Sciweavers

Share
CVPR
2012
IEEE

Pedestrian detection at 100 frames per second

7 years 2 months ago
Pedestrian detection at 100 frames per second
We present a new pedestrian detector that improves both in speed and quality over state-of-the-art. By efficiently handling different scales and transferring computation from test time to training time, detection speed is improved. When processing monocular images, our system provides high quality detections at 50 fps. We also propose a new method for exploiting geometric context extracted from stereo images. On a single CPU+GPU desktop machine, we reach 135 fps, when processing street scenes, from rectified input to detections output.
Rodrigo Benenson, Markus Mathias, Radu Timofte, Lu
Added 28 Sep 2012
Updated 04 Jan 2013
Type Journal
Year 2012
Where CVPR
Authors Rodrigo Benenson, Markus Mathias, Radu Timofte, Luc J. Van Gool
Comments (0)
books