Subpixel accuracy for V-groove center in robot welding is researched and a software measure to increase the accuracy of seam tracking by laser is presented. LOG （ Laplacian of Gaussian ） operator is adopted to detec...Subpixel accuracy for V-groove center in robot welding is researched and a software measure to increase the accuracy of seam tracking by laser is presented. LOG （ Laplacian of Gaussian ） operator is adopted to detect image edge. Vgroove center is extracted by corner detection of extremum curvature. Subpixel position is obtained by Lagarange polynomial interpolation algorithm. Experiment results show that the method is brief and applied, and is sufficient for the real time of robot welding by laser sensors.展开更多
World Wide Fund for Nature(WWF)scientists in collaboration with regional experts around the world, have developed the Global 200 Ecoregions Program, the first comparative analysis of biodiversity to cover biologically...World Wide Fund for Nature(WWF)scientists in collaboration with regional experts around the world, have developed the Global 200 Ecoregions Program, the first comparative analysis of biodiversity to cover biologically outstanding terrestrial,freshwater and marine habitats,spanning five continents and all the world’s oceans.Due to its immense importance,Indus Delta Ecoregion is one of the G200 Ecoregions of展开更多
For the nonuniform microscan system where the interframe translation is no longer equivalent to accurate halfpixel, a 2-dimension non-interpolated subpixel algorithm is proposed to consider arhitrary value of microsca...For the nonuniform microscan system where the interframe translation is no longer equivalent to accurate halfpixel, a 2-dimension non-interpolated subpixel algorithm is proposed to consider arhitrary value of microscanning. The aim of the proposed algorithm is to restore double resolution from 2 × 2 undersampled frames. To solve the ill-posed problem in the process of image reconstruction, the prior boundary condition is introduced, and the proposed subpixel reconstruction algorithm is reformulated into the form of line-by-line backward propagation iteration for reducing the calculation complexity. Since the direction of movement offset relative to the accurate halfpixel determines the transfer matrix of the image degradation process, the recon- struction is classified into 4 types when 2 × 2 mieroscan model is applied. All the simulation results and experiment data demonstrate the double resolution improvement compared with the undersampled images. The focus problem, scarcely any possibility of the operation with accurate halfpixel micromotion, is figured out for en-hancing the feasibility of subpixel reconstruction used in practice.展开更多
Recently, semantic segmentation has been widely applied toimage processing, scene understanding, and many others. Especially, indeep learning-based semantic segmentation, the U-Net with convolutionalencoder-decoder ar...Recently, semantic segmentation has been widely applied toimage processing, scene understanding, and many others. Especially, indeep learning-based semantic segmentation, the U-Net with convolutionalencoder-decoder architecture is a representative model which is proposed forimage segmentation in the biomedical field. It used max pooling operationfor reducing the size of image and making noise robust. However, instead ofreducing the complexity of the model, max pooling has the disadvantageof omitting some information about the image in reducing it. So, thispaper used two diagonal elements of down-sampling operation instead ofit. We think that the down-sampling feature maps have more informationintrinsically than max pooling feature maps because of keeping the Nyquisttheorem and extracting the latent information from them. In addition,this paper used two other diagonal elements for the skip connection. Indecoding, we used Subpixel Convolution rather than transposed convolutionto efficiently decode the encoded feature maps. Including all the ideas, thispaper proposed the new encoder-decoder model called Down-Sampling andSubpixel Convolution U-Net (DSSC-UNet). To prove the better performanceof the proposed model, this paper measured the performance of the UNetand DSSC-UNet on the Cityscapes. As a result, DSSC-UNet achieved89.6% Mean Intersection OverUnion (Mean-IoU) andU-Net achieved 85.6%Mean-IoU, confirming that DSSC-UNet achieved better performance.展开更多
