Simultaneous shape and camera-projector parameter estimation for 3D endoscopic system using CNN-based grid-oneshot scan

[摘要] For effective in situ endoscopic diagnosis and treatment, measurement of polyp sizes is important. For this purpose, 3D endoscopic systems have been researched. Among such systems, an active stereo technique, which projects a special pattern wherein each feature is coded, is a promising approach because of simplicity and high precision. However, previous works of this approach have problems. First, the quality of 3D reconstruction depended on the stabilities of feature extraction from the images captured by the endoscope camera. Second, due to the limited pattern projection area, the reconstructed region was relatively small. In this Letter, the authors propose a learning-based technique using convolutional neural networks to solve the first problem and an extended bundle adjustment technique, which integrates multiple shapes into a consistent single shape, to address the second. The effectiveness of the proposed techniques compared to previous techniques was evaluated experimentally.

[学科分类] 肠胃与肝脏病学

[关键词] image matching;medical image processing;cameras;endoscopes;computer vision;feature extraction;stereo image processing;neural nets;image reconstruction;learning (artificial intelligence);extended bundle adjustment technique;camera-projector parameter estimation;3D endoscopic system;CNN-based grid-oneshot scan;situ endoscopic diagnosis;polyp sizes;active stereo technique;special pattern;feature extraction;endoscope camera;pattern projection area;learning-based technique