Share Email Print

Proceedings Paper

Target-enhanced fusion method based on YCbCr space
Author(s): Hanjie Chen; Xinmin Zhou; Guohua Gu; Weixian Qian; Minjie Wan
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Image fusion is a process of combining complementary information from multiple images of the same scene to generate a composite image. To highlight the thermal target and keep appearance information simultaneously, a target-enhanced fusion method based on YCbCr space is proposed. Firstly, enhancement process is taken in the original infrared image. Three gray images are then obtained via linear computation. Then, color transfer process is accomplished in YCbCr space. Each of the channel' s mean and standard deviation is matched to complete color transfer. Different kinds of reference images are selected to generate different kinds of fusion results. A natural daylight color image is utilized to implement false color fusion, while a reference image with more red components is utilized to implement gray fusion. Besides, parallel acceleration is implemented to improve the practicability of the algorithm. The dynamic memory space allocation problem of Graphics Processing Unit (GPU) is solved by the optimization of multi-dimensional index linearization methods and the algorithm modification for computing statistical parameters. The experiment results of fusion algorithm show that in either mode (color/gray), the proposed method is able to obtain a fused image which pops out enhanced targets, without losing the details of the background. The experiment results of parallel acceleration show that the speedup ratio of an image pair sized around 640×480 is approximately 8, basically realizing real-time process.

Paper Details

Date Published: 18 December 2019
PDF: 6 pages
Proc. SPIE 11338, AOPC 2019: Optical Sensing and Imaging Technology, 113380J (18 December 2019); doi: 10.1117/12.2541551
Show Author Affiliations
Hanjie Chen, Nanjing Univ. of Science and Technology (China)
Xinmin Zhou, Criminal Police Headquarters of Jiangsu Provincial Security Bureau (China)
Guohua Gu, Nanjing Univ. of Science and Technology (China)
Weixian Qian, Nanjing Univ. of Science and Technology (China)
Minjie Wan, Nanjing Univ. of Science and Technology (China)

Published in SPIE Proceedings Vol. 11338:
AOPC 2019: Optical Sensing and Imaging Technology
John E. Greivenkamp; Jun Tanida; Yadong Jiang; HaiMei Gong; Jin Lu; Dong Liu, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?