Graphics enhanced version of this site

Feature-Centric Evaluation for Efficient Cascaded Object Detection
H. Schneiderman
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, June, 2004.

Jump to: Download | Abstract | Notes | Text Reference | BibTeX Reference

Adobe portable document format (pdf) [469 KB]

Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

We describe a cascaded method for object detection. This approach uses a novel organization of the first cascade stage called "feature-centric" evaluation which re-uses feature evaluations across multiple candidate windows. We minimize the cost of this evaluation through several simplifications: (1) localized lighting normalization, (2) representation of the classifier as an additive model and (3) discrete-valued features. Such a method also incorporates a unique feature representation. The early stages in the cascade use simple fast feature evaluations and the later stages use more complex discriminative features. In particular, we propose features based on sparse coding and ordinal relationships among filter responses. This combination of cascaded feature-centric evaluation with features of increasing complexity achieves both computational efficiency and accuracy. We describe object detection experiments on ten objects including faces and automobiles. These results include 97% recognition at equal error rate on the UIUC image database for car detection.

Sponsor: ARDA and TSWG
Grant ID: MDA904-03-C-1789 and N41756-03-C-4024

Associated center: VASC
Associated lab/group: Face Group
Associated projects: Object Recognition Using Statistical Modeling, Face Detection Databases, and Face Detection

H. Schneiderman, "Feature-Centric Evaluation for Efficient Cascaded Object Detection," IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, June, 2004.

@inproceedings{Schneiderman_2004_4687,
   author = "Henry Schneiderman",
   title = "Feature-Centric Evaluation for Efficient Cascaded Object Detection",
   booktitle = "IEEE Conference on Computer Vision and Pattern Recognition (CVPR)",
   month = "June",
   year = "2004",
   publisher = "IEEE"
}