Unsupervised learning based relative localization for WCE in a deformable tubular environment

Xu，Yangxin1; Li，Keyu1; Meng，Max Q.H.2,3

10.1109/ICARM52023.2021.9536182

2021-07-03

6th IEEE International Conference on Advanced Robotics and Mechatronics (ICARM)

978-1-6654-4596-2

2021 6th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2021

119-124

JUL 03-05, 2021

null,Chongqing,PEOPLES R CHINA

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

Wireless capsule endoscopy is a promising technology for screening the entire gastrointestinal tract, but the lack of the capbility to locate the capsule is still one of its limitations. To solve the problem, in this paper, we propose a novel relative localization method based on unsupervised learning. The proposed algorithm can estimate the pose and the depth of each image from a image sequence. A Shape from Shading (SfS) based depth constraint is proposed to overcome the problem of “fake far view” and increase the localization accuracy. The proposed method is verified in an image dataset consisting of several pig colons with the average position error rate of 6.71%, which is 4.01% lower than that of the baseline.

Location awareness Wireless communication Mechatronics Error analysis Shape Prediction algorithms Image sequences

其他

英语

CPCI-S ; EI

National Key R&D program of China[2019YFB1312400]

Automation & Control Systems ; Engineering ; Robotics

Automation & Control Systems ; Engineering, Electrical & Electronic ; Robotics

WOS:000728141500020

20214010982603

Endoscopy ; Mammals

Medicine and Pharmacology:461.6

2-s2.0-85116199591

Scopus

1.The Department of Electronic Engineering,The Chinese University of Hong Kong,Hong Kong
2.The Department of Electronic and Electrical Engineering,The Southern University of Science and Technology,Shenzhen,China
3.The Shenzhen Research Institute,The Chinese University of Hong Kong,Shenzhen,China

Xu，Yangxin,Li，Keyu,Meng，Max Q.H.. Unsupervised learning based relative localization for WCE in a deformable tubular environment[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2021:119-124.