Subpixel localization techniques for estimating the positions of point-like images captured by pixelated image sensors have been widely used in diverse optical measurement fields.With unavoidable imaging noise,there i...Subpixel localization techniques for estimating the positions of point-like images captured by pixelated image sensors have been widely used in diverse optical measurement fields.With unavoidable imaging noise,there is a precision limit(PL)when estimating the target positions on image sensors,which depends on the detected photon count,noise,point spread function(PSF)radius,and PSF’s intra-pixel position.Previous studies have clearly reported the effects of the first three parameters on the PL but have neglected the intra-pixel position information.Here,we develop a localization PL analysis framework for revealing the effect of the intra-pixel position of small PSFs.To accurately estimate the PL in practical applications,we provide effective PSF(e PSF)modeling approaches and apply the Cramér–Rao lower bound.Based on the characteristics of small PSFs,we first derive simplified equations for finding the best PL and the best intra-pixel region for an arbitrary small PSF;we then verify these equations on real PSFs.Next,we use the typical Gaussian PSF to perform a further analysis and find that the final optimum of the PL is achieved at the pixel boundaries when the Gaussian radius is as small as possible,indicating that the optimum is ultimately limited by light diffraction.Finally,we apply the maximum likelihood method.Its combination with e PSF modeling allows us to successfully reach the PL in experiments,making the above theoretical analysis effective.This work provides a new perspective on combining image sensor position control with PSF engineering to make full use of information theory,thereby paving the way for thoroughly understanding and achieving the final optimum of the PL in optical localization.展开更多
The unavoidable nature of Ulva prolifera mixed pixel in low-resolution remote sensing images would result in rough boundary of U.prolifera patches,omission of tiny patches,and overestimation of coverage area.The decom...The unavoidable nature of Ulva prolifera mixed pixel in low-resolution remote sensing images would result in rough boundary of U.prolifera patches,omission of tiny patches,and overestimation of coverage area.The decomposition of U.prolifera mixed pixel addresses the issue of coverage area overestimation,and the remaining problems can be alleviated by subpixel mapping(SPM).Due to the drift and dissipation of U.prolifera,a suitable SPM method is the single image-based unsupervised method.However,the method has difficulties in detail reconstruction,insufficient learning of spectral information,and SPM error introduced by abundance deviation.Therefore,we proposed a multiple-feature decision fusion SPM(MFDFSPM)method.It involves three branches to obtain the spatial,abundance,and spectral features of U.prolifera while considers multi-feature information using the fusion strategy.Experiments on the Geostationary Ocean Color Imager images in the Yellow Sea of China indicate that the MFDFSPM overperforms several typical U.prolifera SPM methods in higher accuracy and stronger robustness in both SPM and abundance calculation,which produced subpixel map with more detailed spatial information and less noise.展开更多
Localization of the inspected chip image is one of the key problems with machine vision aided surface mount devices (SMD) and other micro-electronic equipments. This paper presents a new edge-directed subpixel edge lo...Localization of the inspected chip image is one of the key problems with machine vision aided surface mount devices (SMD) and other micro-electronic equipments. This paper presents a new edge-directed subpixel edge localization method. The image is divided into two regions, edge and non-edge, using edge detection to emphasize the edge feature. Since the edges of the chip image are straight, they have straight-line characteristics locally and globally. First, the line segments of the straight edge are located to subpixel precision, according to their local straight properties, in a 3×3 neighborhood of the edge region. Second, the subpixel midpoints of the line segments are computed. Finally, the straight edge is fitted using the midpoints and the least square method, according to its global straight property in the entire edge region. In this way, the edge is located to subpixel precision. While fitting the edge, the irregular points are eliminated by the angles of the line segments to improve the precision. We can also distinguish different edges and their intersections using the angles of the line segments and distances between the edge points, then give the vectorial result of the image edge with high precision.展开更多
