Arthur R. Pope and David G. Lowe. "Modeling Positional Uncertainty in Object Recognition". Technical report, Department of Computer Science, University of British Columbia, 1994. Technical Report # 94-32. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
A Probabilistic Approach to Object Recognition Using Local.. - Burl, Weber, Perona (1998) (28 citations) (Correct)
....despite a cluttered background in the image, and (c) how to handle partial occlusion of the object. Lanitis, Cootes et al. 14, 6, 7] proposed to use principal components analysis (applied to the shape of an object rather than the photometric appearance) to address the first issue. Pope and Lowe [17, 18] used probability theory to model the variation in shape of triples of features. Brunelli and Poggio [1] showed that an ad hoc face detector consisting of individual features linked together with crude geometry constraints outperformed a rigid correlation based full face detector. Burl, Leung, ....
Arthur R. Pope and David G. Lowe. "Modeling Positional Uncertainty in Object Recognition". Technical report, Department of Computer Science, University of British Columbia, 1994. Technical Report # 94-32.
Recognition of Visual Object Classes - Burl, Leung, Weber, Perona (1996) (Correct)
....based on eigenmodes. Although this approach can be viewed as an approximation of the probability density over feature positions, it is not This is page iii Printer: Opaque this clear that their snake based features will work in cluttered scenes or with occlusion. The work by Pope and Lowe [38, 37] is similar in flavor to ours, but our approach is more rigorous and general, especially the use of joint distributions to model spatial arrangements. The use of shape statistics in computer vision applications has also been examined by [43, 7] 2 Local Feature Detectors The initial step in our ....
Arthur R. Pope and David G. Lowe. "Modeling Positional Uncertainty in Object Recognition". Technical report, Department of Computer Science, University of British Columbia, 1994. Technical Report # 9432.
A Probabilistic Approach to Object Recognition Using Local.. - Burl, Weber, Perona (1998) (28 citations) (Correct)
....despite a cluttered background in the image, and (c) how to handle partial occlusion of the object. Lanitis, Cootes et al. 14, 6, 7] proposed to use principal components analysis (applied to the shape of an object rather than the photometric appearance) to address the first issue. Pope and Lowe [17, 18] used probability theory to model the variation in shape of triples of features. Brunelli and Poggio [1] showed that an ad hoc face detector consisting of individual features linked together with crude geometry constraints outperformed a rigid correlation based full face detector. Burl, Leung, ....
Arthur R. Pope and David G. Lowe. "Modeling Positional Uncertainty in Object Recognition". Technical report, Department of Computer Science, University of British Columbia, 1994. Technical Report # 94-32.
Recognition of Planar Object Classes - Burl, Perona (1996) (20 citations) (Correct)
....a system that uses a shape description based on eigenmodes. Although this approach can be viewed as an approximation of the probability density over feature positions, it is not clear that their snake based features will work in cluttered scenes or with occlusion. The work by Pope and Lowe [25, 24] is similar in flavor to ours, but our approach is more rigorous and general, especially the probabilistic modeling of spatial arrangements. The use of shape statistics in computer vision applications has also been examined by [28, 5] 2 Algorithm Description 2.1 Problem Formulation In this ....
Arthur R. Pope and David G. Lowe. "Modeling Positional Uncertainty in Object Recognition". Technical report, Department of Computer Science, University of British Columbia, 1994. Technical Report # 94-32.
Computer Science Simultaneous Refinement of Pose and Sensor.. - Schwickerath (1997) (Correct)
....or pose determination being tied to sensor fusion (e.g. 19, 13] 1. 2 Model Based Pose Different approaches have been taken to model based pose determination (e.g. 27, 29, 19, 8] This thesis is concerned with those which act directly on 3D model features, rather than 2D deformable graphs [35], or weak perspective (2D rigid projections) methods [8, 2] Methods which deal directly with 3D model features can utilize full 3D perspective and implicitly deal with any view of the object. 2D methods can correct only somewhat for perspective projections. They also must explicitly describe ....
Arthur R. Pope and David G. Lowe. Modeling positional uncertainty in object recognition. Technical Report 94-32, University of British Columbia, November 1994.
Learning Object Recognition Models from Images - Pope, Lowe (1995) (26 citations) Self-citation (Pope Lowe) (Correct)
....test the approach. Section 7 discusses relevant work by others on this and similar problems, and section 8 summarizes the chapter s main ideas. Sections flagged by y contain technical details that can be safely skipped on a first reading. More information may be found in other recent publications [18, 19, 20]. 2 Representation Schemes 2.1 Image representation We represent an image in terms of discrete properties called features. Each feature has a particular type, a location within the image, and a vector of numeric attributes that further characterize it. A feature may, for example, be a segment ....
A. R. Pope and D. G. Lowe. Modeling positional uncertainty in object recognition. Technical Report 94-32, Dept. of Computer Science, Univ. of B.C., Nov. 1994. WWW http://www.cs.ubc.ca/tr/1994/TR-94-32.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC