2017

• Record 241 of
  
  Title:Interface modification based ultrashort laser microwelding between SiC and fused silica
  
  Author(s):Zhang, Guodong(1,2); Bai, Jing(1); Zhao, Wei(1); Zhou, Kaiming(1); Cheng, Guanghua(1)
  Source: Optics Express  Volume: 25  Issue: 3  DOI: 10.1364/OE.25.001702  Published: February 6, 2017  
  Abstract:It is a big challenge to weld two materials with large differences in coefficients of thermal expansion and melting points. Here we report that the welding between fused silica (softening point, 1720°C) and SiC wafer (melting point, 3100°C) is achieved with a near infrared femtosecond laser at 800 nm. Elements are observed to have a spatial distribution gradient within the cross section of welding line, revealing that mixing and inter-diffusion of substances have occurred during laser irradiation. This is attributed to the femtosecond laser induced local phase transition and volume expansion. Through optimizing the welding parameters, pulse energy and interval of the welding lines, a shear joining strength as high as 15.1 MPa is achieved. In addition, the influence mechanism of the laser ablation on welding quality of the sample without pre-optical contact is carefully studied by measuring the laser induced interface modification. © 2017 Optical Society of America.
  Accession Number: 20170603335953
• Record 242 of
  
  Title:Realization and testing of a deployable space telescope based on tape springs
  
  Author(s):Lei, Wang(1,2); Li, Chuang(1); Zhong, Peifeng(1); Chong, Yaqin(1); Jing, Nan(1)
  Source: Proceedings of SPIE - The International Society for Optical Engineering  Volume: 10339  Issue:   DOI: 10.1117/12.2269968  Published: 2017  
  Abstract:For its compact size and light weight, space telescope with deployable support structure for its secondary mirror is very suitable as an optical payload for a nanosatellite or a cubesat. Firstly the realization of a prototype deployable space telescope based on tape springs is introduced in this paper. The deployable telescope is composed of primary mirror assembly, secondary mirror assembly, 6 foldable tape springs to support the secondary mirror assembly, deployable baffle, aft optic components, and a set of lock-released devices based on shape memory alloy, etc. Then the deployment errors of the secondary mirror are measured with three-coordinate measuring machine to examine the alignment accuracy between the primary mirror and the deployed secondary mirror. Finally modal identification is completed for the telescope in deployment state to investigate its dynamic behavior with impact hammer testing. The results of the experimental modal identification agree with those from finite element analysis well. © 2017 SPIE.
  Accession Number: 20173904206130
• Record 243 of
  
  Title:Remote sensing scene classification by unsupervised representation learning
  
  Author(s):Lu, Xiaoqiang(1); Zheng, Xiangtao(1); Yuan, Yuan(1)
  Source: IEEE Transactions on Geoscience and Remote Sensing  Volume: 55  Issue: 9  DOI: 10.1109/TGRS.2017.2702596  Published: September 2017  
  Abstract:With the rapid development of the satellite sensor technology, high spatial resolution remote sensing (HSR) data have attracted extensive attention in military and civilian applications. In order to make full use of these data, remote sensing scene classification becomes an important and necessary precedent task. In this paper, an unsupervised representation learning method is proposed to investigate deconvolution networks for remote sensing scene classification. First, a shallow weighted deconvolution network is utilized to learn a set of feature maps and filters for each image by minimizing the reconstruction error between the input image and the convolution result. The learned feature maps can capture the abundant edge and texture information of high spatial resolution images, which is definitely important for remote sensing images. After that, the spatial pyramid model (SPM) is used to aggregate features at different scales to maintain the spatial layout of HSR image scene. A discriminative representation for HSR image is obtained by combining the proposed weighted deconvolution model and SPM. Finally, the representation vector is input into a support vector machine to finish classification. We apply our method on two challenging HSR image data sets: the UCMerced data set with 21 scene categories and the Sydney data set with seven land-use categories. All the experimental results achieved by the proposed method outperform most state of the arts, which demonstrates the effectiveness of the proposed method. © 1980-2012 IEEE.
  Accession Number: 20173904199634
• Record 244 of
  
  Title:Dimensionality Reduction by Spatial-Spectral Preservation in Selected Bands
  
