End-To-End People Detection in Crowded Scenes

Russell Stewart; Mykhaylo Andriluka; Andrew Y. Ng

CVPR 2016spotlight684 citations

End-To-End People Detection in Crowded Scenes

Russell Stewart, Mykhaylo Andriluka, Andrew Y. Ng

Abstract

Current people detectors operate either by scanning an image in a sliding window fashion or by classifying a discrete set of proposals. We propose a model that is based on decoding an image into a set of people detections. Our system takes an image as input and directly outputs a set of distinct detection hypotheses. Because we generate predictions jointly, common post-processing steps such as non-maximum suppression are unnecessary. We use a recurrent LSTM layer for sequence generation and train our model end-to-end with a new loss function that operates on sets of detections. We demonstrate the effectiveness of our approach on the challenging task of detecting people in crowded scenes

BibTeX

@inproceedings{cvpr2016_endtoendpeoplede,
  title = {End-To-End People Detection in Crowded Scenes},
  author = {Russell Stewart and Mykhaylo Andriluka and Andrew Y. Ng},
  booktitle = {CVPR 2016},
  year = {2016}
}