Xiangjian He

University of Technology Sydney, Sydney, New South Wales, Australia

Are you Xiangjian He?

Claim your profile

Publications (37)28.77 Total impact

  • Tao Zhou · Harish Bhaskar · Kai Xie · Jie Yang · Xiangjian He · Pengfei Shi
    ICIp2015; 09/2015
  • Tao Zhou · Xiangjian He · Kai Xie · Keren Fu · Junhao Zhang · Jie Yang
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, a novel and robust tracking method based on efficient manifold ranking is proposed. For tracking, tracked results are taken as labeled nodes while candidate samples are taken as unlabeled nodes. The goal of tracking is to search the unlabeled sample that is the most relevant to the existing labeled nodes. Therefore, visual tracking is regarded as a ranking problem in which the relevance between an object appearance model and candidate samples is predicted by the manifold ranking algorithm. Due to the outstanding ability of the manifold ranking algorithm in discovering the underlying geometrical structure of a given image database, our tracker is more robust to overcome tracking drift. Meanwhile, we adopt non-adaptive random projections to preserve the structure of original image space, and a very sparse measurement matrix is used to efficiently extract low-dimensional compressive features for object representation. Furthermore, spatial context is used to improve the robustness to appearance variations. Experimental results on some challenging video sequences show that the proposed algorithm outperforms seven state-of-the-art methods in terms of accuracy and robustness.
    Pattern Recognition 08/2015; 48(8). DOI:10.1016/j.patcog.2015.03.008 · 2.58 Impact Factor
  • Tao Zhou · Kai Xie · Junhao Zhang · Jie Yang · Xiangjian He
    Journal of Electronic Imaging 05/2015; 24(3):033005. DOI:10.1117/1.JEI.24.3.033005 · 0.85 Impact Factor
  • Tao Zhang · Zhijie Yang · Wenjing Jia · Baoqing Yang · Jie Yang · Xiangjian He
    [Show abstract] [Hide abstract]
    ABSTRACT: Violence detection is a hot topic for surveillance systems. However, it has not been studied as much as for action recognition. Existing vision-based methods mainly concentrate on violence detection and make little effort to determine the location of violence. In this paper, we propose a fast and robust framework for detecting and localizing violence in surveillance scenes. For this purpose, a Gaussian Model of Optical Flow (GMOF) is proposed to extract candidate violence regions, which are adaptively modeled as a deviation from the normal behavior of crowd observed in the scene. Violence detection is then performed on each video volume constructed by densely sampling the candidate violence regions. To distinguish violent events from nonviolent events, we also propose a novel descriptor, named as Orientation Histogram of Optical Flow (OHOF), which are fed into a linear SVM for classification. Experimental results on several benchmark datasets have demonstrated the superiority of our proposed method over the state-of-the-arts in terms of both detection accuracy and processing speed, even in crowded scenes.
    Multimedia Tools and Applications 05/2015; DOI:10.1007/s11042-015-2648-8 · 1.35 Impact Factor
  • Source
    Kai Xie · Keren Fu · Tao Zhou · Jie Yang · Qiang Wu · Xiangjian He
    [Show abstract] [Hide abstract]
    ABSTRACT: Small target detection is a critical problem in the Infrared Search And Track (IRST) system. Although it has been studied for years, there are some challenges remained, e.g. cloud edges and horizontal lines are likely to cause false alarms. This paper proposes a novel method using an optimization-based filter to detect infrared small target in heavy clutter. First, we design a certain pixel area as active area. Second, a weighted quadratic cost function is performed in the active area. Finally, a filter based on statistics of active area is derived from the cost function. Our method could preserve heterogeneous area, meanwhile, remove target region. Experimental results show our method achieves satisfied performance in heavy clutter.
    Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on; 04/2015
  • Xiongbiao Luo · Ying Wan · Xiangjian He
    [Show abstract] [Hide abstract]
    ABSTRACT: Purpose: Electromagnetically guided endoscopic procedure, which aims at accurately and robustly localizing the endoscope, involves multimodal sensory information during interventions. However, it still remains challenging in how to integrate these information for precise and stable endoscopic guidance. To tackle such a challenge, this paper proposes a new framework on the basis of an enhanced particle swarm optimization method to effectively fuse these information for accurate and continuous endoscope localization.
    Medical Physics 04/2015; 42(4):1808. DOI:10.1118/1.4915285 · 3.01 Impact Factor
  • Xiongbiao Luo · Ying Wan · Xiangjian He · Kensaku Mori
