Lianru Gao

Chinese Academy of Sciences, Peping, Beijing, China

Are you Lianru Gao?

Claim your profile

Publications (44)41.04 Total impact

  • Lianru Gao, Bin Yang, Qian Du, Bing Zhang
    Remote Sensing 06/2015; 7(6):6611-6634. DOI:10.3390/rs70606611
  • [Show abstract] [Hide abstract]
    ABSTRACT: Hyperspectral image classification has been a very active area of research in recent years. It faces challenges related with the high dimensionality of the data and the limited availability of training samples. In order to address these issues, subspace-based approaches have been developed to reduce the dimensionality of the input space in order to better exploit the (limited) training samples available. An example of this strategy is a recently developed subspace-projection-based multinomial logistic regression technique able to characterize mixed pixels, which are also an important concern in the analysis of hyperspectral data. In this letter, we extend the subspace-projection-based concept to support vector machines (SVMs), a very popular technique for remote sensing image classification. For that purpose, we construct the SVM nonlinear functions using the subspaces associated to each class. The resulting approach, called SVM $sub$, is experimentally validated using a real hyperspectral data set collected using the National Aeronautics and Space Administration's Airborne Visible/Infrared Imaging Spectrometer. The obtained results indicate that the proposed algorithm exhibits good performance in the presence of very limited training samples.
    IEEE Geoscience and Remote Sensing Letters 02/2015; 12(2):349-353. DOI:10.1109/LGRS.2014.2341044
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 01/2015; DOI:10.1109/JSTARS.2015.2388797
  • Journal of Applied Remote Sensing 01/2015; 9(1):097295. DOI:10.1117/1.JRS.9.097295
  • [Show abstract] [Hide abstract]
    ABSTRACT: A new hyperspectral unmixing algorithm is proposed based on the normal compositional model (NCM) to estimate the endmembers and abundance parameters jointly in this paper. The NCM considers the hyperspectral imaging as a stochastic process and interprets each pixel value as a random vector, which is linearly mixed by the endmembers. More precisely, these endmembers are also treated as random variables as opposed to deterministic values in order to capture spectral variability that is not well described by the linear mixing model (LMM). However, the higher complexity of such an unmixing model leads to more difficulty in parameter estimation. A particle swarm optimization-expectation maximization (PSO-EM) algorithm, a “winner-take-all” version of the EM, is proposed to solve the parameter estimation problem, which employs a partial E step. The main contribution of the proposed PSO-EM is making optimum use of particle swarm optimization method (PSO) in the partial E step, which solves the difficulty of the integrals in the NCM model. The performance of the proposed methodology is evaluated through synthetic and real data experiments. Our obtained results demonstrate the superior performance of PSO-EM compared to other NCM-based as well as LMM-based methods.
    IEEE Transactions on Geoscience and Remote Sensing 12/2014; 52(12):7782-7792. DOI:10.1109/TGRS.2014.2319337
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes an edge-constrained Markov random field (EC-MRF) method for accurate land cover classification over urban areas using hyperspectral image and LiDAR data. EC-MRF adopts a probabilistic support vector machine for pixel-wise classification of hyperspectral and LiDAR data, while MRF performs as a postprocessing regularizer for spatial smoothness. LiDAR data improve both pixel-wise classification and postprocessing result during an EC-MRF procedure. A variable weighting coefficient, constrained by a combined edge extracted from both hyperspectral and LiDAR data, is introduced for the MRF regularizer to avoid oversmoothness and to preserve class boundaries. The EC-MRF approach is evaluated using synthetic and real data, and results indicate that it is more effective than four similar advanced methods for the classification of hyperspectral and LiDAR data. (C) 2014 Society of Photo-Optical Instrumentation Engineers (SPIE)
    Journal of Applied Remote Sensing 10/2014; 8. DOI:10.1117/1.JRS.8.085089
  • [Show abstract] [Hide abstract]