  Author(s):Zheng, Xiangtao(1); Yuan, Yuan(1); Lu, Xiaoqiang(1)
  Source: IEEE Transactions on Geoscience and Remote Sensing  Volume: 55  Issue: 9  DOI: 10.1109/TGRS.2017.2703598  Published: September 2017  
  Abstract:Dimensionality reduction (DR) has attracted extensive attention since it provides discriminative information of hyperspectral images (HSI) and reduces the computational burden. Though DR has gained rapid development in recent years, it is difficult to achieve higher classification accuracy while preserving the relevant original information of the spectral bands. To relieve this limitation, in this paper, a different DR framework is proposed to perform feature extraction on the selected bands. The proposed method uses determinantal point process to select the representative bands and to preserve the relevant original information of the spectral bands. The performance of classification is further improved by performing multiple Laplacian eigenmaps (LEs) on the selected bands. Different from the traditional LEs, multiple Laplacian matrices in this paper are defined by encoding spatial-spectral proximity on each band. A common low-dimensional representation is generated to capture the joint manifold structure from multiple Laplacian matrices. Experimental results on three real-world HSIs demonstrate that the proposed framework can lead to a significant advancement in HSI classification compared with the state-of-the-art methods. © 2017 IEEE.
  Accession Number: 20172703894546
• Record 245 of
  
  Title:Remote Sensing Image Scene Classification: Benchmark and State of the Art
  
  Author(s):Cheng, Gong(1); Han, Junwei(1); Lu, Xiaoqiang(2)
  Source: Proceedings of the IEEE  Volume: 105  Issue: 10  DOI: 10.1109/JPROC.2017.2675998  Published: October 2017  
  Abstract:Remote sensing image scene classification plays an important role in a wide range of applications and hence has been receiving remarkable attention. During the past years, significant efforts have been made to develop various data sets or present a variety of approaches for scene classification from remote sensing images. However, a systematic review of the literature concerning data sets and methods for scene classification is still lacking. In addition, almost all existing data sets have a number of limitations, including the small scale of scene classes and the image numbers, the lack of image variations and diversity, and the saturation of accuracy. These limitations severely limit the development of new approaches especially deep learning-based methods. This paper first provides a comprehensive review of the recent progress. Then, we propose a large-scale data set, termed 'NWPU-RESISC45,' which is a publicly available benchmark for REmote Sensing Image Scene Classification (RESISC), created by Northwestern Polytechnical University (NWPU). This data set contains 31 500 images, covering 45 scene classes with 700 images in each class. The proposed NWPU-RESISC45 1) is large-scale on the scene classes and the total image number; 2) holds big variations in translation, spatial resolution, viewpoint, object pose, illumination, background, and occlusion; and 3) has high within-class diversity and between-class similarity. The creation of this data set will enable the community to develop and evaluate various data-driven algorithms. Finally, several representative methods are evaluated using the proposed data set, and the results are reported as a useful baseline for future research. © 1963-2012 IEEE.
  Accession Number: 20171503555015
• Record 246 of
  
  Title:Remote sensing image scene classification: Benchmark and state of the art
  
  Author(s):Cheng, Gong(1); Han, Junwei(1); Lu, Xiaoqiang(2)
  Source: arXiv  Volume:   Issue:   DOI:   Published: February 28, 2017  
  Abstract:Remote sensing image scene classification plays an important role in a wide range of applications and hence has been receiving remarkable attention. During the past years, significant efforts have been made to develop various datasets or present a variety of approaches for scene classification from remote sensing images. However, a systematic review of the literature concerning datasets and methods for scene classification is still lacking. In addition, almost all existing datasets have a number of limitations, including the small scale of scene classes and the image numbers, the lack of image variations and diversity, and the saturation of accuracy. These limitations severely limit the development of new approaches especially deep learning-based methods. This paper first provides a comprehensive review of the recent progress. Then, we propose a large-scale dataset, termed "NWPU-RESISC45", which is a publicly available benchmark for REmote Sensing Image Scene Classification (RESISC), created by Northwestern Polytechnical University (NWPU). This dataset contains 31,500 images, covering 45 scene classes with 700 images in each class. The proposed NWPU-RESISC45 (i) is large-scale on the scene classes and the total image number, (ii) holds big variations in translation, spatial resolution, viewpoint, object pose, illumination, background, and occlusion, and (iii) has high within-class diversity and between-class similarity. The creation of this dataset will enable the community to develop and evaluate various data-driven algorithms. Finally, several representative methods are evaluated using the proposed dataset and the results are reported as a useful baseline for future research. Copyright © 2017, The Authors. All rights reserved.
  Accession Number: 20200177870
• Record 247 of
  
