상세정보
학술대회
Performance Evaluation of Depth Map Generation Algorithm for Stereo Endoscopic Camera
- 발행일
- 201611
- 출처
- International Conference on Communication and Information Processing (ICCIP) 2016, pp.120-123
- 협약과제
- 16ZC1400, 환자특이적 수술 플래닝 기반 실감 리허설 기술개발, 박종현
- 초록
- This paper introduces a performance evaluation method for algorithms that generates a depth map using an image from a stereo endoscopic camera for image processing of laparoscope operations. The depth image was created by using a space-time stereo method by illuminating various patterns on scenes consisting of models of the 3D-printed organ model and actual organs from a pig, and the ground truth image was generated for each sub-pixel unit to achieve high accuracy and high precision. Different algorithms were evaluated using the ground truth image data. The number of effective depth pixels compared to the ground truth and the distance error was measured from algorithms based on an edge-preserving filter as real-time algorithms and quasi-dense algorithms. This paper presents an analysis of each algorithm from its evaluation indices to determine which algorithm is appropriate to compute the depth map from laparoscopic images.
- KSP 제안 키워드
- 3D printed, Depth image, Distance error, Edge-preserving filter, Endoscopic camera, Generation algorithm, Ground truth image, High accuracy, Image data, Image processing, Organ model