search

vbalnt / bold

BOLD - Binary Online Learned Descriptor - CVPR 2015
http://www.iis.ee.ic.ac.uk/~vbalnt/
Other
33 stars 13 forks source link

Video Object Detection #2

Closed rodrigo-reboucas closed 7 years ago

rodrigo-reboucas commented 7 years ago

It is possible to use BOLD as TFeat, input: object image and video; Output: object detection in video?

I would like to use the code in OpenCV to generate this result: http://docs.opencv.org/3.2.0/dc/d16/tutorial_akaze_tracking.html

vbalnt commented 7 years ago

Hi, it is possible yes, although it needs some work on interfacing with the standard openCV things like cv::Keypoint etc.

I would suggest to take a look on Steffen's @urbste BOLD implementation, which is much better, cleaner and interfaces directly with openCV.

You should be able to use his code in the way you want.

rodrigo-reboucas commented 7 years ago

Thank you, excellent article.