Affiliation:
1. PLA Rocket Force University of Engineering
Abstract
Abstract
Hyperspectral images have a special attribute with both spectral and spatial information, which is of great significance for the evaluation of the stealth performance of camouflaged targets. Aiming at the problems of a single evaluation index and the low credibility of traditional optical camouflage evaluation methods, this paper proposes a grayscale clustering camouflage-effect evaluation method based on multifeature descriptions of hyperspectral images using similarity indicators that reflect different spectral characteristics of the target and background. The improved Delphi method, which is used to construct weights, better simulates the decision-making process of experts, which gives more intuitive and detailed evaluation indicators reflecting the “pros and cons” of the camouflage effect if the clustering characteristics of the grayscale evaluation method are combined. At the same time, by introducing the whitening weight function and the evaluation grade, the camouflage ability of the camouflage net under different backgrounds is analyzed quantitatively and qualitatively.
Publisher
Research Square Platform LLC
Reference18 articles.
1. Hyperspectral image classification method based on cnn architecture embedding with hashing semantic feature;Yu C;IEEE J. Sel. Top. Appl. Earth Observations Remote Sens.,2019
2. Advances in hyperspectral image and signal processing: A comprehensive overview of the state of the art;Ghamisi P;IEEE Geoscience and Remote Sensing Magazine,2017
3. Capsule networks for hyperspectral image classification;Paoletti ME;IEEE Trans. Geosci. Remote Sens.,2019
4. Evaluation of camouflage effectiveness using hyperspectral images;Zavvartorbati A;J. Appl. Remote Sens.,2017
5. M. Kastek, T. Piatkowski, R. Dulski, M. Chamberland, V. Farley, “Multispectral and hyperspectral measurements of soldier’s camouflage equipment,” Proceedings of SPIE - The International Society for Optical Engineering, vol. 8382, p. 83820K, 2012