What algorithm would be optimal in this situation?
Please suggest what algorithms/tutorials/ how can I achieve the following steps:
- Extract features from a (one) high-quality image on the web.
- Transform into a .xml or .dat file.
- Port file to an ARM, ios or android.
- Obtain video frames
- Apply image recognition, feature extraction etc. to detected object
- Get coordinates of objects on every frame scanned Out of scope of openCV but maybe someone can help:
- Render a video on top of the coordinates