2014

• Record 1 of
  
  Title:Schlieren confocal microscopy for phase-relief imaging
  
  Author(s):Xie, Hao(1,2); Jin, Dayong(3); Yu, Junjie(4); Peng, Tong(1,5); Ding, Yichen(1); Zhou, Changhe(4); Xi, Peng(1)
  Source: Optics Letters  Volume: 39  Issue: 5  DOI: 10.1364/OL.39.001238  Published: March 1, 2014  
  Abstract:We demonstrate a simple phase-sensitive microscopic technique capable of imaging the phase gradient of a transparent specimen, based on the Schlieren modulation and confocal laser scanning microscopy (CLSM). The incident laser is refracted by the phase gradient of the specimen and excites a fluorescence plate behind the specimen to create a secondary illumination; then the fluoresence is modulated by a partial obstructor before entering the confocal pinhole. The quantitative relationship between the image intensity and the sample phase gradient can be derived. This setup is very easy to be adapted to current confocal setups, so that multimodality fluorescence/structure images can be obtained within a single system. © 2014 Optical Society of America.
  Accession Number: 20141517549115
• Record 2 of
  
  Title:Hyperspectral biological images compression based on multiway tensor projection
  
  Author(s):Du, Bo(1); Zhang, Mengfei(1); Zhang, Lefei(1); Li, Xuelong(2)
  Source: Proceedings - IEEE International Conference on Multimedia and Expo  Volume: 2014-September  Issue: Septmber  DOI: 10.1109/ICME.2014.6890252  Published: September 3, 2014  
  Abstract:Since the hyperspectral images (HSI) could provide much more useful discriminative information that cannot be obtained by the conventional imaging techniques, the hyper-spectral imaging technology was widely used in remote sensing area and recently used in many other aspects, such as the biological images recognition. However, most of the time, the size of hyperspectral data is so large that to process these data is both time-consuming and space-consuming. In this paper, a multiway tensor projection (MTP) algorithm is proposed as an extension to the conventional PCA for hyperspectral data compression and reconstruction. Technologically speaking, MTP carries out a tensor data compression in all the modes simultaneously to seek a projection matrix along each order to make sure that the projected core tensor can preserve most of the information present in the original tensor. Since the MTP algorithm uses the arbitrary order tensor as the input, it can preserve the structure information not only among the rows and columns but also among the spectral channels as much as possible and without vectorization. Numerous experiments on hyperspectral biological databases show that the MTP algorithm has better compression performance than PCA in many aspects. © 2014 IEEE.
  Accession Number: 20153001066554
• Record 3 of
  
  Title:An improved stereo match algorithm based on support-weight approach
  
  Author(s):Long, Ren(1); Lei, Yang(1); Xiao-Dong, Zhao(1,2); Zuo-Feng, Zhou(1); Guang-Sen, Liu(1); Fei, Jiaqi(1)
  Source: Proceedings - 2014 4th International Conference on Instrumentation and Measurement, Computer, Communication and Control, IMCCC 2014  Volume:   Issue:   DOI: 10.1109/IMCCC.2014.203  Published: December 22, 2014  
  Abstract:Local stereo matching methods are still used widely because they are fast and simple. But the accuracy of local methods is much poorer than the global methods. They usually achieve accuracy at the expense of speed. Simple local methods are fast, but exhibit systematic errors. In this paper we propose an improved method based on support-weight approach, which can enhance the matching efficiency and accuracy. By utilizing a adaptive support-window which will change the size of the window relying on different area, we use a new disparity cost volume function which is much more simple than the traditional one. From the experimental result, we can see the accuracy of the disparity map is as better as the traditional one while the computational time is reduced. The proposed method includes three procedures, At first, we need to confirm the pixels 'window size in order to calculate the disparity, secondly, the adaptive support-weight of each pixel in left image will be calculated, the final step is to select the most optimal disparity in the right image. After the three steps, we can get the best matching point in the right image which is corresponding to the right image. © 2014 IEEE.
  Accession Number: 20150500470170
• Record 4 of
  
