Giters

okankop / Driver-Anomaly-Detection

PyTorch Implementation of "Driver Anomaly Detection: A Dataset and Contrastive Learning Approach", codes and pretrained models.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Dataset with RGB frames

laura-wang opened this issue · comments

commented

Hi Okan,

Interesting work!
I am quite curious about the reason why you only collect the depth and infrared frames.
I believe that RGB frame is more widely used in general action recognition task. Could you please illustarte more?

commented

Hi @laura-wang, I am happy that you find our project interesting!

For automotive applications, RGB modality becomes useless at night due to dimished or even no illumination. On the other hand, infrared and depth modality is robust to illumination changes, which is why they are preferred over RGB modality at many automotive applications. This was the main motivation to use infrared and depth modalities in our study.