Sorry, you need to enable JavaScript to visit this website.

Dense Optical Flow for the Reconstruction of Weakly Textured and Structured Surfaces: Application to Endoscopy

Citation Author(s):
Tan-Binh Phan, Dinh-Hoan Trinh, Dominique Lamarque, Didier Wolf, Christian Daul
Submitted by:
Christian Daul
Last updated:
11 September 2019 - 11:46am
Document Type:
Tan-Binh Phan
Paper Code:

This paper introduces a structure from motion (SfM)-based surface reconstruction method for images including weak textures and structures. In SfM, the quality of the determination of homologous points between images plays a key role in terms of reconstruction performances. However, classical feature matching-based methods as integrated in the state-of-the-art SfM algorithms are often inoperative for images with weak structures and textures. This contribution describes a dense optical flow-based solution enabling the point correspondence determination in such scenes. The accuracy and robustness of the proposed method were validated using results obtained for a phantom with known dimensions and with real medical data, respectively. Complex internal stomach wall surfaces were constructed using gastroscopic images.

0 users have voted:


Paper presented at ICIP bu Tan-Binh PHAN