Automated crowd behavior analysis and monitoring is a challenging task due to the unpredictable nature of the crowd, making it an open problem. Within this domain, we are focusing on two research problems which deal with low to mid-level analysis of crowd videos. The first problem focuses on how to effectively utilize the readily available compressed motion vector information in an input crowd video to model the motion of the crowd and perform crowd behavior analysis in varying densities of crowds. For this purpose, we consider a mid-level crowd scene analysis task called as motion pattern segmentation. The second research problem focuses on how to efficiently perform motion pattern segmentation using deep neural network-based approaches, given the input trajectories of the crowd.
Recent Publications related to the work:
- Motion pattern-based crowd scene classification using histogram of angular deviations of trajectories | SpringerLink
- Scene-Independent Motion Pattern Segmentation in Crowded Video Scenes Using Spatio-Angular Density-Based Clustering | IEEE Journals & Magazine | IEEE Xplore
- Electronics | Free Full-Text | Human Detection in Aerial Thermal Images Using Faster R-CNN and SSD Algorithms (mdpi.com)
Pai, Abhilash K., "Computer Vision based Analysis of Crowd Behavior for Efficient Video Surveillance in Public Places" (2022). Technical Collection. 37.