ISNN 2005: Advances in Neural Networks – ISNN 2005 pp 765-771 | Cite as
Binocular 3D Reconstruction Based on Neural Network
Conference paper
Abstract
This paper introduces the computer vision to 3D reconstruction of the object. A novel method is developed, which adopts the digital camera as the sensor and uses the techniques of image processing and vision calculation synthetically to realize the untouched 3D measurement. The binocular measurement theory and the camera calibration based on the neural network are also described. Finally, we give the procedures of the binocular 3D reconstruction and simulate a case with Matlab program.
Keywords
Neural Network Camera Calibration Chain Code Canny Operator Neural Network Input
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Preview
Unable to display preview. Download preview PDF.
References
- 1.Wang, X., Ye, M., Wang, X., Wang, H.: Binocular Vision Sensor Modeling Based on Neural Network. Optical Instruments 24, 42–46 (2002)Google Scholar
- 2.Zhao, Q., Sun, Z., Lan, L.: Neural Network Technique in Camera Calibration. Control and Decision 17, 336–338 (2002)Google Scholar
- 3.Smith, S.M., Brady, J.M.: SUSAN-A New Approach to Low Level Image Processing, Internal Technical Report TR95SMS1c (1995)Google Scholar
- 4.Lin, M., Wang, X., Guan, X.: Research on the Feature Extraction for Image Based on Differential Code. Yiqi Yibiao Xuebao 25, 465–467 (2004)Google Scholar
Copyright information
© Springer-Verlag Berlin Heidelberg 2005