An empirical study of context in object detection

• Published in: 2009 IEEE Conference on Computer Vision and Pattern Recognition pp. 1271 - 1278
• Main Authors: Divvala, Santosh K, Hoiem, Derek, Hays, James H, Efros, Alexei A, Hebert, Martial
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2009
• Subjects: Cameras; Computer vision; Context modeling; Gas detectors; Layout; Object detection; Ocean temperature; Pixel; Sea surface; Shape
• ISBN: 1424439922; 9781424439928
• ISSN: 1063-6919; 1063-6919
• DOI: 10.1109/CVPR.2009.5206532

This paper presents an empirical evaluation of the role of context in a contemporary, challenging object detection task - the PASCAL VOC 2008. Previous experiments with context have mostly been done on home-grown datasets, often with non-standard baselines, making it difficult to isolate the contribution of contextual information. In this work, we present our analysis on a standard dataset, using top-performing local appearance detectors as baseline. We evaluate several different sources of context and ways to utilize it. While we employ many contextual cues that have been used before, we also propose a few novel ones including the use of geographic context and a new approach for using object spatial support.