Background Image matching is crucial in numerous computer vision tasks such as 3D reconstruction and simultaneous visual localization and mapping.The accuracy of the matching significantly impacted subsequent studies....Background Image matching is crucial in numerous computer vision tasks such as 3D reconstruction and simultaneous visual localization and mapping.The accuracy of the matching significantly impacted subsequent studies.Because of their local similarity,when image pairs contain comparable patterns but feature pairs are positioned differently,incorrect recognition can occur as global motion consistency is disregarded.Methods This study proposes an image-matching filtering algorithm based on global motion consistency.It can be used as a subsequent matching filter for the initial matching results generated by other matching algorithms based on the principle of motion smoothness.A particular matching algorithm can first be used to perform the initial matching;then,the rotation and movement information of the global feature vectors are combined to effectively identify outlier matches.The principle is that if the matching result is accurate,the feature vectors formed by any matched point should have similar rotation angles and moving distances.Thus,global motion direction and global motion distance consistencies were used to reject outliers caused by similar patterns in different locations.Results Four datasets were used to test the effectiveness of the proposed method.Three datasets with similar patterns in different locations were used to test the results for similar images that could easily be incorrectly matched by other algorithms,and one commonly used dataset was used to test the results for the general image-matching problem.The experimental results suggest that the proposed method is more accurate than other state-of-the-art algorithms in identifying mismatches in the initial matching set.Conclusions The proposed outlier rejection matching method can significantly improve the matching accuracy for similar images with locally similar feature pairs in different locations and can provide more accurate matching results for subsequent computer vision tasks.展开更多
A novel algorithm is presented to make the results of image matching more reliable and accurate based on SIFT (Scale Invariant Feature Transform). SIFT algorithm has been identified as the most resistant matching algo...A novel algorithm is presented to make the results of image matching more reliable and accurate based on SIFT (Scale Invariant Feature Transform). SIFT algorithm has been identified as the most resistant matching algorithm to common image deformations; however, if there are similar regions in images, SIFT algorithm still generates some analogical descriptors and provides many mismatches. This paper examines the local image descriptor used by SIFT and presents a new algorithm by integrating SIFT with two-dimensional moment invariants and disparity gradient to improve the matching results. In the new algorithm, decision tree is used, and the whole matching process is divided into three levels with different primitives. Matching points are considered as correct ones only when they satisfy all the three similarity measurements. Experiment results demonstrate that the new approach is more reliable and accurate.展开更多
Histogram of collinear gradient-enhanced coding (HCGEC), a robust key point descriptor for multi-spectral image matching, is proposed. The HCGEC mainly encodes rough structures within an image and suppresses detaile...Histogram of collinear gradient-enhanced coding (HCGEC), a robust key point descriptor for multi-spectral image matching, is proposed. The HCGEC mainly encodes rough structures within an image and suppresses detailed textural information, which is desirable in multi-spectral image matching. Experiments on two multi-spectral data sets demonstrate that the proposed descriptor can yield significantly better results than some state-of- the-art descriptors.展开更多
Image matching based on scale invariant feature transform(SIFT) is one of the most popular image matching algorithms, which exhibits high robustness and accuracy. Grayscale images rather than color images are genera...Image matching based on scale invariant feature transform(SIFT) is one of the most popular image matching algorithms, which exhibits high robustness and accuracy. Grayscale images rather than color images are generally used to get SIFT descriptors in order to reduce the complexity. The regions which have a similar grayscale level but different hues tend to produce wrong matching results in this case. Therefore, the loss of color information may result in decreasing of matching ratio. An image matching algorithm based on SIFT is proposed, which adds a color offset and an exposure offset when converting color images to grayscale images in order to enhance the matching ratio. Experimental results show that the proposed algorithm can effectively differentiate the regions with different colors but the similar grayscale level, and increase the matching ratio of image matching based on SIFT. Furthermore, it does not introduce much complexity than the traditional SIFT.展开更多
A coding-based method to solve the image matching problems in stereovision measurement is presented. The solution is to add and append an identity ID to the retro-reflect point, so it can be identified efficiently und...A coding-based method to solve the image matching problems in stereovision measurement is presented. The solution is to add and append an identity ID to the retro-reflect point, so it can be identified efficiently under the complicated circumstances and has the characteristics of rotation, zooming, and deformation independence. Its design architecture and implementation process in details based on the theory of stereovision measurement are described. The method is effective on reducing processing data time, improving accuracy of image matching and automation of measuring system through experiments.展开更多