    ABSTRACT: Anomaly detection is an active topic in hyperspectral imaging, with many practical applications. Reed-Xiaoli detector (RXD), a widely used method for anomaly detection, uses the covariance matrix and mean vector to represent background signals, assuming that the background information adjusts to a multivariate normal distribution. However, in general, real images present very complex backgrounds. As a result, in many situations, the background information cannot be properly modeled. An important reason is that that background samples often contain also anomalous pixels and noise, which lead to a high false alarm rate. Therefore, the characterization of the background is essential for successful anomaly detection. In this paper, we develop two novel approaches: weighted-RXD (W-RXD) and linear filter-based RXD (LF-RXD) aimed at improving background in RXD-based anomaly detection. By reducing the weight of the anomalous pixels or noise signals and increasing the weight of the background samples, W-RXD can provide better estimations of the background information. In turn, LF-RXD uses the probability of each pixel as background to filter wrong anomalous or noisy instances. Our experimental results, intended to analyze the performance of the newly developed anomaly detectors, indicate that the proposed approaches achieve good performance when compared with other classic approaches for anomaly detection in the literature.
    IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 06/2014; 7(6):2351-2366. DOI:10.1109/JSTARS.2014.2302446
  • [Show abstract] [Hide abstract]
    ABSTRACT: Image simulation of remote sensing systems is important for the development of new instruments and validations of data processing algorithms. In image simulation process, surface scene simulation is a fundamental issue and usually has the first priority. For two mid-infrared absorption bands near 2.7 µm and 4.3 µm, although there are a lot of applications in remote sensing field, relevant research on surface scene simulation is very limited. In these two mid-infrared ranges, surface radiance is a combination of reflected and emitted radiance. However, the radiance is generally reduced because of strong absorption by atmosphere. Therefore, analysis of surface reflected radiance is essential for simulation work. In this paper, we use a radiative transfer model MODTRAN to simulate proportions of surface reflected radiance for common ground materials under various observation conditions. The obtained results show that proportions of studied materials are 0.8%–99.8% in the band of 2.63–2.83 µm and 1.1%–94.8% in the band of 4.2–4.5 µm. The proportions of surface reflected radiance in both absorption bands are affected by surface reflectivity. In addition, in the band of 2.7 µm the proportion of surface reflected radiance is sensitive to solar geometry, water vapor content and surface temperature, whereas it is insensitive in the band of 4.3 µm. Based on these results, we conduct that both reflection and emission are important for surface scene simulations in the 2.7 µm and 4.3 µm absorption bands.
    IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 06/2014; 7(6):2639-2646. DOI:10.1109/JSTARS.2013.2272633
  • Journal of Applied Remote Sensing 01/2014; 8(1):085094. DOI:10.1117/1.JRS.8.085094
  • Journal of Applied Remote Sensing 01/2014; 8(1):084797. DOI:10.1117/1.JRS.8.084797
  • [Show abstract] [Hide abstract]
    ABSTRACT: Pixel clustering is a common hyperspectral image processing technique. Its process is to find the appropriate cluster centers and assign each pixel to a center according to a certain metric. Artificial Bee Colony (ABC) algorithm based pattern clustering is proved to have better performance than traditional clustering methods such as K-means. Therefore, studies on hyperspectral image clustering method based on ABC algorithm are done. The target function and feasible solution space are determined, and the complete process is given. The proposed algorithm and other algorithms are compared and analyzed with the use of two sets of real hyperspectral remote sensing data and ground survey results.
    2013 Sixth International Conference on Advanced Computational Intelligence (ICACI); 10/2013
  • [Show abstract] [Hide abstract]
    ABSTRACT: Optical remotely sensed data, especially hyperspectral data have emerged as the most useful data source for regional crop classification. Hyperspectral data contain fine spectra, however, their spatial coverage are narrow. Multispectral data may not realize unique identification of crop endmembers because of coarse spectral resolution, but they do provide broad spatial coverage. This paper proposed a method of multisensor analysis to fully make use of the virtues from both data and to improve multispectral classification with the multispectral signatures convert from hyperspectral signatures in overlap regions. Full-scene crop mapping using multispectral data was implemented by the multispectral signatures and SVM classification. The accuracy assessment showed the proposed classification method is promising.
    SPIE Defense, Security, and Sensing; 05/2013