  Title:Latent semantic concept regularized model for blind image deconvolution
  
  Author(s):Ye, Renzhen(1,2); Li, Xuelong(1)
  Source: Neurocomputing  Volume: 257  Issue:   DOI: 10.1016/j.neucom.2016.11.064  Published: September 27, 2017  
  Abstract:Blind image deconvolution refers to the recovery of a sharp image when the degradation processing is unknown. Many existing methods have the problem that they are designed to exploit low level image descriptors (e.g. image pixels or image gradient) only, rather than high-level latent semantic concepts, thus there is no guarantee of human visual perception. To address this problem, in this paper, a latent semantic concept regularized (LSCR) method is proposed to reduce the blind deconvolution problem at a semantic level. The proposed method explores the relationship between different image descriptors and exploits sparse measure to favor sharp images over blurry images. And matrix factorization is introduced to learn the latent concepts from the image descriptors. Then, the image prior can be described and constrained by the learned latent semantic concepts of image descriptors using a much more effective convolution matrix. In this case, the blind deconvolution problem can be regularized and the sharp version of the blurry image can be recovered at a new latent semantic level. Furthermore, an iterative algorithm is exploited to derive optimal solution. The proposed model is evaluated on two different datasets, including simulation dataset and real dataset, and state-of-the-art performance is achieved compared with other methods. © 2017 Elsevier B.V.
  Accession Number: 20170803359894
• Record 248 of
  
  Title:Bilateral K - Means algorithm for fast co-clustering
  
  Author(s):Han, Junwei(1); Song, Kun(1); Nie, Feiping(1,2); Li, Xuelong(3)
  Source: 31st AAAI Conference on Artificial Intelligence, AAAI 2017  Volume:   Issue:   DOI:   Published: 2017  
  Abstract:With the development of the information technology, the amount of data, e.g. text, image and video, has been increased rapidly. Efficiently clustering those large scale data sets is a challenge. To address this problem, this paper proposes a novel co-clustering method named bilateral k-means algorithm (BKM) for fast co-clustering. Different from traditional k-means algorithms, the proposed method has two indicator matrices P and Q and a diagonal matrix S to be solved, which represent the cluster memberships of samples and features, and the co-cluster centres, respectively. Therefore, it could implement different clustering tasks on the samples and features simultaneously. We also introduce an effective approach to solve the proposed method, which involves less multiplication. The computational complexity is analyzed. Extensive experiments on various types of data sets are conducted. Compared with the state-of-the-art clustering methods, the proposed BKM not only has faster computational speed, but also achieves promising clustering results. Copyright © 2017, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
  Accession Number: 20174104242952
• Record 249 of
  
  Title:Parameter free large margin nearest neighbor for distance metric learning
  
  Author(s):Song, Kun(1); Nie, Feiping(2); Han, Junwei(1); Li, Xuelong(3)
  Source: 31st AAAI Conference on Artificial Intelligence, AAAI 2017  Volume:   Issue:   DOI:   Published: 2017  
  Abstract:We introduce a novel supervised metric learning algorithm named parameter free large margin nearest neighbor (PFLMNN) which can be seen as an improvement of the classical large margin nearest neighbor (LMNN) algorithm. The contributions of our work consist of two aspects. First, our method discards the cost term which shrinks the distances between inquiry input and its k target neighbors (the k nearest neighbors with same labels as inquiry input) in LMNN, and only focuses on improving the action to push the imposters (the samples with different labels form the inquiry input) apart out of the neighborhood of inquiry. As a result, our method does not have the parameter needed to tune on the validating set, which makes it more convenient to use. Second, by leveraging the geometry information of the imposters, we construct a novel cost function to penalize the small distances between each inquiry and its imposters. Different from LMNN considering every imposter located in the neighborhood of each inquiry, our method only takes care of the nearest imposters. Because when the nearest imposter is pushed out of the neighborhood of its inquiry, other imposters would be all out. In this way, the constraints in our model are much less than that of LMNN, which makes our method much easier to find the optimal distance metric. Consequently, our method not only learns a better distance metric than LMNN, but also runs faster than LMNN. Extensive experiments on different data sets with various sizes and difficulties are conducted, and the results have shown that, compared with LMNN, PFLMNN achieves better classification results. Copyright © 2017, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
  Accession Number: 20174104242953
• Record 250 of
  
