# Anomaly Detection in Traffic Scenes via Spatial-aware Motion Reconstruction

## TL;DR

This paper introduces a novel spatial-aware sparse coding approach for traffic scene anomaly detection, effectively handling challenging conditions like camera waggle and dynamic backgrounds to improve safety in autonomous driving.

## Contribution

It proposes a new method that measures motion orientation and magnitude separately, incorporates spatial localization into sparse coding, and adaptively fuses these aspects for robust anomaly detection.

## Key findings

- Outperforms traditional methods in accuracy and efficiency
- Effective in complex traffic scenarios with camera movement
- Validated on nine challenging video sequences

## Abstract

Anomaly detection from a driver's perspective when driving is important to autonomous vehicles. As a part of Advanced Driver Assistance Systems (ADAS), it can remind the driver about dangers timely. Compared with traditional studied scenes such as the university campus and market surveillance videos, it is difficult to detect abnormal event from a driver's perspective due to camera waggle, abidingly moving background, drastic change of vehicle velocity, etc. To tackle these specific problems, this paper proposes a spatial localization constrained sparse coding approach for anomaly detection in traffic scenes, which firstly measures the abnormality of motion orientation and magnitude respectively and then fuses these two aspects to obtain a robust detection result. The main contributions are threefold: 1) This work describes the motion orientation and magnitude of the object respectively in a new way, which is demonstrated to be better than the traditional motion descriptors. 2) The spatial localization of object is taken into account of the sparse reconstruction framework, which utilizes the scene's structural information and outperforms the conventional sparse coding methods. 3) Results of motion orientation and magnitude are adaptively weighted and fused by a Bayesian model, which makes the proposed method more robust and handle more kinds of abnormal events. The efficiency and effectiveness of the proposed method are validated by testing on nine difficult video sequences captured by ourselves. Observed from the experimental results, the proposed method is more effective and efficient than the popular competitors, and yields a higher performance.