Dense feature correspondence for video-based endoscope three-dimensional motion tracking

This paper presents an improved video-based endoscope tracking approach on the basis of dense feature correspondence. Currently video-based methods often fail to track the endoscope motion due to low-quality endoscopic video images. To address such failure, we use image texture information to boost the tracking performance. A local image descriptor - DAISY is introduced to efficiently detect dense texture or feature information from endoscopic images. After these dense feature correspondence, we compute relative motion parameters between the previous and current endoscopic images in terms of epipolar geometric analysis. By initializing with the relative motion information, we perform 2-D/3-D or video-volume registration and determine the current endoscope pose information with six degrees of freedom (6DoF) position and orientation parameters. We evaluate our method on clinical datasets. Experimental results demonstrate that our proposed method outperforms state-of-the-art approaches. The tracking error was significantly reduced from 7.77 mm to 4.78 mm.