This paper presents a new formulation of the problem of motion estimation which attempts to give solutions to classical problems in the field, such as detection of motion discontinuities and insufficiency of the optical flow constraint in areas with low intensity variation. An initial intensity segmentation phase partitions each frame into patches so that areas with low intensity variation are guaranteed to belong to the same patch. A parametric model is assumedto describe the motion of each patch. Regularization in the motion parameter space provides the additional constraints for patches where the intensity variation is insufficient to constrain the estimation of the motion parameters and smooths the corresponding motion field. In orderto preserve motion discontinuities we use robust functions as a regularization mean. Experimental results show that the proposed method deals successfully with motions large in magnitude, motion discontinuities and produces accurate piecewise smooth motion fields.
{"title":"Regularized Patch Motion Estimation","authors":"I. Patras, M. Worring","doi":"10.1109/ICPR.2002.10010","DOIUrl":"https://doi.org/10.1109/ICPR.2002.10010","url":null,"abstract":"This paper presents a new formulation of the problem of motion estimation which attempts to give solutions to classical problems in the field, such as detection of motion discontinuities and insufficiency of the optical flow constraint in areas with low intensity variation. An initial intensity segmentation phase partitions each frame into patches so that areas with low intensity variation are guaranteed to belong to the same patch. A parametric model is assumedto describe the motion of each patch. Regularization in the motion parameter space provides the additional constraints for patches where the intensity variation is insufficient to constrain the estimation of the motion parameters and smooths the corresponding motion field. In orderto preserve motion discontinuities we use robust functions as a regularization mean. Experimental results show that the proposed method deals successfully with motions large in magnitude, motion discontinuities and produces accurate piecewise smooth motion fields.","PeriodicalId":74516,"journal":{"name":"Proceedings of the ... IAPR International Conference on Pattern Recognition. International Conference on Pattern Recognition","volume":"1 1","pages":"323-326"},"PeriodicalIF":0.0,"publicationDate":"2002-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79858343","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 : 2002-08-11DOI: 10.1109/ICPR.2002.1048167
Richard J. Campbell, P. Flynn
Range images (depth maps) are seeing increased usage in a variety of application areas including entertainment, industrial automation, inspection, remote sensing, and military tactical planning. As the corpus of range imagery increases in size and the need to communicate such images over fixed-bandwidth channels increases, the compression of range data deserves investigation. Since the geometry encoded by range sensors is inherently "low-bandwidth", transform-based techniques seem appropriate for investigation in this context. This paper reports on experiments with a popular zerotree-based image codec (the SPIHT algorithm developed by Said and Pearlman) and its application to the compression of range imagery. Experiments suggest that compression rates of 1 bit/pixel and below are achievable with minimal impact on fidelity.
{"title":"Experiments in Transform-Based Range Image Compression","authors":"Richard J. Campbell, P. Flynn","doi":"10.1109/ICPR.2002.1048167","DOIUrl":"https://doi.org/10.1109/ICPR.2002.1048167","url":null,"abstract":"Range images (depth maps) are seeing increased usage in a variety of application areas including entertainment, industrial automation, inspection, remote sensing, and military tactical planning. As the corpus of range imagery increases in size and the need to communicate such images over fixed-bandwidth channels increases, the compression of range data deserves investigation. Since the geometry encoded by range sensors is inherently \"low-bandwidth\", transform-based techniques seem appropriate for investigation in this context. This paper reports on experiments with a popular zerotree-based image codec (the SPIHT algorithm developed by Said and Pearlman) and its application to the compression of range imagery. Experiments suggest that compression rates of 1 bit/pixel and below are achievable with minimal impact on fidelity.","PeriodicalId":74516,"journal":{"name":"Proceedings of the ... IAPR International Conference on Pattern Recognition. International Conference on Pattern Recognition","volume":"20 1","pages":"875-878"},"PeriodicalIF":0.0,"publicationDate":"2002-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83573957","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 : 2002-08-11DOI: 10.1109/ICPR.2002.1048012
Richard J. Campbell, P. Flynn
Describes a system for recognizing free-form 3D objects in dense range data employing local features and object-centered geometric models. Local features are extracted from range images and object models using curvature analysis, and variability in feature size is accommodated by decomposition of features into sub-features. Shape indices and other attributes provide a basis for correspondence between compatible image and model features and subfeatures, as well as pruning of invalid correspondences. A verification step provides a final ranking of object identity and pose hypotheses. The evaluation system contained 10 free-form objects and was tested using 10 range images with two objects from the database in each image. Comments address strengths of the proposed technique as well as areas for future improvement.
