Hybrid RF Localization inside Small Intestine using Images from Wireless Capsule Endoscopy

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. However, since the shape of the small intestine is extremely complex and the length of small intestine varies from 5m to 9m, localization of the capsule inside small intestine is very challenging. Existing commercial used radio frequency (RF) localization systems using the received signal strength (RSS) are not able to provide satisfactory localization accuracy due to the severe shadow fading and non-homogeneity of the body tissues. In this paper, we present a hybrid localization technique that takes advantage of data fusion from image sequence captured by the WCE’s embedded camera and the RF signal emitted by the capsule to enhance the positioning accuracy. The proposed method 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 RF measurements by employing a Kalman filter to smooth the localization results. Performance of the proposed hybrid algorithm is validated under a virtual testbed that emulates the transition of capsule inside small intestine against the traditional RSS-based RF localization.