Notice of Removal: Novel dataset for fine-grained abnormal behavior understanding in crowd
- 10 November 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 95-101
Abstract
Despite the huge research on crowd on behavior understanding in visual surveillance community, lack of publicly available realistic datasets for evaluating crowd behavioral interaction led not to have a fair common test bed for researchers to compare the strength of their methods in the real scenarios. This work presents a novel crowd dataset contains around 45,000 video clips which annotated by one of the five different fine-grained abnormal behavior categories. We also evaluated two state-of-the-art methods on our dataset, showing that our dataset can be effectively used as a benchmark for fine-grained abnormality detection. The details of the dataset and the results of the baseline methods are presented in the paper.Keywords
This publication has 23 references indexed in Scilit:
- Detecting Abnormal Behavioral Patterns in Crowd Scenarios2016
- Crowd motion monitoring using tracklet-based commotion measure2015
- Abnormality Detection with Improved Histogram of Oriented Tracklets2015
- Analyzing Tracklets for the Detection of Abnormal Crowd Behavior2015
- Temporal Poselets for Collective Activity Detection and Recognition2013
- Violent flows: Real-time detection of violent crowd behavior2012
- How simple rules determine pedestrian behavior and crowd disastersProceedings of the National Academy of Sciences, 2011
- Anomaly detection in crowded scenes2010
- Tracking in unstructured crowded scenes2009
- Human Detection Using Oriented Histograms of Flow and Appearance2006