軽量なマルチフレーム統合による動画内YOLO物体検出の堅牢化
Lightweight Multi-Frame Integration for Robust YOLO Object Detection in Videos
複数の連続フレームをYOLOに入力し、対象フレームの出力のみを監視する簡潔な手法で、動画物体検出の堅牢性を向上させ、軽量モデルと重量モデルの性能差を縮めた。
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: Yitong Quan, Benjamin Kiefer, Martin Messmer, Andreas Zell
分類: cs.CV, cs.RO
原文アブストラクト
Modern image-based object detection models, such as YOLOv7, primarily process individual frames independently, thus ignoring valuable temporal context naturally present in videos. Meanwhile, existing video-based detection methods often introduce complex temporal modules, significantly increasing model size and computational complexity. In practical applications such as surveillance and autonomous driving, transient challenges including motion blur, occlusions, and abrupt appearance changes can severely degrade single-frame detection performance. To address these issues, we propose a straightforward yet highly effective strategy: stacking multiple consecutive frames as input to a YOLO-based detector while supervising only the output corresponding to a single target frame. This approach leverages temporal information with minimal modifications to existing architectures, preserving simplicity, computational efficiency, and real-time inference capability. Extensive experiments on the challenging MOT20Det and our BOAT360 datasets demonstrate that our method improves detection robustness, especially for lightweight models, effectively narrowing the gap between compact and heavy detection networks. Additionally, we contribute the BOAT360 benchmark dataset, comprising annotated fisheye video sequences captured from a boat, to support future research in multi-frame video object detection in challenging real-world scenarios.
