You are here

ResnetCrowd: A Residual Deep Learning Architecture for Crowd Counting, Violent Behaviour Detection and Crowd Density Level Classification

Publication Type: 
Refereed Conference Meeting Proceeding
Abstract: 
In this paper we propose ResnetCrowd, a deep residual architecture for simultaneous crowd counting, violent behaviour detection and crowd density level classification. To train and evaluate the proposed multi-objective technique, a new 100 image dataset referred to as Multi Task Crowd is constructed. This new dataset is the first computer vision dataset fully annotated for crowd counting, violent behaviour detection and density level classification. Our experiments show that a multi-task approach boosts individual task performance for all tasks and most notably for violent behaviour detection which receives a 9\% boost in ROC curve AUC (Area under the curve). The trained ResnetCrowd model is also evaluated on several additional benchmarks highlighting the superior generalisation of crowd analysis models trained for multiple objectives.
Conference Name: 
2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS). . IEEE Computer Society.
Proceedings: 
Proceedings of 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS). . IEEE Computer Society.
Digital Object Identifer (DOI): 
10.1109/AVSS.2017.8078482
Publication Date: 
30/05/2017
Conference Location: 
Italy
Research Group: 
Institution: 
Dublin City University (DCU)
Open access repository: 
Yes