Pub Date : 1999-06-23DOI: 10.1109/CVPR.1999.786928
Charles T. Loop, Zhengyou Zhang
Image rectification is the process of applying a pair of 2D projective transforms, or homographies, to a pair of images whose epipolar geometry is known so that epipolar lines in the original images map to horizontally aligned lines in the transformed images. We propose a novel technique for image rectification based on geometrically well defined criteria such that image distortion due to rectification is minimized. This is achieved by decomposing each homography into a specialized projective transform, a similarity transform, followed by a shearing transform. The effect of image distortion at each stage is carefully considered.
{"title":"Computing rectifying homographies for stereo vision","authors":"Charles T. Loop, Zhengyou Zhang","doi":"10.1109/CVPR.1999.786928","DOIUrl":"https://doi.org/10.1109/CVPR.1999.786928","url":null,"abstract":"Image rectification is the process of applying a pair of 2D projective transforms, or homographies, to a pair of images whose epipolar geometry is known so that epipolar lines in the original images map to horizontally aligned lines in the transformed images. We propose a novel technique for image rectification based on geometrically well defined criteria such that image distortion due to rectification is minimized. This is achieved by decomposing each homography into a specialized projective transform, a similarity transform, followed by a shearing transform. The effect of image distortion at each stage is carefully considered.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":"78 1","pages":"125-131 Vol. 1"},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87094612","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1999-06-23DOI: 10.1109/CVPR.1999.784643
Lin Zhou, C. Kambhamettu, Dmitry Goldgof
Image sequences capturing Hurricane Luis through meteorological satellites (GOES-8 and GOES-9) are used to estimate hurricane-top heights (structure) and hurricane winds (motion). This problem is difficult not only due to the absence of correspondence but also due to the lack of depth cues in the 2D hurricane images (scaled orthographic projection). In this paper, we present a structure and motion analysis system, called SMAS. In this system, the hurricane images are first segmented into small square areas. We assume that each small area is undergoing similar nonrigid motion. A suitable nonrigid motion model for cloud motion is first defined. Then, non-linear least-square method is used to fit the nonrigid motion model for each area in order to estimate the structure, motion model, and 3D nonrigid motion correspondences. Finally, the recovered hurricane-top heights and winds are presented along with an error analysis. Both structure and 3D motion correspondences are estimated to subpixel accuracy. Our results are very encouraging, and have many potential applications in earth and space sciences, especially in cloud models for weather prediction.
{"title":"Extracting nonrigid motion and 3D structure of hurricanes from satellite image sequences without correspondences","authors":"Lin Zhou, C. Kambhamettu, Dmitry Goldgof","doi":"10.1109/CVPR.1999.784643","DOIUrl":"https://doi.org/10.1109/CVPR.1999.784643","url":null,"abstract":"Image sequences capturing Hurricane Luis through meteorological satellites (GOES-8 and GOES-9) are used to estimate hurricane-top heights (structure) and hurricane winds (motion). This problem is difficult not only due to the absence of correspondence but also due to the lack of depth cues in the 2D hurricane images (scaled orthographic projection). In this paper, we present a structure and motion analysis system, called SMAS. In this system, the hurricane images are first segmented into small square areas. We assume that each small area is undergoing similar nonrigid motion. A suitable nonrigid motion model for cloud motion is first defined. Then, non-linear least-square method is used to fit the nonrigid motion model for each area in order to estimate the structure, motion model, and 3D nonrigid motion correspondences. Finally, the recovered hurricane-top heights and winds are presented along with an error analysis. Both structure and 3D motion correspondences are estimated to subpixel accuracy. Our results are very encouraging, and have many potential applications in earth and space sciences, especially in cloud models for weather prediction.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":"54 1","pages":"280-285 Vol. 2"},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76850843","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1999-06-23DOI: 10.1109/CVPR.1999.784716
Zhiqian Wang, J. Ben-Arie
This paper presents a novel approach for detection and segmentation of generic shapes in cluttered images. The underlying assumption is that generic objects that are man made, frequently have surfaces which closely resemble standard model shapes such as rectangles, semi-circles etc. Due to the perspective transformations of optical imaging systems, a model shape may appear differently in the image with various orientations and aspect ratios. The set of possible appearances can be represented compactly by a few vectorial eigenbases that are derived from a small set of model shapes which are affine transformed in a wide parameter range. Instead of regular boundary of standard models, we apply a vectorial boundary which improves robustness to noise, background clutter and partial occlusion. The detection of generic shapes is realized by detecting local peaks of a similarity measure between the image edge map and an eigenspace combined set of the appearances. At each local maxima, a fast search approach based on a novel representation by an angle space is employed to determine the best matching between models and the underlying subimage. We find that angular representation in multidimensional search corresponds better to Euclidean distance than conventional projection and yields improved classification of noisy shapes. Experiments are performed in various interfering distortions, and robust detection and segmentation are achieved.
