End-to-End People Detection in Crowded Scenes

@article{Stewart2016EndtoEndPD,
  title={End-to-End People Detection in Crowded Scenes},
  author={Russell Stewart and Mykhaylo Andriluka and Andrew Y. Ng},
  journal={2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2016},
  pages={2325-2333}
}
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… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 70 CITATIONS, ESTIMATED 31% COVERAGE

Computer Vision – ACCV 2018

  • Lecture Notes in Computer Science
  • 2018
VIEW 8 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

CrowdHuman: A Benchmark for Detecting Human in a Crowd

  • ArXiv
  • 2018
VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

FCHD: A fast and accurate head detector

  • ArXiv
  • 2018
VIEW 9 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

People Detection from Overhead Cameras

  • 2018
VIEW 17 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

Sidewalk-level People Flow Estimation Using Dashboard Cameras Based on Deep Learning

  • 2018 Eleventh International Conference on Mobile Computing and Ubiquitous Network (ICMU)
  • 2018
VIEW 5 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Variational Methods for Human Modeling

VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

An Incremental Framework for Video-Based Traffic Sign Detection, Tracking, and Recognition

  • IEEE Transactions on Intelligent Transportation Systems
  • 2017
VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Representations, Analysis and Recognition of Shape and Motion from Imaging Data

  • Communications in Computer and Information Science
  • 2017
VIEW 6 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Social Scene Understanding: End-to-End Multi-person Action Localization and Collective Activity Recognition

  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2016
2019

CITATION STATISTICS

  • 12 Highly Influenced Citations

  • Averaged 20 Citations per year over the last 3 years

  • 30% Increase in citations per year in 2018 over 2017

References

Publications referenced by this paper.
SHOWING 1-10 OF 19 REFERENCES

Filtered channel features for pedestrian detection

  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
VIEW 1 EXCERPT

Going deeper with convolutions

  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015

The Pascal Visual Object Classes Challenge: A Retrospective

  • International Journal of Computer Vision
  • 2014
VIEW 1 EXCERPT

Similar Papers

Loading similar papers…