Endo-VMFuseNet: Deep Visual-Magnetic Sensor Fusion Approach for Uncalibrated, Unsynchronized and Asymmetric Endoscopic Capsule Robot Localization Data
This work addresses the challenge of accurate perception for capsule robots in medical procedures, which is incremental as it applies existing deep learning methods to a specific domain.
The paper tackled the problem of uncalibrated, asynchronous, and asymmetric sensor fusion for endoscopic capsule robots by extending deep learning approaches, achieving sub-millimeter precision in translational and rotational movements on real pig stomach datasets.
In the last decade, researchers and medical device companies have made major advances towards transforming passive capsule endoscopes into active medical robots. One of the major challenges is to endow capsule robots with accurate perception of the environment inside the human body, which will provide necessary information and enable improved medical procedures. We extend the success of deep learning approaches from various research fields to the problem of uncalibrated, asynchronous, and asymmetric sensor fusion for endoscopic capsule robots. The results performed on real pig stomach datasets show that our method achieves sub-millimeter precision for both translational and rotational movements and contains various advantages over traditional sensor fusion techniques.