Creat membership Creat membership
Sign in

Forgot password?

Confirm
  • Forgot password?
    Sign Up
  • Confirm
    Sign In
home > search

Now showing items 1 - 16 of 23

  • Joint Video Frame Set Division and Low-Rank Decomposition for Background Subtraction

    Wen, Jiajun   Xu, Yong   Tang, Jinhui   Zhan, Yinwei   Lai, Zhihui   Guo, Xiaotang  

    The recently proposed robust principle component analysis (RPCA) has been successfully applied in background subtraction. However, low-rank decomposition makes sense on the condition that the foreground pixels (sparsity patterns) are uniformly located at the scene, which is not realistic in real-world applications. To overcome this limitation, we reconstruct the input video frames and aim to make the foreground pixels not only sparse in space but also sparse in time. Therefore, we propose a joint video frame set division and RPCA-based method for background subtraction. In addition, we use the motion as a priori knowledge which has not been considered in the current subspace-based methods. The proposed method consists of two phases. In the first phase, we propose a lower bound-based within-class maximum division method to divide the video frame set into several subsets. In this way, the successive frames are assigned to different subsets in which the foregrounds are located at the scene randomly. In the second phase, we augment each subset using the frames with a small quantity of motion. To evaluate the proposed method, the experiments are conducted on real-world and public datasets. The comparisons with the state-of-the-art background subtraction methods validate the superiority of our method.
    Download Collect
  • METHOD AND APPARATUS FOR GUIDING SERVICE FLOW

    Provided are a method and apparatus for guiding service flow. The method comprises: with regard to a target service, acquiring historical behaviour data of a user using the target service; analysing the historical behaviour data to obtain user features for defining target users of a guided service flow; from among users not using the target service, selecting as the target user a user conforming to the user features; and sending service flow guiding information to the target user, so as to guide said target user to use the target service. The present disclosure guides flow in a more targeted manner, thus improving the effect of a guided service flow.
    Download Collect
  • The L2,1-norm-based unsupervised optimal feature selection with applications to action recognition

    Wen, Jiajun   Lai, Zhihui   Zhan, Yinwei   Cui, Jinrong  

    Download Collect
  • The complexation of rhizosphere and nonrhizosphere soil organic matter with chromium: Using elemental analysis combined with FTIR spectroscopy

    Wen, Jiajun   Li, Zhongwu   Huang, Bin   Luo, Ninglin   Huang, Mei   Yang, Ren   Zhang, Qiu   Zhai, Xiuqing   Zeng, Guangming  

    Download Collect
  • One-Pot Electrodeposition of NiS Nanoparticles as an Efficient Electrode for Nonenzymatic H 2 O 2 and Glucose Sensors

    Huang, Zhiheng   Gu, Chunchuan   Wen, Jiajun   Zhu, Langlang   Zhang, Mingzhen   liu, Hongying  

    Download Collect
  • [IEEE 2014 22nd International Conference on Pattern Recognition (ICPR) - Stockholm, Sweden (2014.8.24-2014.8.28)] 2014 22nd International Conference on Pattern Recognition - Optimal Feature Selection for Robust Classification via l2,1-Norms Regularization

    Wen, Jiajun   Lai, Zhihui   Wong, Wai Keung   Cui, Jinrong   Wan, Minghua  

    Download Collect
  • [ACM Press the 2nd International Conference - Seoul, Korea (2009.11.24-2009.11.26)] Proceedings of the 2nd International Conference on Interaction Sciences Information Technology, Culture and Human - ICIS \"09 - Vision-based two hand detection and tracking

    Wen, Jiajun   Zhan, Yinwei  

    Download Collect
  • Passivating Effect of Dewatered Sludge and Biochar on As-Contaminated Soil

    Luo, Ninglin   Wen, Jiajun   Li, Zhongwu   Huang, Mei   Yang, Ren  

    Download Collect
  • Effects of Fe(III)-fulvic acid on Cu removal via adsorption versus coprecipitation.

    Yang, Ren   Li, Zhongwu   Huang, Bin   Luo, Ninglin   Huang, Mei   Wen, Jiajun   Zhang, Qiu   Zhai, Xiuqing   Zeng, Guangming  

    This study compared the sorption and extractability of Cu following adsorption (SOR) and coprecipitation(CPT). The effect of solution pH, Fe: organic carbon (OC) ratios and fulvic acid (FA) on the combined removal of Cu was investigated in the batch tests using Fe(III) precipitates as a sorbent. Transmission electron microscope (TEM) images demonstrated that the coexisting FA reduced the particle size of ferrihydrites as expected. Generally, more Cu was eliminated in coprecipitation compared with adsorption and the dissolved Cu left in solutions decreased as the pH increased, most of dissolved Cu was trapped at pH 6 and above. Meanwhile, the inhibition or promotion of Cu removal really depended on the different Fe: OC ratios. The addition of FA led to a further decrease of Cu concentrations in CPT systems with Fe/OC ratio of 1:3, however, Cu removal was hindered in the presence of FA in SOR systems. In the case of extraction experiments, the addition of l-malic acid (MA), oxalic acid (OA) and citric acid (CA) resulted in lower extractability of coprecipitated Cu than adsorption samples. The gaps in extractions were seemed to be a consequence of tight Cu binding in CPT products, and the more feasible desorption of Cu from the surface of SOR samples. Based on the results of Cu adsorption and coprecipitation, coprecipitation of Cu with ferrihydrites was the more effective Cu sequestration mechanism in the removal of Cu. These results are helpful to understand the complicated interactions among Fe(III), FA and Cu (II) in the natural environment. Copyright =C2=A9 2018 Elsevier Ltd. All rights reserved.
    Download Collect
  • An amorphous Zn–P/graphite composite with chemical bonding for ultra-reversible lithium storage

