This package provides a minimal set of tools for working with the KITTI dataset [1] in Python. So far only the raw datasets and odometry benchmark datasets are supported, but we're working on adding support for the others. We welcome contributions from the community.
To install the package from source, simply clone or download the repository to your machine
git clone https://github.com/utiasSTARS/pykitti.git
and run the provided setup tool
cd pykitti
python setup.py develop
Note that if you have previously installed pykitti you might have to remove all the previous versions.
pip uninstall pykitti
This package assumes that you have also downloaded the calibration data associated with the sequences you want to work on (these are separate files from the sequences themselves), and that the directory structure is unchanged from the original structure laid out in the KITTI zip files.
Homogeneous coordinate transformations are provided as 4x4 numpy.array
objects and are denoted as T_destinationFrame_originFrame
.
Pinhole camera intrinsics for camera N
are provided as 3x3 numpy.array
objects and are denoted as K_camN
. Stereo pair baselines are given in meters as b_gray
for the monochrome stereo pair (cam0
and cam1
), and b_rgb
for the color stereo pair (cam2
and cam3
).
More detailed examples can be found in the demos
directory, but the general idea is to specify what dataset you want to load, then access the parts you need and do something with them.
Camera and velodyne data are available via generators for easy sequential access (e.g., for visual odometry), and by indexed getter methods for random access (e.g., for deep learning). Images are loaded as PIL.Image
objects using Pillow.
import pykitti
basedir = '/your/dataset/dir'
date = '2011_09_26'
drive = '0002'
# The 'frames' argument is optional - default: None, which loads the whole dataset.
# Calibration, timestamps, and IMU data are read automatically.
# Camera and velodyne data are available via properties that create generators
# when accessed, or through getter methods that provide random access.
data = pykitti.raw(basedir, date, drive, dataset='extract', frames=range(0, 50, 5))
# to use the synced datasets, set dataset='sync'
# dataset.calib: Calibration data are accessible as a named tuple
# dataset.timestamps: Timestamps are parsed into a list of datetime objects
# dataset.oxts: List of OXTS packets and 6-dof poses as named tuples
# dataset.camN: Returns a generator that loads individual images from camera N
# dataset.get_camN_timestamp(idx): Return the timestamp of the image from camera N at idx
# dataset.get_camN(idx): Returns the image from camera N at idx
# dataset.gray: Returns a generator that loads monochrome stereo pairs (cam0, cam1)
# dataset.get_gray(idx): Returns the monochrome stereo pair at idx
# dataset.rgb: Returns a generator that loads RGB stereo pairs (cam2, cam3)
# dataset.get_rgb(idx): Returns the RGB stereo pair at idx
# dataset.velo: Returns a generator that loads velodyne scans as [x,y,z,reflectance]
# dataset.get_velo(idx): Returns the velodyne scan at idx
point_velo = np.array([0,0,0,1])
point_cam0 = data.calib.T_cam0_velo.dot(point_velo)
point_imu = np.array([0,0,0,1])
point_w = [o.T_w_imu.dot(point_imu) for o in data.oxts]
for cam0_image in data.cam0:
# do something
pass
cam2_image, cam3_image = data.get_rgb(3)
PIL Image data can be converted to an OpenCV-friendly format using numpy and cv2.cvtColor
:
img_np = np.array(img)
img_cv2 = cv2.cvtColor(img_np, cv2.COLOR_RGB2BGR)
import pykitti
basedir = '/home/user/data' # path to folder data is contained in
date = '2011_09_26'
drive = '0002'
data = pykitti.raw(basedir, date, drive, dataset='extract')
# for synced datasets, set dataset='sync'
gt_file = '/home/user/data/data.csv' # where you want to save the ground truth csv
data.export_gt_to_csv(gt_file)
Note: This package does not actually require that OpenCV be installed on your system, except to run demo_raw_cv2.py
.
[1] A. Geiger, P. Lenz, C. Stiller, and R. Urtasun, "Vision meets robotics: The KITTI dataset," Int. J. Robot. Research (IJRR), vol. 32, no. 11, pp. 1231–1237, Sep. 2013. http://www.cvlibs.net/datasets/kitti/ `