Presents a new parallel image matching algorithm based on the concept of entropy feature vector and suitable to SIMD computer, which, in comparison with other algorithms, has the following advantages:(1)The spatial in...Presents a new parallel image matching algorithm based on the concept of entropy feature vector and suitable to SIMD computer, which, in comparison with other algorithms, has the following advantages:(1)The spatial information of an image is appropriately introduced into the definition of image entropy. (2) A large number of multiplication operations are eliminated, thus the algorithm is sped up. (3) The shortcoming of having to do global calculation in the first instance is overcome, and concludes the algorithm has very good locality and is suitable for parallel processing.展开更多
Multi-modal image matching is crucial in aerospace applications because it can fully exploit the complementary and valuable information contained in the amount and diversity of remote sensing images.However,it remains...Multi-modal image matching is crucial in aerospace applications because it can fully exploit the complementary and valuable information contained in the amount and diversity of remote sensing images.However,it remains a challenging task due to significant non-linear radiometric,geometric differences,and noise across different sensors.To improve the performance of heterologous image matching,this paper proposes a normalized self-similarity region descriptor to extract consistent structural information.We first construct the pointwise self-similarity region descriptor based on the Euclidean distance between adjacent image blocks to reflect the structural properties of multi-modal images.Then,a linear normalization approach is used to form Modality Independent Region Descriptor(MIRD),which can effectively distinguish structural features such as points,lines,corners,and flat between multi-modal images.To further improve the matching accuracy,the included angle cosine similarity metric is adopted to exploit the directional vector information of multi-dimensional feature descriptors.The experimental results show that the proposed MIRD has better matching accuracy and robustness for various multi-modal image matching than the state-of-the-art methods.MIRD can effectively extract consistent geometric structure features and suppress the influence of SAR speckle noise using non-local neighboring image blocks operation,effectively applied to various multi-modal image matching.展开更多
Augmented solar images were used to research the adaptability of four representative image extraction and matching algorithms in space weather domain.These include the scale-invariant feature transform algorithm,speed...Augmented solar images were used to research the adaptability of four representative image extraction and matching algorithms in space weather domain.These include the scale-invariant feature transform algorithm,speeded-up robust features algorithm,binary robust invariant scalable keypoints algorithm,and oriented fast and rotated brief algorithm.The performance of these algorithms was estimated in terms of matching accuracy,feature point richness,and running time.The experiment result showed that no algorithm achieved high accuracy while keeping low running time,and all algorithms are not suitable for image feature extraction and matching of augmented solar images.To solve this problem,an improved method was proposed by using two-frame matching to utilize the accuracy advantage of the scale-invariant feature transform algorithm and the speed advantage of the oriented fast and rotated brief algorithm.Furthermore,our method and the four representative algorithms were applied to augmented solar images.Our application experiments proved that our method achieved a similar high recognition rate to the scale-invariant feature transform algorithm which is significantly higher than other algorithms.Our method also obtained a similar low running time to the oriented fast and rotated brief algorithm,which is significantly lower than other algorithms.展开更多
In feature based image matching,distinctive features in images are detected and represented by feature descriptors.Matching is then carried out by assessing the similarity of the descriptors of potentially conjugate p...In feature based image matching,distinctive features in images are detected and represented by feature descriptors.Matching is then carried out by assessing the similarity of the descriptors of potentially conjugate points.In this paper,we first shortly discuss the general frame-work.Then,we review feature detection as well as the determination of affine shape and orientation of local features,before analyzing feature description in more detail.In the feature description review,the general framework of local feature description is presented first.Then,the review discusses the evolution from hand-crafted feature descriptors,e.g.SIFT(Scale Invariant Feature Transform),to machine learning and deep learning based descriptors.The machine learning models,the training loss and the respective training data of learning-based algorithms are looked at in more detail;subsequently the various advantages and challenges of the different approaches are discussed.Finally,we present and assess some current research directions before concluding the paper.展开更多
Targeting at a reliable image matching of multiple remote sensing images for the generation of digital surface models,this paper presents a geometric-constrained multi-view image matching method,based on an energy min...Targeting at a reliable image matching of multiple remote sensing images for the generation of digital surface models,this paper presents a geometric-constrained multi-view image matching method,based on an energy minimization framework.By employing a geometrical constraint,the cost value of the energy function was calculated from multiple images,and the cost value was aggregated in an image space using a semi-global optimization approach.A homography transform parameter calculation method is proposed for fast calculation of projection pixel on each image when calculation cost values.It is based on the known interior orientation parameters,exterior orientation parameters,and a given elevation value.For an efficient and reliable processing of multiple remote sensing images,the proposed matching method was performed via a coarse-to-fine strategy through image pyramid.Three sets of airborne remote sensing images were used to evaluate the performance of the proposed method.Results reveal that the multi-view image matching can improve matching reliability.Moreover,the experimental results show that the proposed method performs better than traditional methods.展开更多
