| Group |
2016-5 |
Status |
completed |
| Title |
Enhanced Mapping of Spaces for Augmented Reality |
| Supervisor |
Dr. Maria A. Amer |
| Description |
Augmented reality (AR) is a technique for adding and supplementing virtual content over real world. A typical AR system consists of tracking and registration between augmented and real world objects. Pose tracking in AR refers to determining the pose, i.e., three-dimensional position and orientation, of the camera. Object tracking in video processing means data association, also called matching or correspondence, between consecutive frames in a video sequence. The alignment of virtual and real objects depends on accurate tracking of the viewing pose, relative to the real environment and the annotated objects. Registration is the proper alignment of virtual objects to the real world objects which is key task of AR applications. This proposal deals with the development of a marker-less AR system to be used in applications such as gaming, video production, medical sciences, and education. In the proposed system, an object tracker such as DS-KCF and Struck will be used to track an object in a video sequence while user can manually select any object (e.g., by selecting a bounding box around the object). The selected object will be augmented on the tracked object in key frames of a video sequence. In order to handle the scale changes, upsampling and downsampling will be applied. In order to handle the rotation and translation of the augmented object, pose estimation will be utilized. The following figure shows an overview of the proposed AR system. |
| Requirement |
Solid background in DSP (Elec442 DSP course). |
| Tools |
Solid background in C++ and in cloud & mobile programming. |
| Number of Students |
3 |
| Students |
Suzette Slim,Julien Valognes,Justin Jean-Pierre |
| Comments: |
[1] P. Khandelwal, “Detection of features to track objects and segmentation using
grabcut for application in marker-less augmented reality," Procedia Computer Science 58, pp. 698{705, 2015.
[2] S. A. Z. A. Edmund Ng Giap Weng, Rehman Ullah Khan and O. Y. Bee, “Objects tracking from natural features in mobile augmented reality," The 9th International Conference on Cognitive Science, pp. 753{760, 2013.
|
| Links: |
|