{"title":"Generic object detection using model based segmentation","authors":"Zhiqian Wang, J. Ben-Arie","doi":"10.1109/CVPR.1999.784716","DOIUrl":"https://doi.org/10.1109/CVPR.1999.784716","url":null,"abstract":"This paper presents a novel approach for detection and segmentation of generic shapes in cluttered images. The underlying assumption is that generic objects that are man made, frequently have surfaces which closely resemble standard model shapes such as rectangles, semi-circles etc. Due to the perspective transformations of optical imaging systems, a model shape may appear differently in the image with various orientations and aspect ratios. The set of possible appearances can be represented compactly by a few vectorial eigenbases that are derived from a small set of model shapes which are affine transformed in a wide parameter range. Instead of regular boundary of standard models, we apply a vectorial boundary which improves robustness to noise, background clutter and partial occlusion. The detection of generic shapes is realized by detecting local peaks of a similarity measure between the image edge map and an eigenspace combined set of the appearances. At each local maxima, a fast search approach based on a novel representation by an angle space is employed to determine the best matching between models and the underlying subimage. We find that angular representation in multidimensional search corresponds better to Euclidean distance than conventional projection and yields improved classification of noisy shapes. Experiments are performed in various interfering distortions, and robust detection and segmentation are achieved.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":"16 1","pages":"428-433 Vol. 2"},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73784272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1999-06-23DOI: 10.1109/CVPR.1999.787002
Hai Tao, Thomas S. Huang
Capturing real motions from video sequences is a powerful method for automatic building of facial articulation models. In this paper, we propose an explanation-based facial motion tracking algorithm based on a piecewise Bezier volume deformation model (PBVD). The PBVD is a suitable model both for the synthesis and the analysis of facial images. It is linear and independent of the facial mesh structure. With this model, basic facial movements, or action units, are interactively defined. By changing the magnitudes of these action units, animated facial images are generated. The magnitudes of these action units can also be computed from real video sequences using a model-based tracking algorithm. However, in order to customize the articulation model for a particular face, the predefined PBVD action units need to be adaptively modified. In this paper, we first briefly introduce the PBVD model and its application in facial animation. Then a multiresolution PBVD-based motion tracking algorithm is presented. Finally, we describe an explanation-based tracking algorithm that takes the predefined action units as the initial articulation model and adaptively improves them during the tracking process to obtain a more realistic articulation model. Experimental results on PBVD-based animation, model-based tracking, and explanation-based tracking are shown in this paper.
{"title":"Explanation-based facial motion tracking using a piecewise Bezier volume deformation model","authors":"Hai Tao, Thomas S. Huang","doi":"10.1109/CVPR.1999.787002","DOIUrl":"https://doi.org/10.1109/CVPR.1999.787002","url":null,"abstract":"Capturing real motions from video sequences is a powerful method for automatic building of facial articulation models. In this paper, we propose an explanation-based facial motion tracking algorithm based on a piecewise Bezier volume deformation model (PBVD). The PBVD is a suitable model both for the synthesis and the analysis of facial images. It is linear and independent of the facial mesh structure. With this model, basic facial movements, or action units, are interactively defined. By changing the magnitudes of these action units, animated facial images are generated. The magnitudes of these action units can also be computed from real video sequences using a model-based tracking algorithm. However, in order to customize the articulation model for a particular face, the predefined PBVD action units need to be adaptively modified. In this paper, we first briefly introduce the PBVD model and its application in facial animation. Then a multiresolution PBVD-based motion tracking algorithm is presented. Finally, we describe an explanation-based tracking algorithm that takes the predefined action units as the initial articulation model and adaptively improves them during the tracking process to obtain a more realistic articulation model. Experimental results on PBVD-based animation, model-based tracking, and explanation-based tracking are shown in this paper.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":"42 1","pages":"611-617 Vol. 1"},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75580711","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1999-06-23DOI: 10.1109/CVPR.1999.784641
D. Slater, G. Healey
Automated material classification from airborne imagery is an important capability for many applications including target recognition and geospatial database construction. Hyperspectral imagery provides a rich source of information for this purpose but utilization is complicated by the variability in a material's observed spectral signature due to the ambient conditions and the scene geometry. In this paper, we present a method that uses a single spectral radiance function measured from a material under unknown conditions to synthesize a comprehensive set of radiance spectra that corresponds to that material over a wide range of conditions. This set of radiance spectra can be used to build a hyperspectral subspace representation that can be used for material identification over a wide range of circumstances. We demonstrate the use of these algorithms for model synthesis and material mapping using HYDICE imagery acquired at Fort Hood, Texas. The method correctly maps several classes of roofing materials, roads, and vegetation over significant spectral changes due to variation in surface orientation. We show that the approach outperforms methods based on direct spectral comparison.