{"title":"Recognition of Free-Form Objects in Dense Range Data Using Local Features","authors":"Richard J. Campbell, P. Flynn","doi":"10.1109/ICPR.2002.1048012","DOIUrl":"https://doi.org/10.1109/ICPR.2002.1048012","url":null,"abstract":"Describes a system for recognizing free-form 3D objects in dense range data employing local features and object-centered geometric models. Local features are extracted from range images and object models using curvature analysis, and variability in feature size is accommodated by decomposition of features into sub-features. Shape indices and other attributes provide a basis for correspondence between compatible image and model features and subfeatures, as well as pruning of invalid correspondences. A verification step provides a final ranking of object identity and pose hypotheses. The evaluation system contained 10 free-form objects and was tested using 10 range images with two objects from the database in each image. Comments address strengths of the proposed technique as well as areas for future improvement.","PeriodicalId":74516,"journal":{"name":"Proceedings of the ... IAPR International Conference on Pattern Recognition. International Conference on Pattern Recognition","volume":"4 1","pages":"607-610"},"PeriodicalIF":0.0,"publicationDate":"2002-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85392257","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}
Relative convex hulls have been suggested for multigrid-convergent surface area estimation. Besides the existence of a convergence theorem there is no efficient algorithmic solution so far for calculating relative convex hulls. This article discusses an approximative solution based on minimum-length polygon calculations. It is illustrated that this approximative calculation also proves (experimentally) to provide a multigrid convergent measurement. 1 Center for Image Technology and Robotics Tamaki Campus, The University of Auckland, Auckland, New Zealand. lyu011@ec.auckland.ac.nz and r.klette@auckland.ac.nz You are granted permission for the non-commercial reproduction, distribution, display, and performance of this technical report in any format, BUT this permission is only for a period of 45 (forty-five) days from the most recent time that you verified that this technical report is still available from the CITR Tamaki web site under terms that include this permission. All other rights are reserved by the author(s). An Approximative Calculation of Relative Convex Hulls for Surface Area Estimation Linjiang Yu and Reinhard Klette
{"title":"An Approximative Calculation of Relative Convex Hulls for Surface Area Estimation of 3D Digital Objects","authors":"Linjiang Yu, R. Klette","doi":"10.1109/ICPR.2002.10013","DOIUrl":"https://doi.org/10.1109/ICPR.2002.10013","url":null,"abstract":"Relative convex hulls have been suggested for multigrid-convergent surface area estimation. Besides the existence of a convergence theorem there is no efficient algorithmic solution so far for calculating relative convex hulls. This article discusses an approximative solution based on minimum-length polygon calculations. It is illustrated that this approximative calculation also proves (experimentally) to provide a multigrid convergent measurement. 1 Center for Image Technology and Robotics Tamaki Campus, The University of Auckland, Auckland, New Zealand. lyu011@ec.auckland.ac.nz and r.klette@auckland.ac.nz You are granted permission for the non-commercial reproduction, distribution, display, and performance of this technical report in any format, BUT this permission is only for a period of 45 (forty-five) days from the most recent time that you verified that this technical report is still available from the CITR Tamaki web site under terms that include this permission. All other rights are reserved by the author(s). An Approximative Calculation of Relative Convex Hulls for Surface Area Estimation Linjiang Yu and Reinhard Klette","PeriodicalId":74516,"journal":{"name":"Proceedings of the ... IAPR International Conference on Pattern Recognition. International Conference on Pattern Recognition","volume":"27 1","pages":"131-134"},"PeriodicalIF":0.0,"publicationDate":"2002-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83407563","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 : 2002-08-11DOI: 10.1109/ICPR.2002.1048003
K. Boyer, Ravi Srikantiah, P. Flynn
We introduce an efficient, robust means to obtain reliable surface descriptions, suitable for free form object recognition, at multiple scales from range data. Mean and Gaussian curvatures are used to segment the surface into four saliency classes based on curvature consistency as evaluated in a robust multivoting scheme. Contiguous regions consistent in both mean and Gaussian curvature are identified as the most homogeneous segments, followed by those consistent in mean curvature but not Gaussian curvature, followed by those consistent in Gaussian curvature only. Segments at each level of the hierarchy are extracted in the order of size, large to small, such that the most salient features of the surface are recovered first. This has potential for efficient object recognition by stopping once a just sufficient description is extracted.
