KITTI Dataset에 대한 이해가 좀더 필요해서 관련한 코드를 스터디해본다.
https://github.com/navoshta/KITTI-Dataset
navoshta/KITTI-Dataset
Visualising LIDAR data from KITTI dataset. Contribute to navoshta/KITTI-Dataset development by creating an account on GitHub.
github.com
Focused on point cloud data and plotting labeled tracklets for visualisation.
Cars are marked in blue, trams in red and cyclists in green.
****************************
KITTI website에서 다운로드
Calibration, tracklet 데이터 다운로드
Directory 구조 세팅필요 - 아래와 같은 폴더 구성
1. calibration data 위치
>> data/2011_09_26/calib_imu_to_velo.txt
2. tacklet data 위치
>> data/2011_09_26/2011_09_26_drive_0001_sync/tracklet_labels.xml
Library 추가 설치
pip install moviepy
%time - 삭제
******************************
'DL_Algorithm' 카테고리의 다른 글
| Yolo V4 (0) | 2020.06.04 |
|---|---|
| Poly-Yolo (Instant Segmentation) (0) | 2020.06.04 |
| MsakRCNN object detection & semantic segmentation (0) | 2020.04.27 |
| 3D Object Detection -Complex-YOLO (3) | 2020.04.27 |
| Panoptic Segmentation - Detectron 2 (0) | 2020.04.27 |
