Share Email Print
cover

Proceedings Paper

Night vision image fusion for target detection with improved 2D maximum entropy segmentation
Author(s): Lian-fa Bai; Ying-bin Liu; Jiang Yue; Yi Zhang
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Infrared and LLL image are used for night vision target detection. In allusion to the characteristics of night vision imaging and lack of traditional detection algorithm for segmentation and extraction of targets, we propose a method of infrared and LLL image fusion for target detection with improved 2D maximum entropy segmentation. Firstly, two-dimensional histogram was improved by gray level and maximum gray level in weighted area, weights were selected to calculate the maximum entropy for infrared and LLL image segmentation by using the histogram. Compared with the traditional maximum entropy segmentation, the algorithm had significant effect in target detection, and the functions of background suppression and target extraction. And then, the validity of multi-dimensional characteristics AND operation on the infrared and LLL image feature level fusion for target detection is verified. Experimental results show that detection algorithm has a relatively good effect and application in target detection and multiple targets detection in complex background.

Paper Details

Date Published: 16 August 2013
PDF: 8 pages
Proc. SPIE 8912, International Symposium on Photoelectronic Detection and Imaging 2013: Low-Light-Level Technology and Applications, 89120X (16 August 2013); doi: 10.1117/12.2034021
Show Author Affiliations
Lian-fa Bai, Nanjing Univ. of Science and Technology (China)
Ying-bin Liu, Nanjing Univ. of Science and Technology (China)
Jiang Yue, Nanjing Univ. of Science and Technology (China)
Yi Zhang, Nanjing Univ. of Science and Technology (China)


Published in SPIE Proceedings Vol. 8912:
International Symposium on Photoelectronic Detection and Imaging 2013: Low-Light-Level Technology and Applications
Benkang Chang; Hui Guo, Editor(s)

© SPIE. Terms of Use
Back to Top