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 125 fps, when processing street scenes, from rectified input to detections output.Benenson R., Mathias M., Timofte R., Van Gool L., ''Pedestrian detection at 100 frames per second'', 25th IEEE computer society conference on computer vision and pattern recognition - CVPR 2012, pp. 2903-2910, June 18-20, 2012, Providence, Rhode Island, USA.status: publishe