Bien Do

Hi, see [C3D](https://github.com/dolongbien/HumanBehaviorBKU/tree/master/C3D) and [Scripts](https://github.com/dolongbien/HumanBehaviorBKU/tree/master/Scripts) for *.txt & *.mat file

Hi, The dataset (Road Accident video/Normal video) is collected manually by us. A few of them are from the UCF crime dataset.

> @dolongbien thanks for your great works. Could you please publish your dataset? I am very interested in traffic accident detection, and recently I want to make some related work....

There's no problem with the link. You may try again.

Hi, make sure you were running under the GPU mode of Colab. Also, double-check the CUDA version and follow the right instruction on C3D notebook of this repo.

Hi, libprotoc version is 3.0.0

Hi, Maybe you were feeding the Normal video so that the output score is all zero. Try using abnormal video instead, there are some sample videos under WebApp/media dir. That's...

yea, there is a pre-processing step (resize) before putting into C3D model. Our training videos are fallen under some specific constraints and types of accidents, therefore the model only works...

No, just a few. But the UCF Crime dataset is all you need, as you are trying to reproduce the feature and score. We take some road accident videos from...

Hi, please take a look at Script folder and C3D feature extraction notebook in this repo.