  Title:Optical Bloch oscillations of an Airy beam in a photonic lattice with a linear transverse index gradient
  
  Author(s):Xiao, Fajun(1); Li, Baoran(1); Wang, Meirong(1); Zhu, Weiren(2); Zhang, Peng(1,3); Liu, Sheng(1); Premaratne, Malin(2); Zhao, Jianlin(1)
  Source: Optics Express  Volume: 22  Issue: 19  DOI: 10.1364/OE.22.022763  Published: September 22, 2014  
  Abstract:We theoretically report the existence of optical Bloch oscillations (BO) of an Airy beam in a one-dimensional optically induced photonic lattice with a linear transverse index gradient. The Airy beam experiencing optical BO shows a more robust non-diffracting feature than its counterparts in free space or in a uniform photonic lattice. Interestingly, a periodical recurrence of Airy shape accompanied with constant alternation of its acceleration direction is also found during the BO. Furthermore, we demonstrate that the period and amplitude of BO of an Airy beam can be readily controlled over a wide range by varying the index gradient and/or the lattice period. Exploiting these features, we propose a scheme to rout an Airy beam to a predefined output channel without losing its characteristics by longitudinally modulating the transverse index gradient. © 2014 Optical Society of America.
  Accession Number: 20144100091706
• Record 5 of
  
  Title:Action recognition based on semantic feature description and cross classification
  
  Author(s):Zhao, Yang(1,3); Wang, Qi(2); Yuan, Yuan(1)
  Source: 2014 IEEE China Summit and International Conference on Signal and Information Processing, IEEE ChinaSIP 2014 - Proceedings  Volume:   Issue:   DOI: 10.1109/ChinaSIP.2014.6889319  Published: September 3, 2014  
  Abstract:Action recognition is a challenging topic in computer vision. In this work, we present a novel method for action recognition which is based on two claimed contributions: semantic feature description and cross classification. The designed descriptor is combined by several local 3D-SIFT and is informative and distinctive, reflecting the spatiooral clues of the video. The cross classification effectively combines the feature localization and action categorization together. The proposed method is justified on a popular dateset named UCF50 and the experimental results demonstrate that our method outperforms the state-of-the-art competitors. © 2014 IEEE.
  Accession Number: 20152100870644
• Record 6 of
  
  Title:Video quality assessment via supervised topic model
  
  Author(s):Guo, Qun(1,2); Lu, Xiaoqiang(1); Yuan, Yuan(1)
  Source: 2014 IEEE China Summit and International Conference on Signal and Information Processing, IEEE ChinaSIP 2014 - Proceedings  Volume:   Issue:   DOI: 10.1109/ChinaSIP.2014.6889321  Published: September 3, 2014  
  Abstract:Video quality assessment (VQA) plays a very important role in many video processing and communication systems. Since video signals are ultimately delivered to human observers, an accurate objective video quality metric should agree well with judgment of human visual system (HVS). In this paper, a novel full-reference VQA scheme is developed to measure the perceived video quality in both local and global aspects. First, to account for the crucial impact of motion on perception, effective quality features are extracted from the local spatiooral volumes which are generated around the motion trajectories in the video. Second, a statistical model is utilized to discover the latent relation between local quality and global perceived quality. Experimental results on LIVE database demonstrate promising performance of the proposed metric in comparison with state-of-the-art VQA metrics. © 2014 IEEE.
  Accession Number: 20152100870583
• Record 7 of
  
  Title:Adaptive road detection towards multiscale-multilevel probabilistic analysis
  
