Content-based Video Retrieval in Traffic Videos using Latent Dirichlet Allocation Topic Model

TL;DR

This paper introduces an unsupervised LDA-based method for content-based video retrieval in traffic surveillance, improving accuracy and efficiency by reducing ambiguity and optimizing search strategies.

Contribution

It proposes a novel approach to scene annotation using LDA, addressing ambiguity issues, and introduces four search strategies with a lightweight database for faster retrieval.

Findings

At least 80% false positive reduction

124% improvement in true positive responses

Faster search with less storage compared to low-level feature methods

Abstract

Content-based video retrieval is one of the most challenging tasks in surveillance systems. In this study, Latent Dirichlet Allocation (LDA) topic model is used to annotate surveillance videos in an unsupervised manner. In scene understanding methods, some of the learned patterns are ambiguous and represents a mixture of atomic actions. To address the ambiguity issue in the proposed method, feature vectors, and the primary model are processed to obtain a secondary model which describes the scene with primitive patterns that lack any ambiguity. Experiments show performance improvement in the retrieval task compared to other topic model-based methods. In terms of false positive and true positive responses, the proposed method achieves at least 80\% and 124\% improvement respectively. Four search strategies are proposed, and users can define and search for a variety of activities using the proposed query formulation which is based on topic models. In addition, the lightweight database in our method occupies much fewer storage which in turn speeds up the search procedure compared to the methods which are based on low-level features.