Learn More
We present a linear numerical scheme for a model of epitaxial thin film growth without slope selection. The PDE, which is a nonlinear, fourth-order parabolic equation, is the L 2 gradient flow of the energy (− 1 2 ln(1 + |∇φ| 2) + 2 2 |φ(x)| 2) dx. The idea of convex-concave decomposition of the energy functional is applied, which results in a numerical(More)
In this paper, we propose an approach for 2D discrete vector field segmentation based on the Green function and normalized cut. The method is inspired by discrete Hodge Decomposition such that a discrete vector field can be broken down into three simpler components, namely, curl-free, divergence-free, and harmonic components. We show that the Green Function(More)
We present a novel approach to 3D human action recognition based on a feature-level fusion of spatiotemporal features and skeleton joints. First, 3D interest points detection and local feature description are performed to extract spa-tiotemporal motion information. Then the frame difference and pairwise distances of skeleton joint positions are computed to(More)
Supervised local tangent space alignment (SLTSA) is an extension of local tangent space alignment (LTSA) to supervised feature extraction. Two al-gorithmic improvements are made upon LTSA for classification. First a simple technique is proposed to map new data to the embedded low-dimensional space and make LTSA suitable in a changing, dynamic environment.(More)
Video Stabilization is one of those important video processing techniques to remove the unwanted camera vibration in a video sequence. In this paper, we present a practical method to remove the annoying shaky motion and reconstruct a stabilized video sequence with good visual quality. Here, the scale invariant(SIFT) features, proved to be invariant to image(More)