segmentation result.Experimental results show that the proposed model offers reduced experimental complexity and achieves good performance,realizing not only automatic image segmentation,but also good segmentation results.
文摘Superpixel as an important pre-processing technique has been successfully used in many vision applications. In this paper, we proposed a region merging method to improve superpixel segmentation accuracy with low computational cost. We first segmented the image into many accurate small regions, and then progressively agglomerated them until the desired region number was reached. The region merging weight was derived from a novel energy function, which encourages the superpixel with color consistency and similar size. Experimental results on the Berkeley BSDS500 data set showed that our region merging method can significantly improve the accuracy of superpixel segmentation. Moreover, the region merging method only need 50ms to process a 481x321 image on a single Intel i3 CPU at 2.5 GHz.