Cross-correlation (CC) is the most time-consuming in the implementation of image matching algorithms based on the correlation method. Therefore, how to calculate CC fast is crucial to real-time image matching. This ...Cross-correlation (CC) is the most time-consuming in the implementation of image matching algorithms based on the correlation method. Therefore, how to calculate CC fast is crucial to real-time image matching. This work reveals that the single cascading multiply-accumulate (CAMAC) and concurrent multiply-accumulate (COMAC) architectures which have been widely used in the past, actually, do not necessarily bring about a satisfactory time performance for CC. To obtain better time performance and higher resource efficiency, this paper proposes a configurable circuit involving the advantages of CAMAC and COMAC for a large amount of multiply-accumulate (MAC) operations of CC in exhaustive search. The proposed circuit works in an array manner and can better adapt to changing size image matching in real-time processing. Experimental results demonstrate that this novel circuit which involves the two structures can complete vast MAC calculations at a very high speed. Compared with existing related work, it improves the computation density further and is more flexible to use.展开更多
A new method of view synthesis is proposed based on Delaunay triangulation. The first step of this method is making the Delaunay triangulation of 2 reference images. Secondly, matching the image points using the epipo...A new method of view synthesis is proposed based on Delaunay triangulation. The first step of this method is making the Delaunay triangulation of 2 reference images. Secondly, matching the image points using the epipolar geometry constraint. Finally, constructing the third view according to pixel transferring under the trilinear constraint. The method gets rid of the classic time consuming dense matching technique and takes advantage of Delaunay triangulation. So it can not only save the computation time but also enhance the quality of the synthesized view. The significance of this method is that it can be used directly in the fields of video coding, image compressing and virtual reality.展开更多
Image matching is one of the key technologies for digital Earth.This paper presents a combined image matching method for Chinese satellite images.This method includes the following four steps:(1)a modified Wallis-type...Image matching is one of the key technologies for digital Earth.This paper presents a combined image matching method for Chinese satellite images.This method includes the following four steps:(1)a modified Wallis-type filter is proposed to determine parameters adaptively while avoiding over-enhancement;(2)a mismatch detection procedure based on a global-local strategy is introduced to remove outliers generated by the Scale-invariant feature transform algorithm,and geometric orientation with bundle block adjustment is employed to compensate for the systematic errors of the position and attitude observations;(3)we design a novel similarity measure(distance,angle and the Normalized Cross-Correlation similarities,DANCC)which considers geometric similarity and textural similarity;and(4)we introduce a hierarchical matching strategy to refine the matching result level by level.Four typical image pairs acquired from Mapping Satellite-1,ZY-102C,ZY-3 and GeoEye-1,respectively,are used for experimental analysis.A comparison with the two current main matching algorithms for satellite imagery confirms that the proposed method is capable of producing reliable and accurate matching results on different terrains from not only Chinese satellite images,but also foreign satellite images.展开更多
As the fundamental problem in the computer vision area,image matching has wide applications in pose estimation,3D reconstruction,image retrieval,etc.Suffering from the influence of external factors,the process of imag...As the fundamental problem in the computer vision area,image matching has wide applications in pose estimation,3D reconstruction,image retrieval,etc.Suffering from the influence of external factors,the process of image matching using classical local detectors,e.g.,scale-invariant feature transform(SIFT),and the outlier filtering approaches,e.g.,Random sample consensus(RANSAC),show high computation speed and pool robustness under changing illumination and viewpoints conditions,while image matching approaches with deep learning strategy(such as HardNet,OANet)display reliable achievements in large-scale datasets with challenging scenes.However,the past learning-based approaches are limited to the distinction and quality of the dataset and the training strategy in the image-matching approaches.As an extension of the previous conference paper,this paper proposes an accurate and robust image matching approach using fewer training data in an end-to-end manner,which could be used to estimate the pose error This research first proposes a novel dataset cleaning and construction strategy to eliminate the noise and improve the training efficiency;Secondly,a novel loss named quadratic hinge triplet loss(QHT)is proposed to gather more effective and stable feature matching;Thirdly,in the outlier filtering process,the stricter OANet and bundle adjustment are applied for judging samples by adding the epipolar distance constraint and triangulation constraint to generate more outstanding matches;Finally,to recall the matching pairs,dynamic guided matching is used and then submit the inliers after the PyRANSAC process.Multiple evaluation metrics are used and reported in the 1st place in the Track1 of CVPR Image-Matching Challenge Workshop.The results show that the proposed method has advanced performance in large-scale and challenging Phototourism benchmark.展开更多
