A simple algorithm for selecting and linking interesting flow vectors across a sequence of frames for computing motion trajectories is presented. Tokens that have both interesting pixel gray values in the spatial domain and in the optical flow field in the temporal domain are tracked. This AND operation effectively removes some redundant trajectories. Due to errors introduced during the computation of optical flow, and the linking of such flow vectors across a sequence of frames, the resultant trajectories are not always smooth. A Kalman-filtering-based approach for smoothing the trajectories is discussed.<>
{"title":"Motion trajectories","authors":"M. Shah, K. Rangarajan, P. Tsai","doi":"10.1109/21.247894","DOIUrl":"https://doi.org/10.1109/21.247894","url":null,"abstract":"A simple algorithm for selecting and linking interesting flow vectors across a sequence of frames for computing motion trajectories is presented. Tokens that have both interesting pixel gray values in the spatial domain and in the optical flow field in the temporal domain are tracked. This AND operation effectively removes some redundant trajectories. Due to errors introduced during the computation of optical flow, and the linking of such flow vectors across a sequence of frames, the resultant trajectories are not always smooth. A Kalman-filtering-based approach for smoothing the trajectories is discussed.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117254241","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 : 1992-12-01DOI: 10.1109/CVPR.1992.223243
G. Nudd, T. Atherton, D. Kerbyson
The use of a heterogeneous multiple-SIMD (M-SIMD) architecture with image-based measurements and optimal (Kalman) estimators for the analysis of image sequences is illustrated. The architecture integrates SIMD and MIMD processing paradigms, combining heterogeneity of processor types matched to the computation at each level and operational autonomy within an SIMD array. It is suited to real-time simultaneous data parallel (iconic) and control parallel (numeric) processing.<>
{"title":"An heterogeneous M-SIMD architecture for Kalman filter controlled processing of image sequences","authors":"G. Nudd, T. Atherton, D. Kerbyson","doi":"10.1109/CVPR.1992.223243","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223243","url":null,"abstract":"The use of a heterogeneous multiple-SIMD (M-SIMD) architecture with image-based measurements and optimal (Kalman) estimators for the analysis of image sequences is illustrated. The architecture integrates SIMD and MIMD processing paradigms, combining heterogeneity of processor types matched to the computation at each level and operational autonomy within an SIMD array. It is suited to real-time simultaneous data parallel (iconic) and control parallel (numeric) processing.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121491347","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 : 1992-07-01DOI: 10.1109/CVPR.1992.223257
W. Grimson, D. Huttenlocher, T. D. Alter
Object recognition systems that use a small number of pairings of data and model features to compute the 3D transformation from model to sensor coordinates are considered. The effects of 2D sensor uncertainty on such computations are examined. The uncertainty in transformation parameters is bounded, and the effect of this uncertainty on false positive recognition rates is analyzed.<>
{"title":"Recognizing 3D objects from 2D images: an error analysis","authors":"W. Grimson, D. Huttenlocher, T. D. Alter","doi":"10.1109/CVPR.1992.223257","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223257","url":null,"abstract":"Object recognition systems that use a small number of pairings of data and model features to compute the 3D transformation from model to sensor coordinates are considered. The effects of 2D sensor uncertainty on such computations are examined. The uncertainty in transformation parameters is bounded, and the effect of this uncertainty on false positive recognition rates is analyzed.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131467164","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 : 1992-06-15DOI: 10.1109/CVPR.1992.223274
Phillip N. Smith, B. Sridhar, B. Hussien
Computer-vision-based methods provide one general approach for obstacle detection and range estimation for pilot assistance during low-altitude flight. Results obtained using helicopter flight data with a feature-based range estimation algorithm are presented. A method for recursively estimating range using a Kalman filter with a monocular sequence of images and knowledge of the camera's motion is described. The helicopter flight experiment and one of four resulting datasets are briefly discussed. The performance of the range estimation algorithm is examined by comparing the range estimates with true range measurements collected during the flight experiment.<>
