Detector-in-the-Loop Tracking: Active Memory Rectification for Stable Glottic Opening Localization

2026-02-22

AI Summary

This work addresses the temporal instability in laryngeal opening localization during video laryngoscopy, which arises from the lack of temporal context in single-frame detection and memory drift in conventional trackers. To tackle this, the authors propose a Closed-Loop Memory Correction (CL-MC) framework that introduces, for the first time, a training-free closed-loop feedback mechanism. During inference, high-confidence detection outputs are dynamically integrated into the tracking pipeline to semantically reset and actively correct the tracker’s memory. By coupling SAM2 with a confidence-aligned state decision strategy, the method enables online, training-free memory correction. Evaluated on emergency intubation videos, CL-MC achieves state-of-the-art performance, substantially reducing tracking drift and missed detections, thereby demonstrating the critical role of memory correction in clinical video analysis.

Technology Category

• Computer Vision: Motion & Tracking
• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: State Estimation

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Security and Privacy: Tracking, profiling, and countermeasures against them

Abstract

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.

Problem

• glottic opening localization
• temporal stability
• memory drift
• video laryngoscopy
• tracking error

Innovation

• detector-in-the-loop
• memory rectification
• temporal stability
• glottic opening localization
• foundation model tracking