Open-World Crimson Snapper Individual Re-Identification via Vision-Language Priors

Long-term tracking of individual crimson snapper in aquaculture is difficult: inter-individual appearance differences are subtle, underwater image quality fluctuates, and in real deployment new and unregistered individuals appear continuously — so a closed-set recognition assumption does not hold.

Build an open-world recognition method on vision-language priors that both identifies known identities and rejects unknown ones, while compressing the model to a deployable size.

Designed a Compact256 projection layer on the CLIP-ReID backbone to compress feature dimensionality by 5×; proposed a Quality-Aware Identity Prototype Mechanism (QACM) that folds image-quality estimation into identity prototype modelling, unifying known-identity recognition and unknown-identity rejection; built a crimson snapper individual dataset covering 92 identities and over ten thousand images, then ran both closed-set and deployment-level open-set evaluations.

This project delivers a single-fish video runtime system for open-world fish individual re-identification. Centred on track-level identity lifecycle management, five core mechanisms — including Fast Warm-up, post-confirmation identity retention, and dynamic confidence updating — solve stable recognition under track breaks, frame-quality fluctuation, and identity conflicts.

System V3.1.1 meets the single-fish engineering freeze standard: it outputs stable, auditable identity results and provides a reusable technical baseline for active identity management and multi-track conflict handling in future multi-fish scenarios.