What Matters in Autonomous Driving Anomaly Detection: A Weakly Supervised Horizon

TL;DR

This paper advances weakly-supervised video anomaly detection for autonomous driving by reorganizing datasets, analyzing method modifications, and proposing a feature transformation block to enhance detection performance in moving camera scenarios.

Contribution

It introduces a new approach to adapt and improve weakly-supervised VAD methods specifically for autonomous driving with moving cameras.

Findings

Reorganized the DoTA dataset for moving camera scenarios.

Proposed a feature transformation block that improves detection accuracy.

Demonstrated significant performance gains with the new modifications.

Abstract

Video anomaly detection (VAD) in autonomous driving scenario is an important task, however it involves several challenges due to the ego-centric views and moving camera. Due to this, it remains largely under-explored. While recent developments in weakly-supervised VAD methods have shown remarkable progress in detecting critical real-world anomalies in static camera scenario, the development and validation of such methods are yet to be explored for moving camera VAD. This is mainly due to existing datasets like DoTA not following training pre-conditions of weakly-supervised learning. In this paper, we aim to promote weakly-supervised method development for autonomous driving VAD. We reorganize the DoTA dataset and aim to validate recent powerful weakly-supervised VAD methods on moving camera scenarios. Further, we provide a detailed analysis of what modifications on state-of-the-art methods can significantly improve the detection performance. Towards this, we propose a "feature transformation block" and through experimentation we show that our propositions can empower existing weakly-supervised VAD methods significantly in improving the VAD in autonomous driving. Our codes/dataset/demo will be released at github.com/ut21/WSAD-Driving