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.
For downloading the MED dataset please run med_get.sh
script or directly download from here.
[1] "Novel Dataset for Fine-grained Abnormal Behavior Understanding in Crowd", Rabiee, HR and Haddadnia, J and Mousavi, H and Kalantarzadeh, M and Nabi, M and Murino, V, IEEE Advanced Video and Signal-based Surveillance (AVSS), 2016.
[2] "Emotion-Based Crowd Representation for Abnormality Detection", H Rabiee, J Haddadnia, H Mousavi, M Nabi, V Murino, N Sebe, arXiv preprint arXiv:1607.07646, 2016.