Magnetic-Visual Sensor Fusion based Medical SLAM for Endoscopic Capsule Robot

Abstract

A reliable, real-time simultaneous localization and mapping (SLAM) method is crucial for the navigation of actively controlled capsule endoscopy robots. These robots are an emerging, minimally invasive diagnostic and therapeutic technology for use in the gastrointestinal (GI) tract. In this study, we propose a dense, non-rigidly deformable, and real-time map fusion approach for actively controlled endoscopic capsule robot applications. The method combines magnetic and vision based localization, and makes use of frame-to-model fusion and model-to-model loop closure. The performance of the method is demonstrated using an ex-vivo porcine stomach model. Across four trajectories of varying speed and complexity, and across three cameras, the root mean square localization errors range from 0.42 to 1.92 cm, and the root mean square surface reconstruction errors range from 1.23 to 2.39 cm.

Cited by in corpus (4)

• Deep EndoVO: A Recurrent Convolutional Neural Network (RCNN) based Visual Odometry Approach for Endoscopic Capsule Robots
• Sparse-then-Dense Alignment based 3D Map Reconstruction Method for Endoscopic Capsule Robots
• A fully dense and globally consistent 3D map reconstruction approach for GI tract to enhance therapeutic relevance of the endoscopic capsule robot
• Endo-VMFuseNet: Deep Visual-Magnetic Sensor Fusion Approach for Uncalibrated, Unsynchronized and Asymmetric Endoscopic Capsule Robot Localization Data