Title :
Fast 3D Object Alignment from Depth Image with 3D Fourier Moment Matching on GPU
Author :
Hong-Ren Su ; Hao-Yuan Kuo ; Shang-Hong Lai ; Chin-Chia Wu
Author_Institution :
Inst. of Inf. Syst. & Applic., Nat. Tsing Hua Univ., Hsinchu, Taiwan
Abstract :
In this paper, we develop a fast and accurate 3D object alignment system which can be applied to detect objects and estimate their 3D pose from a depth image containing cluttered background. The proposed 3D alignment system consists of two main algorithms: the first is the 3D detection algorithm to detect the top-level object from a depth map of the cluttered 3D objects, and the second is the 3D Fourier based point-set alignment algorithm to estimate the 3D object pose from an input depth image. We also implement the proposed 3D alignment algorithm on a GPU computing platform to speed up the computation of the object detection and Fourier-based image alignment algorithms in order to align the 3D object in real time.
Keywords :
Fourier transforms; graphics processing units; image matching; object detection; pose estimation; 3D Fourier based point-set alignment algorithm; 3D Fourier moment matching; 3D detection algorithm; 3D object pose estimation; Fourier-based image alignment algorithms; GPU computing platform; cluttered background; depth image; depth map; fast 3D object alignment system; top-level object detection; Fourier transforms; Graphics processing units; Image segmentation; Object detection; Parallel processing; Three-dimensional displays; 3D object alignment; Fourier moment; GPU;
Conference_Titel :
3D Vision (3DV), 2014 2nd International Conference on
Conference_Location :
Tokyo
DOI :
10.1109/3DV.2014.91