{"title":"Vision-based range estimation using helicopter flight data","authors":"Phillip N. Smith, B. Sridhar, B. Hussien","doi":"10.1109/CVPR.1992.223274","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223274","url":null,"abstract":"Computer-vision-based methods provide one general approach for obstacle detection and range estimation for pilot assistance during low-altitude flight. Results obtained using helicopter flight data with a feature-based range estimation algorithm are presented. A method for recursively estimating range using a Kalman filter with a monocular sequence of images and knowledge of the camera's motion is described. The helicopter flight experiment and one of four resulting datasets are briefly discussed. The performance of the range estimation algorithm is examined by comparing the range estimates with true range measurements collected during the flight experiment.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115651005","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 : 1992-06-15DOI: 10.1109/CVPR.1992.223250
A. Gross
A survey and critique of previous work is given, and two object-based heuristics are developed. The structured nature of objects is the motivation for the nonaccidental alignment criterion; parallel lines within the object's bounding contour are related to the object-centered coordinate system. The regularity and symmetry inherent in many man-made objects is the motivation for the orthogonal basis constraint, an oblique set of coordinate axes in the image is presumed to be the projection of an orthogonal set of 3D coordinate axes in the scene. These heuristics are demonstrated on real and synthetic image contours.<>
{"title":"Towards object-based heuristics","authors":"A. Gross","doi":"10.1109/CVPR.1992.223250","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223250","url":null,"abstract":"A survey and critique of previous work is given, and two object-based heuristics are developed. The structured nature of objects is the motivation for the nonaccidental alignment criterion; parallel lines within the object's bounding contour are related to the object-centered coordinate system. The regularity and symmetry inherent in many man-made objects is the motivation for the orthogonal basis constraint, an oblique set of coordinate axes in the image is presumed to be the projection of an orthogonal set of 3D coordinate axes in the scene. These heuristics are demonstrated on real and synthetic image contours.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124732570","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 : 1992-06-15DOI: 10.1109/CVPR.1992.223159
B. Modayur, L. Shapiro, R. Haralick
A CAD-model-based machine vision system for dimensional inspection of machine parts is described, with emphasis on the theory behind the system. The original contributions of this work are: (1) the use of precise definitions of geometric tolerances suitable for use in image processing, (2) the development of measurement algorithms corresponding directly to these definitions, (3) the derivation of the uncertainties in the measurement tasks, and (4) the use of this uncertainty information in the decision-making process. Initial experimental results have verified the uncertainty derivations statistically and proved that the error probabilities obtained by propagating uncertainties are lower than those obtainable without uncertainty propagation.<>
{"title":"Visual inspection of machined parts","authors":"B. Modayur, L. Shapiro, R. Haralick","doi":"10.1109/CVPR.1992.223159","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223159","url":null,"abstract":"A CAD-model-based machine vision system for dimensional inspection of machine parts is described, with emphasis on the theory behind the system. The original contributions of this work are: (1) the use of precise definitions of geometric tolerances suitable for use in image processing, (2) the development of measurement algorithms corresponding directly to these definitions, (3) the derivation of the uncertainties in the measurement tasks, and (4) the use of this uncertainty information in the decision-making process. Initial experimental results have verified the uncertainty derivations statistically and proved that the error probabilities obtained by propagating uncertainties are lower than those obtainable without uncertainty propagation.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"194 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123305718","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 : 1992-06-15DOI: 10.1109/CVPR.1992.223155
S. Negahdaripour, B. Hayashi, Y. Aloimonos
The problem of motion recovery for a head-eye system from stereo image sequences is addressed. Two types of motions, the translation of the vehicle and the panning motion of the head, are considered. It is shown how these motions and the depth map can be estimated directly from the measurements of image gradients and time derivatives. There is no need to estimate image motion, track a scene feature over time, or establish point correspondences in a stereo image pair. The results of various experiments with real scenes are presented.<>