    Li, Wenwu   Yu, Jiale   Wen, Jiajun   Liao, Jun   Ye, Ziyao   Zhao, Bote   Li, Xinwei   Zhang, Haiyan   Liu, Meilin   Guo, Zaiping  

    Download Collect
  • Binding characteristics of cadmium and zinc onto soil organic matter in different water managements and rhizosphere environments

    Wen, Jiajun   Li, Zhongwu   Luo, Ninglin   Huang, Mei   Ding, Xiang   Bu, Xianrong   Chen, Ming  

    Download Collect
  • In situ investigation of intrinsic relationship between protonation behavior and HA characteristics in sediments

    Huang, Mei   Li, Zhongwu   Chen, Ming   Wen, Jiajun   Xu, Weihua   Ding, Xiang   Yang, Ren   Luo, Ninglin   Xing, Wenle  

    Download Collect
  • Appearance-based representative samples refining method for palmprint recognition

    Wen, Jiajun   Chen, Yan  

    The sparse representation can deal with the lack of sample problem due to utilizing of all the training samples. However, the discrimination ability will degrade when more training samples are used for representation. We propose a novel appearance-based palmprint recognition method. We aim to find a compromise between the discrimination ability and the lack of sample problem so as to obtain a proper representation scheme. Under the assumption that the test sample can be well represented by a linear combination of a certain number of training samples, we first select the representative training samples according to the contributions of the samples. Then we further refine the training samples by an iteration procedure, excluding the training sample with the least contribution to the test sample for each time. Experiments on PolyU multispectral palmprint database and two-dimensional and three-dimensional palmprint database show that the proposed method outperforms the conventional appearance-based palmprint recognition methods. Moreover, we also explore and find out the principle of the usage for the key parameters in the proposed algorithm, which facilitates to obtain high-recognition accuracy. (C) 2012 Society of Photo-Optical Instrumentation Engineers (SPIE). [DOI: 10.1117/1.OE.51.7.077203]
    Download Collect
  • Nuclear norm based two-dimensional sparse principal component analysis

    Chen, Yudong   Lai, Zhihui   Wen, Jiajun   Gao, Can  

    Two-Dimensional Principal Component Analysis (2D-PCA) is one of the most simple and effective feature extraction methods in the field of pattern recognition. However, the traditional 2D-PCA lacks robustness and the function of sparse feature extraction. In this paper, we propose a new feature extraction approach based on the traditional 2D-PCA, which is called Nuclear Norm Based Two-Dimensional Sparse Principal Component Analysis (N-2D-SPCA). To improve the robustness of 2D-PCA, we utilize nuclear norm to measure the reconstruction error of loss function. At the same time, we obtain sparse feature extraction by adding L-1-norm and L-2-norm regularization terms to the model. By designing an alternatively iterative algorithm, we can solve the optimization problem and learn a projection matrix for use with feature extraction. Besides, we present a bilateral projections model (BN-2D-SPCA) to further compress the dimensions of the feature matrix. We verify the effectiveness of our method on four benchmark face databases including AR, ORL, FERET and Yale databases. Experimental results show that the proposed method is more robust than some state-of-the-art methods and the traditional 2D-PCA.
    Download Collect
  • Characteristics of fulvic acid during coprecipitation and adsorption to iron oxides‑copper aqueous system

    Yang, Ren   Li, Zhongwu   Huang, Mei   Luo, Ninglin   Wen, Jiajun   Zeng, Guangming  

    Download Collect
  • A palmprint recognition method based on multi-step representation

    Wen, Jiajun   Chen, Yan   Mi, Jianxun  

    Sparse representation uses all training samples to represent a test sample only once, which can be regarded as a one step representation. However, in palmprint recognition, the appearances of palms are highly correlated which means the information provided by all the training samples are redundant while using the representation-based methods. Hence, how to obtain suitable samples for representation deserves exploring. In this paper, we devise a multi-step representation manner to extract the most representative samples for representation and recognition. In addition, the proposed sample selection strategy is based on contributions of the classes, not merely the effort of a single sample. Compared with some other appearance-based methods, the proposed method obtained a competitive result on PolyU multispectral palmprint database. (C) 2013 Elsevier GmbH. All rights reserved.
    Download Collect
1 2

Contact

If you have any feedback, Please follow the official account to submit feedback.

Turn on your phone and scan

Submit Feedback