Open hust-zXX opened 1 year ago
As far as the detection part is concerned, the cause is probably a too small number of training examples that have these features. I believe that, for example, static individuals are more likely to have these features, but are filtered out within datasets such as MOT16 and MOT20:
MOT16: A Benchmark for Multi-Object Tracking
This also affects the re-id part, as it may reduce the similarity between, for example, a person standing and squatting.
To improve this part, the appropriate way would be to finetune the model. Maybe an improvement could be achieved if static persons are not filtered out of the datasets.
Another option would be to use better alternatives to the kalman filter and hungarian algorithm.
As far as the detection part is concerned, the cause is probably a too small number of training examples that have these features. I believe that, for example, static individuals are more likely to have these features, but are filtered out within datasets such as MOT16 and MOT20:
MOT16: A Benchmark for Multi-Object Tracking This also affects the re-id part, as it may reduce the similarity between, for example, a person standing and squatting. To improve this part, the appropriate way would be to finetune the model. Maybe an improvement could be achieved if static persons are not filtered out of the datasets.
Another option would be to use better alternatives to the kalman filter and hungarian algorithm.
thanks,I will try it
When I applied it, I found that if the person squatted down or only exposed the upper body, the target could not be effectively tracked. Is there any quick way to improve it?