{"title":"Multiscale Surface Organization and Description for Free Form bject Recognition","authors":"K. Boyer, Ravi Srikantiah, P. Flynn","doi":"10.1109/ICPR.2002.1048003","DOIUrl":"https://doi.org/10.1109/ICPR.2002.1048003","url":null,"abstract":"We introduce an efficient, robust means to obtain reliable surface descriptions, suitable for free form object recognition, at multiple scales from range data. Mean and Gaussian curvatures are used to segment the surface into four saliency classes based on curvature consistency as evaluated in a robust multivoting scheme. Contiguous regions consistent in both mean and Gaussian curvature are identified as the most homogeneous segments, followed by those consistent in mean curvature but not Gaussian curvature, followed by those consistent in Gaussian curvature only. Segments at each level of the hierarchy are extracted in the order of size, large to small, such that the most salient features of the surface are recovered first. This has potential for efficient object recognition by stopping once a just sufficient description is extracted.","PeriodicalId":74516,"journal":{"name":"Proceedings of the ... IAPR International Conference on Pattern Recognition. International Conference on Pattern Recognition","volume":"1 1","pages":"569-572"},"PeriodicalIF":0.0,"publicationDate":"2002-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90309702","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 : 2000-09-03DOI: 10.1109/ICPR.2000.905420
Jaesik Min, M. Powell, K. Bowyer
We have developed an automated framework for performance evaluation of curved-surface range image segmentation algorithms. Enhancements over our previous work include automated training of parameter values, correcting the artifact problem in K/sup 2/T scanner images, and acquisition of images of the same scenes from different range scanners. The image dataset includes planar, spherical, cylindrical, conical, and toroidal surfaces. We have evaluated the automated parameter tuning technique and found that it compares favorably with manual parameter tuning. We present initial results from comparing curved-surface segmenters by Besl and Jain (1988) and by Jiang and Bunke (1998).
{"title":"Progress in Automated Evaluation of Curved Surface Range Image Segmentation","authors":"Jaesik Min, M. Powell, K. Bowyer","doi":"10.1109/ICPR.2000.905420","DOIUrl":"https://doi.org/10.1109/ICPR.2000.905420","url":null,"abstract":"We have developed an automated framework for performance evaluation of curved-surface range image segmentation algorithms. Enhancements over our previous work include automated training of parameter values, correcting the artifact problem in K/sup 2/T scanner images, and acquisition of images of the same scenes from different range scanners. The image dataset includes planar, spherical, cylindrical, conical, and toroidal surfaces. We have evaluated the automated parameter tuning technique and found that it compares favorably with manual parameter tuning. We present initial results from comparing curved-surface segmenters by Besl and Jain (1988) and by Jiang and Bunke (1998).","PeriodicalId":74516,"journal":{"name":"Proceedings of the ... IAPR International Conference on Pattern Recognition. International Conference on Pattern Recognition","volume":"68 1","pages":"1644-1647"},"PeriodicalIF":0.0,"publicationDate":"2000-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88112294","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}
Intensity information is a strong cue for segmentation but on its own cannot be used to distinguish between accidental and non-accidental alignments in a scene, thus resulting in incorrect segmentations. However, motion information can be used to distinguish between accidental and nonaccidental alignments. In this paper an integrated method using both intensity and motion information for the segmentation and tracking of objects in a sequence is presented. The method is based on an extension to active contours (snakes) called spiders. This paper deals with the problems of motion tracking and object segmentation in an integrated common framework. The techniques presented here are based on the observation that segmentation is easier if features have already been successfully tracked over several frames, and tracking is easier if segmentation has already been performed. This suggests an integrated approach to both problems. Feature points on a single rigid object are often connected by quite strong edges and this can be used as a useful cue for segmentation. However, accidental alignment may also cause feature points on separate objects to be connected by a strong edge, so any segmentation using edge strength between feature points will not be able to discriminate between real connections and accidental ones. On the other hand, tracking of moving objects over an image sequence will eventually lead to any accidental alignments becoming non-aligned. Therefore, it seems reasonable to expect that reliable segmentation (and therefore tracking) is best achieved using a combination of intensity and motion cues. It is this conjecture which is addressed in this paper. Motion based segmentation techniques typically come in two flavours: region based methods (usually based on optical flow); and feature based methods. This paper describes a system of the latter type. Combined techniques are also possible and