Copyright © 2001-2002
All Rights Reserved By
Ning Xu
Research Projects:
|
3D Object Reconstruction from Multiple Views Using Iterative Node Cut we present an approach to model three-dimensional (3D) object given its images acquired from different viewpoints. The generated model includes both shape and color information of the object so that it can be used not only to make 3D measurements but also to render new views of the object ... |
|
Omni-focus Image and Range Map Generation of Panoramic Views Using Nonfrontal Imaging Camera The objective of this project is to use Non-frontal Imaging Camera (NICAM) to generate omni-focus panoramic images and corresponding range maps. We first propose a new focus measure that is shown to be capable of handling the problem those existing frequency based focus measures would encounter in the neighborhood of intensity edges. Then we construct a three dimensional (3D) node-capacitated graph and apply a graph cut based optimization method to ... |
|
Object Segmentation Using Graph Cuts based Active Contours (GCBAC) Graph cuts based active contours (GCBAC) approach is a combination of active contours and the optimization tool of graph cuts. It differs fundamentally from traditional active contours in that it uses graph cuts at each step, and consequently has several advantages ... |
|
INTERACTIVE OBJECT SELECTION USING S-T MINIMUM CUT This project intends to develop an interactive object selection tool that having the following properties. 1) Interactivity, 2) Robustness and 3) Controllability... |
|
3D Object Surface Estimation Using a Three-view Matching Algorithm and Iterative Feedback We developed 3D surface estimation algorithm which uses a novel three-view stereo matching algorithm and iterative feedbacks from differences between input images and rendered virtual images from the same viewpoints. The three-view matching algorithm can provide robust stereo matching results and surface normal directions simultaneously ... |
|
Object Contour Tracking Using Graph Cuts based Active Contours (GCBAC) Graph cuts based active contours (GCBAC) algorithm is applied in a two step approach to track object contour in video sequences. This approach takes advantages of both the intensity information of a frame and the difference between consecutive frames. The approach does not require an a priori global shape model and the resulting contours are globally optimal within their neighborhoods ... |
|
Learning Non-Viable Regions in Delayed Enhancement MR Images We presented a method employing machine learning based methods to segment non-viable tissues in the myocardium based on DEMR image and Cine MR images ... |
|
Automated Lung Nodule Segmentation in 3D CT Volume we present a robust and automated algorithm to segment lung nodules in three dimensional (3D) Computed Tomography (CT) volume dataset ... |
