Object Detection and Segmentation from Joint Embedding of Parts and Pixels
Title | Object Detection and Segmentation from Joint Embedding of Parts and Pixels |
Publication Type | Conference Paper |
Year of Publication | 2011 |
Authors | Maire, M., Yu S. X., & Perona P. |
Published in | Proceedings of International Conference on Computer Vision |
Date Published | 09/2011 |
Keywords | angular embedding, figure-ground organization, object segmentation, poselets |
Abstract | We present a new framework in which image segmentation, figure/ground organization, and object detection all appear as the result of solving a single grouping problem. This framework serves as a perceptual organization stage that integrates information from low-level image cues with that of high-level part detectors. Pixels and parts each appear as nodes in a graph whose edges encode both affinity and ordering relationships. We derive a generalized eigen-problem from this graph and read off an interpretation of the image from the solution eigenvectors. Combining an off-the-shelf top-down part-based person detector with our low-level cues and grouping formulation, we demonstrate improvements to object detection and segmentation. |
Acknowledgment | ONR MURI N00014-06-1-0734, ONR MURI 1015 G NA127, and ARL Cooperative Agreement |
URL | http://www1.icsi.berkeley.edu/~stellayu/publication/doc/2011objICCV.pdf |
ICSI Research Group | Vision |