Title :
A vision based navigation for capsule endoscopies
Author :
Ying Zhao ; Yunjiang Lou
Author_Institution :
Shenzhen Grad. Sch., Key Lab. for Adv. Motion Control & Modern Autom. Equipments, Harbin Inst. of Technol., Shenzhen, China
Abstract :
In this paper, a novel navigation method based on vision is proposed by integrating the advantages of watershed and pyramid segmentation methods. Using the idea of the continuity between two successive images, it is possible to give a reasonable advisory when the visual navigation fails. Besides that, we proposed to set a region of interest to accelerate the algorithm, using the method of image morphology to eliminate diverticula and introducing necessary auxiliary operations to avoid medical malpractice. A set of endoscopic images is tested to demonstrate the effectiveness of the proposed approach.
Keywords :
endoscopes; image segmentation; medical image processing; vision; capsule endoscopy; endoscopic image segmentation; image morphology method; pyramid segmentation method; region of interest; visual navigation method; watershed segmentation method; Accuracy; Endoscopes; Image edge detection; Image segmentation; Navigation; Surgery; Visualization; capsule endoscopy; pyramid segmentation; region of interest; vision based navigation; watershed segmentation;
Conference_Titel :
Industrial Electronics and Applications (ICIEA), 2013 8th IEEE Conference on
Conference_Location :
Melbourne, VIC
Print_ISBN :
978-1-4673-6320-4
DOI :
10.1109/ICIEA.2013.6566462
