Anomalous Situation Detection in Complex Scenes

TL;DR

This paper proposes a robust method for anomaly detection in complex scenes by combining LBP and LoG features to train an MLP neural network, effectively identifying irregular situations in crowded environments.

Contribution

It introduces a novel feature fusion approach using LBP and LoG for anomaly detection, improving accuracy in dense crowded scenes compared to existing descriptors.

Findings

Higher accuracy in anomaly detection in crowded scenes

Effective feature fusion improves detection robustness

Validated on benchmark video sequences

Abstract

In this paper we investigate a robust method to identify anomalies in complex scenes. This task is performed by evaluating the collective behavior by extracting the local binary patterns (LBP) and Laplacian of Gaussian (LoG) features. We fuse both features together which are exploited to train an MLP neural network during the training stage, and the anomaly is identified on the test samples. Considering the challenge of tracking individuals in dense crowded scenes due to multiple occlusions and clutter, in this paper we extract LBP and LoG features and use them as an approximate representation of the anomalous situation. These features well match the appearance of anomaly and their consistency, and accuracy is higher both in regular and irregular areas compared to other descriptors. In this paper, these features are exploited as input prior to train the neural network. The MLP neural network is subsequently explored to consider these features that can detect the anomalous situation. The experimental tests are conducted on a set of benchmark video sequences commonly used for anomaly situation detection.