Learning to localize detected objects

10 years 2 months ago
Learning to localize detected objects
In this paper, we propose an approach to accurately localize detected objects. The goal is to predict which features pertain to the object and define the object extent with segmentation or bounding box. Our initial detector is a slight modification of the DPM detector by Felzenszwalb et al., which often reduces confusion with background and other objects but does not cover the full object. We then describe and evaluate several color models and edge cues for local predictions, and we propose two approaches for localization: learned graph cut segmentation and structural bounding box prediction. Our experiments on the PASCAL VOC 2010 dataset show that our approach leads to accurate pixel assignment and large improvement in bounding box overlap, sometimes leading to large overall improvement in detection accuracy.
Qieyun Dai, Derek Hoiem
Added 28 Sep 2012
Updated 28 Sep 2012
Type Journal
Year 2012
Where CVPR
Authors Qieyun Dai, Derek Hoiem
Comments (0)