Closed shi-yan closed 5 years ago
Even though input into the tracker is a RGB image, correlation filter is calculated on higher dimensional features. So, "channel" refers to a channel of multi-channel features: 18 channels of HoG + 1 channel of grayscale image + 10 channels of colornames feature image. Total feature channels is therefore 29, resulting in the same number of channel reliability weights.
Thank you for the answers!
I installed Matlab and now am trying to debug to understand this code deeper.
Hello there,
I have a question regarding the meaning of "channel". I thought it meant the RGB channel, but after looking at the video of channel reliability weights visualization, there are so many of them. I thought there should be only 3 weights, one for each color channel.
If there are so many of them, then, channel can't be the RGB channel.
But by reading the code, I still think channel here is really the RGB channel, right?
Then how come the visualization shows so many weights?
Thanks,