ankitdhall / lidar_camera_calibration

ROS package to find a rigid-body transformation between a LiDAR and a camera for "LiDAR-Camera Calibration using 3D-3D Point correspondences"
http://arxiv.org/abs/1705.09785
GNU General Public License v3.0
1.47k stars 459 forks source link

Using transformation matrix #143

Open Gold3nFox opened 2 years ago

Gold3nFox commented 2 years ago

After running and copying transformation matrix from terminal I'm trying to use that transformation matrix to extract color from image and add it to pcd output of velodyne lidar, I used open3d to read point cloud and extract each point which has x and y and z and transformed it with transformation matrix. Range of each point before and after transformation is : x: -6.706142902374268 -> 39.4197998046875 y: -65.62940216064453 -> 6.3055100440979 z: -0.8670438528060913 -> 9.03710079193 But pictures x and y is from 0 to page width pixel , 0 to page height pixel I'm new to this and i don't really know how to use x and y and z after transformation to get that pixel from image, I assumed i should ignore z as the image is 2d.