CHAD: Charlotte Anomaly Dataset

TL;DR

The paper introduces CHAD, a comprehensive, multi-view, high-resolution anomaly dataset with detailed annotations for video anomaly detection in surveillance, enabling better training and evaluation of models in real-world scenarios.

Contribution

It presents the first multi-view, fully annotated anomaly dataset with bounding boxes, identities, and poses, specifically designed for skeleton-based anomaly detection in surveillance videos.

Findings

Benchmarking shows state-of-the-art algorithms perform variably on CHAD.

The dataset enables detailed qualitative and quantitative analysis of anomaly detection methods.

CHAD's multi-view setup improves the robustness of anomaly detection models.

Abstract

In recent years, we have seen a significant interest in data-driven deep learning approaches for video anomaly detection, where an algorithm must determine if specific frames of a video contain abnormal behaviors. However, video anomaly detection is particularly context-specific, and the availability of representative datasets heavily limits real-world accuracy. Additionally, the metrics currently reported by most state-of-the-art methods often do not reflect how well the model will perform in real-world scenarios. In this article, we present the Charlotte Anomaly Dataset (CHAD). CHAD is a high-resolution, multi-camera anomaly dataset in a commercial parking lot setting. In addition to frame-level anomaly labels, CHAD is the first anomaly dataset to include bounding box, identity, and pose annotations for each actor. This is especially beneficial for skeleton-based anomaly detection, which is useful for its lower computational demand in real-world settings. CHAD is also the first anomaly dataset to contain multiple views of the same scene. With four camera views and over 1.15 million frames, CHAD is the largest fully annotated anomaly detection dataset including person annotations, collected from continuous video streams from stationary cameras for smart video surveillance applications. To demonstrate the efficacy of CHAD for training and evaluation, we benchmark two state-of-the-art skeleton-based anomaly detection algorithms on CHAD and provide comprehensive analysis, including both quantitative results and qualitative examination. The dataset is available at https://github.com/TeCSAR-UNCC/CHAD.