Search

The current proliferation of Unmanned Aircraft Systems provides an increasing amount of full-motion video (FMV) that, among other things, encodes geospatial intelligence. But the FMV is rarely converted into useful products, thus the intel potential is wasted. We have developed four concept demonstrations of methods to convert FMV into more immediately useful products, including: more accurate coordinates for objects of interest; timely, geo-registered, orthorectified imagery; conversion of mouse-clicks to object coordinates; and first-person-perspective visualization of graphical control measures. We believe these concepts can convey valuable geospatial intelligence to the tactical user.

To command a rover to go to a location of scientific interest on a remote planet, the rover must be capable of reliably tracking the target designated by a scientist from about ten rover lengths away. The rover must maintain lock on the target while traversing rough terrain and avoiding obstacles without the need for communication with Earth. Among the challenges of tracking targets from a rover are the large changes in the appearance and shape of the selected target as the rover approaches it, the limited frame rate at which images can be acquired and processed, and the sudden changes in camera pointing as the rover goes over rocky terrain. We have investigated various techniques for combining 2D and 3D information in order to increase the reliability of visually tracking targets under Mars like conditions. We present the approaches that we have examined on simulated data and tested onboard the Rocky 8 rover in the JPL Mars Yard and the K9 rover in the ARC Marscape. These techniques include results for 2D trackers, ICP, visual odometry, and 2D/3D trackers.