Scheduled System Maintenance:
Some services will be unavailable Sunday, March 29th through Monday, March 30th. We apologize for the inconvenience.
By Topic

Flexible Edge Arrangement Templates for Object Detection

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

The purchase and pricing options are temporarily unavailable. Please try again later.
4 Author(s)
Yan Li ; Carnegie Mellon Univ., Pittsburgh, PA ; Tsin, Y. ; Genc, Y. ; Kanade, T.

We present a novel feature representation for categorical object detection. Unlike previous approaches that have concentrated on generic interest-point detectors, we construct object-specific features directly from the training images. Our feature is represented by a collection of Flexible Edge Arrangement Templates (FEATs). We propose a two-stage semi-supervised learning approach to feature selection. A subset of frequent templates are first selected from a large template pool. In the second stage, we formulate feature selection as a regression problem and use LASSO method to find the most discriminative templates from the preselected ones. FEATs adaptively capture the image structure and naturally accommodate local shape variations. We show that this feature can be complemented by the traditional holistic patch method, thus achieving both efficiency and accuracy. We evaluate our method on three well-known car datasets, showing performance competitive with existing methods.

Published in:

Applications of Computer Vision, 2008. WACV 2008. IEEE Workshop on

Date of Conference:

7-9 Jan. 2008