In Defense of Kalman Filtering for Polyp Tracking from Colonoscopy Videos
This work addresses the need for real-time and robust polyp detection to assist doctors during colonoscopy exams, though it is incremental as it applies an existing tracking method to a specific domain.
The paper tackles the problem of real-time polyp detection in colonoscopy videos by proposing a Kalman filtering tracker combined with efficient detectors, achieving state-of-the-art accuracy with metrics like an F1 score of 0.799 on CVC-ClinicDB and 0.914 on Hyper-Kvasir, while running at 30 frames per second.
Real-time and robust automatic detection of polyps from colonoscopy videos are essential tasks to help improve the performance of doctors during this exam. The current focus of the field is on the development of accurate but inefficient detectors that will not enable a real-time application. We advocate that the field should instead focus on the development of simple and efficient detectors that an be combined with effective trackers to allow the implementation of real-time polyp detectors. In this paper, we propose a Kalman filtering tracker that can work together with powerful, but efficient detectors, enabling the implementation of real-time polyp detectors. In particular, we show that the combination of our Kalman filtering with the detector PP-YOLO shows state-of-the-art (SOTA) detection accuracy and real-time processing. More specifically, our approach has SOTA results on the CVC-ClinicDB dataset, with a recall of 0.740, precision of 0.869, $F_1$ score of 0.799, an average precision (AP) of 0.837, and can run in real time (i.e., 30 frames per second). We also evaluate our method on a subset of the Hyper-Kvasir annotated by our clinical collaborators, resulting in SOTA results, with a recall of 0.956, precision of 0.875, $F_1$ score of 0.914, AP of 0.952, and can run in real time.