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes an observation-driven adaptive differential evolution algorithm that fuses bronchoscopic video sequences, electromagnetic sensor measurements, and computed tomography images for accurate and smooth bronchoscope three-dimensional motion tracking. Currently an electromagnetic tracker with a position sensor fixed at the bronchoscope tip is commonly used to estimate bronchoscope movements. The large tracking error from directly using sensor measurements, which may be deteriorated heavily by patient respiratory motion and the magnetic field distortion of the tracker, limits clinical applications. How to effectively use sensor measurements for precise and stable bronchoscope electromagnetic tracking remains challenging. We here exploit an observation-driven adaptive differential evolution framework to address such a challenge and boost the tracking accuracy and smoothness. In our framework, two advantageous points are distinguished from other adaptive differential evolution methods: (1) the current observation including sensor measurements and bronchoscopic video images is used in the mutation equation and the fitness computation, respectively, and (2) the mutation factor and the crossover rate are determined adaptively on the basis of the current image observation. The experimental results demonstrate that our framework provides much more accurate and smooth bronchoscope tracking than the state-of-the-art methods. Our approach reduces the tracking error from 3.96 to 2.89 mm, improves the tracking smoothness from 4.08 to 1.62 mm, and increases the visual quality from 0.707 to 0.741.
    Medical Image Analysis 01/2015; DOI:10.1016/j.media.2015.01.002 · 3.68 Impact Factor
  • Fengli Zhang · Jun Li · Feng Li · Min Xu · Richard Xu · Xiangjian He
    [Show abstract] [Hide abstract]
    ABSTRACT: Community detection is a significant but challenging task in the field of social network analysis. Many effective methods have been proposed to solve this problem. However, most of them are mainly based on the topological structure or node attributes. In this paper, based on SPAEM [1], we propose a joint probabilistic model to detect community which combines node attributes and topological structure. In our model, we create a novel feature-based weighted network, within which each edge weight is represented by the node feature similarity between two nodes at the end of the edge. Then we fuse the original network and the created network with a parameter and employ expectation-maximization algorithm (EM) to identify a community. Experiments on a diverse set of data, collected from Facebook and Twitter, demonstrate that our algorithm has achieved promising results compared with other algorithms.
    MultiMedia Modeling, 01/2015: pages 418-429;
  • Tao Zhou · Xiangjian He · Kia Xie · Keren Fu · Jie Yang
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, a novel and robust tracking method based on efficient manifold ranking is proposed. For tracking, tracked results are taken as labeled nodes while candidate samples are taken as unlabeled nodes. The goal of tracking is to search the unlabeled sample that is the most relevant to the existing labeled nodes. Therefore, visual tracking is regarded as a ranking problem in which the relevance between an object appearance model and candidate samples is predicted by the manifold ranking algorithm. Due to the outstanding ability of the manifold ranking algorithm in discovering the underlying geometrical structure of a given image database, our tracker is more robust to overcome tracking drift. Meanwhile, we adopt non-adaptive random projections to preserve the structure of original image space, and a very sparse measurement matrix is used to efficiently extract low-dimensional compressive features for object representation. Furthermore, spatial context is used to improve the robustness to appearance variations. Experimental results on some challenging video sequences show that the proposed algorithm outperforms seven state-of-the-art methods in terms of accuracy and robustness.
    Pattern Recognition 01/2015; · 2.58 Impact Factor
  • Source
    Xiongbiao Luo · Ying Wan · Xiangjian He · Kensaku Mori
    [Show abstract] [Hide abstract]
    ABSTRACT: Registration of pre-clinical images to physical space is indispensable for computer-assisted endoscopic interventions in operating rooms. Electromagnetically navigated endoscopic interventions are increasingly performed at current diagnoses and treatments. Such interventions use an electromagnetic tracker with a miniature sensor that is usually attached at an endoscope distal tip to real time track endoscope movements in a pre-clinical image space. Spatial alignment between the electromagnetic tracker (or sensor) and pre-clinical images must be performed to navigate the endoscope to target regions. This paper proposes an adaptive marker-free registration method that uses a multiple point selection strategy. This method seeks to address an assumption that the endoscope is operated along the centerline of an intraluminal organ which is easily violated during interventions. We introduce an adaptive strategy that generates multiple points in terms of sensor measurements and endoscope tip center calibration. From these generated points, we adaptively choose the optimal point, which is the closest to its assigned the centerline of the hollow organ, to perform registration. The experimental results demonstrate that our proposed adaptive strategy significantly reduced the target registration error from 5.32 to 2.59 mm in static phantoms validation, as well as from at least 7.58mm to 4.71mm in dynamic phantom validation compared to current available methods. Copyright © 2014 Elsevier Ireland Ltd. All rights reserved.
    Computer Methods and Programs in Biomedicine 12/2014; 118(2). DOI:10.1016/j.cmpb.2014.11.008 · 1.90 Impact Factor
  • M. Anwar Hasan · Min Xu · Xiangjian He · Changsheng Xu
