ROS Resources: Documentation | Support | Discussion Forum | Index | Service Status | ros @ Robotics Stack Exchange
Ask Your Question

Revision history [back]

click to hide/show revision 1
initial version

I've recently used aruco_detect successfully. It worked well first time using the DICT_5X5_50 dictionary. (I only needed a few landmarks.) The only problem I had was that it needed to run on a Raspberry Pi. aruco_detect (or the underlying library in OpenCV) could only process about 1fps on the RPi. I used the message_filters package to drop image frame rate down to 1fps before using the detector. (If the frame rate is too fast for aruco_detect, the node eventually used enough memory – presumably for message buffering – to hang the RPi.)