Mingyi He received BEng. and MEng. from Northwestern Polytechnical University (NPU) in 1982 and 1985, respectively, and Ph.D. from Xidian University, China, in 1994.
Dr He has been with the School of Electronics and Information, NPU, where he is currently the Leading Professor for NPU signal and information processing. He is the Founder and Director of Shaanxi Key Laboratory of Information Acquisition and Processing and the Director and Chief Scientist of the Center for Earth Observation Research. He was a visiting professor with the University of Adelaide and the University of Sydney, Australia. He conducted a number of national projects and international joint research projects or joint graduate programs (such as 863 HiTech programs and NSFC key project in China; Rockwell International Collins project in USA, joint education programs and research with the University of Adelaide and NPU, and international R&D Center with MENSI, France). He has published more than 300 papers in the IEEE Trans. Pattern Analysis and Machine Intelligence, Geoscience and Remote Sensing, International Journal of Computer Vision, Signal Processing, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), ICIP, IGARSS, ChinaSIP, ICIEA, etc. He is the author or coauthor of five books (including Digital Image Processing: Science Press, 2008 and Neural Network and Signal Processing Systems: NPU Press, 1998), etc. He has made valuable contributions to hyperspectral image processing, computer vision and image processing, neural networks and intelligent information processing with notable applications to X-ray image processing for luggage inspection, laser-finder test system for airborne systems, and hyperspectral image processing applications etc.
Prof. He has been a member of the Advisor Committee of China National Council for Higher Education on Electronics and Information, a member of the Chinese lunar exploration expert group, the vice-director of Spectral Imaging Earth Observation Committee of China Committee of International Digital Earth Society, the vice-president of Space Remote Sensing Society in Chinese Society of Astronautics (CSA), and the vice-chairman of the Institution of Engineering and Technology (IET) at Xi’an Network, the vice-president and SIP committee chairman of Shaanxi Institute of Electronics. He has served in a number international conferences (such as, general co-chair of IEEE ICIEA’09, co-chair of the ICIEA’13 TPC, general chair of IEEE SPS sponsored ChinaSIP 2014). He was the recipient of the IEEE CVPR 2012 Best Paper Award and is recognized as the ‘2012 Chinese Scientist of the Year’ and was awarded 10 scientific prizes from China and the governmental lifelong subsidy for outstanding contribution to higher education and scientific research by the State Council of China since 1993.
Signal and Information Processing in Hyperspectral Imaging Remote Sensing
Hyperspectral imaging (HSI), also known as imaging spectroscopy, is concerned with the measurement, processing, analysis, and interpretation of spectra acquired from a given scene (or specific objects) at spectral resolution of about 1 to10 nm in the visible to near-inferred wavelength range mainly by an air-borne or satellite-borne HSI sensor (hyperspectral scanner), that contains the objects and their background’s spectral data. In recent years, as evolutional development of remote sensing, HSI remote sensing (HSIRS, or HRS: hyperspectral remote sensing) has become a core area within the remote sensing community and has attracted great increasing attention and contributions from wide communities[1-6], such as signal and information processing[6,7], electronic and optical imaging, sensors and automation[1], automatical target recognition (ATR), computer vision and pattern recognition, machine learning, communication, and computer application etc. With HSI data, we can detect and recognize difficult targets appearing at pixel or subpixel level, classify targets with greatly improved accuracy, analyze and identify combined or mixed objects in a pixel. There are great advances in HRS in recent years[1-7], which has resulted in an enormous number of applications, such as airborne and satellite-borne observation of earth (including surveillance, reconnaissance, environment monitoring, land-cover mapping or land-change detection, mineral identification, and camouflage detection, etc.). HSI is also a key technique for planetary exploration, astrophysics, precision remote sensing, medical detection, food inspection and forensics.