To solve the heterogeneous image scene matching problem, a non-linear pre-processing method for the original images before intensity-based correlation is proposed. The result shows that the proper matching probability...To solve the heterogeneous image scene matching problem, a non-linear pre-processing method for the original images before intensity-based correlation is proposed. The result shows that the proper matching probability is raised greatly. Especially for the low S/N image pairs, the effect is more remarkable.展开更多
The concept of dual image reversible data hiding(DIRDH) is the technique that can produce two camouflage images after embedding secret data into one original image.Moreover,not only can the secret data be extracted ...The concept of dual image reversible data hiding(DIRDH) is the technique that can produce two camouflage images after embedding secret data into one original image.Moreover,not only can the secret data be extracted from two camouflage images but also the original image can be recovered.To achieve high image quality,Lu et al.'s method applied least-significant-bit(LSB) matching revisited to DIRDH.In order to further improve the image quality,the proposed method modifies LSB matching revisited rules and applies them to DIRDH.According to the experimental results,the image quality of the proposed method is better than that of Lu et al.'s method.展开更多
Automatic Digital Orthophoto Map(DOM)generation plays an important role in many downstream works such as land use and cover detection,urban planning,and disaster assessment.Existing DOM generation methods can generate...Automatic Digital Orthophoto Map(DOM)generation plays an important role in many downstream works such as land use and cover detection,urban planning,and disaster assessment.Existing DOM generation methods can generate promising results but always need ground object filtered DEM generation before otho-rectification;this can consume much time and produce building facade contained results.To address this problem,a pixel-by-pixel digital differential rectification-based automatic DOM generation method is proposed in this paper.Firstly,3D point clouds with texture are generated by dense image matching based on an optical flow field for a stereo pair of images,respectively.Then,the grayscale of the digital differential rectification image is extracted directly from the point clouds element by element according to the nearest neighbor method for matched points.Subsequently,the elevation is repaired grid-by-grid using the multi-layer Locally Refined B-spline(LR-B)interpolation method with triangular mesh constraint for the point clouds void area,and the grayscale is obtained by the indirect scheme of digital differential rectification to generate the pixel-by-pixel digital differentially rectified image of a single image slice.Finally,a seamline network is automatically searched using a disparity map optimization algorithm,and DOM is smartly mosaicked.The qualitative and quantitative experimental results on three datasets were produced and evaluated,which confirmed the feasibility of the proposed method,and the DOM accuracy can reach 1 Ground Sample Distance(GSD)level.The comparison experiment with the state-of-the-art commercial softwares showed that the proposed method generated DOM has a better visual effect on building boundaries and roof completeness with comparable accuracy and computational efficiency.展开更多
The existence of a global minimizer for a variational problem arising in registration of diffusion tensor images is proved, which ensures that there is a regular spatial transformation for the registration of diffusio...The existence of a global minimizer for a variational problem arising in registration of diffusion tensor images is proved, which ensures that there is a regular spatial transformation for the registration of diffusion tensor images.展开更多
To solve the problem of wide-baseline stereo image matching based on multiple cameras,the paper puts forward an image matching method of combining maximally stable extremal regions (MSER) with Scale Invariant Feature ...To solve the problem of wide-baseline stereo image matching based on multiple cameras,the paper puts forward an image matching method of combining maximally stable extremal regions (MSER) with Scale Invariant Feature Transform (SIFT) . It uses MSER to detect feature regions instead of difference of Gaussian. After fitted into elliptical regions,those regions will be normalized into unity circles and represented with SIFT descriptors. The method estimates fundamental matrix and removes outliers by auto-maximum a posteriori sample consensus after initial matching feature points. The experimental results indicate that the method is robust to viewpoint changes,can reduce computational complexity effectively and improve matching accuracy.展开更多
Background Exploring correspondences across multiview images is the basis of various computer vision tasks.However,most existing methods have limited accuracy under challenging conditions.Method To learn more robust a...Background Exploring correspondences across multiview images is the basis of various computer vision tasks.However,most existing methods have limited accuracy under challenging conditions.Method To learn more robust and accurate correspondences,we propose DSD-MatchingNet for local feature matching in this study.First,we develop a deformable feature extraction module to obtain multilevel feature maps,which harvest contextual information from dynamic receptive fields.The dynamic receptive fields provided by the deformable convolution network ensure that our method obtains dense and robust correspondence.Second,we utilize sparse-to-dense matching with symmetry of correspondence to implement accurate pixel-level matching,which enables our method to produce more accurate correspondences.Result Experiments show that our proposed DSD-MatchingNet achieves a better performance on the image matching benchmark,as well as on the visual localization benchmark.Specifically,our method achieved 91.3%mean matching accuracy on the HPatches dataset and 99.3%visual localization recalls on the Aachen Day-Night dataset.展开更多
