Prof. Jun Li Profile

Prof. Jun Li

at China University of Geoscience

SPIE Involvement:

Author | Editor

SPIE Journal Paper | 3 September 2021

Change prediction and modeling of dynamic mangrove ecosystem using remotely sensed hyperspectral image data

Dipanwita Ghosh, Somdatta Chakravortty, Antonio Plaza Miguel, Jun Li

JARS, Vol. 15, Issue 04, 042606, (September 2021) https://doi.org/10.1117/12.10.1117/1.JRS.15.042606

KEYWORDS: Ecosystems, Data modeling, Hyperspectral imaging, Data acquisition, Atmospheric modeling, Atmospheric corrections, Sensors, Machine learning, Biological research, Reflectivity

Read Abstract +

SPIE Journal Paper | 1 September 2021

Lithological mapping using EO-1 Hyperion hyperspectral data and semisupervised self-learning method

Xiaoye Guo, Peijun Li, Jun Li

JARS, Vol. 15, Issue 03, 032209, (September 2021) https://doi.org/10.1117/12.10.1117/1.JRS.15.032209

KEYWORDS: Solid state lighting, Associative arrays, Lithium, Statistical analysis, Hyperspectral imaging, Image classification, Remote sensing, Atmospheric corrections, Spatial resolution, Reliability

Read Abstract +

SPIE Journal Paper | 17 November 2016

Improved discrete swarm intelligence algorithms for endmember extraction from hyperspectral remote sensing images

Yuanchao Su, Xu Sun, Lianru Gao, Jun Li, Bing Zhang

JARS, Vol. 10, Issue 04, 045018, (November 2016) https://doi.org/10.1117/12.10.1117/1.JRS.10.045018

KEYWORDS: Lithium, Hyperspectral imaging, Optimization (mathematics), Remote sensing, Detection and tracking algorithms, Evolutionary algorithms, Computer simulations, Signal to noise ratio, Particle swarm optimization, Sun

Read Abstract +

Proceedings Article | 24 October 2016 Presentation + Paper

A new semi-supervised classification strategy combining active learning and spectral unmixing of hyperspectral data

Yanli Sun, Xia Zhang, Antonio Plaza, Jun Li, Inmaculada Dópido, Yi Liu

Proceedings Volume 10007, 1000708 (2016) https://doi.org/10.1117/12.2241635

KEYWORDS: Hyperspectral imaging, Image classification, Remote sensing, Analytical research, Image analysis, Statistical analysis, Visible radiation, Data communications, Sun, Lithium

Read Abstract +

Hyperspectral remote sensing allows for the detailed analysis of the surface of the Earth by providing high-dimensional images with hundreds of spectral bands. Hyperspectral image classification plays a significant role in hyperspectral image analysis and has been a very active research area in the last few years. In the context of hyperspectral image classification, supervised techniques (which have achieved wide acceptance) must address a difficult task due to the unbalance between the high dimensionality of the data and the limited availability of labeled training samples in real analysis scenarios. While the collection of labeled samples is generally difficult, expensive, and time-consuming, unlabeled samples can be generated in a much easier way. Semi-supervised learning offers an effective solution that can take advantage of both unlabeled and a small amount of labeled samples. Spectral unmixing is another widely used technique in hyperspectral image analysis, developed to retrieve pure spectral components and determine their abundance fractions in mixed pixels. In this work, we propose a method to perform semi-supervised hyperspectral image classification by combining the information retrieved with spectral unmixing and classification. Two kinds of samples that are highly mixed in nature are automatically selected, aiming at finding the most informative unlabeled samples. One kind is given by the samples minimizing the distance between the first two most probable classes by calculating the difference between the two highest abundances. Another kind is given by the samples minimizing the distance between the most probable class and the least probable class, obtained by calculating the difference between the highest and lowest abundances. The effectiveness of the proposed method is evaluated using a real hyperspectral data set collected by the airborne visible infrared imaging spectrometer (AVIRIS) over the Indian Pines region in Northwestern Indiana. In the paper, techniques for efficient implementation of the considered technique in high performance computing architectures are also discussed.