the close photogrammetric 3-D coordinate measurement is a newmeasuring technology in the fields of the coordinate measurementmachine (CMM) in recent years. In this method, we usually place sometargets on the measured ...the close photogrammetric 3-D coordinate measurement is a newmeasuring technology in the fields of the coordinate measurementmachine (CMM) in recent years. In this method, we usually place sometargets on the measured object and take image of targets to determinethe object coordinate. The subpixel location of target image plays animportant role in high accuracy 3-D coordinate measuring procedure.In this paper, some subpixel location methods are reviewed and somefactors which affect location precision are analyzed.展开更多
With the high-speed development of digital image processing technology, machine vision technology has been widely used in automatic detection of industrial products. A large amount of products can be treated by comput...With the high-speed development of digital image processing technology, machine vision technology has been widely used in automatic detection of industrial products. A large amount of products can be treated by computer instead of human in a shorter time. In the process of automatic detection, edge detection is one of the most commonly used methods. But with the increasing demand for detection precision,traditional pixel-level methods are difficult to meet the requirement, and more subpixel level methods are in the use. This paper presents a new method to detect curved edge with high precision. First, the target area ratio of pixels near the edge is computed by using one-dimensional edge detection method. Second, parabola is used to approximately represent the curved edge. And we select appropriate parameters to obtain accurate results. This method is able to detect curved edges in subpixel level, and shows its practical effectiveness in automatic measure of products with arc shape in large industrial scene.展开更多
针对目前遥感图像小目标检测任务中易出现漏检和误检的问题,提出一种SCS-YOLO[SMCA+CSC+SIoU(shape-aware intersection over union loss)-you only look once]的遥感图像小目标检测算法。首先,针对遥感图像中目标小而聚集的问题,构建...针对目前遥感图像小目标检测任务中易出现漏检和误检的问题,提出一种SCS-YOLO[SMCA+CSC+SIoU(shape-aware intersection over union loss)-you only look once]的遥感图像小目标检测算法。首先,针对遥感图像中目标小而聚集的问题,构建空间多尺度卷积注意力(spatial multi-scale convolutional attention,SMCA),提升模型对空间和通道信息的特征提取能力;其次,针对深层网络传递时小目标语义信息容易丢失的问题,设计聚合亚像素卷积(concentrated sub-pixel convolution,CSC),采用多尺度聚合特征提取方法,增强了网络对语义信息的提取能力;最后,将SIoU损失函数替代原模型中的CIoU(complete intersection over union loss)损失函数,加快了网络的收敛速度。SCS-YOLO模型在RSOD和NWPU VHR-10数据集上,平均精确率的平均值(mAP)分别达到97%和90.9%,相较于原模型分别提升了2.2%和2.7%,可见该方法在遥感图像小目标检测任务中的有效性。展开更多
基金This work is financially supported by National Nature Science Foundation of China (Grant No. 50175027).
文摘Subpixel accuracy for V-groove center in robot welding is researched and a software measure to increase the accuracy of seam tracking by laser is presented. LOG （ Laplacian of Gaussian ） operator is adopted to detect image edge. Vgroove center is extracted by corner detection of extremum curvature. Subpixel position is obtained by Lagarange polynomial interpolation algorithm. Experiment results show that the method is brief and applied, and is sufficient for the real time of robot welding by laser sensors.
文摘World Wide Fund for Nature(WWF)scientists in collaboration with regional experts around the world, have developed the Global 200 Ecoregions Program, the first comparative analysis of biodiversity to cover biologically outstanding terrestrial,freshwater and marine habitats,spanning five continents and all the world’s oceans.Due to its immense importance,Indus Delta Ecoregion is one of the G200 Ecoregions of
基金Sponsored by the Ministerial Level Advanced Research Foundation (A1120060884)
文摘For the nonuniform microscan system where the interframe translation is no longer equivalent to accurate halfpixel, a 2-dimension non-interpolated subpixel algorithm is proposed to consider arhitrary value of microscanning. The aim of the proposed algorithm is to restore double resolution from 2 × 2 undersampled frames. To solve the ill-posed problem in the process of image reconstruction, the prior boundary condition is introduced, and the proposed subpixel reconstruction algorithm is reformulated into the form of line-by-line backward propagation iteration for reducing the calculation complexity. Since the direction of movement offset relative to the accurate halfpixel determines the transfer matrix of the image degradation process, the recon- struction is classified into 4 types when 2 × 2 mieroscan model is applied. All the simulation results and experiment data demonstrate the double resolution improvement compared with the undersampled images. The focus problem, scarcely any possibility of the operation with accurate halfpixel micromotion, is figured out for en-hancing the feasibility of subpixel reconstruction used in practice.
