HJ-1A Hyper-spectral Remote Sensing Alteration Information Extraction and Analysis

Compared with the traditional geological survey and prospecting mapping, hyper-spectral geological mapping costs low, low consumption, therefore, the selection of hyper-spectral remote sensing data is the potential prospects of innovative traditional survey methods. The study field of Xiemisitai Mountain east section of west Junggar Basin northwest is main objection. Using geological data and hyper-spectral remote sensing alteration information extraction technology researching as a starting point, through field measurements of the spectral characteristics of alteration minerals analysis, combined with China's environmental mitigation satellite (hereinafter referred to as the HJ-1-A) HSI image to extract the iron ore alteration of the study area. Introduction In this study, HSI images of HJ-1-A satellite were pre-processed by geometric correction, radiation enhancement, FLASH correction and image cropping. The fieldwork and sampling points were designed and 124 sampling points were located in 3 sections. A total of 313 alluvial samples of rock and mineral samples were collected. The weathering and fresh surfaces of the rock samples were respectively subjected to field spectroscopy, indoor control spectroscopy, and mineral element testing and microscopic observation of the sample flakes. The results of spectral reflectance comparison of weathered surface and fresh surface show that the weathering effect has little effect on the spectral characteristics of rock minerals and only affects the reflectivity of the rock minerals [1-3]. The correlation between mineral elements and mineral components and the spectral characteristics. The relationship was analyzed and the spectral characteristics and spectral indices of different samples were extracted to provide data for extracting alteration information from hyper-spectral data [4]. Spectral Feature Recognition of Alternated Minerals According to the study of geological data and sampling conditions, there are more than ten kinds of altered minerals in its spectral characteristics. The standard spectral curves of these altered minerals are then extracted from the USGS spectral database, as shown in Figure 1. Based on the analysis of the spectral curves of these altered minerals and related references, the central wavelengths of the characteristic spectra of these altered minerals in the 350-2500 nm band are extracted as shown in Table 1. Observation of Figure 1, the various types of altered minerals spectral characteristics from the morphological differences, the difference in reflectance is also very obvious, most of the minerals in the 0.9-1.8 m band within the range of good distinction, rock mineral samples within this range of several iron-containing altered minerals that have definite spectral characteristics at 0.42-0.95 μm.

[1]  Xing Zhao,et al.  Spectral–Spatial Classification of Hyperspectral Data Based on Deep Belief Network , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[2]  Seungmin Rho,et al.  Face hallucination and recognition in social network services , 2015, The Journal of Supercomputing.

[3]  Trac D. Tran,et al.  Hyperspectral Image Classification Using Dictionary-Based Sparse Representation , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[4]  Jhing-Fa Wang,et al.  Structuralized context-aware content and scalable resolution support for wireless VoD services , 2009, IEEE Transactions on Consumer Electronics.

[5]  J. Chanussot,et al.  Hyperspectral Remote Sensing Data Analysis and Future Challenges , 2013, IEEE Geoscience and Remote Sensing Magazine.

[6]  Jhing-Fa Wang,et al.  Smart Homecare Surveillance System: Behavior Identification Based on State-Transition Support Vector Machines and Sound Directivity Pattern Analysis , 2013, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[7]  Feng Jiang,et al.  Viewpoint-independent hand gesture recognition with Kinect , 2014 .

[8]  Chong-Yung Chi,et al.  Convex geometry based outlier-insensitive estimation of number of endmembers in hyperspectral images , 2013, 2013 5th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS).

[9]  Heng Li,et al.  Hyperspectral image supervised classification via multi-view nuclear norm based 2D PCA feature extraction and kernel ELM , 2016, 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[10]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[11]  Wen Ji,et al.  Intelligent Marketing in Smart Cities: Crowdsourced Data for Geo-Conquesting , 2016, IT Professional.