Detecting Pedestrians by Learning Shapelet Features

I introduce in this paper a method of detecting pedestrians, presented by Payam Sabzmeydani and Greg Mori [1]. Local gradient information is used for the classification task and the results are 14 percentage points lower (at 10−6 FPPW, false positive per window) than a previous state of the art detector of Dalal and Triggs [2]. During the explanations I will often draw a comparison to a composition of Andreas Opelt, Axel Pinz and Andrew Zisserman [4]. There are several similarities but Andreas Opelt has also the ability to locate the object in an image. This could be a big advantage to have this information for real time applications.

[1]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[2]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[3]  Andrew Zisserman,et al.  A Boundary-Fragment-Model for Object Detection , 2006, ECCV.

[4]  Greg Mori,et al.  Detecting Pedestrians by Learning Shapelet Features , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.