He Wang

He Wang is an Associate Professor in University of Leeds

  • HOME
  • Publications
  • Research
  • Funding
  • Teaching
  • About
Globally Continuous and Non-Markovian Crowd Activity Analysis from Videos
ECCV 2016 spotlight
He Wang1 Carol O'Sullivan2
University of Leeds, UK1 Trinity Colledge Dublin, Ireland2

Abstract

Automatically recognizing activities in video is a classic problem in vision and helps to understand behaviors, describe scenes and detect anomalies. We propose an unsupervised method for such purposes. Given video data, we discover recurring activity patterns that appear, peak, wane and disappear over time. By using non-parametric Bayesian methods, we learn coupled spatial and temporal patterns with minimum prior knowledge. To model the temporal changes of patterns, previous works compute Markovian progressions or locally continuous motifs whereas we model time in a globally continuous and non-Markovian way. Visually, the patterns depict flows of major activities. Temporally, each pattern has its own unique appearance-disappearance cycles. To compute compact pattern representations, we also propose a hybrid sampling method. By combining these patterns with detailed environment information, we interpret the semantics of activities and report anomalies. Also, our method fits data better and detects anomalies that were difficult to detect previously.

Resources

Downloads

PDF     Supplement     Code    Video

Bibtex

@Inbook{wang_globally_2016,
author="Wang, He
and O'Sullivan, Carol",
title="Globally Continuous and Non-Markovian Crowd Activity Analysis from Videos",
bookTitle="Computer Vision -- ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part V",
year="2016",
pages="527--544",
}

Copyright 2016 He Wang