  Author(s):Jiang, Zhiyu(1,3); Wang, Qi(2); Yuan, Yuan(1)
  Source: 2014 IEEE China Summit and International Conference on Signal and Information Processing, IEEE ChinaSIP 2014 - Proceedings  Volume:   Issue:   DOI: 10.1109/ChinaSIP.2014.6889334  Published: September 3, 2014  
  Abstract:Vision-based road detection is a challenging problem because of the changeable shape and varying illumination. Though many efforts have been spent on this topic, the achieved performance is far from satisfactory. To this end, this paper formulates a Bayesian method which simultaneously explores the multiscale-multilevel clues that are considered to be complementary. Two contributions are claimed in this proposed method. 1) By computing the prior distribution in superpixellevel with a novel Laplacian Sparse Subspace Clustering and observation likelihood in pixel-level with statistical color similarity, the posterior probability of road region can be effectively inferred. 2) To ensure the adaptivity of road model in various conditions, a multiscale strategy is presented to fuse the detection results of different scales. Experimental results on several challenging video sequences verify the superiority of the proposed method compared with several popular ones. © 2014 IEEE.
  Accession Number: 20152100870571
• Record 8 of
  
  Title:Pylon line spatial correlation assisted transmission line detection
  
  Author(s):Zhang, Jun(1); Shan, Haotian(1); Cao, Xianbin(1); Yan, Pingkun(2); Li, Xuelong(2)
  Source: IEEE Transactions on Aerospace and Electronic Systems  Volume: 50  Issue: 4  DOI: 10.1109/TAES.2014.120732  Published: October 1, 2014  
  Abstract:A transmission line is one of the most hazardous objects to low altitude flying aircraft. Due to its extremely tiny size and unsalient visual features, transmission line detection (TLD) is a well-recognized problem. In this paper, a novel TLD method is proposed with the assistance of the spatial correlation between pylon and line for TLD. First, a unidirectional spatial mapping is built up to describe the pylon line spatial correlation. Then, the proposed pylon line spatial correlation and other line features are integrated into a Bayesian framework, which is trained in advance and used to estimate the probability of one line segment belonging to a transmission line. Compared with three other line-based TLD methods, the experimental results demonstrate that the proposed method can obtain better detection performance with higher detection rates and much lower false alarm rates. Poles and towers, Power transmission lines, Correlation, Image segmentation, Feature extraction, Silicon, Bayes methods © 2014 IEEE.
  Accession Number: 20145200373641
• Record 9 of
  
  Title:A comprehensive survey to face hallucination
  
  Author(s):Wang, Nannan(1); Tao, Dacheng(2); Gao, Xinbo(1); Li, Xuelong(3); Li, Jie(1)
  Source: International Journal of Computer Vision  Volume: 106  Issue: 1  DOI: 10.1007/s11263-013-0645-9  Published: January 2014  
  Abstract:This paper comprehensively surveys the development of face hallucination (FH), including both face super-resolution and face sketch-photo synthesis techniques. Indeed, these two techniques share the same objective of inferring a target face image (e.g. high-resolution face image, face sketch and face photo) from a corresponding source input (e.g. low-resolution face image, face photo and face sketch). Considering the critical role of image interpretation in modern intelligent systems for authentication, surveillance, law enforcement, security control, and entertainment, FH has attracted growing attention in recent years. Existing FH methods can be grouped into four categories: Bayesian inference approaches, subspace learning approaches, a combination of Bayesian inference and subspace learning approaches, and sparse representation-based approaches. In spite of achieving a certain level of development, FH is limited in its success by complex application conditions such as variant illuminations, poses, or views. This paper provides a holistic understanding and deep insight into FH, and presents a comparative analysis of representative methods and promising future directions. © 2013 Springer Science+Business Media New York.
  Accession Number: 20140617268778
• Record 10 of
  