基金Supported by the Natural Science Foundation of China(62072388,62276146)the Industry Guidance Project Foundation of Science technology Bureau of Fujian province(2020H0047)+2 种基金the Natural Science Foundation of Science Technology Bureau of Fujian province(2019J01601)the Creation Fund project of Science Technology Bureau of Fujian province(JAT190596)Putian University Research Project(2022034)。
文摘Background Image matching is crucial in numerous computer vision tasks such as 3D reconstruction and simultaneous visual localization and mapping.The accuracy of the matching significantly impacted subsequent studies.Because of their local similarity,when image pairs contain comparable patterns but feature pairs are positioned differently,incorrect recognition can occur as global motion consistency is disregarded.Methods This study proposes an image-matching filtering algorithm based on global motion consistency.It can be used as a subsequent matching filter for the initial matching results generated by other matching algorithms based on the principle of motion smoothness.A particular matching algorithm can first be used to perform the initial matching;then,the rotation and movement information of the global feature vectors are combined to effectively identify outlier matches.The principle is that if the matching result is accurate,the feature vectors formed by any matched point should have similar rotation angles and moving distances.Thus,global motion direction and global motion distance consistencies were used to reject outliers caused by similar patterns in different locations.Results Four datasets were used to test the effectiveness of the proposed method.Three datasets with similar patterns in different locations were used to test the results for similar images that could easily be incorrectly matched by other algorithms,and one commonly used dataset was used to test the results for the general image-matching problem.The experimental results suggest that the proposed method is more accurate than other state-of-the-art algorithms in identifying mismatches in the initial matching set.Conclusions The proposed outlier rejection matching method can significantly improve the matching accuracy for similar images with locally similar feature pairs in different locations and can provide more accurate matching results for subsequent computer vision tasks.
文摘A novel algorithm is presented to make the results of image matching more reliable and accurate based on SIFT (Scale Invariant Feature Transform). SIFT algorithm has been identified as the most resistant matching algorithm to common image deformations; however, if there are similar regions in images, SIFT algorithm still generates some analogical descriptors and provides many mismatches. This paper examines the local image descriptor used by SIFT and presents a new algorithm by integrating SIFT with two-dimensional moment invariants and disparity gradient to improve the matching results. In the new algorithm, decision tree is used, and the whole matching process is divided into three levels with different primitives. Matching points are considered as correct ones only when they satisfy all the three similarity measurements. Experiment results demonstrate that the new approach is more reliable and accurate.
文摘Histogram of collinear gradient-enhanced coding (HCGEC), a robust key point descriptor for multi-spectral image matching, is proposed. The HCGEC mainly encodes rough structures within an image and suppresses detailed textural information, which is desirable in multi-spectral image matching. Experiments on two multi-spectral data sets demonstrate that the proposed descriptor can yield significantly better results than some state-of- the-art descriptors.
基金supported by the National Natural Science Foundation of China(61271315)the State Scholarship Fund of China
文摘Image matching based on scale invariant feature transform(SIFT) is one of the most popular image matching algorithms, which exhibits high robustness and accuracy. Grayscale images rather than color images are generally used to get SIFT descriptors in order to reduce the complexity. The regions which have a similar grayscale level but different hues tend to produce wrong matching results in this case. Therefore, the loss of color information may result in decreasing of matching ratio. An image matching algorithm based on SIFT is proposed, which adds a color offset and an exposure offset when converting color images to grayscale images in order to enhance the matching ratio. Experimental results show that the proposed algorithm can effectively differentiate the regions with different colors but the similar grayscale level, and increase the matching ratio of image matching based on SIFT. Furthermore, it does not introduce much complexity than the traditional SIFT.
基金This project is supported by National Natural Science Foundation of China(No.50475176) and Municipal Natural Science Foundation of Beijing(No.KZ200511232019).
文摘A coding-based method to solve the image matching problems in stereovision measurement is presented. The solution is to add and append an identity ID to the retro-reflect point, so it can be identified efficiently under the complicated circumstances and has the characteristics of rotation, zooming, and deformation independence. Its design architecture and implementation process in details based on the theory of stereovision measurement are described. The method is effective on reducing processing data time, improving accuracy of image matching and automation of measuring system through experiments.
