Target tracking confidence

[12w2]

Dear author:
Hello, I have reproduced your experimental results, and its performance is excellent.
But I have a question: your work mentioned that it is mainly target tracking based on the motion relationship between the front and back frames. If my target disappears for several frames, it cannot continue to track the target.
I know it is difficult for radar to deal with this situation, so can your code output a confidence level to remind users that the target may be lost.
thank you.

[BryanChen024]

Dear author: Hello, I have reproduced your experimental results, and its performance is excellent. But I have a question: your work mentioned that it is mainly target tracking based on the motion relationship between the front and back frames. If my target disappears for several frames, it cannot continue to track the target. I know it is difficult for radar to deal with this situation, so can your code output a confidence level to remind users that the target may be lost. thank you.

Hello, my friend.
Regarding the result of reproducing on the KITTI dataset, I found that the results I reproduced on the Car and Cyclist data sets were basically the same, but the results on Pedestrian and Van were very different.

The reproducing success/precision on Pedestrians are near 50/75, much lower than the results in the paper 60/89.

I just change the dataset name in the yaml cfg file (Car to Pedestrian) and then train it. I would be appreciated if you can share me more details on the model parameter setting if i fogot to set.

Thank you very much!