Posts

Tuesday, 12 February 2019

How to run ORB SLAM with KITTI Dataset

How to run ORB SLAM with KITTI Dataset



Monocular Examples

1. Download the dataset (grayscale images) from http://www.cvlibs.net/datasets/kitti/eval_odometry.php

2. Execute the following command. Change KITTIX.yamlby KITTI00-02.yaml, KITTI03.yaml or KITTI04-12.yaml for sequence 0 to 2, 3, and 4 to 12 respectively. Change PATH_TO_DATASET_FOLDER to the uncompressed dataset folder. Change SEQUENCE_NUMBER to 00, 01, 02,.., 11.


./Examples/Monocular/mono_kitti Vocabulary/ORBvoc.txt Examples/Monocular/KITTIX.yaml PATH_TO_DATASET_FOLDER/dataset/sequences/SEQUENCE_NUMBER



Map I got

In KeyFrameTrajectory.txt file, every row has 8 entries containing time stamp (in seconds), position and orientation: 'timestamp x y z q_x q_y q_z q_w'
So to achieve what you want to do, you could for example load the file as a table (similar to a .csv file) and then the columns 2 to 4 are your x, y, z values (or 1 to 3 if you count from 0)

Stetro Examples


1. Download the dataset above.

2. Execute the following command. Change KITTIX.yamlto KITTI00-02.yaml, KITTI03.yaml or KITTI04-12.yaml for sequence 0 to 2, 3, and 4 to 12 respectively. Change PATH_TO_DATASET_FOLDER to the uncompressed dataset folder. Change SEQUENCE_NUMBER to 00, 01, 02,.., 11.

./Examples/Stereo/stereo_kitti Vocabulary/ORBvoc.txt Examples/Stereo/KITTIX.yaml PATH_TO_DATASET_FOLDER/dataset/sequences/SEQUENCE_NUMBER

No comments:

Post a Comment

[ new blog ]

new blog https://jihyo-jeon.github.io/