文摘Presents a new parallel image matching algorithm based on the concept of entropy feature vector and suitable to SIMD computer, which, in comparison with other algorithms, has the following advantages:(1)The spatial information of an image is appropriately introduced into the definition of image entropy. (2) A large number of multiplication operations are eliminated, thus the algorithm is sped up. (3) The shortcoming of having to do global calculation in the first instance is overcome, and concludes the algorithm has very good locality and is suitable for parallel processing.
基金supported by the National Natural Science Foundation of China,China(No.61801491)。
文摘Multi-modal image matching is crucial in aerospace applications because it can fully exploit the complementary and valuable information contained in the amount and diversity of remote sensing images.However,it remains a challenging task due to significant non-linear radiometric,geometric differences,and noise across different sensors.To improve the performance of heterologous image matching,this paper proposes a normalized self-similarity region descriptor to extract consistent structural information.We first construct the pointwise self-similarity region descriptor based on the Euclidean distance between adjacent image blocks to reflect the structural properties of multi-modal images.Then,a linear normalization approach is used to form Modality Independent Region Descriptor(MIRD),which can effectively distinguish structural features such as points,lines,corners,and flat between multi-modal images.To further improve the matching accuracy,the included angle cosine similarity metric is adopted to exploit the directional vector information of multi-dimensional feature descriptors.The experimental results show that the proposed MIRD has better matching accuracy and robustness for various multi-modal image matching than the state-of-the-art methods.MIRD can effectively extract consistent geometric structure features and suppress the influence of SAR speckle noise using non-local neighboring image blocks operation,effectively applied to various multi-modal image matching.
基金Supported by the Key Research Program of the Chinese Academy of Sciences(ZDRE-KT-2021-3)。
文摘Augmented solar images were used to research the adaptability of four representative image extraction and matching algorithms in space weather domain.These include the scale-invariant feature transform algorithm,speeded-up robust features algorithm,binary robust invariant scalable keypoints algorithm,and oriented fast and rotated brief algorithm.The performance of these algorithms was estimated in terms of matching accuracy,feature point richness,and running time.The experiment result showed that no algorithm achieved high accuracy while keeping low running time,and all algorithms are not suitable for image feature extraction and matching of augmented solar images.To solve this problem,an improved method was proposed by using two-frame matching to utilize the accuracy advantage of the scale-invariant feature transform algorithm and the speed advantage of the oriented fast and rotated brief algorithm.Furthermore,our method and the four representative algorithms were applied to augmented solar images.Our application experiments proved that our method achieved a similar high recognition rate to the scale-invariant feature transform algorithm which is significantly higher than other algorithms.Our method also obtained a similar low running time to the oriented fast and rotated brief algorithm,which is significantly lower than other algorithms.
基金The authors would like to thank NVIDIA Corp.for donating the GPU used in this research through its GPU grant program.The first author Lin Chen would also like to thank the China Scholarship Council(CSC)for financially supporting his PhD study.
文摘In feature based image matching,distinctive features in images are detected and represented by feature descriptors.Matching is then carried out by assessing the similarity of the descriptors of potentially conjugate points.In this paper,we first shortly discuss the general frame-work.Then,we review feature detection as well as the determination of affine shape and orientation of local features,before analyzing feature description in more detail.In the feature description review,the general framework of local feature description is presented first.Then,the review discusses the evolution from hand-crafted feature descriptors,e.g.SIFT(Scale Invariant Feature Transform),to machine learning and deep learning based descriptors.The machine learning models,the training loss and the respective training data of learning-based algorithms are looked at in more detail;subsequently the various advantages and challenges of the different approaches are discussed.Finally,we present and assess some current research directions before concluding the paper.
基金This work was supported by the National Key Research and Development Program of China[grant number 2017YFC0803802]and the National Natural Science Foundation of China[grant number 41771486].
文摘Targeting at a reliable image matching of multiple remote sensing images for the generation of digital surface models,this paper presents a geometric-constrained multi-view image matching method,based on an energy minimization framework.By employing a geometrical constraint,the cost value of the energy function was calculated from multiple images,and the cost value was aggregated in an image space using a semi-global optimization approach.A homography transform parameter calculation method is proposed for fast calculation of projection pixel on each image when calculation cost values.It is based on the known interior orientation parameters,exterior orientation parameters,and a given elevation value.For an efficient and reliable processing of multiple remote sensing images,the proposed matching method was performed via a coarse-to-fine strategy through image pyramid.Three sets of airborne remote sensing images were used to evaluate the performance of the proposed method.Results reveal that the multi-view image matching can improve matching reliability.Moreover,the experimental results show that the proposed method performs better than traditional methods.