  Title:Large aperture lidar receiver optical system based on diffractive primary lens
  
  Author(s):Zhu, Jinyi(1,2); Xie, Yongjun(1)
  Source: Hongwai yu Jiguang Gongcheng/Infrared and Laser Engineering  Volume: 46  Issue: 5  DOI: 10.3788/IRLA201746.0518001  Published: May 25, 2017  
  Abstract:Diffractive optical systems are promising in large aperture lidar receiver applications. The negative dispersion effect on lidar image quality caused by the diffractive primary lens was analyzed. Two chromatic aberration correcting methods, inserting high dispersion glass and adopting Schupmann theory, were discussed. An achromatic system based on Schupmann theory was lightweight, and provided perfect image quality. And the system light transmittance was over 60%. A design of lidar receiver optical system with 1m aperture and 1 mrad max FOV was demonstrated, and the system f/# was 8. The image quality attained diffraction limit approximately. © 2017, Editorial Board of Journal of Infrared and Laser Engineering. All right reserved.
  Accession Number: 20173304042248
• Record 251 of
  
  Title:A novel strategy to prepare 2D g-C3N4nanosheets and their photoelectrochemical properties
  
  Author(s):Miao, Hui(1,2,3); Zhang, Guowei(1); Hu, Xiaoyun(1,3); Mu, Jianglong(1); Han, Tongxin(1); Fan, Jun(4); Zhu, Changjun(6); Song, Lixun(6); Bai, Jintao(1,3); Hou, Xun(2,3,5)
  Source: Journal of Alloys and Compounds  Volume: 690  Issue:   DOI: 10.1016/j.jallcom.2016.08.184  Published: 2017  
  Abstract:Herein, 2D g-C3N4nanosheets was successfully prepared by two processes: acid treatment and liquid exfoliation. The thickness of the nanosheets was nearly 4.545 nm containing ∼13 C-N layers. The acid treatment process before liquid exfoliation for bulk g-C3N4could effectively destroy the in-plane periodicity of the aromatic systems and made the bulk easily exfoliated. This work carefully discussed the acid treatment effect for bulk by XRD patterns, nitrogen adsorption-desorption isotherm, FT-IR spectra, and UV–vis–NIR absorption spectra. Moreover, the nanosheets was fabricated and transferred onto FTO substrates by vacuum filtration self-assembled method to carefully investigate their optical, electrical, and photoelectrochemical properties. The thin film filtrated by 2 ml g-C3N4nanosheets supernatant showed the best photocurrent response nearly 0.5 μA/cm2and the lowest resistance of charge transfer (Rct) at the interface between FTO and electrolyte. The photocurrent response could be further effectively improved from nearly 0.5 to 1.8 μA/cm2by the integration of CNTs to promote charge separation and transfer. Thus, the easy, safe, and indirect synthesis of 2D g-C3N4-based nanosheets thin films opens new possibilities for the fabrication of many energy-related devices. © 2016 Elsevier B.V.
  Accession Number: 20163502755891
• Record 252 of
  
  Title:Latent Semantic Minimal Hashing for Image Retrieval
  
  Author(s):Lu, Xiaoqiang(1); Zheng, Xiangtao(1); Li, Xuelong(1)
  Source: IEEE Transactions on Image Processing  Volume: 26  Issue: 1  DOI: 10.1109/TIP.2016.2627801  Published: January 2017  
  Abstract:Hashing-based similarity search is an important technique for large-scale query-by-example image retrieval system, since it provides fast search with computation and memory efficiency. However, it is a challenge work to design compact codes to represent original features with good performance. Recently, a lot of unsupervised hashing methods have been proposed to focus on preserving geometric structure similarity of the data in the original feature space, but they have not yet fully refined image features and explored the latent semantic feature embedding in the data simultaneously. To address the problem, in this paper, a novel joint binary codes learning method is proposed to combine image feature to latent semantic feature with minimum encoding loss, which is referred as latent semantic minimal hashing. The latent semantic feature is learned based on matrix decomposition to refine original feature, thereby it makes the learned feature more discriminative. Moreover, a minimum encoding loss is combined with latent semantic feature learning process simultaneously, so as to guarantee the obtained binary codes are discriminative as well. Extensive experiments on several well-known large databases demonstrate that the proposed method outperforms most state-of-the-art hashing methods. © 1992-2012 IEEE.
  Accession Number: 20170803379991