An Adaptive Training-less System for Anomaly Detection in Crowd Scenes

TL;DR

This paper introduces a training-free, adaptive system for real-time anomaly detection in crowd scenes that dynamically adjusts to new data without prior scene training.

Contribution

It presents a novel adaptive, training-less framework combining 3D-DCT, saliency-modulated optic flow, and EMD for effective anomaly detection in crowd videos.

Findings

Achieves comparable performance to state-of-the-art methods

Operates without prior scene training data

Effective in diverse crowd surveillance datasets

Abstract

Anomaly detection in crowd videos has become a popular area of research for the computer vision community. Several existing methods generally perform a prior training about the scene with or without the use of labeled data. However, it is difficult to always guarantee the availability of prior data, especially, for scenarios like remote area surveillance. To address such challenge, we propose an adaptive training-less system capable of detecting anomaly on-the-fly while dynamically estimating and adjusting response based on certain parameters. This makes our system both training-less and adaptive in nature. Our pipeline consists of three main components, namely, adaptive 3D-DCT model for multi-object detection-based association, local motion structure description through saliency modulated optic flow, and anomaly detection based on earth movers distance (EMD). The proposed model, despite being training-free, is found to achieve comparable performance with several state-of-the-art methods on the publicly available UCSD, UMN, CHUK-Avenue and ShanghaiTech datasets.