Translator Disclaimer
Paper
15 November 2018 Computer-aided infrared camouflage effectiveness evaluation method based on image saliency
Author Affiliations +
Proceedings Volume 10964, Tenth International Conference on Information Optics and Photonics; 109644G (2018) https://doi.org/10.1117/12.2506095
Event: Tenth International Conference on Information Optics and Photonics (CIOP 2018), 2018, Beijing, China
Abstract
This paper reports on a new computer-aided method for the infrared camouflage effectiveness evaluation of a target based on its image saliency. The image saliency of a target was computed according to its background-related features, including intensity, contrast, gradient and orientation features in one real infrared image. On the basis of the former saliency value, the camouflage effectiveness value of a target was calculated quantitatively. The results clearly indicated that the target without infrared camouflage had a low camouflage effectiveness value, while a target with good infrared camouflage (the camouflage pattern patches of the target matched well with the background) had a high camouflage effectiveness value, which proved that this method could not only reflect the infrared camouflage effectiveness of a target in the corresponding background actually but also help us differentiate the camouflage quality of different materials quantitatively. This method should be of importance for us to evaluate the infrared camouflage effectiveness of a target more quickly and objectively with the help of computers, instead of human observations.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xiaopeng Cheng, Dapeng Zhao, Zhijie Yu, Jinhua Zhang, and Dabin Yu "Computer-aided infrared camouflage effectiveness evaluation method based on image saliency", Proc. SPIE 10964, Tenth International Conference on Information Optics and Photonics, 109644G (15 November 2018); https://doi.org/10.1117/12.2506095
PROCEEDINGS
10 PAGES


SHARE
Advertisement
Advertisement
Back to Top