search

hku-mars / livox_camera_calib

This repository is used for automatic calibration between high resolution LiDAR and camera in targetless scenes.
GNU General Public License v2.0
925 stars 207 forks source link

opencv error : how to solve #103

Open 963070827 opened 9 months ago

963070827 commented 9 months ago

OpenCV Error: Assertion failed (npoints >= 0 && (depth == CV_32F || depth == CV_64F)) in projectPoints, file /build/opencv-L2vuMj/opencv-3.2.0+dfsg/modules/calib3d/src/calibration.cpp, line 3269 terminate called after throwing an instance of 'cv::Exception' what(): /build/opencv-L2vuMj/opencv-3.2.0+dfsg/modules/calib3d/src/calibration.cpp:3269: error: (-215) npoints >= 0 && (depth == CV_32F || depth == CV_64F) in function projectPoints

[lidar_camera_calib-2] process has died [pid 30868, exit code -6, cmd /home/book/catkin_ws/devel/lib/livox_camera_calib/lidar_camera_calib name:=lidar_camera_calib log:=/home/book/.ros/log/fcc6bae4-d009-11ee-a8f2-000c29375306/lidar_camera_calib-2.log]. log file: /home/book/.ros/log/fcc6bae4-d009-11ee-a8f2-000c29375306/lidar_ca image mera_calib-2*.log

image

Richard-Cold commented 4 months ago

我也遇到了相同的问题，请问你解决这个问题了吗？

happypuppy128 commented 3 months ago

同样的，我也遇到了这个问题，请问你们有解决吗？

Richard-Cold commented 3 months ago

main调用的calibra.colorCloud函数->在向pts_3d容器中添加元素时，过滤条件color_intensity_threshold_值偏高，导致没有元素被添加到pts_3d中，进而导致传入cv::projectPoints函数的pts_3d.size=0。 在pcd文件中，第四列为intensity激光强度。需要根据这这个数据来修改calib_outdoor.yaml中对应值。