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This letter presents a new technique for clustering hyperspectral images that exploits neighborhood-constrained spatial information. The main feature of the proposed method is the introduction of a neighborhood homogeneity index (NHI) and the use of this index to measure the spatial homogeneity in a local area. A new similarity measurement integrates NHI and spectral information using an adaptive distance norm for clustering. The performance of the proposed neighborhood-constrained-clustering algorithm was assessed through a synthetic image and a real hyperspectral image and compared with those obtained by advanced spectral-spatial clustering algorithms. Experimental results show that the proposed scheme gives better performances.
    IEEE Geoscience and Remote Sensing Letters 05/2013; 10(3):588-592. DOI:10.1109/LGRS.2012.2215005
  • Bing Zhang, Jianwei Gao, Lianru Gao, Xu Sun
    [Show abstract] [Hide abstract]
    ABSTRACT: Endmember extraction is a vital step in spectral unmixing of hyperspectral images. The Ant Colony Optimization (ACO) algorithm has been recently developed for endmember extraction from hyperspectral data. However, this algorithm may result in a local optimal solution for some hyperspectral images without prescient information, and also has limitation in computational performance. Therefore, in this paper, we proposed several new methods to improve the ACO algorithm for endmember extraction (ACOEE). Firstly, the heuristic information was optimized to improve the algorithm accuracy. In the improved ACOEE, only the pheromones were adopted as the heuristic information when there was no prescient information about hyperspectral data. Then, to enhance algorithm performance, an elitist strategy was proposed to lessen the iteration numbers without reducing the accuracy, and the parallel implementation of ACOEE on graphics processing units (GPUs) also was utilized to shorten the computational time per iteration. The experiment for real hyperspectral data demonstrated that both the endmember extraction accuracy and the computational performance of ACOEE benefited from these methods.
    IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 04/2013; 6(2):522-530. DOI:10.1109/JSTARS.2012.2236821
  • [Show abstract] [Hide abstract]
    ABSTRACT: In the traditional signal model, signal is assumed to be deterministic, and noise is assumed to be random, additive and uncorrelated to the signal component. A hyperspectral image has high spatial and spectral correlation, and a pixel can be well predicted using its spatial and/or spectral neighbors; any prediction error can be considered from noise. Using this concept, several algorithms have been developed for noise estimation for hyperspectral images. However, these algorithms have not been rigorously analyzed with a unified scheme. In this paper, we conduct a comparative study for such linear regression-based algorithms using simulated images with different signal-to-noise ratio (SNR) and real images with different land cover types. Based on experimental results, instructive guidance is concluded for their practical applications.
    IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 04/2013; 6(2):488-498. DOI:10.1109/JSTARS.2012.2227245
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In classifying very high spatial resolution (VHR) hyperspectral imagery, intra-class variation often adversely affects classification accuracy, mainly due to a low signal-to-noise ratio (SNR) and high spatial heterogeneity. To address this problem, this article develops a neighbourhood-constrained k-means (NC-k-means) algorithm by incorporating the pure neighbourhood index into the traditional k-means algorithm. The performance of the NC-k-means algorithm was assessed through a series of simulated images and a real hyperspectral image. The results indicate that the classification accuracy of NC-k-means algorithm is consistently better than that of the traditional k-means algorithm, in particular for the images with significant spatial autocorrelations among neighbouring pixels.
    Remote Sensing Letters 02/2013; 4(2). DOI:10.1080/2150704X.2012.713139
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The important techniques in processing hyperspectral data acquired by interference imaging spectrometer onboard Small Satellite Constellation for Environment and Disaster mitigation (HJ-1A) are studied in this article. First, a new noise estimation method, named residual-scaled local standard deviations, is used to analyze the noise condition of HJ-1A hyperspectral images. Then, an optimized maximum noise fraction (OMNF) transform is proposed for dimensionality reduction of HJ-1A images, which adopts an accurately estimated noise covariance matrix for noise whitening. The proposed OMNF method is less sensitive to noise distribution and interference existence, thus it can more efficiently compact useful data information in a low-dimensional space. The proposed OMNF is evaluated through two applications, i.e., spectral unmixing and classification, using the HJ-1A image acquired at the Bohai Sea area in China. It demonstrates that the proposed OMNF provides better performance in comparison with other traditional dimensionality reduction methods.
