It's reasonable since self-driving car requires a fixed view (the car has to be centered bottom of the image)
However, other applications of 3D point clouds object detection may have different settings such as industrial factories and warehouses like what I tried to do. We may need to augment using translation to increase the diversity of our limited dataset.
What
The current repo doesn't support Random Translation augmentation methods.
This PR adds Random Translation methods here: https://github.com/maudzung/Complex-YOLOv4-Pytorch/blob/ffb67cd38ee72fd0ad884bcb2f9b11b0cc131f54/src/data_process/transformation.py#L376-L403
Why
It's reasonable since self-driving car requires a fixed view (the car has to be centered bottom of the image)
However, other applications of 3D point clouds object detection may have different settings such as industrial factories and warehouses like what I tried to do. We may need to augment using translation to increase the diversity of our limited dataset.
Testing
We will make changes to
train_lidar_transforms
here: https://github.com/maudzung/Complex-YOLOv4-Pytorch/blob/a712f52542a35893ddedbd7b782f34f31a0ff796/src/data_process/kitti_dataloader.py#L22-L28After changing, run
1) No Augmentation
2) Random_Rotate (Existing augmentation)
3) Random_Scaling (Existing augmentation)
You can see that's it's zoomed out![image](https://user-images.githubusercontent.com/41280374/138544817-0808984d-3b93-4a10-97bc-feb761f44d1f.png)
4) Random_Translate (Added in this PR)
You can see the image is translated, the view shifts upwards, no longer starting from the car![image](https://user-images.githubusercontent.com/41280374/138544879-a4081d5d-7842-41e0-b0a6-8ee7ce9908f2.png)