文摘Cross-correlation (CC) is the most time-consuming in the implementation of image matching algorithms based on the correlation method. Therefore, how to calculate CC fast is crucial to real-time image matching. This work reveals that the single cascading multiply-accumulate (CAMAC) and concurrent multiply-accumulate (COMAC) architectures which have been widely used in the past, actually, do not necessarily bring about a satisfactory time performance for CC. To obtain better time performance and higher resource efficiency, this paper proposes a configurable circuit involving the advantages of CAMAC and COMAC for a large amount of multiply-accumulate (MAC) operations of CC in exhaustive search. The proposed circuit works in an array manner and can better adapt to changing size image matching in real-time processing. Experimental results demonstrate that this novel circuit which involves the two structures can complete vast MAC calculations at a very high speed. Compared with existing related work, it improves the computation density further and is more flexible to use.
文摘A new method of view synthesis is proposed based on Delaunay triangulation. The first step of this method is making the Delaunay triangulation of 2 reference images. Secondly, matching the image points using the epipolar geometry constraint. Finally, constructing the third view according to pixel transferring under the trilinear constraint. The method gets rid of the classic time consuming dense matching technique and takes advantage of Delaunay triangulation. So it can not only save the computation time but also enhance the quality of the synthesized view. The significance of this method is that it can be used directly in the fields of video coding, image compressing and virtual reality.
基金This work was supported in part by the National Natural Science Foundation of China under Grant 41322010 and 41571434the National Hi-Tech Research and Development Program under Grant 2013AA12A401+1 种基金and the academic award for excellent Ph.D.Candidates funded by Ministry of Education of China under Grant 5052012213002Heartfelt thanks are also given for the comments and contributions of anonymous reviewers and members of the editorial team.
文摘Image matching is one of the key technologies for digital Earth.This paper presents a combined image matching method for Chinese satellite images.This method includes the following four steps:(1)a modified Wallis-type filter is proposed to determine parameters adaptively while avoiding over-enhancement;(2)a mismatch detection procedure based on a global-local strategy is introduced to remove outliers generated by the Scale-invariant feature transform algorithm,and geometric orientation with bundle block adjustment is employed to compensate for the systematic errors of the position and attitude observations;(3)we design a novel similarity measure(distance,angle and the Normalized Cross-Correlation similarities,DANCC)which considers geometric similarity and textural similarity;and(4)we introduce a hierarchical matching strategy to refine the matching result level by level.Four typical image pairs acquired from Mapping Satellite-1,ZY-102C,ZY-3 and GeoEye-1,respectively,are used for experimental analysis.A comparison with the two current main matching algorithms for satellite imagery confirms that the proposed method is capable of producing reliable and accurate matching results on different terrains from not only Chinese satellite images,but also foreign satellite images.
文摘As the fundamental problem in the computer vision area,image matching has wide applications in pose estimation,3D reconstruction,image retrieval,etc.Suffering from the influence of external factors,the process of image matching using classical local detectors,e.g.,scale-invariant feature transform(SIFT),and the outlier filtering approaches,e.g.,Random sample consensus(RANSAC),show high computation speed and pool robustness under changing illumination and viewpoints conditions,while image matching approaches with deep learning strategy(such as HardNet,OANet)display reliable achievements in large-scale datasets with challenging scenes.However,the past learning-based approaches are limited to the distinction and quality of the dataset and the training strategy in the image-matching approaches.As an extension of the previous conference paper,this paper proposes an accurate and robust image matching approach using fewer training data in an end-to-end manner,which could be used to estimate the pose error This research first proposes a novel dataset cleaning and construction strategy to eliminate the noise and improve the training efficiency;Secondly,a novel loss named quadratic hinge triplet loss(QHT)is proposed to gather more effective and stable feature matching;Thirdly,in the outlier filtering process,the stricter OANet and bundle adjustment are applied for judging samples by adding the epipolar distance constraint and triangulation constraint to generate more outstanding matches;Finally,to recall the matching pairs,dynamic guided matching is used and then submit the inliers after the PyRANSAC process.Multiple evaluation metrics are used and reported in the 1st place in the Track1 of CVPR Image-Matching Challenge Workshop.The results show that the proposed method has advanced performance in large-scale and challenging Phototourism benchmark.
文摘To solve the heterogeneous image scene matching problem, a non-linear pre-processing method for the original images before intensity-based correlation is proposed. The result shows that the proper matching probability is raised greatly. Especially for the low S/N image pairs, the effect is more remarkable.