{"title":"Direct motion stereo for passive navigation","authors":"S. Negahdaripour, B. Hayashi, Y. Aloimonos","doi":"10.1109/CVPR.1992.223155","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223155","url":null,"abstract":"The problem of motion recovery for a head-eye system from stereo image sequences is addressed. Two types of motions, the translation of the vehicle and the panning motion of the head, are considered. It is shown how these motions and the depth map can be estimated directly from the measurements of image gradients and time derivatives. There is no need to estimate image motion, track a scene feature over time, or establish point correspondences in a stereo image pair. The results of various experiments with real scenes are presented.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125405383","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 : 1992-06-15DOI: 10.1109/CVPR.1992.223209
D. Huttenlocher, W. Rucklidge, G. A. Klanderman
Efficient algorithms are provided for computing the Hausdorff distance between a binary image and all possible relative positions (translations) of a model, or a portion of that model. The computation is in many ways similar to binary correlation. However, it is more tolerant of perturbations in the locations of points because it measures proximity rather than exact superposition.<>
{"title":"Comparing images using the Hausdorff distance under translation","authors":"D. Huttenlocher, W. Rucklidge, G. A. Klanderman","doi":"10.1109/CVPR.1992.223209","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223209","url":null,"abstract":"Efficient algorithms are provided for computing the Hausdorff distance between a binary image and all possible relative positions (translations) of a model, or a portion of that model. The computation is in many ways similar to binary correlation. However, it is more tolerant of perturbations in the locations of points because it measures proximity rather than exact superposition.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114254967","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 : 1992-06-15DOI: 10.1109/CVPR.1992.223143
P. Belhumeur, D. Mumford
A half-occluded region in a stereo pair is a set of pixels in one image representing points in space visible to that camera or eye only, and not to the other. These occur typically as parts of the background immediately to the left and right sides of nearby occluding objects, and are present in most natural scenes. Previous approaches to stereo either ignored these unmatchable points or attempted to weed them out in a second pass. An algorithm that incorporates them from the start as a strong clue to depth discontinuities is presented. The authors first derive a measure for goodness of fit and a prior based on a simplified model of objects in space, which leads to an energy functional depending both on the depth as measured from a central cyclopean eye and on the regions of points occluded from the left and right eye perspectives. They minimize this using dynamic programming along epipolar lines followed by annealing in both dimensions. Experiments indicate that this method is very effective even in difficult scenes.<>
{"title":"A Bayesian treatment of the stereo correspondence problem using half-occluded regions","authors":"P. Belhumeur, D. Mumford","doi":"10.1109/CVPR.1992.223143","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223143","url":null,"abstract":"A half-occluded region in a stereo pair is a set of pixels in one image representing points in space visible to that camera or eye only, and not to the other. These occur typically as parts of the background immediately to the left and right sides of nearby occluding objects, and are present in most natural scenes. Previous approaches to stereo either ignored these unmatchable points or attempted to weed them out in a second pass. An algorithm that incorporates them from the start as a strong clue to depth discontinuities is presented. The authors first derive a measure for goodness of fit and a prior based on a simplified model of objects in space, which leads to an energy functional depending both on the depth as measured from a central cyclopean eye and on the regions of points occluded from the left and right eye perspectives. They minimize this using dynamic programming along epipolar lines followed by annealing in both dimensions. Experiments indicate that this method is very effective even in difficult scenes.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114491387","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 : 1992-06-15DOI: 10.1109/CVPR.1992.223118
J. Bigün, J. D. Buf
An approach to image feature extraction is proposed. Complex moments of the Gabor power spectrum are used to detect linear, rectangular, hexagonal/triangular, and other structures with very fine to very coarse resolutions. When the method is applied to texture segmentation, good results are obtained.<>
{"title":"Geometric image primitives by complex moments in Gabor space and the application to texture segmentation","authors":"J. Bigün, J. D. Buf","doi":"10.1109/CVPR.1992.223118","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223118","url":null,"abstract":"An approach to image feature extraction is proposed. Complex moments of the Gabor power spectrum are used to detect linear, rectangular, hexagonal/triangular, and other structures with very fine to very coarse resolutions. When the method is applied to texture segmentation, good results are obtained.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128592480","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：