自動運転のためのオープンボキャブラリ手法による文脈ベース動作検索
Context-based Motion Retrieval using Open Vocabulary Methods for Autonomous Driving
SMPL動作と映像を言語と共通埋め込み空間で結び、テキストクエリで自動運転データセット中の稀な歩行者行動を検索する枠組みを提案し、Waymo拡張データセットWayMoCoで最大27.5%の精度向上を達成した。
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: Stefan Englmeier, Max A. Büttner, Katharina Winter, Fabian B. Flohr
分類: cs.CV, cs.CL, cs.IR, cs.RO
原文アブストラクト
Autonomous driving systems must operate reliably in safety-critical scenarios, particularly those involving unusual or complex behavior by Vulnerable Road Users (VRUs). Identifying these edge cases in driving datasets is essential for robust evaluation and generalization, but retrieving such rare human behavior scenarios within the long tail of large-scale datasets is challenging. To support targeted evaluation of autonomous driving systems in diverse, human-centered scenarios, we propose a novel context-aware motion retrieval framework. Our method combines Skinned Multi-Person Linear (SMPL)-based motion sequences and corresponding video frames before encoding them into a shared multimodal embedding space aligned with natural language. Our approach enables the scalable retrieval of human behavior and their context through text queries. This work also introduces our dataset WayMoCo, an extension of the Waymo Open Dataset. It contains automatically labeled motion and scene context descriptions derived from generated pseudo-ground-truth SMPL sequences and corresponding image data. Our approach outperforms state-of-the-art models by up to 27.5% accuracy in motion-context retrieval, when evaluated on the WayMoCo dataset.
