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

Revision history [back]

I don't understand first part of your question. Pose estimation in training we do for calculation transformation between frames.

mode = xx

Now tod_detecting contains two recognizers. First version of TOD (textured_object_detection) was implemented for recognizing objects on 5 MP prosilica dataset. Later we with Ethan began to re-factor this code. In result we get two versions of detection algorithms: Kinect mode and TOD mode. Kinect mode gives better results on Kinect data, TOD mode gives better results on 5MP data.

I don't understand first part of your question. Pose We do pose estimation in training we do for calculation transformation between frames.

mode = xx

Now tod_detecting contains two recognizers. First version of TOD (textured_object_detection) (textured_object_detection package) was implemented for recognizing objects on 5 MP prosilica dataset. Later we with Ethan and me began to re-factor refactor this code. In result we get two versions of detection algorithms: Kinect mode and TOD mode. Kinect mode gives better results on Kinect data, TOD mode gives better results on 5MP data.