Proceedings Article | 24 October 2016 Presentation + Paper

A new tool for supervised classification of satellite images available on web servers: Google Maps as a case study

Agustín García-Flores, Abel Paz-Gallardo, Antonio Plaza, Jun Li

Proceedings Volume 10007, 1000702 (2016) https://doi.org/10.1117/12.2240088

KEYWORDS: Image classification, Satellite imaging, Earth observing sensors, Satellites, Graphics processing units, Human-machine interfaces, Algorithm development, Image processing, Interfaces, Lithium

Read Abstract +

Proceedings Article | 24 October 2016 Presentation + Paper

Spatial-spectral preprocessing for endmember extraction on GPU's

Luis Jimenez, Javier Plaza, Antonio Plaza, Jun Li

Proceedings Volume 10007, 100070K (2016) https://doi.org/10.1117/12.2241288

KEYWORDS: Hyperspectral imaging, Algorithm development, Graphics processing units, Principal component analysis, Calcite, Image processing, Minerals, Lithium, Remote sensing, Optimization (mathematics)

Read Abstract +

Spectral unmixing is focused in the identification of spectrally pure signatures, called endmembers, and their corresponding abundances in each pixel of a hyperspectral image. Mainly focused on the spectral information contained in the hyperspectral images, endmember extraction techniques have recently included spatial information to achieve more accurate results. Several algorithms have been developed for automatic or semi-automatic identification of endmembers using spatial and spectral information, including the spectral-spatial endmember extraction (SSEE) where, within a preprocessing step in the technique, both sources of information are extracted from the hyperspectral image and equally used for this purpose. Previous works have implemented the SSEE technique in four main steps: 1) local eigenvectors calculation in each sub-region in which the original hyperspectral image is divided; 2) computation of the maxima and minima projection of all eigenvectors over the entire hyperspectral image in order to obtain a candidates pixels set; 3) expansion and averaging of the signatures of the candidate set; 4) ranking based on the spectral angle distance (SAD). The result of this method is a list of candidate signatures from which the endmembers can be extracted using various spectral-based techniques, such as orthogonal subspace projection (OSP), vertex component analysis (VCA) or N-FINDR. Considering the large volume of data and the complexity of the calculations, there is a need for efficient implementations. Latest- generation hardware accelerators such as commodity graphics processing units (GPUs) offer a good chance for improving the computational performance in this context. In this paper, we develop two different implementations of the SSEE algorithm using GPUs. Both are based on the eigenvectors computation within each sub-region of the first step, one using the singular value decomposition (SVD) and another one using principal component analysis (PCA). Based on our experiments with hyperspectral data sets, high computational performance is observed in both cases.

Proceedings Article | 24 October 2016 Presentation + Paper

A multiple criteria-based spectral partitioning method for remotely sensed hyperspectral image classification

Yi Liu, Jun Li, Antonio Plaza, Yanli Sun

Proceedings Volume 10007, 100070C (2016) https://doi.org/10.1117/12.2241299

KEYWORDS: Image classification, Hyperspectral imaging, Remote sensing, Feature extraction, Imaging systems, Spectroscopy, Surface plasmons, Scene classification, Principal component analysis, Signal to noise ratio

Read Abstract +

Hyperspectral remote sensing offers a powerful tool in many different application contexts. The imbalance between the high dimensionality of the data and the limited availability of training samples calls for the need to perform dimensionality reduction in practice. Among traditional dimensionality reduction techniques, feature extraction is one of the most widely used approaches due to its flexibility to transform the original spectral information into a subspace. In turn, band selection is important when the application requires preserving the original spectral information (especially the physically meaningful information) for the interpretation of the hyperspectral scene. In the case of hyperspectral image classification, both techniques need to discard most of the original features/bands in order to perform the classification using a feature set with much lower dimensionality. However, the discriminative information that allows a classifier to provide good performance is usually classdependent and the relevant information may live in weak features/bands that are usually discarded or lost through subspace transformation or band selection. As a result, in practice, it is challenging to use either feature extraction or band selection for classification purposes. Relevant lines of attack to address this problem have focused on multiple feature selection aiming at a suitable fusion of diverse features in order to provide relevant information to the classifier. In this paper, we present a new dimensionality reduction technique, called multiple criteria-based spectral partitioning, which is embedded in an ensemble learning framework to perform advanced hyperspectral image classification. Driven by the use of a multiple band priority criteria that is derived from classic band selection techniques, we obtain multiple spectral partitions from the original hyperspectral data that correspond to several band subgroups with much lower spectral dimensionality as compared with the original band set. An ensemble learning technique is then used to fuse the information from multiple features, taking advantage of the relevant information provided by each classifier. Our experimental results with two real hyperspectral images, collected by the reflective optics system imaging spectrometer (ROSIS) over the University of Pavia in Italy and the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) over the Salinas scene, reveal that our presented method, driven by multiple band priority criteria, is able to obtain better classification results compared with classic band selection techniques. This paper also discusses several possibilities for computationally efficient implementation of the proposed technique using various high-performance computing architectures.

