PromptTAD: Object-Prompt Enhanced Traffic Anomaly Detection

Abstract

Ego-centric Traffic Anomaly Detection (TAD) aims to identify abnormal events in videos captured by dashboardmounted cameras in vehicles. Compared to anomaly detection in roadside surveillance videos, ego-centric TAD poses greater challenges due to the dynamic backgrounds caused by vehicle motion. Previous frame-level methods are often vulnerable to interference from these dynamic backgrounds and struggle to detect small objects located at a distance or off-center. To address these challenges, we propose an object-prompt enhanced method that integrates detected traffic objects into a framelevel TAD framework. Our approach introduces an objectprompt scheme comprising an object prompt encoder, along with two cross-attention-based aggregation modules: an instancewise aggregation module for fusing information between object instances and the scene, and a relation-wise aggregation module for capturing relationships inter-objects. Additionally, we design an instance-level loss to supervise anomaly detection at the object level. Our method effectively mitigates interference from dynamic backgrounds, improves the detection of distant or offcenter anomalies, and enables precise spatial localization of anomalies. Experimental results on the DoTA and DADA-2000 datasets demonstrate that our method achieves state-of-the-art performance.