Mono + IMU - Realsense d455 shows nothing on ubuntu 20.04 Orin NX

[Hendyley]

I am following the instruction from

https://github.com/HKUST-Aerial-Robotics/VINS-Fusion/

I successfully catkin_make

however when I try to run

3.1 Monocualr camera + IMU
roslaunch vins vins_rviz.launch
rosrun vins vins_node ~/catkin_ws/src/VINS-Fusion/config/euroc/euroc_mono_imu_config.yaml
(optional) rosrun loop_fusion loop_fusion_node ~/catkin_ws/src/VINS-Fusion/config/euroc/euroc_mono_imu_config.yaml
rosbag play MH_01_easy.bag

I got error

terminate called after throwing an instance of 'cv::Exception'
what(): OpenCV(4.5.4) /home/ubuntu/build_opencv/opencv/modules/core/src/matrix.cpp:250: error: (-215:Assertion failed) s >= 0 in function 'setSize'
OR
terminate called after throwing an instance of 'cv::Exception'
what(): OpenCV(4.5.4) /home/ubuntu/build_opencv/opencv/modules/core/src/alloc.cpp:73: error: (-4:Insufficient memory) Failed to allocate 558470286869760 bytes in function 'OutOfMemoryError'

[Zhihaibi]

Well, I got the same problem in ubuntu 20.04, Jetson Orin NX:

When run the demo:
roslaunch vins vins_rviz.launch
rosrun vins vins_node ~/catkin_ws/src/VINS-Fusion/config/euroc/euroc_mono_imu_config.yaml
(optional) rosrun loop_fusion loop_fusion_node ~/catkin_ws/src/VINS-Fusion/config/euroc/euroc_mono_imu_config.yaml
rosbag play MH_01_easy.bag

I got the error:

terminate called after throwing an instance of 'cv::Exception'
what(): OpenCV(4.5.4) /home/ubuntu/build_opencv/opencv/modules/core/src/alloc.cpp:73: error: (-4:Insufficient memory) Failed to allocate 558470286869760 bytes in function 'OutOfMemoryError'

[libobo6]

I got the same error in ubuntu 20.04, Jetson Xavier NX. Is there a good solution currently available？

[lijiaming5550]

同样问题

[lijiaming5550]

该问题是由于cv_bridge与opencv版本冲突导致的：例如本机采用的opencv版本为4.6.0，而采用apt-get install cv_bridge的对应版本为4.2.0.
解决方案为：将cv_bridge并链接到自己的opencv版本，可参考csdn相关博客

This issue is caused by a conflict between the cv_bridge and opencv versions: for example, the opencv version used on this machine is 4.6.0, while the corresponding version of apt-get install cv_bridge is 4.2.0.
The solution is to link cv_bridge to your own opencv version, which can be referred to on CSDN related blogs