3D Reconstruction using Kinect Sensor and Parallel Processing on 3D Graphics Processing Unit

Abstract

One of depth cameras such as the Microsoft Kinect is much cheaper than conventional 3D scanning devices, thus it can be acquired for everyday users easily. However, the depth data captured by Kinect over a certain distance is of low quality. In this work, we implement a set of algorithms allowing users to capture 3D surfaces by using the handheld Kinect. As a classic alignment algorithm such as the Iterative Closest Point (ICP) does not show efficacy in aligning point clouds that have limited overlapped regions, another coarse alignment using the Sample Consensus Initial Alignment (SAC-IA) is incorporated in to the registration process in order to ameliorate 3D point clouds’ fitness. Two robust reconstruction methods namely the Alpha Shapes and the Grid Projection are also implemented to reconstruct 3D surface from registered point clouds. The experimental results have shown the efficiency and applicability of of our blueprint. The constructed system obtains acceptable results in a few minutes with a low price device, thus it may practically be an useful approach for avatar generations or online shoppings.