الملخص
Quantifying collective fish behavior requires accurate trajectories, yet multi-view 3D tracking remains challenging due to frequent occlusions, visually similar individuals, and the long-standing scarcity of identity annotations. We present TrackFish3D, a geometry-driven self-supervised framework for dense multi-camera 3D tracking of schooling fish. Instead of relying on appearance-based re-identification or manually annotated identities, TrackFish3D turns calibrated multi-view geometry into supervision: triangulation and reprojection consistency provide pseudo-associations, while a geometric encoder and global association transformer learn all-to-all cross-view correspondence within each frame. To make these associations identity-aware, TrackFish3D introduces a self-supervised contrastive objective that separates co-visible individuals in the embedding space, together with a temporal predictor that preserves identities and bridges short occlusions across frames. The resulting model is trained once on unlabeled footage and applied directly to unseen test videos, requiring no cross-view identity labels, temporal annotations, 3D ground truth, appearance features, or test-time optimization. On our benchmark, TrackFish3D improves 3D Multi-Object Tracking Accuracy from 87.7% for the strongest baseline to 95.8%. On the 3D-ZeF zebrafish benchmark, it achieves 81.1% MOTA, compared with 77.4% for the best geometric baseline. TrackFish3D also generalizes beyond fish, achieving strong results on real-world bird tracking.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Phurtivilai, P., Dou, Z., Wu, Y., Chu, K., Liu, Y., Yang, L., Wang, W., & Komura, T. (2026). TrackFish3D: Self-Supervised 3D Tracking of Schooling Fish from Multi-view Videos. https://omanscience.com/ar/articles/trackfish3d-self-supervised-3d-tracking-of-schooling-fish-from-multi-view-videos
MLA 9
Phurtivilai, Patt, et al. "TrackFish3D: Self-Supervised 3D Tracking of Schooling Fish from Multi-view Videos." https://omanscience.com/ar/articles/trackfish3d-self-supervised-3d-tracking-of-schooling-fish-from-multi-view-videos.
شيكاغو (المؤلف–التاريخ)
Phurtivilai, Patt, Zhiyang Dou, Yifan Wu, Kinfung Chu, Yuan Liu, Lei Yang, Wenping Wang, and Taku Komura. 2026. "TrackFish3D: Self-Supervised 3D Tracking of Schooling Fish from Multi-view Videos." https://omanscience.com/ar/articles/trackfish3d-self-supervised-3d-tracking-of-schooling-fish-from-multi-view-videos.
هارفارد
Phurtivilai, P., Dou, Z., Wu, Y., Chu, K., Liu, Y., Yang, L., Wang, W. and Komura, T. (2026) 'TrackFish3D: Self-Supervised 3D Tracking of Schooling Fish from Multi-view Videos', Available at: https://omanscience.com/ar/articles/trackfish3d-self-supervised-3d-tracking-of-schooling-fish-from-multi-view-videos.
فانكوفر
Phurtivilai P, Dou Z, Wu Y, Chu K, Liu Y, Yang L, et al. TrackFish3D: Self-Supervised 3D Tracking of Schooling Fish from Multi-view Videos. https://omanscience.com/ar/articles/trackfish3d-self-supervised-3d-tracking-of-schooling-fish-from-multi-view-videos
IEEE
P. Phurtivilai, Z. Dou, Y. Wu, K. Chu, Y. Liu, L. Yang, W. Wang, and T. Komura, "TrackFish3D: Self-Supervised 3D Tracking of Schooling Fish from Multi-view Videos," https://omanscience.com/ar/articles/trackfish3d-self-supervised-3d-tracking-of-schooling-fish-from-multi-view-videos.