    Journal on Advances in Signal Processing 01/2013; 2013(1). DOI:10.1186/1687-6180-2013-65
  • Lianru Gao, Qian Du, Wei Yang, Bing Zhang
    [Show abstract] [Hide abstract]
    ABSTRACT: In the traditional signal model, signal is assumed to be deterministic, and noise is assumed to be random, additive and uncorrelated to the signal component. A hyperspectral image has high spatial and spectral correlation, and a pixel can be well predicted using its spatial and/or spectral neighbors; any prediction error can be considered from noise. Using this concept, several algorithms have been developed for noise estimation for hyperspectral images. However, these algorithms have not been rigorously analyzed with a unified scheme. In this paper, we conduct a comparative study for these algorithms using real images with different land cover types. Based on experimental results, instructive guidance is concluded for their practical applications.
    2012 4th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS); 06/2012
  • [Show abstract] [Hide abstract]
    ABSTRACT: Military target detection is an important application of hyperspectral remote sensing. It highly demands real-time or near real-time processing. However, the massive amount of hyperspectral image data seriously limits the processing speed. Real-time image processing based on hardware platform, such as digital signal processor (DSP), is one of recent developments in hyperspectral target detection. In hyperspectral target detection algorithms, correlation matrix or covariance matrix calculation is always used to whiten data, which is a very time-consuming process. In this paper, a strategy named spatial-spectral information extraction (SSIE) is presented to accelerate the speed of hyperspectral image processing. The strategy is composed of bands selection and sample covariance matrix estimation. Bands selection fully utilizes the high-spectral correlation in spectral image, while sample covariance matrix estimation fully utilizes the high-spatial correlation in remote sensing image. Meanwhile, this strategy is implemented on the hardware platform of DSP. The hardware implementation of constrained energy minimization (CEM) algorithm is composed of hardware architecture and software architecture. The hardware architecture contains chips and peripheral interfaces, and software architecture establishes a data transferring model to accomplish the communication between DSP and PC. In experiments, the performance on software of ENVI with that on hardware of DSP is compared. Results show that the processing speed and recognition result on DSP are better than those on ENVI. Detection results demonstrate that the strategy implemented by DSP is sufficient to enable near real-time supervised target detection.
    SPIE Defense, Security, and Sensing; 05/2012
  • [Show abstract] [Hide abstract]
    ABSTRACT: Target detection is an important research content in hyperspectral remote sensing technology, which is widely used in securities and defenses. Nowadays, many target detection algorithm have been proposed. One of the key evaluation indicators of these algorithms performance is false-alarm rate. The feature-level fusion of different target detection results is a simple and effective method to reduce false-alarm rate. But the different value ranges of different algorithms bring difficulties for data fusion. This paper proposed a feature-level fusion method based on RXD detector, which is to integrate multiple target detection results into a multi-bands image, and fuse detection results using principal theory of abnormal detection. Experiments revealed that, this method is not restricted by the quantity of target detection algorithms and not influenced by different value ranges of different algorithms, which can reduce false-alarm rate effectively.
    Proceedings of SPIE - The International Society for Optical Engineering 05/2012; DOI:10.1117/12.918794

Publication Stats

115 Citations
41.04 Total Impact Points

Institutions

  • 2007–2014
    • Chinese Academy of Sciences
      • • Institute of Remote Sensing and Digital Earth
      • • Center for Earth Observation and Digital Earth
      • • Institute of Remote Sensing Applications
      Peping, Beijing, China
  • 2012
    • Center for Earth Observation and Digital Earth (CEODE)
      Peping, Beijing, China