基金supported by MOST under Grants No.105-2410-H-468-010 and No.105-2221-E-468-019
文摘The concept of dual image reversible data hiding(DIRDH) is the technique that can produce two camouflage images after embedding secret data into one original image.Moreover,not only can the secret data be extracted from two camouflage images but also the original image can be recovered.To achieve high image quality,Lu et al.'s method applied least-significant-bit(LSB) matching revisited to DIRDH.In order to further improve the image quality,the proposed method modifies LSB matching revisited rules and applies them to DIRDH.According to the experimental results,the image quality of the proposed method is better than that of Lu et al.'s method.
基金supported by the National Natural Science Foundation of China[Grant No.41771479]the National High-Resolution Earth Observation System(the Civil Part)[Grant No.50-H31D01-0508-13/15]the Japan Society for the Promotion of Science[Grant No.22H03573].
文摘Automatic Digital Orthophoto Map(DOM)generation plays an important role in many downstream works such as land use and cover detection,urban planning,and disaster assessment.Existing DOM generation methods can generate promising results but always need ground object filtered DEM generation before otho-rectification;this can consume much time and produce building facade contained results.To address this problem,a pixel-by-pixel digital differential rectification-based automatic DOM generation method is proposed in this paper.Firstly,3D point clouds with texture are generated by dense image matching based on an optical flow field for a stereo pair of images,respectively.Then,the grayscale of the digital differential rectification image is extracted directly from the point clouds element by element according to the nearest neighbor method for matched points.Subsequently,the elevation is repaired grid-by-grid using the multi-layer Locally Refined B-spline(LR-B)interpolation method with triangular mesh constraint for the point clouds void area,and the grayscale is obtained by the indirect scheme of digital differential rectification to generate the pixel-by-pixel digital differentially rectified image of a single image slice.Finally,a seamline network is automatically searched using a disparity map optimization algorithm,and DOM is smartly mosaicked.The qualitative and quantitative experimental results on three datasets were produced and evaluated,which confirmed the feasibility of the proposed method,and the DOM accuracy can reach 1 Ground Sample Distance(GSD)level.The comparison experiment with the state-of-the-art commercial softwares showed that the proposed method generated DOM has a better visual effect on building boundaries and roof completeness with comparable accuracy and computational efficiency.
基金supported by NSFC under grant No.11471331partially supported by National Center for Mathematics and Interdisciplinary Sciences
文摘The existence of a global minimizer for a variational problem arising in registration of diffusion tensor images is proved, which ensures that there is a regular spatial transformation for the registration of diffusion tensor images.
基金Sponsored by the Scientific Research Common Program of Beijing Municipal Commission of Education(Grant No. KM201010772021the National High Technology Research and Development Program of China (863 Program) (Grant No. 2006AA74105)the National Natural Science Foundation of Chi-na(Grant No. 60803103)
文摘To solve the problem of wide-baseline stereo image matching based on multiple cameras,the paper puts forward an image matching method of combining maximally stable extremal regions (MSER) with Scale Invariant Feature Transform (SIFT) . It uses MSER to detect feature regions instead of difference of Gaussian. After fitted into elliptical regions,those regions will be normalized into unity circles and represented with SIFT descriptors. The method estimates fundamental matrix and removes outliers by auto-maximum a posteriori sample consensus after initial matching feature points. The experimental results indicate that the method is robust to viewpoint changes,can reduce computational complexity effectively and improve matching accuracy.
基金Supported by the National Natural Science Foundation of China under Grants 61872241,62077037 and 62272298in part by Shanghai Municipal Science and Technology Major Project under Grant 2021SHZDZX0102。
文摘Background Exploring correspondences across multiview images is the basis of various computer vision tasks.However,most existing methods have limited accuracy under challenging conditions.Method To learn more robust and accurate correspondences,we propose DSD-MatchingNet for local feature matching in this study.First,we develop a deformable feature extraction module to obtain multilevel feature maps,which harvest contextual information from dynamic receptive fields.The dynamic receptive fields provided by the deformable convolution network ensure that our method obtains dense and robust correspondence.Second,we utilize sparse-to-dense matching with symmetry of correspondence to implement accurate pixel-level matching,which enables our method to produce more accurate correspondences.Result Experiments show that our proposed DSD-MatchingNet achieves a better performance on the image matching benchmark,as well as on the visual localization benchmark.Specifically,our method achieved 91.3%mean matching accuracy on the HPatches dataset and 99.3%visual localization recalls on the Aachen Day-Night dataset.