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose a nonparametric camera motion descriptor for video shot classification. In the proposed method, a motion vector field (MVF) is constructed for each consecutive video frame by computing the motion vector (MV) of each macroblock. Then, the MVFs are divided into a number of local region of equal size. Next, the inconsistent/noisy MVs of each local region are eliminated by a motion consistency analysis. The remaining MVs of each local region from a number of consecutive frames are further collected for a compact representation. Initially, a matrix is formed using the MVs. Then, the matrix is decomposed using a singular value decomposition technique to represent the dominant motion. Finally, the angle of the most variance retaining principal component is computed and quantized to represent the motion of a local region by using a histogram. In order to represent the global camera motion, the local histograms are combined. The effectiveness of the proposed motion descriptor for video shot classification is tested by using a support vector machine. First, the proposed camera motion descriptors for video shots classification are computed on a video data set consisting of regular camera motion patterns (e.g., pan, zoom, tilt, static). Then, we apply the camera motion descriptors with an extended set of features to the classification of cinematographic shots. The experimental results show that the proposed shot level camera motion descriptor has a strong discriminative capability to classify different camera motion patterns of different videos effectively. We also show that our approach outperforms state-of-the-art methods.
    IEEE Transactions on Circuits and Systems for Video Technology 10/2014; 24(10):1682-1695. DOI:10.1109/TCSVT.2014.2345933 · 2.26 Impact Factor
  • Tao Zhou · Junhao Zhang · Kai Xie · Jie Yang · Xiangjian He
    ICIP; 09/2014
  • Tao Zhou · Xiangjian He · Kai Xie · Keren Fu · Junhao Zhang · Jie Yang
    ICME; 07/2014
  • Lei Zhou · Yu Qiao · Yijun Li · XiangJian He · Jie Yang
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes a novel interactive segmentation method based on conditional random field (CRF) model to utilize the location and color information contained in user input. The CRF is configured with the optimal weights between two features, which are the color Gaussian Mixture Model (GMM) and probability model of location information. To construct the CRF model, we propose a method to collect samples for the cuttraining tasks of learning the optimal weights on a single image׳s basis and updating the parameters of features. To refine the segmentation results iteratively, our method applies the active learning strategy to guide the process of CRF model updating or guide users to input minimal training data for training the optimal weights and updating the parameters of features. Experimental results show that the proposed method demonstrates qualitative and quantitative improvement compared with the state-of-the-art interactive segmentation methods. The proposed method is also a convenient tool for interactive object segmentation.
    Neurocomputing 07/2014; 135:240–252. DOI:10.1016/j.neucom.2013.12.026 · 2.01 Impact Factor
  • Ying Wan · Qiang Wu · Xiangjian He
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents an improved video-based endoscope tracking approach on the basis of dense feature correspondence. Currently video-based methods often fail to track the endoscope motion due to low-quality endoscopic video images. To address such failure, we use image texture information to boost the tracking performance. A local image descriptor - DAISY is introduced to efficiently detect dense texture or feature information from endoscopic images. After these dense feature correspondence, we compute relative motion parameters between the previous and current endoscopic images in terms of epipolar geometric analysis. By initializing with the relative motion information, we perform 2-D/3-D or video-volume registration and determine the current endoscope pose information with six degrees of freedom (6DoF) position and orientation parameters. We evaluate our method on clinical datasets. Experimental results demonstrate that our proposed method outperforms state-of-the-art approaches. The tracking error was significantly reduced from 7.77 mm to 4.78 mm.
    2014 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI); 06/2014
  • Lei Zhou · Keren Fu · Yijun Li · Yu Qiao · XiangJian He · Jie Yang
    [Show abstract] [Hide abstract]
    ABSTRACT: Salient object detection is essential for applications, such as image classification, object recognition and image retrieval. In this paper, we design a new approach to detect salient objects from an image by describing what does salient objects and backgrounds look like using statistic of the image. Firstly, we introduce a saliency driven clustering method to reveal distinct visual patterns of images by generating image clusters. The Gaussian Mixture Model (GMM) is applied to represent the statistic of each cluster, which is used to compute the color spatial distribution. Secondly, three kinds of regional saliency measures, i.e, regional color contrast saliency, regional boundary prior saliency and regional color spatial distribution, are computed and combined. Then, a region selection strategy integrating color contrast prior, boundary prior and visual patterns information of images is presented. The pixels of an image are divided into either potential salient region or background region adaptively based on the combined regional saliency measures. Finally, a Bayesian framework is employed to compute the saliency value for each pixel taking the regional saliency values as priority. Our approach has been extensively evaluated on two popular image databases. Experimental results show that our approach can achieve considerable performance improvement in terms of commonly adopted performance measures in salient object detection.
