End-to-End People Detection in Crowded Scenes | IEEE Conference Publication | IEEE Xplore

End-to-End People Detection in Crowded Scenes


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 o...Show More

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 nonmaximum 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 scenes1.
Date of Conference: 27-30 June 2016
Date Added to IEEE Xplore: 12 December 2016
ISBN Information:
Electronic ISSN: 1063-6919
Conference Location: Las Vegas, NV, USA
Stanford University, USA
Stanford University, USA
Max Planck Institute for Informatics, Germany
Stanford University, USA

Stanford University, USA
Stanford University, USA
Max Planck Institute for Informatics, Germany
Stanford University, USA
Contact IEEE to Subscribe

References

References is not available for this document.