Oriented FAST and Rotated BRIEF (ORB) is basically a fusion of FAST keypoint detector and BRIEF descriptor with many modifications to enhance the performance. First it use FAST to find keypoints, then apply Harris corner measure to find top N points among them. It also use pyramid to produce multiscale-features. I will be using opencv-python for the implementation of the assignment and algorithm.
Major advantages of the ORB:
- Scale Invariance
- Rotational Invariance
- Illumination Invariance
- Noise Invariance
The final json is contained in file final_data.json
- python version 3.5.1
- pip version 19.1.1
- Preferred OS: Ubuntu 16.04 (tested)
Now go to the directly and run the following command:
- pip install -r requirements.txt
The final code lies in the file get_json.py
For step wise understanding the ORB code please check: ORB- Feature Matcher
So just run the file to get the output as final_data.json
The algorithm is majorly implemented in file feature_match.py, which contain the feature matching orb algorithm and also the outlier removal code.
For more insight into code implementation, please check the assignment report Report