文摘Recently, semantic segmentation has been widely applied toimage processing, scene understanding, and many others. Especially, indeep learning-based semantic segmentation, the U-Net with convolutionalencoder-decoder architecture is a representative model which is proposed forimage segmentation in the biomedical field. It used max pooling operationfor reducing the size of image and making noise robust. However, instead ofreducing the complexity of the model, max pooling has the disadvantageof omitting some information about the image in reducing it. So, thispaper used two diagonal elements of down-sampling operation instead ofit. We think that the down-sampling feature maps have more informationintrinsically than max pooling feature maps because of keeping the Nyquisttheorem and extracting the latent information from them. In addition,this paper used two other diagonal elements for the skip connection. Indecoding, we used Subpixel Convolution rather than transposed convolutionto efficiently decode the encoded feature maps. Including all the ideas, thispaper proposed the new encoder-decoder model called Down-Sampling andSubpixel Convolution U-Net (DSSC-UNet). To prove the better performanceof the proposed model, this paper measured the performance of the UNetand DSSC-UNet on the Cityscapes. As a result, DSSC-UNet achieved89.6% Mean Intersection OverUnion (Mean-IoU) andU-Net achieved 85.6%Mean-IoU, confirming that DSSC-UNet achieved better performance.
基金the support from the National Natural Science Foundation of China(51827806)the National Key Research and Development Program of China(2016YFB0501201)the Xplorer Prize funded by the Tencent Foundation。
文摘Subpixel localization techniques for estimating the positions of point-like images captured by pixelated image sensors have been widely used in diverse optical measurement fields.With unavoidable imaging noise,there is a precision limit(PL)when estimating the target positions on image sensors,which depends on the detected photon count,noise,point spread function(PSF)radius,and PSF’s intra-pixel position.Previous studies have clearly reported the effects of the first three parameters on the PL but have neglected the intra-pixel position information.Here,we develop a localization PL analysis framework for revealing the effect of the intra-pixel position of small PSFs.To accurately estimate the PL in practical applications,we provide effective PSF(e PSF)modeling approaches and apply the Cramér–Rao lower bound.Based on the characteristics of small PSFs,we first derive simplified equations for finding the best PL and the best intra-pixel region for an arbitrary small PSF;we then verify these equations on real PSFs.Next,we use the typical Gaussian PSF to perform a further analysis and find that the final optimum of the PL is achieved at the pixel boundaries when the Gaussian radius is as small as possible,indicating that the optimum is ultimately limited by light diffraction.Finally,we apply the maximum likelihood method.Its combination with e PSF modeling allows us to successfully reach the PL in experiments,making the above theoretical analysis effective.This work provides a new perspective on combining image sensor position control with PSF engineering to make full use of information theory,thereby paving the way for thoroughly understanding and achieving the final optimum of the PL in optical localization.
