Paper
12 October 2010 Point detection and positioning system of the target based on surface cluster eyes
Fang Guo, Hao Zhang, Keyi Wang
Author Affiliations +
Abstract
The research of target detection and position is a challenge task in the fields where machine vision was used to develop various systems. However, monocular vision and binocular vision traditionally are difficult to meet the applications for high resolution and high sensitivity. Because compound eye imaging system is capacity of the large field of view for moving target detection with high sensitivity, the optical system has the potential to meet the applications above mentioned. In this paper, a preliminary exploration of the surface imaging system for the characteristics of cluster eyes was made and the optical signal processing methods of cluster eyes were introduced in detail. First the structure of the cluster eyes was described and the imaging channels of cluster eyes were ray traced with Zemax. Then based on the surface imaging mechanism with clusters eyes, the center of gravity of image space for target was extracted. Subsequently by the neural networks training based on LM (Levenberg-Marquardt) algorithm, the non-linear relationship between target and image was effectively calibrated. Finally, the corresponding relationship between target point and its image point among the various channels was established. The experimental results show that the multicast visual imaging systems are capable of providing the information of target azimuth and distance. Some attempts to study the systems were made to achieve high resolution, high sensitivity of target detection and positioning tasks. At the same time the surface imaging system also laid a solid foundation for the large compound eye imaging system from theory to practical application.
© (2010) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Fang Guo, Hao Zhang, and Keyi Wang "Point detection and positioning system of the target based on surface cluster eyes", Proc. SPIE 7656, 5th International Symposium on Advanced Optical Manufacturing and Testing Technologies: Optical Test and Measurement Technology and Equipment, 765663 (12 October 2010); https://doi.org/10.1117/12.867252
Lens.org Logo
CITATIONS
Cited by 1 scholarly publication.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Target detection

Imaging systems

Neural networks

Eye

Calibration

Detection and tracking algorithms

Evolutionary algorithms

Back to Top