Localization of Wireless Endoscopic Capsule inside GI Tract


CWINS has received $1.2 Million funding from NIST to work on the cutting edge wireless body area networks (W-BAN). This project investigates wireless access and localization for body area networks with focus on localization for wireless video capsule endoscopy inside the human gastrointestinal tract.

Wireless capsule endoscope (WCE) provides a noninvasive method to examine the entire gastrointestinal (GI) tract including small intestine, which other video endoscopic instruments cannot reach. Since the shape of small intestine is extremely complex and the length of small intestine varies from 5 to 9 meters, localization of the WCE inside the small intestine is very challenging. Traditional radio frequency (RF) localization techniques using the received signal strength (RSS) are not able to provide satisfactory location information of the capsule inside the small intestine. In this project, we developped a hybrid localization technique that takes advantage of data fusion from image sequence captured by the WCE's embedded camera and the RSS of the RF signal emitted by the capsule to enhance the positioning accuracy. This hybrid localization technique estimates the speed and direction of movement of the capsule by analyzing displacements of feature points between consecutive image frames and this motion information is integrated with RSS measurements by employing a Kalman filter to smooth the RF localization results.

Principal Investigators

Kaveh Pahlavan (CWINS)

Research Staff (CWINS)

Yunxing Ye, Guanqun Bao, Yishuang Geng, Umair Khan, Jin Chen, Zhuoran Liu, Ruijun Fu, Yi Wang, Shen Li, Jie He, Liang Mi




Started from 2009

NIST publication