基金Supported by the Shandong Provincial Natural Science Foundation of China(No.ZR2019MD023)the National Natural Science Foundation of China(No.41776182)。
文摘The unavoidable nature of Ulva prolifera mixed pixel in low-resolution remote sensing images would result in rough boundary of U.prolifera patches,omission of tiny patches,and overestimation of coverage area.The decomposition of U.prolifera mixed pixel addresses the issue of coverage area overestimation,and the remaining problems can be alleviated by subpixel mapping(SPM).Due to the drift and dissipation of U.prolifera,a suitable SPM method is the single image-based unsupervised method.However,the method has difficulties in detail reconstruction,insufficient learning of spectral information,and SPM error introduced by abundance deviation.Therefore,we proposed a multiple-feature decision fusion SPM(MFDFSPM)method.It involves three branches to obtain the spatial,abundance,and spectral features of U.prolifera while considers multi-feature information using the fusion strategy.Experiments on the Geostationary Ocean Color Imager images in the Yellow Sea of China indicate that the MFDFSPM overperforms several typical U.prolifera SPM methods in higher accuracy and stronger robustness in both SPM and abundance calculation,which produced subpixel map with more detailed spatial information and less noise.
文摘Localization of the inspected chip image is one of the key problems with machine vision aided surface mount devices (SMD) and other micro-electronic equipments. This paper presents a new edge-directed subpixel edge localization method. The image is divided into two regions, edge and non-edge, using edge detection to emphasize the edge feature. Since the edges of the chip image are straight, they have straight-line characteristics locally and globally. First, the line segments of the straight edge are located to subpixel precision, according to their local straight properties, in a 3×3 neighborhood of the edge region. Second, the subpixel midpoints of the line segments are computed. Finally, the straight edge is fitted using the midpoints and the least square method, according to its global straight property in the entire edge region. In this way, the edge is located to subpixel precision. While fitting the edge, the irregular points are eliminated by the angles of the line segments to improve the precision. We can also distinguish different edges and their intersections using the angles of the line segments and distances between the edge points, then give the vectorial result of the image edge with high precision.
文摘the close photogrammetric 3-D coordinate measurement is a newmeasuring technology in the fields of the coordinate measurementmachine (CMM) in recent years. In this method, we usually place sometargets on the measured object and take image of targets to determinethe object coordinate. The subpixel location of target image plays animportant role in high accuracy 3-D coordinate measuring procedure.In this paper, some subpixel location methods are reviewed and somefactors which affect location precision are analyzed.
基金This work was supported in part by the National Natural Science Foundation of China (No. 61170094), Shanghai Committee of Science and Technology (14JC1402202 and 14441904403), and 863 Program 2014AA015101.
文摘With the high-speed development of digital image processing technology, machine vision technology has been widely used in automatic detection of industrial products. A large amount of products can be treated by computer instead of human in a shorter time. In the process of automatic detection, edge detection is one of the most commonly used methods. But with the increasing demand for detection precision,traditional pixel-level methods are difficult to meet the requirement, and more subpixel level methods are in the use. This paper presents a new method to detect curved edge with high precision. First, the target area ratio of pixels near the edge is computed by using one-dimensional edge detection method. Second, parabola is used to approximately represent the curved edge. And we select appropriate parameters to obtain accurate results. This method is able to detect curved edges in subpixel level, and shows its practical effectiveness in automatic measure of products with arc shape in large industrial scene.
文摘针对目前遥感图像小目标检测任务中易出现漏检和误检的问题,提出一种SCS-YOLO[SMCA+CSC+SIoU(shape-aware intersection over union loss)-you only look once]的遥感图像小目标检测算法。首先,针对遥感图像中目标小而聚集的问题,构建空间多尺度卷积注意力(spatial multi-scale convolutional attention,SMCA),提升模型对空间和通道信息的特征提取能力;其次,针对深层网络传递时小目标语义信息容易丢失的问题,设计聚合亚像素卷积(concentrated sub-pixel convolution,CSC),采用多尺度聚合特征提取方法,增强了网络对语义信息的提取能力;最后,将SIoU损失函数替代原模型中的CIoU(complete intersection over union loss)损失函数,加快了网络的收敛速度。SCS-YOLO模型在RSOD和NWPU VHR-10数据集上,平均精确率的平均值(mAP)分别达到97%和90.9%,相较于原模型分别提升了2.2%和2.7%,可见该方法在遥感图像小目标检测任务中的有效性。
