Fast object segmentation from a moving camera
2005 (English)In: 2005 IEEE Intelligent Vehicles Symposium Proceedings, NEW YORK, NY: IEEE , 2005, 136-141 p.Conference paper (Refereed)
Segmentation of the scene is a fundamental component in computer vision to find regions of interest. Most systems that aspire to run in real-time use a fast segmentation stage that considers the whole image, and then a more costly stage for classification. In this paper we present a novel approach to segment moving objects from images taken with a moving camera. The segmentation algorithm is based on a special representation of optical flow, on which u-disparity is applied. The u-disparity is used to indirectly find and mask out the background flow in the image, by approximating it with a quadratic function. Robustness in the optical flow calculation is achieved by contrast content filtering. The algorithm successfully segments moving pedestrians from a moving vehicle with few false positive segments. Most false positive segments are due to poles and organic structures, such as trees. Such false positives are, however, easily rejected in a classification stage. The presented segmentation algorithm is intended to be used as a component in a detection/classification framework.
Place, publisher, year, edition, pages
NEW YORK, NY: IEEE , 2005. 136-141 p.
Algorithms, Cameras, Classification (of information), Computer vision, Image segmentation, Quadratic programming, Real time systems, Robustness (control systems)
Computer and Information Science
IdentifiersURN: urn:nbn:se:kth:diva-43143DOI: 10.1109/IVS.2005.1505091ISI: 000235518700022ScopusID: 2-s2.0-33745937929ISBN: 0-7803-8961-1OAI: oai:DiVA.org:kth-43143DiVA: diva2:448234
IEEE Intelligent Vechicles Symposium. Las Vegas, NV. JUN 06-08, 2005
QC 201110142011-10-142011-10-132011-10-14Bibliographically approved