SPIE Journal Paper | 30 October 2015

Hyperspectral image clustering method based on artificial bee colony algorithm and Markov random fields

Xu Sun, Lina Yang, Lianru Gao, Bing Zhang, Shanshan Li, Jun Li

JARS, Vol. 9, Issue 01, 095047, (October 2015) https://doi.org/10.1117/12.10.1117/1.JRS.9.095047

KEYWORDS: Composites, Hyperspectral imaging, Magnetorheological finishing, Optimization (mathematics), Signal to noise ratio, Computer simulations, Hyperspectral simulation, Image classification, Mathematical modeling, Remote sensing

Read Abstract +

SPIE Journal Paper | 30 March 2015

Graphics processing unit–accelerated computation of the Markov random fields and loopy belief propagation algorithms for hyperspectral image classification

Yuanfeng Wu, Jun Li, Lianru Gao, Xuemin Tan, Bing Zhang

JARS, Vol. 9, Issue 01, 097295, (March 2015) https://doi.org/10.1117/12.10.1117/1.JRS.9.097295

KEYWORDS: Hyperspectral imaging, Image classification, Graphics processing units, Spectroscopy, Image processing, Linear algebra, Imaging systems, Optimization (mathematics), Data modeling, Library classification systems

Read Abstract +

We propose a commodity graphics processing units (GPUs)–based massively parallel efficient computation for spectral-spatial classification of hyperspectral images. The spectral-spatial classification framework is based on the marginal probability distribution which uses all of the information in the hyperspectral data. In this framework, first, the posterior class probability is modeled with discriminative random field in which the association potential is linked with a multinomial logistic regression (MLR) classifier and the interaction potential modeling the spatial information is linked to a Markov random field multilevel logistic (MLL) prior. Second, the maximizers of the posterior marginals are computed via the loopy belief propagation (LBP) method. In addition, the regressors of the multinominal logistic regression classifier are inferred by the logistic regression via variable splitting and augmented Lagrangian (LORSAL) algorithm. Although the spectral-spatial classification framework exhibited state-of-the-art accuracy performance with regard to similar approaches, its computational complexity is very high. We take advantage of the massively parallel computing capability of NVIDIA Tesla C2075 with the compute unified device architecture including a set of GPU-accelerated linear algebra libraries (CULA) to dramatically improve the computation speed of this hyperspectral image classification framework. The shared memory and the asynchronous transfer techniques are also used for further computationally efficient optimization. Real hyperspectral data sets collected by the National Aeronautics and Space Administration’s airborne visible infrared imaging spectrometer and the reflective optics system imaging spectrometer system are used for effectiveness evaluation. The results show that we achieved a speedup of 92-fold on LORSAL, 69-fold on MLR, 127-fold on MLL, 160-fold on LBP, and 73-fold on the whole spectral-spatial classification framework as compared with its single-core central processing unit counterpart, respectively.

SPIE Journal Paper | 3 November 2014

Probabilistic anomaly detector for remotely sensed hyperspectral data

Lianru Gao, Qiandong Guo, Antonio Plaza, Jun Li, Bing Zhang

JARS, Vol. 8, Issue 01, 083538, (November 2014) https://doi.org/10.1117/12.10.1117/1.JRS.8.083538

KEYWORDS: Target detection, Sensors, Detection and tracking algorithms, Remote sensing, Statistical analysis, Hyperspectral target detection, Hyperspectral imaging, Algorithm development, Signal detection, Data centers

Read Abstract +

SPIE Journal Paper | 17 October 2014

Edge-constrained Markov random field classification by integrating hyperspectral image with LiDAR data over urban areas

Li Ni, Lianru Gao, Shanshan Li, Jun Li, Bing Zhang

JARS, Vol. 8, Issue 01, 085089, (October 2014) https://doi.org/10.1117/12.10.1117/1.JRS.8.085089

KEYWORDS: LIDAR, Image classification, Magnetorheological finishing, Hyperspectral imaging, Fusion energy, Data modeling, Roads, Data acquisition, Image fusion, Lithium

Read Abstract +

SPIE Journal Paper | 13 August 2014

Real-time implementation of optimized maximum noise fraction transform for feature extraction of hyperspectral images

Yuanfeng Wu, Lianru Gao, Bing Zhang, Haina Zhao, Jun Li

JARS, Vol. 8, Issue 01, 084797, (August 2014) https://doi.org/10.1117/12.10.1117/1.JRS.8.084797

KEYWORDS: Hyperspectral imaging, Feature extraction, Data transmission, Principal component analysis, Signal to noise ratio, Interference (communication), 3D modeling, Graphics processing units, Image classification, Computer architecture

Read Abstract +

Proceedings Article | 25 February 2005 Paper

Approach for counting vehicles in congested traffic flow

Xiaojun Tan, Jun Li, Wei Liu

Proceedings Volume 5671, (2005) https://doi.org/10.1117/12.585794

KEYWORDS: Video, Detection and tracking algorithms, Cameras, Inspection, Image segmentation, Roads, Filtering (signal processing), Feature extraction, Intelligence systems, Sensors

Read Abstract +