J
Jun Zhang
Researcher at University of Wisconsin–Milwaukee
Publications - 27
Citations - 691
Jun Zhang is an academic researcher from University of Wisconsin–Milwaukee. The author has contributed to research in topics: Total least squares & Rayleigh quotient. The author has an hindex of 11, co-authored 25 publications receiving 542 citations. Previous affiliations of Jun Zhang include New York University.
Papers
More filters
Journal ArticleDOI
Robust depth estimation for light field via spinning parallelogram operator
TL;DR: Experimental results demonstrate that the proposed method outperforms state-of-the-art depth estimation methods on light field images, including both real world images and synthetic images, especially near occlusion boundaries.
Journal ArticleDOI
Heterogeneous Association Graph Fusion for Target Association in Multiple Object Tracking
TL;DR: A heterogeneous association graph is constructed that fuses high-level detections and low-level image evidence for target association and the novel idea of adaptive weights is proposed to analyze the contribution between motion and appearance.
Journal ArticleDOI
Object representation and recognition in shape spaces
TL;DR: A shape space based approach for invariant object representation and recognition that is invariant to similarity transformations and is relatively insensitive to noise and occlusion, potentially used for 3D object recognition.
Journal ArticleDOI
Occlusion-aware depth estimation for light field using multi-orientation EPIs
TL;DR: The multi-orientation EPIs and optimal orientation selection are proved to be effective in detecting and excluding occlusions and outperforms state-of-the-art depth estimation methods, especially near occlusion boundaries.
Journal ArticleDOI
Novel Approach to Position and Orientation Estimation in Vision-Based UAV Navigation
TL;DR: A novel approach to position and orientation estimation for vision-based UAV (unmanned aerial vehicle) navigation is described, which is formulated as a tracking problem and solved by using an extended Kalman filter (EKF).