HOG Descriptors can be uesd to identify an object with a sliding window. It is very slow, so the goal is to train an SVM on the data to speed up the process. This method is much more reliable then the color segmentation we had previously relied on. Below is a snapshot of the selection window…
This Week We Got one competition task working using point cloud data, in the pool Successfully bumped the buoy Proved that the cameras work pretty well in dark conditions Ralph got all of the bags on the sub onto the third computer in MIL, “WALL-E” Forrest added a bunch of features to TxROS at our request,…
To all visitors and interested students: the Machine Intelligence Lab has changed rooms from MAEB 325 to MAEC 126.
2012 assembly auvsi board design buoy competition controller DDS dvl electrical ethernet failure fall grabber GUI hydrophone mae manufacturing merge board Outreach packing Panama City pcb pelican pipe pool python rain robosub ROS seabotix shooter software spring 2012 software pneumatics pool summer testing thrusters trajectory generator travel tropical storm Twitter vision visual servoing waterproofing webcast