Trajectory-based Scene Understanding using Dirichlet Process Mixture Model

TL;DR

This paper introduces an unsupervised, nonparametric approach using Dirichlet Process Mixture models to learn typical traffic paths from moving object tracks, aiding anomaly detection and traffic management.

Contribution

It proposes a novel hierarchical model, TIGM extended as DEM, that efficiently learns scene traffic patterns without prior knowledge of the number of paths.

Findings

Learns traffic paths in $igO(kn)$ time

Outperforms state-of-the-art methods in scene learning

Enables traffic anomaly detection and decision making

Abstract

Appropriate modeling of a surveillance scene is essential for detection of anomalies in road traffic. Learning usual paths can provide valuable insight into road traffic conditions and thus can help in identifying unusual routes taken by commuters/vehicles. If usual traffic paths are learned in a nonparametric way, manual interventions in road marking road can be avoided. In this paper, we propose an unsupervised and nonparametric method to learn frequently used paths from the tracks of moving objects in $\Theta(kn)$ time, where $k$ denotes the number of paths and $n$ represents the number of tracks. In the proposed method, temporal dependencies of the moving objects are considered to make the clustering meaningful using Temporally Incremental Gravity Model (TIGM). In addition, the distance-based scene learning makes it intuitive to estimate the model parameters. Further, we have extended TIGM hierarchically as Dynamically Evolving Model (DEM) to represent notable traffic dynamics of a scene. Experimental validation reveals that the proposed method can learn a scene quickly without prior knowledge about the number of paths ($k$). We have compared the results with various state-of-the-art methods. We have also highlighted the advantages of the proposed method over existing techniques popularly used for designing traffic monitoring applications. It can be used for administrative decision making to control traffic at junctions or crowded places and generate alarm signals, if necessary.