The signal and information processing for HSIRS contains, Preprocessing (including data calibration, correction, enhancement, fusion, compression, etc.), Signal representation, Feature mining, Classification/Recognition, Unmixing analysis, Fast computation, etc. and the features and classifiers are two main issues for hyperspectral imaging remote sensing applications. In this talk, the signal and information processing for HRS will be briefly addressed with emphasis on feature mining techniques[6-14]. Hyperspectral data is typically composed of hundred spectral measurements for each spatial element of an imaged scene. They form the original set of features. From these features, many new features, such as transformed features, weighted features, derivative features, and spatial texture features, can be formed. The feature mining of HSI remote sensing images for target detection, recognition and classification are divided into multi-pixels, single pixel and sub-pixel levels, which are more natural for target size scale and sensor’s spatial resolution and easier for analysis of feature acquisition techniques. Differing from the traditional frame of only feature selection and feature extraction, a unified frame for the feature mining of HSI remote sensing is summed up as (1) Feature selection which maintains the sensor’s physical meaning; (2) Feature extraction which comprehensively utilizes all the sensed data; and (3) Feature mixing which takes into account of all mixing information over a pixel covering multi small size (sub-pixel) targets. Demonstrated results with several methods for feature mining of real HSIRS data are shown to compare the performances. Moreover, the hot topics in signal and information processing for HSIRS is also outlined. Especially, a framework to integrate spectral, spatial and temporal information by using hyperspectral imaging sensors, video cameras, multiview cameras[15] for more complicated target detection problems will be suggested, which is expected to insight into more valuable research and potential new applications in the area.
References:
[1].
Jensen J, Trew R, Woolard
D, et al. Editorial Special Issue on Enhancement Algorithms, Methodologies
and Technology for Spectral Sensing.
IEEE J
Sensors,
10(3), 2010.
[2].
Chanussot J, Crawford M, Kuo B. Foreword to the Special Issue on
Hyperspectral Image and Signal Processing.
IEEE Trans. Geosci. and Remote Sens.,
48(11), 2010
[3].
Camps-Valls G, Benediktsson J, Bruzzone L,
et al. Introduction to the Issue on Advances in Remote Sensing Image
Processing. IEEE JSTARS,
5(3), 2011
[4].
Plaza A, Du Q, Bioucas-Dias J,
et al. Foreword to the Special Issue on Spectral Unmixing of Remotely Sensed
Data.
IEEE Trans. Geosci. and Remote Sens., 49(11), 2011
[5].
Benediktsson
J,
Chanussot
J,
Moon
W.
Advances in Very-High-Resolution Remote Sensing.
The Proceedings of
IEEE,101(3),
2013
[6].
Ma
W;
Bioucas-Dias
J,
Chanussot
J,
Gade
P, Special Issue on Signal and
Image Processing in Hyperspectral Remote Sensing,
IEEE Signal Process Magazine. Jan. 2014
[7].
He M.
Advances
in Signal and Image Processing for Hyperspectral Remote Sensing (Invited
talk),
ICIEA2007, Harbin, China. May 2007
[8].
Jia X and He M. Feature Mining for Hyperspectral Data. Invited Tutorial at
IEEE GRSS
4th
Workshop on Hyperspectral Image and Signal Processing,
Shanghai, China, June
2012
[9].
Jia X and He M. Feature Mining for Hyperspectral Data. Invited Tutorial at
IEEE GRSS
5th
Workshop on Hyperspectral Image and Signal Processing,
Gainesville,
Florida, USA,
June 2013
[10].
He M, Chang W and Mei S. Advance in Feature Mining from Hyperspectral Remote
Sensing Data.
Spacecraft Recovery & Remote Sens.,
34(1), 2013
[11].
Huang R, He M. Band Selection
Based
on Feature Weighting for Classification of Hyperspectral Data.
IEEE GSRSL, 2(2), 2005
[12].
Xia J, He M. Feature Extraction in Kernel Space Using Bhattacharyya Distance
as Criterion Function. Chinese J
Computers, 27(5), 2004
[13].
Mei S, He M,
et al. Spatial Purity Based Endmember
Extraction for Spectral Mixture Analysis.
IEEE Trans. Geosci. and Remote Sens.,
48(9), 2010
[14].
Mei S, He M,
et al. Improving Spatial-Spectral Endmember
Extraction in the Presence of Anomalous Ground Objects.
IEEE Trans. Geosci. and Remote Sens.,
49(11), 2011
[15].
Dai Y, Li H and He M. Projective Multiview Structure and
Motion from Element-Wise Factorization.
IEEE TPAMI,
35(9), 2013