KUCL: Korea University Camera-LIDAR Dataset

<p><strong>Overview</strong></p> <p>The&nbsp;Korea University Camera-LIDAR (KUCL) dataset&nbsp;contains images and point clouds acquired in indoor and outdoor environments for various applications (e.g., calibration of rigid-body transformation between camera and LIDAR) in robotics and computer vision communities.</p> <ul> <li>Indoor dataset: contains 63 pairs of images and point clouds (&#39;indoor.zip&#39;). We collected the indoor dataset in a static indoor environment with walls, floor, and ceiling.</li> <li>Outdoor dataset: 61 pairs of images and point clouds (&#39;outdoor.zip&#39;). We collected the outdoor dataset in an outdoor environment including buildings and trees.</li> </ul> <p><strong>Setup</strong></p> <p>The images were taken using a Point Grey Ladybug5 (<a href="https://www.ptgrey.com/ladybug5-30-mp-usb-30-spherical-digital-video-camera-black">specifications</a>) camera and point clouds were acquired with a Velodyne VLP-16 LIDAR (<a href="https://velodynelidar.com/vlp-16.html">specifications</a>). We rigidly mounted both&nbsp;sensors on the sensor frame during the overall data acquisition. Each pair of images and point clouds was discretely acquired while maintaining the sensor system standing still to reduce time-synchronization problems.</p> <p><strong>Description</strong></p> <p>Each dataset (zip file) is organized as follows:</p> <ul> <li>images/pano: This folder contains spherical panorama images (8000 X 4000) collected using the Ladybug5.</li> <li>images/pinhole/cam0~cam5: These&nbsp;folders contain rectified pinhole images (2448 X 2048)&nbsp;collected using six cameras (cam0~cam5) of the Ladybug5.</li> <li>images/pinhole/mask: This folder contains the mask (BW image) of each camera of the Ladybug5.</li> <li>images/pinhole/cam_param_pinhole.txt: This file contains extrinsic (transformation from the Ladybug5 to each lens) and intrinsic (focal length and center) parameters of each lens of the Ladybug5.&nbsp;For details of Ladybug5 coordinate system, please refer to the <a href="https://www.ptgrey.com/tan/10621">technical application note</a>.</li> <li>scans: This folder contains point clouds collected using the VLP-16 LIDAR in text files. The first line of each file is the number of points (N), and the remaining lines are points and corresponding reflectivities (N X 4).</li> </ul> <p>We also provide MATLAB <a href="https://drive.google.com/file/d/1aeYfmquaivnUWWTjJ6kBT1jtPEihr-1g/view?usp=sharing">functions</a> projecting point cloud onto spherical panorama and pinhole images. Before running the following functions, please unzip the dataset file (&#39;indoor.zip&#39; or &#39;outdoor.zip&#39;) under the main directory.</p> <ul> <li>run_pano_projection.m: This function projects points onto a spherical panorama image. Lines 19-20 select dataset and index of an image and a point cloud.</li> <li>run_pinhole_projection.m: This function projects points onto a pinhole&nbsp;image. Lines 19-21 select dataset, index of an image and a point cloud, and pinhole camera index.</li> </ul> <p>The rigid-body transformation between the&nbsp;Ladybug5 and the&nbsp;VLP-16&nbsp;in each function&nbsp;is acquired using our edge-based Camera-LIDAR calibration method with Gaussian Mixture Model (GMM). For the details, please refer to our paper (<a href="https://doi.org/10.1002/rob.21893">https://doi.org/10.1002/rob.21893</a>).</p> <p><strong>Citation</strong></p> <p>Please cite the following paper when using this dataset in your work.</p> <ul> <li>Jaehyeon Kang and Nakju L. Doh, &quot;Automatic Targetless Camera-LIDAR Calibration by Aligning Edge with Gaussian Mixture Model,&quot; Journal of Field Robotics, vol. 37, no. 1, pp.158-179, 2020.</li> <li>@ARTICLE {kang-2020-jfr,<br> &nbsp; &nbsp; AUTHOR = {Jaehyeon Kang and Nakju Lett Doh},<br> &nbsp; &nbsp; TITLE = {Automatic Targetless Camera&ndash;{LIDAR} Calibration by Aligning Edge with {Gaussian} Mixture Model},<br> &nbsp; &nbsp; JOURNAL = {Journal of Field Robotics},<br> &nbsp; &nbsp; YEAR = {2020},<br> &nbsp; &nbsp; VOLUME = {37},<br> &nbsp; &nbsp; NUMBER = {1},<br> &nbsp; &nbsp; PAGES = {158--179},<br> }</li> </ul> <p><strong>License information</strong></p> <p>The KUCL dataset&nbsp;is released under a Creative Commons Attribution 4.0 International License,&nbsp;<a href="https://creativecommons.org/licenses/by/4.0/">CC BY&nbsp;4.0</a></p> <p><strong>Contact Information</strong></p> <p>If you have any issues about the KUCL dataset, please contact us at&nbsp;<a href="mailto:kangjae07@gmail.com">kangjae07@gmail.com</a>.</p>