{"title":"Material classification for 3D objects in aerial hyperspectral images","authors":"D. Slater, G. Healey","doi":"10.1109/CVPR.1999.784641","DOIUrl":"https://doi.org/10.1109/CVPR.1999.784641","url":null,"abstract":"Automated material classification from airborne imagery is an important capability for many applications including target recognition and geospatial database construction. Hyperspectral imagery provides a rich source of information for this purpose but utilization is complicated by the variability in a material's observed spectral signature due to the ambient conditions and the scene geometry. In this paper, we present a method that uses a single spectral radiance function measured from a material under unknown conditions to synthesize a comprehensive set of radiance spectra that corresponds to that material over a wide range of conditions. This set of radiance spectra can be used to build a hyperspectral subspace representation that can be used for material identification over a wide range of circumstances. We demonstrate the use of these algorithms for model synthesis and material mapping using HYDICE imagery acquired at Fort Hood, Texas. The method correctly maps several classes of roofing materials, roads, and vegetation over significant spectral changes due to variation in surface orientation. We show that the approach outperforms methods based on direct spectral comparison.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":"26 1","pages":"268-273 Vol. 2"},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73232609","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1999-06-23DOI: 10.1109/CVPR.1999.786959
Michael J. Black
A spatio-temporal representation for complex optical flow events is developed that generalizes traditional parameterized motion models (e.g. affine). These generative spatio-temporal models may be non-linear or stochastic and are event-specific in that they characterize a particular type of object motion (e.g. sitting or walking). Within a Bayesian framework we seek the appropriate model, phase, rate, spatial position, and scale to account for the image variation. The posterior distribution over this parameter space conditioned on image measurements is typically non-Gaussian. The distribution is represented using factored sampling and is predicted and updated over time using the condensation algorithm. The resulting framework automatically detects, localizes, and recognizes motion events.
{"title":"Explaining optical flow events with parameterized spatio-temporal models","authors":"Michael J. Black","doi":"10.1109/CVPR.1999.786959","DOIUrl":"https://doi.org/10.1109/CVPR.1999.786959","url":null,"abstract":"A spatio-temporal representation for complex optical flow events is developed that generalizes traditional parameterized motion models (e.g. affine). These generative spatio-temporal models may be non-linear or stochastic and are event-specific in that they characterize a particular type of object motion (e.g. sitting or walking). Within a Bayesian framework we seek the appropriate model, phase, rate, spatial position, and scale to account for the image variation. The posterior distribution over this parameter space conditioned on image measurements is typically non-Gaussian. The distribution is represented using factored sampling and is predicted and updated over time using the condensation algorithm. The resulting framework automatically detects, localizes, and recognizes motion events.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":"77 1","pages":"326-332 Vol. 1"},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74912455","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1999-06-23DOI: 10.1109/CVPR.1999.784604
S. Seitz, P. Anandan
A technique is presented for representing linear features as probability density functions in two or three dimensions. Three chief advantages of this approach are (1) a unified representation and algebra for manipulating points, lines, and planes, (2) seamless incorporation of uncertainty information, and (3) a very simple recursive solution for maximum likelihood shape estimation. Applications to uncalibrated affine scene reconstruction are presented, with results on images of an outdoor environment.
