ROS Resources: Documentation | Support | Discussion Forum | Index | Service Status | ros @ Robotics Stack Exchange |
1 | initial version |
All of the answers are outdated. Please completely forget ork, you will just waste your time on it for poor results on all pipelines.
Use v4r https://github.com/strands-project/v4r_ros_wrappers/blob/master/Readme.md form debians for a solution at least 10 times better than everything mentioned before. Install it from debians and use the multishot version. It works with textured an untextured objects (SIFT and SHOT based) .
A neural network alternative is YOLO https://pjreddie.com/darknet/yolo/ but it has no pose estimation afaik.
2 | No.2 Revision |
All of the answers are outdated. Please completely forget ork, you will just waste your time on it for poor results on all pipelines.
Use v4r https://github.com/strands-project/v4r_ros_wrappers/blob/master/Readme.md form debians https://rgit.acin.tuwien.ac.at/v4r/v4r_ros_wrappers for a solution at least 10 times better than everything mentioned before. Install it from debians and use the multishot version. It works with textured an untextured objects (SIFT and SHOT based) .
A neural network alternative is YOLO https://pjreddie.com/darknet/yolo/ but it has no pose estimation afaik. afaik.
3 | No.3 Revision |
All of the answers are outdated. Please completely forget ork, you will just waste your time on it for poor results on all pipelines.
Use v4r https://rgit.acin.tuwien.ac.at/v4r/v4r_ros_wrappers for a solution at least 10 times better than everything mentioned before. Install it from debians and use the multishot version. It works with textured an untextured objects (SIFT and SHOT based) .
A neural network alternative is YOLO https://pjreddie.com/darknet/yolo/ but it has no pose estimation afaik.
Another try is this package: https://github.com/cagbal/ros_people_object_detection_tensorflow/blob/master/README.md
4 | No.4 Revision |
All of the answers are outdated. Please completely forget ork, you will just waste your time on it for poor results on all pipelines.
Use v4r https://rgit.acin.tuwien.ac.at/v4r/v4r_ros_wrappers v4r for a solution at least 10 times better than everything mentioned before. Install it from debians and use the multishot version. It works with textured an untextured objects (SIFT and SHOT based) .
A neural network alternative is YOLO https://pjreddie.com/darknet/yolo/ YOLO but it has no pose estimation afaik.
Another try is this package: https://github.com/cagbal/ros_people_object_detection_tensorflow/blob/master/README.mdpackage