GOTURN
GOTURN copied to clipboard
davheld
How to use this model to do other tasks without re-train the tracker?
I am now learning this method to do other tasks and I find it not ideal, so that I modify the parameters in 'helper/bouding_box.cpp' including 'kContextFactor ' and 'kScaleFactor ' to let the tracker search in a smaller region. But I found the output not ideal, all the bouding boxes turn out to be a small red dot finally.
My question is: is it exist a way to modify the parameters of 'sizeof search region' in order to let the tracker do other task(here I use it to track the dead object in background in order to calculate background optical flow so that I want to modify parameters to let it search in a smaller region)without re-train the tracker?
Thank you
I don't believe so - if you change the parameters you will likely have to retrain the tracker.
On Sat, Oct 8, 2016 at 10:32 PM, raoqi [email protected] wrote:
I am now learning this method to do other tasks and I find it not ideal, so that I modify the parameters in 'helper/bouding_box.cpp' including ' kContextFactor ' and 'kScaleFactor ' to let the tracker search in a smaller region. But I found the output not ideal, all the bouding boxes turn out to be a small red dot finally.
My question is: is it exist a way to modify the parameters of 'sizeof search region' in order to let the tracker do other task(here I use it to track the dead object in background in order to calculate background optical flow so that I want to modify parameters to let it search in a smaller region)without re-train the tracker?
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/davheld/GOTURN/issues/12, or mute the thread https://github.com/notifications/unsubscribe-auth/AEHoHOZgaEvO3Y5X1RGzLR8TTUNDg97fks5qyHxjgaJpZM4KR6Xd .
Ok, I know. And do you remember how long have you spent to train your tracker?
A few days, I believe?
On Mon, Oct 10, 2016 at 1:29 PM, raoqi [email protected] wrote:
Ok, I know. And do you remember how long have you spent to train your tracker?
— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/davheld/GOTURN/issues/12#issuecomment-252592794, or mute the thread https://github.com/notifications/unsubscribe-auth/AEHoHK2c0r5BBLA5qjpLgEjpjlXwoE4nks5qyiGHgaJpZM4KR6Xd .
@davheld Hi, @rao1219 I want to increase the searching area during the test using VOT2014, do I need to retrain the model or just change the parameters in 'helper/bouding_box.cpp' including 'kContextFactor ' and 'kScaleFactor ' ?
In theory, I don't think you should need to retrain the model, but in practice I found that it helps a lot if you do. You can try it without retraining, but I'm guessing that you'll need to retrain. If anyone else has tried this, feel free to pipe in here.