RoboVAD: ロボットアーム操作動画における異常検知のための大規模クロスドメイン評価ベンチマーク
RoboVAD: A Large Cross-Domain Evaluation Benchmark for Anomaly Detection in Robotic Arm Manipulation Videos
ロボットアーム操作動画の異常検知を、未見のタスクや異常タイプを含むクロスドメイン設定で評価する大規模ベンチマークを構築し、既存手法と新手法を比較した。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Alexandru-Bogdan Dura, Sebastian Balmus, Radu Tudor Ionescu
分類: cs.CV, cs.AI, cs.LG, cs.RO
原文アブストラクト
Video anomaly detection (VAD) is an actively studied task, having wide applications in typical scenarios such as public surveillance and road traffic safety. The task is also relevant for robotic arm interactions, where it has several downstream applications, including learning better interaction and manipulation abilities, triggering recovery procedures when anomalies occur, etc. Despite its relevance, the exploration of anomaly detection in robotic arm manipulation videos is limited by the low number of available resources. To this end, we introduce RoboVAD, a large-scale benchmark for video anomaly detection that comprises challenging cross-domain evaluation scenarios, where certain actions (tasks executed by a robotic arm) and anomaly types (mistakes that occur while performing certain tasks) remain unseen during training. RoboVAD is designed to benchmark VAD methods in realistic scenarios, where robotic arms can perform unforeseen tasks, and thereby encounter new anomaly types. We train and evaluate several state-of-the-art VAD methods, including a novel method specifically adapted for robotic arm manipulation. While the proposed method outperforms many state-of-the-art competitors, all methods remain below a micro-averaged frame-level AUC threshold of 70% in the most challenging evaluation setup, confirming the difficulty of the proposed benchmark. We publicly release our dataset and code at https://zenodo.org/records/22754659.