Real-time Tracking Based on Object Recognition(II)
Loading...
6,608
Uploader Comments (ningxu)
see all
All Comments (6)
-
Looks great! Could you tell me the exact name of the algorithm? Thx!
-
I have seen three of your demostrations. However, it is not exactly the situation I am talking about. If you can take a look at my video samples. I think you may get my point. In my opinion, similarity based tracking algorithm will fail in this case. Maybe we can discuss about this problem sometime?
Loading...
中国的?
能做个交流么?
zerniken 3 years ago
Yes, I am a Chinese student.
ningxu 3 years ago
Have you worked with motion tracking while object consists of high nonlinear transformation and identity? The kernel method will fail if the image is multi-model instead of having global optimal. Do you have other solution?
KuanDannYan 4 years ago
In fact, I've solved multiple object tracking in another way, that is multiple object recognition. You may refer to my other demos in YouTube.
ningxu 4 years ago
this is amazing. i am working on a project to recognize plates. do you know where i could start. amazing job. way the go.
hmenshari 4 years ago
I think first you should find a robust object recognition algorithm. I've used Lowe's SIFT(or more accurately, a modification to SIFT) in the demo.
ningxu 4 years ago