Paragios and Deriche [6] describe a promising technique using an extension of geodesic active contours for segmentation and tracking in a video surveillance application. Although it appears to work very well, their method relies on relatively static backgrounds common in surveillance applications. In contrast, the technique presented in this paper does not rely on static backgrounds and is therefore likely to be more useful for mobile robotic applications. Smith and Brady [8] describe ASSET-2, a real time motion segmenter and tracker. ASSET-2 utilises corner points which are matched between frames and clustered to produce an object segmentation. The object clusters are then used to improve the reliability of tracking in future frames. The limitation of this system is that until reliable clusters are formed, each feature must be tracked individually. Of course, it is more difficult to track individual features robustly. The system described in this paper does not suffer from this limitation since features are initially tracked dependent on their neighbours ac
{"title":"Snakes and Spiders","authors":"B. McCane","doi":"10.1109/ICPR.2000.10008","DOIUrl":"https://doi.org/10.1109/ICPR.2000.10008","url":null,"abstract":"Intensity information is a strong cue for segmentation but on its own cannot be used to distinguish between accidental and non-accidental alignments in a scene, thus resulting in incorrect segmentations. However, motion information can be used to distinguish between accidental and nonaccidental alignments. In this paper an integrated method using both intensity and motion information for the segmentation and tracking of objects in a sequence is presented. The method is based on an extension to active contours (snakes) called spiders. This paper deals with the problems of motion tracking and object segmentation in an integrated common framework. The techniques presented here are based on the observation that segmentation is easier if features have already been successfully tracked over several frames, and tracking is easier if segmentation has already been performed. This suggests an integrated approach to both problems. Feature points on a single rigid object are often connected by quite strong edges and this can be used as a useful cue for segmentation. However, accidental alignment may also cause feature points on separate objects to be connected by a strong edge, so any segmentation using edge strength between feature points will not be able to discriminate between real connections and accidental ones. On the other hand, tracking of moving objects over an image sequence will eventually lead to any accidental alignments becoming non-aligned. Therefore, it seems reasonable to expect that reliable segmentation (and therefore tracking) is best achieved using a combination of intensity and motion cues. It is this conjecture which is addressed in this paper. Motion based segmentation techniques typically come in two flavours: region based methods (usually based on optical flow); and feature based methods. This paper describes a system of the latter type. Combined techniques are also possible and Paragios and Deriche [6] describe a promising technique using an extension of geodesic active contours for segmentation and tracking in a video surveillance application. Although it appears to work very well, their method relies on relatively static backgrounds common in surveillance applications. In contrast, the technique presented in this paper does not rely on static backgrounds and is therefore likely to be more useful for mobile robotic applications. Smith and Brady [8] describe ASSET-2, a real time motion segmenter and tracker. ASSET-2 utilises corner points which are matched between frames and clustered to produce an object segmentation. The object clusters are then used to improve the reliability of tracking in future frames. The limitation of this system is that until reliable clusters are formed, each feature must be tracked individually. Of course, it is more difficult to track individual features robustly. The system described in this paper does not suffer from this limitation since features are initially tracked dependent on their neighbours ac","PeriodicalId":74516,"journal":{"name":"Proceedings of the ... IAPR International Conference on Pattern Recognition. International Conference on Pattern Recognition","volume":"22 1 1","pages":"1652-1655"},"PeriodicalIF":0.0,"publicationDate":"2000-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83824833","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}
Visual information retrieval is attracting an increasing number of researchers from disparate fields, like image analysis, computer vision, databases, knowledge representation, artificial intelligence, man-machine interaction. Although a number of prototype systems have been made available, nevertheless this discipline has not yet reached a mature stage, and overall has not yet been credited as of concrete use in practical applications. Among the very many different lines of development we focus particularly on the importance of bridging the semantic gap between the user and visual information retrieval systems. We focus on usage of semiotics as a framework for extraction of semantics, graphs and graph matching as the representation model and retrieval engine and visualization spaces to capture semantics during the interaction.
