Temporal Unknown Incremental Clustering Model for Analysis of Traffic Surveillance Videos

• Published in: IEEE transactions on intelligent transportation systems 2019-05, Vol.20 (5), p.1762-1773
• Main Authors: Santhosh, Kelathodi Kumaran, Dogra, Debi Prosad, Roy, Partha Pratim
• Format: Article
• Language: English
• Subjects: Abnormalities; Algorithms; Automobiles; Bayesian analysis; Bayesian inference; Clustering; Data models; Dirichlet process; Gibbs sampling; incremental clustering; Mixture models; Object recognition; Optical flow (image analysis); Pixels; Real time; real-time event detection; Real-time systems; Surveillance; Traffic models; Traffic surveillance; Trajectory; Videos
• ISSN: 1524-9050; 1558-0016
• DOI: 10.1109/TITS.2018.2834958

Optimized scene representation is an important characteristic of a framework for detecting abnormalities on live videos. One of the challenges for detecting abnormalities in live videos is real-time detection of objects in a non-parametric way. Another challenge is to efficiently represent the state of objects temporally across frames. In this paper, a Gibbs sampling-based heuristic model referred to as temporal unknown incremental clustering has been proposed to cluster pixels with motion. Pixel motion is first detected using optical flow and a Bayesian algorithm has been applied to associate pixels belonging to a similar cluster in subsequent frames. The algorithm is fast and produces accurate results in \Theta (kn) time, where k is the number of clusters and n the number of pixels. Our experimental validation with publicly available data sets reveals that the proposed framework has good potential to open up new opportunities for real-time traffic analysis.