In this paper, we present a novel depth map enhancement for real-time 3D reconstruction by the Microsoft Kinect. The Kinect sensor is... Show moreIn this paper, we present a novel depth map enhancement for real-time 3D reconstruction by the Microsoft Kinect. The Kinect sensor is relatively affordable and capable of generating high-resolution color image and depth maps of the scene at realtime rates. However, owning the low- cost, there are several artifacts. Generated depth map contains lots of holes, which they are missing information around object boundaries and mis-alignment with color image. The objective of 3D reconstruction is to recreate a real scene, as accurate as possible within a virtual three-dimensional space using a computer. The algorithm of 3D-recosntrution is highly based on the quality of the depth map. This poor depth map could not be applied in potential real-time 3D reconstruction. We present novel multi-step upsampling-based our novel anisotropic diffusion algorithms with generated depth map and color image by Kinect. This method has better performance than existed bilateral filtering and original anisotropic filtering in terms of filling holes, sharpening the boundaries of objects and alignment between depth map and color image. We compare the performance of these filters. It is difficult to do a meaningful comparison of two algorithms with using output of Kinect sensor directly; as for each observation of the same scene, we will get different sensed value. In order to circumvent this problem and to achieve an accurate comparison process, we used dataset from Computer Vision Group at Munchen Technology Universty(TUM). This dataset and the scripts is related to quantitative error metrics are avail at http://vision.in.tum.de/data/datasets/rgbd-‐dataset. We also contribute making our project parallel and GPU computing to satisfy real-time system condition. M.S. in Electrical Engineering, July 2015 Show less
