Temporal Unknown Incremental Clustering (TUIC) Model for Analysis of Traffic Surveillance Videos
This addresses real-time traffic analysis for surveillance systems, but it appears incremental as it builds on existing clustering and optical flow methods.
The paper tackles real-time abnormality detection in traffic surveillance videos by proposing the Temporal Unknown Incremental Clustering (TUIC) model, which clusters pixels with motion using Gibbs sampling and Bayesian association, achieving results in Θ(kn) time.
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 (TUIC) 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 similar cluster in subsequent frames. The algorithm is fast and produces accurate results in $Θ(kn)$ time, where $k$ is the number of clusters and $n$ the number of pixels. Our experimental validation with publicly available datasets reveals that the proposed framework has good potential to open-up new opportunities for real-time traffic analysis.