Computer Vision | Tongji Univ. SSE Course Project
Sometimes, when capturing, we can only get a partial image of the object, especially when the size of the object is extremely large. However, if the two partial images have some content overlapping, we can make use of CV algorithms to "stitch" them together to get a panorama of the scene. This is exactly the purpose of this project.
-
Experiment/. ├── doc │ └── paper_reading.pdf ├── img │ ├── ... ├── paper │ └── ... ├── pre │ ├── pre.pdf │ └── script.md └── src └── ... -
document/
- Scale Space and Image Pyramids
- Localizing Extrema
- Generating Orientations and Descriptors
- Hessian Detector
- Math Behind Hessian Matrix
- Construction of feature vector
- Comparision between SIFT and SURF
- Results
- Current Approaches
- Summary
- Color and Luminance Compensation
- Optimal Seam Finding and Image Labeling
- Image Blending
- Results
| Item | Name | |
|---|---|---|
| Team Leader | Zhe ZHANG | dbzdbz@tongji.edu.cn |
| Team Member | Kaixin CHEN | 1753188@tongji.edu.cn |
| Team Member | Yunxin SUN | 1551534@tongji.edu.cn |
| Advisor | Prof. Lin ZHANG | cslinzhang@tongji.edu.cn |