Paper
6 April 2007 Three-dimensional vision inspection based on structured light projection and neurocalibration
Kai Xie, Wan Yu Liu, Zhao-Bang Pu
Author Affiliations +
Proceedings Volume 6595, Fundamental Problems of Optoelectronics and Microelectronics III; 65954J (2007) https://doi.org/10.1117/12.726609
Event: Fundamental Problems of Optoelectronics and Microelectronics III, 2006, Harbin, China
Abstract
Structured light three dimensional (3D) vision inspection is an increasing common means for acquiring three dimensional geometry of objects due to its short acquisition time, low cost and its robustness in the presence of ambient light. In this paper, we proposed a method of structure light 3D vision inspection based on neurocalibration. First, the principle of linear structured light 3D vision inspection and Back Propagation (BP) neural network are described. Second, a calibration method based on BP neural network without any knowledge of 3D object and computer vision is proposed, which has the advantage of resolving the system nonlinearity. The feasibility of the approach is based on the fact that multilayer feed-forward networks are capable of approximating an arbitrary continuous nonlinear function and solving least squares problem. The network consists of an input layer and an output layer, with a hidden layer in between. The input neurons denote the coordinates of 2D image pixels and the output neurons denote the corresponding coordinates of 3D world points. At the end, the accuracy and the robustness of the proposed method are tested by experiments. It has been shown that the proposed method is simple, robust and effective.
© (2007) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Kai Xie, Wan Yu Liu, and Zhao-Bang Pu "Three-dimensional vision inspection based on structured light projection and neurocalibration", Proc. SPIE 6595, Fundamental Problems of Optoelectronics and Microelectronics III, 65954J (6 April 2007); https://doi.org/10.1117/12.726609
Lens.org Logo
CITATIONS
Cited by 1 scholarly publication.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Calibration

3D vision

Structured light

Neural networks

Inspection

3D image processing

Cameras

Back to Top