Automatic expansion extraction algorithm of remote sensing images
Li XUE1,2, Shuwen YANG1,2(), Jijing MA1,2, Xin JIA1,2, Ruliu YAN1,2
1.Faculty of Geomatics, Lanzhou Jiaotong University, Lanzhou 730070, China 2.Gansu Provincial Engineering Laboratory for National Geographic State Monitoring, Lanzhou 730070, China
To tackle the incomplete extraction problem faced by most remote sensing images shadow extraction algorithms for extracting shadow,this paper purposes an automatic expansion extraction algorithm of remote sensing images shadow. Firstly, based on the characteristics that there is a peak of the rate of change of pixel values at the shadow boundary of the near infrared band and the rate of change of pixel values is stable inside the shadow, the authors established the criteria of shadow boundary judgment to determine whether the pixel is located in the shadow boundary. Second, on the basis of initial shadow extraction, each shadow is expanded by the criterion from the inside outward, which not only can take into account a single shadow area, but also is no longer confined to the global image features or local features of remote sensing images, so that shadow is extracted more completely. Experimental results show that the algorithm can effectively improve the accuracy and efficiency of shadow extraction.
Finlayson G D, Hordley S D, Drew M S. Removing shadows from images using retinex [C]//Proceeding of the 10th Color Image Conference.Scottsclale:CIC, 2002: 823-836.
[2]
Irvir R B, Mckeown D M . Methods for exploiting the relationship between buildings and their shadows in aerial imagery[J]. IEEE Transaction on Systems:Man and Cybernetics, 1989,19(16):1564-1575.
doi: 10.1117/12.952691
[3]
Mamassian P, Knill D C, Kersten D . The perception of cast shadows[J]. Trends in Cognitive Sciences, 1998,2(8):288-295.
doi: 10.1016/S1364-6613(98)01204-2
pmid: 21227211
[4]
Etemadnia H, Alsha RIF M R.Automatic image shadow identification using LPF in homomorphic processing system [C]//Proceedings of VII Digital Image Computing: Techniques and Applications.Sydney:Committee of DICTA, 2003.
Yao H Q, Yang S W, Liu Z J , et al. A method of shadow detection for city tall ground objects based on QuickBird images[J]. Remote Sensing for Land and Resources, 2015,27(2):51-55.doi: 10.6046/gtyyg.2015.02.08.
Guo J H, Tian Q J, Wu Y Z . Study on multispectral detecting shadow areas and a theoretical model of removing shadows from remote sensing images[J]. Journal of Remote Sensing, 2006,10(2):151-159.
Yu D F, Yin J P, Zhang G M . An automatic shadow detection method for remote sensing images based on gray histogram[J]. Computer Engineering and Science, 2008,30(12):43-44,93.
[9]
韩青松 . 基于Otsu算法的遥感图像阈值分割[D]. 新疆:新疆大学, 2011.
Han Q S . Remote Sensing Image Thresholding Segmentation Based on the Otsu Algorithm[D]. Xinjiong:Xinjiang University, 2011.
Gao X J, Wan Y C, Zheng S Y , et al. Automatic shadow detection and compensation of aerial remote sensing images[J]. Geomatics and Information Science of Wuhan University, 2012,37(11):1299-1302.
Li Y K, Yang S W, Liu T . An automatic threshold selection approach for remote sensing imagery of multimodal histograms[J]. Journal of Lanzhou Jiaotong University, 2013,32(6):199-204.
Zhao X F, Hu X W, Zhao X . A method of remote sensing images shadow detection based on color models[J].Bulletin of Surveying and Mapping, 2014(5):20-22,59.
Wei M L, Zhan Z Q . An improved method of automatic shadow detection for aerial remote sensing images[J].Bulletin of Surveying and Mapping, 2016(6):14-17.
Yang M, Yang S W, Yong W L , et al. Multi-scale shadow segmentation method based on characteristic component[J]. Remote Sensing Information, 2017,32(1):109-114.
Chi Y F, Lai R W, Yan Q , et al. Detection and extraction of mountain shadow information from Landsat8 OLI data[J]. Mountain Research, 2017,35(4):580-589.