    Signal Processing Image Communication 03/2014; 29(3). DOI:10.1016/j.image.2014.01.001 · 1.15 Impact Factor
  • Chen Gong · Keren Fu · Lei Zhou · Jie Yang · Xiangjian He
    [Show abstract] [Hide abstract]
    ABSTRACT: Traditional graph-based semi-supervised learning (GBSSL) algorithms usually scale badly due to the expensive computational burden. The main bottleneck is that they need to compute the inversion of a huge matrix. In order to alleviate this problem, this paper proposes Neumann series approximation (NSA) to explicitly approximate the inversion process required by conventional GBSSL methodologies, which makes them computationally tractable for relatively large datasets. It is proved that the deviation between the approximation and direct inversion is bounded. Using real-world datasets related to handwritten digit recognition, speech recognition and text classification, the experimental results reveal that NSA accelerates the speed significantly without decreasing too much precision. We also empirically show that NSA outperforms other scalable approaches such as Nyström method, Takahashi equation, Lanczos process based SVD and AnchorGraph regularization, in terms of both efficiency and accuracy.
    Neural Processing Letters 01/2014; 42(1). DOI:10.1007/s11063-014-9351-z · 1.24 Impact Factor
  • Tao Zhang · Zhijie Yang · Wenjing Jia · Qiang Wu · Jie Yang · Xiangjian He
    [Show abstract] [Hide abstract]
    ABSTRACT: Head detection in images and videos plays an important role in a wide range of computer vision and surveillance applications. Aiming to detect heads with arbitrarily occluded faces and head pose, in this paper, we propose a novel Gaussian energy function based algorithm for elliptical head contour detection. Starting with the localization of head and shoulder by an improved Gaussian Mixture Model (GMM) approach, the precise head contour is obtained by making use of the Omega shape formed from the head and shoulder. Experimental results on several benchmark datasets demonstrate the superiority of the proposed idea over the state-of-the-art in both detection accuracy and processing speed, even though there are various types of severe occlusions in faces.
    Multimedia Tools and Applications 01/2014; DOI:10.1007/s11042-014-2110-3 · 1.35 Impact Factor
  • Chen Gong · Keren Fu · Enmei Tu · Jie Yang · Xiangjian He
    [Show abstract] [Hide abstract]
    ABSTRACT: Object tracking is widely used in many applications such as intelligent surveillance, scene understanding, and behavior analysis. Graph-based semisupervised learning has been introduced to deal with specific tracking problems. However, existing algorithms following this idea solely focus on the pairwise relationship between samples and hence could decrease the classification accuracy for unlabeled samples. On the contrary, we regard tracking as a one-class classification issue and present a novel graph-based semisupervised tracker. The proposed tracker uses linear neighborhood propagation, which aims to exploit the local information around each data point. Moreover, the manifold structure embedded in the whole sample set is discovered to allow the tracker to better model the target appearance, which is crucial to resisting the appearance variations of the object. Experiments on some public-domain sequences show that the proposed tracker can exhibit reliable tracking performance in the presence of partial occlusions, complicated background, and appearance changes, etc.
    Journal of Electronic Imaging 01/2013; 22(1):3015-. DOI:10.1117/1.JEI.22.1.013015 · 0.85 Impact Factor
  • Sheng Wang · Xiangjian He · Qiang Wu · Jie Yang
    [Show abstract] [Hide abstract]
    ABSTRACT: Local Binary Pattern (LBP) has been well recognised and widely used in various texture analysis applications of computer vision and image processing. It integrates properties of texture structural and statistical texture analysis. LBP is invariant to monotonic gray-scale variations and has also extensions to rotation invariant texture analysis. In recent years, various improvements have been achieved based on LBP. One of extensive developments was replacing binary representation with ternary representation and proposed Local Ternary Pattern (LTP). This paper further generalises the local pattern representation by formulating it as a generalised weight problem of Bachet de Meziriac and proposes Local N-ary Pattern (LNP). The encouraging performance is achieved based on three benchmark datasets when compared with its predecessors.
    Advanced Video and Signal Based Surveillance (AVSS), 2013 10th IEEE International Conference on; 01/2013

Publication Stats

53 Citations
28.77 Total Impact Points

Institutions

  • 2010–2015
    • University of Technology Sydney
      • • School of Computing and Communications
      • • Faculty of Engineering and Information Technology
      Sydney, New South Wales, Australia
    • University of Sydney
      • School of Information Technologies
      Sydney, New South Wales, Australia
    • Shanghai University
      Shanghai, Shanghai Shi, China