acfr / cam_lidar_calibration

(ITSC 2021) Optimising the selection of samples for robust lidar camera calibration. This package estimates the calibration parameters from camera to lidar frame.
Apache License 2.0
438 stars 103 forks source link

Can't filter point cloud with rqt #63

Open EMIR-Mh01 opened 1 month ago

EMIR-Mh01 commented 1 month ago

Screenshot from 2024-07-19 02-26-46 i work with velodyne as lidar and an optical camera and i want the topic of features_extraction to appear in rviz but the only points that appear are velodyne_points i want the calibration with my own data . I have changed the params.yaml and camera_info.yaml according to my dataset. distortion_model: "plumb_bob" width: 1280 height: 720 D: [0.137822,0.35667,-0.035565,0.006467] K: [975.093708 , 0, 649.525527 ,0. , 980.29991878, 310.223634,0. 0. 1. ]]

Topics

camera_topic: "/rtsp_stream" camera_info: "/camera_info" lidar_topic: "/velodyne_points"

Dynamic rqt_reconfigure default bounds

feature_extraction: x_min: 3.0 x_max: 7.0 y_min: -3.0 y_max: 3.0 z_min: -1.7 z_max: 0.0 k: 50 z: 1 voxel_res: 0.4

Properties of chessboard calibration target

chessboard: pattern_size: height: 7 width: 5 square_length: 70 board_dimension: width: 45.7 height: 58.7 translation_error: x: 2 y: 2 I am currently trying your v2 package as well. Still the dynamic rqt window can't apply to my data. I can't see the pointcloud data change after I apply the filter. Do I suppose to wait longer? Btw, I made to few changes to let the package compile with my ROS Noetic version.

zayedrmdn commented 1 month ago

Has this issue been solved? @EMIR-Mh01