AnoVox: A Benchmark for Multimodal Anomaly Detection in Autonomous Driving

TL;DR

AnoVox introduces the largest multimodal anomaly detection benchmark for autonomous driving, enabling comprehensive evaluation of methods across various sensors and anomaly types, including content and temporal anomalies.

Contribution

It presents a new large-scale multimodal benchmark with spatial voxel ground truth, formal normality definition, and diverse anomaly types, addressing limitations of previous camera-focused datasets.

Findings

First benchmark with multimodal sensor data for anomaly detection

Includes content and temporal anomalies for comprehensive evaluation

Provides a formal normality definition and compliant training data

Abstract

The scale-up of autonomous vehicles depends heavily on their ability to deal with anomalies, such as rare objects on the road. In order to handle such situations, it is necessary to detect anomalies in the first place. Anomaly detection for autonomous driving has made great progress in the past years but suffers from poorly designed benchmarks with a strong focus on camera data. In this work, we propose AnoVox, the largest benchmark for ANOmaly detection in autonomous driving to date. AnoVox incorporates large-scale multimodal sensor data and spatial VOXel ground truth, allowing for the comparison of methods independent of their used sensor. We propose a formal definition of normality and provide a compliant training dataset. AnoVox is the first benchmark to contain both content and temporal anomalies.