Title
Improving An Object Detector And Extracting Regions Using Superpixels
Abstract
We propose an approach to improve the detection performance of a generic detector when it is applied to a particular video. The performance of offline-trained objects detectors are usually degraded in unconstrained video environments due to variant illuminations, backgrounds and camera viewpoints. Moreover, most object detectors are trained using Haar-like features or gradient features but ignore video specific features like consistent color patterns. In our approach, we apply a Super pixel-based Bag-of-Words (BoW) model to iteratively refine the output of a generic detector. Compared to other related work, our method builds a video-specific detector using super pixels, hence it can handle the problem of appearance variation. Most importantly, using Conditional Random Field (CRF) along with our super pixel-based BoW model, we develop and algorithm to segment the object from the background. Therefore our method generates an output of the exact object regions instead of the bounding boxes generated by most detectors. In general, our method takes detection bounding boxes of a generic detector as input and generates the detection output with higher average precision and precise object regions. The experiments on four recent datasets demonstrate the effectiveness of our approach and significantly improves the state-of-art detector by 5-16% in average precision. © 2013 IEEE.
Publication Date
11-15-2013
Publication Title
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Number of Pages
3721-3727
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/CVPR.2013.477
Copyright Status
Unknown
Socpus ID
84887387475 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/84887387475
STARS Citation
Shu, Guang; Dehghan, Afshin; and Shah, Mubarak, "Improving An Object Detector And Extracting Regions Using Superpixels" (2013). Scopus Export 2010-2014. 6461.
https://stars.library.ucf.edu/scopus2010/6461