Detector-in-the-Loop Tracking: Active Memory Rectification for Stable Glottic Opening Localization
This work addresses the challenge of reliable clinical video tracking for emergency medical procedures, representing an incremental improvement by integrating a detector to correct memory drift in existing trackers.
The paper tackled the problem of temporal instability in glottic opening localization during video laryngoscopy by proposing a detector-in-the-loop framework that uses active memory rectification to mitigate drift in foundation-model trackers, achieving state-of-the-art performance with reduced drift and missing rates on emergency intubation videos.
Temporal stability in glottic opening localization remains challenging due to the complementary weaknesses of single-frame detectors and foundation-model trackers: the former lacks temporal context, while the latter suffers from memory drift. Specifically, in video laryngoscopy, rapid tissue deformation, occlusions, and visual ambiguities in emergency settings require a robust, temporally aware solution that can prevent progressive tracking errors. We propose Closed-Loop Memory Correction (CL-MC), a detector-in-the-loop framework that supervises Segment Anything Model 2(SAM2) through confidence-aligned state decisions and active memory rectification. High-confidence detections trigger semantic resets that overwrite corrupted tracker memory, effectively mitigating drift accumulation with a training-free foundation tracker in complex endoscopic scenes. On emergency intubation videos, CL-MC achieves state-of-the-art performance, significantly reducing drift and missing rate compared with the SAM2 variants and open loop based methods. Our results establish memory correction as a crucial component for reliable clinical video tracking. Our code will be available in https://github.com/huayuww/CL-MR.