Fast processing method of high resolution remote sensing image based on decision tree classification
DOI: 10.23977/aeroe.2020.010101 | Downloads: 2 | Views: 69
Haitao Yang 1, Jinyu Wang 1, Bin Su 1,2
1 School of Space Information, Space Engineering University, Beijing, 101416, China
2 Troop 32022 of PLA, Wuhan, 430074, China
Corresponding AuthorBin Su
In order to accurately distinguish the information of the nodes to be identified in remote sensing images and generate a global image processing strategy, a fast processing method for high-resolution remote sensing images based on decision tree classification is proposed. According to the classification principle of decision tree organization, the image data is preprocessed to complete the UAV remote sensing image coordination and registration, and the remote sensing image edge detection based on decision tree classification method is realized. On this basis, the convolution neural network is established, and the regularized constraint processing results are obtained by predicting the image scale. The fast processing method of high-resolution remote sensing image based on decision tree classification is successfully applied. The experimental results show that, compared with the traditional feature point matching principle, the average detection accuracy of the fast processing method is higher, and the node parameter matching accuracy is higher, which meets the practical application requirements of accurate resolution of the information to be identified in remote sensing images.
KEYWORDSDecision tree classification; Remote sensing image; Fast processing; Convolution neural network; Image scale; Node information; Feature point matching; Detection accuracy
CITE THIS PAPER
Haitao Yang, Jinyu Wang, Bin Su, Fast processing method of high resolution remote sensing image based on decision tree classification. Aerospace and Electronics (2020) 1: 1-11. DOI: http://dx.doi.org/10.23977/aeroe.2020.010101.
 Yan Hongjie, Xiao Junbing, Song Yanpo, et al. Cold model on bubble growth and detachment in bottom blowing process[J]. Transactions of Nonferrous Metals Society of China, 2019, 29(001):213-221.
 Wang Liguo, Zhao Liang, Liu Danfeng. A review on the application of SVM in hyperspectral image processing[J]. Journal of Harbin Engineering University, 2018, v.39；No.260(06):23-33.
 Huang Wei, Xiang Wei, Wang Jinge, et al. Development and application of digital image processing technology based soil tensile apparatus[J]. Rock and Soil Mechanics, 2018, 39(009):3486-3494.
 Sun Jianping, Liang Yi, Jiang Zhilin, et al. Application and Prospect of Performance Evaluation for Bamboo-wood Composite Materials Based on Image Processing Technology[J]. Journal of Northwest Forestry University, 2019, 34(02):252-255+262.
 Peng Yanbo, Chen Genyu, Zhou Cong, et al. Algorithm and Implementation of Laser Tangential Shaping Grinding Wheel System Based on Image Processing[J]. Applied Laser, 2018, v.38(03):138-144.
 Liu Jun, Li Wei, Wu Mengting, et al. Skyline Detection Algorithm Based on Multiple Feature Extraction Fusing Edge Correction[J]. Computer Engineering and Applications, 2019, 55(06):192-196.
 WANG Qi, LIU Sheng-wei, ZHU De-cheng, et al. Total Hip Replacement Aided Diagnosis Algorithm Based on CT Image [J]. Science Technology and Engineering, 2019, 019(001):183-189.
 Xia Xingyu, Gao Hao, Wang Chuangye. Multi-level Image Segmentation Based on an Improved Particle Swarm Optimization with an Equilibrium Strategy[J]. Journal of Zhengzhou University(Engineering Science) , 2018, 39(01):63-70.
 Yu Ping, Hao Chengcheng. Foggy Image Enhancement by Combined Fractional Differential and Multi-Scale Retinex[J]. Laser & Optoelectronics Progress, 2018, 055(001):274-279.
 Zhou Xianchun, Wu Ting, Shi Lanfang, et al. A Kind of Wavelet Transform Image Denoising Method Based on Curvature Variation Regularization[J]. Acta Electronica Sinica, 2018, 46(003):621-628.