{"title":"Issues and Directions in Visual Information Retrieval","authors":"A. Bimbo","doi":"10.1109/ICPR.2000.10029","DOIUrl":"https://doi.org/10.1109/ICPR.2000.10029","url":null,"abstract":"Visual information retrieval is attracting an increasing number of researchers from disparate fields, like image analysis, computer vision, databases, knowledge representation, artificial intelligence, man-machine interaction. Although a number of prototype systems have been made available, nevertheless this discipline has not yet reached a mature stage, and overall has not yet been credited as of concrete use in practical applications. Among the very many different lines of development we focus particularly on the importance of bridging the semantic gap between the user and visual information retrieval systems. We focus on usage of semiotics as a framework for extraction of semantics, graphs and graph matching as the representation model and retrieval engine and visualization spaces to capture semantics during the interaction.","PeriodicalId":74516,"journal":{"name":"Proceedings of the ... IAPR International Conference on Pattern Recognition. International Conference on Pattern Recognition","volume":"44 1","pages":"4031-4038"},"PeriodicalIF":0.0,"publicationDate":"2000-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79468314","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}
Wide acceptance of inexpensive writing tablets with high functionality motivates the development of individualized, adaptive on-line recognition of cursive script. We demonstrate a lexical algorithm based on bigram matches. The solution we propose is to (i) Generate a match list by partial-word matching against a reference list in the owner's script. (ii) Identify each unknown word by eliminating, from a large lexicon, every word that partially matches the transcript of any word on the reference list that is not on the match list, or that fails to match any word on the match list. With perfect feature-level matching, a surprisingly short reference list yields a high recognition rate.
{"title":"Ink-Link","authors":"A. El-Nasan, G. Nagy","doi":"10.1109/ICPR.2000.10018","DOIUrl":"https://doi.org/10.1109/ICPR.2000.10018","url":null,"abstract":"Wide acceptance of inexpensive writing tablets with high functionality motivates the development of individualized, adaptive on-line recognition of cursive script. We demonstrate a lexical algorithm based on bigram matches. The solution we propose is to (i) Generate a match list by partial-word matching against a reference list in the owner's script. (ii) Identify each unknown word by eliminating, from a large lexicon, every word that partially matches the transcript of any word on the reference list that is not on the match list, or that fails to match any word on the match list. With perfect feature-level matching, a surprisingly short reference list yields a high recognition rate.","PeriodicalId":74516,"journal":{"name":"Proceedings of the ... IAPR International Conference on Pattern Recognition. International Conference on Pattern Recognition","volume":"241 1","pages":"2573-2576"},"PeriodicalIF":0.0,"publicationDate":"2000-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73439390","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 : 1994-10-09DOI: 10.1109/ICPR.1994.576327
Matthew P. Howell, P. Flynn
Geometric hashing is an invariant feature-driven approach to model-based object recognition. Previous interest has focused on its ability to accommodate sensor error. This paper presents an enhancement of the geometric hashing technique which guarantees, under only a few constraints, that models will not be missed due to sensor noise. The authors' geometric hashing algorithm enters model affine invariants into hash table regions defined by an exact error model, brings together known optimizations (table symmetry and the use of more than 3 model-scene point correspondences) and uses novel data organization. Experimental results (on both synthetic and real data) suggest that the authors' modifications to a geometric hashing recognition scheme effectively overcome sensor noise.
{"title":"Guaranteed geometric hashing","authors":"Matthew P. Howell, P. Flynn","doi":"10.1109/ICPR.1994.576327","DOIUrl":"https://doi.org/10.1109/ICPR.1994.576327","url":null,"abstract":"Geometric hashing is an invariant feature-driven approach to model-based object recognition. Previous interest has focused on its ability to accommodate sensor error. This paper presents an enhancement of the geometric hashing technique which guarantees, under only a few constraints, that models will not be missed due to sensor noise. The authors' geometric hashing algorithm enters model affine invariants into hash table regions defined by an exact error model, brings together known optimizations (table symmetry and the use of more than 3 model-scene point correspondences) and uses novel data organization. Experimental results (on both synthetic and real data) suggest that the authors' modifications to a geometric hashing recognition scheme effectively overcome sensor noise.","PeriodicalId":74516,"journal":{"name":"Proceedings of the ... IAPR International Conference on Pattern Recognition. International Conference on Pattern Recognition","volume":"265 1","pages":"465-469"},"PeriodicalIF":0.0,"publicationDate":"1994-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77814659","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：