  Title:Realistic action recognition via sparsely-constructed Gaussian processes
  
  Author(s):Liu, Li(1,2); Shao, Ling(1,2); Zheng, Feng(2); Li, Xuelong(3)
  Source: Pattern Recognition  Volume: 47  Issue: 12  DOI: 10.1016/j.patcog.2014.07.006  Published: December 1, 2014  
  Abstract:Realistic action recognition has been one of the most challenging research topics in computer vision. The existing methods are commonly based on non-probabilistic classification, predicting category labels but not providing an estimation of uncertainty. In this paper, we propose a probabilistic framework using Gaussian processes (GPs), which can tackle regression problems with explicit uncertain models, for action recognition. A major challenge for GPs when applied to large-scale realistic data is that a large covariance matrix needs to be inverted during inference. Additionally, from the manifold perspective, the intrinsic structure of the data space is only constrained by a local neighborhood and data relationships with far-distance usually can be ignored. Thus, we design our GPs covariance matrix via the proposed 1construction and a local approximation (LA) covariance weight updating method, which are demonstrated to be robust to data noise, automatically sparse and adaptive to the neighborhood. Extensive experiments on four realistic datasets, i.e., UCF YouTube, UCF Sports, Hollywood2 and HMDB51, show the competitive results of 1-GPs compared with state-of-the-art methods on action recognition tasks. © 2014 Elsevier Ltd.
  Accession Number: 20143600022099
• Record 11 of
  
  Title:Image annotation by multiple-instance learning with discriminative feature mapping and selection
  
  Author(s):Hong, Richang(1); Wang, Meng(1); Gao, Yue(2); Tao, Dacheng(3); Li, Xuelong(4); Wu, Xindong(1,5)
  Source: IEEE Transactions on Cybernetics  Volume: 44  Issue: 5  DOI: 10.1109/TCYB.2013.2265601  Published: May 2014  
  Abstract:Multiple-instance learning (MIL) has been widely investigated in image annotation for its capability of exploring region-level visual information of images. Recent studies show that, by performing feature mapping, MIL can be cast to a single-instance learning problem and, thus, can be solved by traditional supervised learning methods. However, the approaches for feature mapping usually overlook the discriminative ability and the noises of the generated features. In this paper, we propose an MIL method with discriminative feature mapping and feature selection, aiming at solving this problem. Our method is able to explore both the positive and negative concept correlations. It can also select the effective features from a large and diverse set of low-level features for each concept under MIL settings. Experimental results and comparison with other methods demonstrate the effectiveness of our approach. © 2013 IEEE.
  Accession Number: 20141917692025
• Record 12 of
  
  Title:Effects of Sb2O3 on the mechanical properties of the borosilicate foam glasses sintered at low temperature
  
  Author(s):Zhai, Chenxi(1); Li, Zhe(2); Zhu, Yumei(1); Zhang, Jing(1); Wang, Xiuduo(3); Zhao, Lejun(3); Pan, Liuming(3); Wang, Pengfei(4)
  Source: Advances in Materials Science and Engineering  Volume: 2014  Issue:   DOI: 10.1155/2014/703194  Published: December 28, 2014  
  Abstract:The physical properties and microstructure of a new kind of borosilicate foam glasses with different Sb2O3 doping content are comprehensively investigated. The experimental results show that appropriate addition of Sb2O3 has positive impact on the bulk porosity and compressive strength of the foam glass. It is more suitable in this work to introduce 0.9 wt.% Sb2O3 into the Na2O-K2O-B2O3-Al2O3-SiO2 basic foam glass component and sinter at 775°C. And the obtained foam glasses present much more uniform microstructure, large pore size, and smooth cell walls, which bring them with better performance including a lower bulk density, low water absorption, and an appreciable compressive strength. The microstructure analysis indicates that, with the increase of the content of Sb2O3 additives, the cell size tends to increase at first and then decreases. Larger amounts of Sb2O3 do not change the crystalline phase of foam glass but increase its vitrification. It is meaningful to prepare the foam glass at a relatively low temperature for reducing the heat energy consumption. © 2014 Chenxi Zhai et al.
  Accession Number: 20150400438318