Vision guided navigation based on dark regions and template matching for capsule endoscopies

In this paper, a novel navigation based on vision for wireless capsule endoscopies is proposed. The algorithm based on dark regions was improved by setting the Region of Interest (ROI) to limit the search coverage around the last navigation point, introducing the morphology method to eliminate diverticula and vesicae and raising the concept of position weight to reckon navigation points in the case of lacking for valid dark regions. Besides that, we proposed the method based on template matching, which is common in industrial detection, to navigate when the method mentioned above fails. Finally, the two methods were fused and it´s proved beneficial to both the success rate and the computation speed by simulation and experiments.