Yan Niu

Jilin University, Yung-chi, Jilin Sheng, China

Are you Yan Niu?

Claim your profile

Publications (7)10.82 Total impact

  • Yan Niu · Zhiwen Xu · Xiangjiu Che ·
    [Show abstract] [Hide abstract]
    ABSTRACT: Pyramidal Lucas-Kanade (LK) optical ow is a real-time registration technique widely employed by a variety of cutting edge consumer applications. Traditionally, the LK algorithm is applied selectively to image feature points that have strong spatial variation, which include outliers in textured areas. To detect and discard the falsely selected features, previous methods generally assess the goodness of each feature after the ow computation is completed. Such a screening process incurs additional cost. This paper provides a handy (but not obvious) tool for the users of the LK algorithm to remove false features without degrading the algorithm's efciency. We propose a condence predictor, which evaluates the ill-posedness of an LK system directly from the underlying data, at a cost lower than solving the system. We then incorporate our condence predictor into the courseto- ne LK registration to dynamically detect false features and terminate their ow computation at an early stage. This improves the registration accuracy by preventing the error propagation and maintains (or increases) the computation speed by saving the runtime on false features. Experimental results on state-of-the-art benchmarks validate that our method is more accurate and efcient than related works.
    IEEE Transactions on Image Processing 06/2014; 23(8). DOI:10.1109/TIP.2014.2331140 · 3.63 Impact Factor
  • Yan Niu · Anthony Dick · Michael Brooks ·
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes a new image signature, called Compass Rose, which is particularly suited to optical flow computation. It is differentiable, fast to compute, and robust to additive illumination changes, translation, and fast rotation. We design a sparse flow computation system based on the invariance of the Compass Rose signatures. This is then extended to dense motion estimation by the addition of an optional diffusion step. Quantitative testing on several benchmark sequences shows the Compass Rose attains higher accuracy than the traditional flow signatures under a range of conditions. Finally, we demonstrate its application to human motion estimation, which is challenging for optical flow methods due to fast limb rotation.
    IEEE Transactions on Circuits and Systems for Video Technology 01/2014; 24(1):63-73. DOI:10.1109/TCSVT.2013.2276854 · 2.62 Impact Factor
  • Yan Niu · Anthony Dick · Michael Brooks ·
    [Show abstract] [Hide abstract]
    ABSTRACT: Optical flow computation methods are traditionally classified to two categories: local and global. Several previous works have investigated the combination of them by exploiting their complementary effects. Unlike previous works, this paper is motivated by the common weakness of the two schemes and proposes linking local and global computation by subspace regularization. We will show that the subspace regularization can effectively reduce the error caused by ill-conditioned local computation systems, while inhibiting error diffusion suffered by the global regularization. Experimental results on benchmark sequences validate the enhanced performance of the proposed combination scheme.
    Optical Engineering 03/2013; 52(3-3):037205-037205. DOI:10.1117/1.OE.52.3.037205 · 0.95 Impact Factor
  • Yan Niu · Anthony Dick · Michael Brooks ·
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes the use of an adaptive locally oriented coordinate frame when calculating an optical flow field. The coordinate frame is aligned with the least curvature direction in a local window about each pixel. This has advantages to both fitting the flow field to the image data and in imposing smoothness constraints between neighboring pixels. In terms of fitting, robustness is obtained to a wider variety of image motions due to the extra invariance provided by the coordinate frame. Smoothness constraints are naturally propagated along image boundaries which often correspond to motion boundaries. In addition, moving objects can be efficiently segmented in the least curvature direction. We show experimentally the benefits of the method and demonstrate robustness to fast rotational motion, such as what often occurs in human motion.
    IEEE Transactions on Image Processing 12/2011; 21(4):1573-86. DOI:10.1109/TIP.2011.2177847 · 3.63 Impact Factor
  • Yan Niu · Anthony Dick · Michael Brooks ·
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes a new measure that continuously measures the degree of inconsistency for a linear system. We apply the new measure to two essential vision problems. One is to predict the fidelity of a local optical flow computation system; The other is to detect motion boundaries. Experimental results on benchmark sequences validate the performance of the proposed measure on both problems.
    Image and Vision Computing New Zealand, 2009. IVCNZ '09. 24th International Conference; 12/2009
  • Y. Niu · A. Dick · M. Brooks ·
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper describes an approach to optical flow computation that combines local and global constraints. A local flow estimate is obtained at each pixel, and is used to segment the image into regions of smooth motion. Within each region, global constraints are applied to reduce noise in local flow estimates while preserving motion boundaries. The main novel contributions in this framework are: (1) the derivation of a consistency measure for local flow computation, and the use of this measure to preserve motion boundary in the estimation; (2) the combined use of global subspace and spatial smoothness constraints to complement local flow estimation. Results on standard test sequences demonstrate improved accuracy in flow estimation, and analyse the role that each contribution plays in this improvement.
    Image and Vision Computing New Zealand, 2008. IVCNZ 2008. 23rd International Conference; 12/2008
  • Yan Niu · Anthony Dick · Michael Brooks ·
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents an optical flow estimation technique that improves the accuracy of existing methods in the problematic case of motion discontinuity. An initial flow estimate at a pixel is calculated from selected "reliable" pixels in the spatial neighbourhood. This initial estimate is then used to distinguish smooth and discontinuous regions. The flow estimate in a smooth region is refined using data from the temporal neighbourhood. Flow in a discontinuous region is estimated by reasoning about the local motion boundary, which can result in accurate estimation even when the optical flow constraint does not hold. By carefully structuring this computation, the method runs at the same speed as existing methods in the literature, while preliminary experiments indicate it can produce more accurate results near motion boundaries.
    Digital Image Computing Techniques and Applications, 9th Biennial Conference of the Australian Pattern Recognition Society on; 01/2008

Publication Stats

8 Citations
10.82 Total Impact Points


  • 2011-2014
    • Jilin University
      • College of Computer Science & Technology
      Yung-chi, Jilin Sheng, China
  • 2008-2009
    • University of Adelaide
      • School of Computer Science
      Tarndarnya, South Australia, Australia