This paper presents research conducted into the automatic recognition of features and objects on topographic maps (for example, buildings, roads, land parcels etc.) using a selection of shape description methods devel...
详细信息
ISBN:
(纸本)0780370597
This paper presents research conducted into the automatic recognition of features and objects on topographic maps (for example, buildings, roads, land parcels etc.) using a selection of shape description methods developed mostly in the field of computervision. In particular the work here focuses on the proposal and evaluation of fusion techniques (at the decision level of representation) for the classification of topographic data. A set of Ordnance Survey large-scale digital data (1:1250 and 1:2500) was used to evaluate the classification performance of the shape recognition methods used. Each technique proved partially successful in distinguishing classes of objects, however, no one technique provided a general solution to the problem. Further outlined experiments combine these techniques, using a data fusion methodology, on the real-world problem of checking and assigning feature codes in large-scale Ordnance Survey digital data.
Mathematical methods has been a dominant research path in computational vision leading to a number of areas like ?ltering, segmentation, motion analysis and stereo reconstruction. Within such a branch visual perceptio...
详细信息
ISBN:
(数字)9783540321095
ISBN:
(纸本)9783540293484
Mathematical methods has been a dominant research path in computational vision leading to a number of areas like ?ltering, segmentation, motion analysis and stereo reconstruction. Within such a branch visual perception tasks can either be addressed through the introduction of application-driven geometric ?ows or through the minimization of problem-driven cost functions where their lowest potential corresponds to image understanding. The 3rd ieeeworkshop on variational, Geometric and levelsetmethods focused on these novel mathematical techniques and their applications to c- puter vision problems. To this end, from a substantial number of submissions, 30 high-quality papers were selected after a fully blind review process covering a large spectrum of computer-aided visual understanding of the environment. The papers are organized into four thematic areas: (i) Image Filtering and Reconstruction, (ii) Segmentation and Grouping, (iii) Registration and Motion Analysis and (iiii) 3D and Reconstruction. In the ?rst area solutions to image enhancement, inpainting and compression are presented, while more advanced applications like model-free and model-based segmentation are presented in the segmentation area. Registration of curves and images as well as multi-frame segmentation and tracking are part of the motion understanding track, while - troducing computationalprocessesinmanifolds,shapefromshading,calibration and stereo reconstruction are part of the 3D track. We hope that the material presented in the proceedings exceeds your exp- tations and will in?uence your research directions in the future. We would like to acknowledge the support of the Imaging and Visualization Department of Siemens Corporate Research for sponsoring the Best Student Paper Award.
暂无评论