{"title":"Implicit representation and scene reconstruction from probability density functions","authors":"S. Seitz, P. Anandan","doi":"10.1109/CVPR.1999.784604","DOIUrl":"https://doi.org/10.1109/CVPR.1999.784604","url":null,"abstract":"A technique is presented for representing linear features as probability density functions in two or three dimensions. Three chief advantages of this approach are (1) a unified representation and algebra for manipulating points, lines, and planes, (2) seamless incorporation of uncertainty information, and (3) a very simple recursive solution for maximum likelihood shape estimation. Applications to uncalibrated affine scene reconstruction are presented, with results on images of an outdoor environment.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":"22 1","pages":"28-34 Vol. 2"},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73898246","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1999-06-23DOI: 10.1109/CVPR.1999.786926
Philip W. Smith, Keith B. Johnson, M. Abidi
Wide-Angle lenses are not often used for 3D reconstruction tasks, in spite of the potential advantages offered by their increased field-of-view, because (1) existing algorithms for high-distortion lens compensation perform poorly at image extremities and (2) procedures for the reconstruction of recti-linear images place a large burden on system resources. In this paper, a projection model based on quadric surfaces is presented which accurately characterizes the effect of wide-angle lenses across the entire image and allows for the use of novel feature matching strategies that do not require nonlinear distortion compensation.
{"title":"Efficient techniques for wide-angle stereo vision using surface projection models","authors":"Philip W. Smith, Keith B. Johnson, M. Abidi","doi":"10.1109/CVPR.1999.786926","DOIUrl":"https://doi.org/10.1109/CVPR.1999.786926","url":null,"abstract":"Wide-Angle lenses are not often used for 3D reconstruction tasks, in spite of the potential advantages offered by their increased field-of-view, because (1) existing algorithms for high-distortion lens compensation perform poorly at image extremities and (2) procedures for the reconstruction of recti-linear images place a large burden on system resources. In this paper, a projection model based on quadric surfaces is presented which accurately characterizes the effect of wide-angle lenses across the entire image and allows for the use of novel feature matching strategies that do not require nonlinear distortion compensation.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":"3 1","pages":"113-118 Vol. 1"},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73923881","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1999-06-23DOI: 10.1109/CVPR.1999.784638
Vera M. Kettnaker, R. Zabih
The task of multicamera surveillance is to reconstruct the paths taken by all moving objects that are temporally visible from multiple non-overlapping cameras. We present a Bayesian formalization of this task, where the optimal solution is the set of object paths with the highest posterior probability given the observed data. We show how to efficiently approximate the maximum a posteriori solution by linear programming and present initial experimental results.
{"title":"Bayesian multi-camera surveillance","authors":"Vera M. Kettnaker, R. Zabih","doi":"10.1109/CVPR.1999.784638","DOIUrl":"https://doi.org/10.1109/CVPR.1999.784638","url":null,"abstract":"The task of multicamera surveillance is to reconstruct the paths taken by all moving objects that are temporally visible from multiple non-overlapping cameras. We present a Bayesian formalization of this task, where the optimal solution is the set of object paths with the highest posterior probability given the observed data. We show how to efficiently approximate the maximum a posteriori solution by linear programming and present initial experimental results.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":"12 1","pages":"253-259 Vol. 2"},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74722130","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1999-06-23DOI: 10.1109/CVPR.1999.786991
L. Joyeux, Olivier Buisson, B. Besserer, S. Boukir
Line scratches are common degradations in motion picture films. This paper presents an efficient method for line scratches detection strengthened by a Kalman filter. A new interpolation technique, dealing with both low and high frequencies (i.e. film grain) around the line artifacts, is investigated to achieve a nearby invisible reconstruction of damaged areas. Our line scratches detection and removal techniques have been validated on several film sequences.
{"title":"Detection and removal of line scratches in motion picture films","authors":"L. Joyeux, Olivier Buisson, B. Besserer, S. Boukir","doi":"10.1109/CVPR.1999.786991","DOIUrl":"https://doi.org/10.1109/CVPR.1999.786991","url":null,"abstract":"Line scratches are common degradations in motion picture films. This paper presents an efficient method for line scratches detection strengthened by a Kalman filter. A new interpolation technique, dealing with both low and high frequencies (i.e. film grain) around the line artifacts, is investigated to achieve a nearby invisible reconstruction of damaged areas. Our line scratches detection and removal techniques have been validated on several film sequences.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":"97 1","pages":"548-553 Vol. 1"},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76553220","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：