MotionDSP: The increasing importance of the GPU in the Armed Forces

Unmanned Aerial Vehicles (UAVs) represent the latest in high-tech weaponry deployed to strengthen and improve the military’s capabilities.

But with new technologies come new challenges, such as capturing actionable intelligence while flying at speeds upwards of 140 mph, 10 miles above the earth.

One key feature of the UAV is that it is capable of providing a real-time stream of detailed images taken with multiple cameras on the vehicle simultaneously. The challenge is that the resulting images need to be rendered, stabilized and enhanced in real-time and across vast distances in order to be useful.

Once they have been processed, the images can give infantry critical information about potential challenges ahead—the end goal being to ensure the safety and protection of military personnel in the field. Using CPUs alone, this process is very time consuming and does not allow information to be viewed in real-time. As a result, military action could be based on potentially outdated intelligence data and inaccurate guides.

MotionDSP, a software company based in San Mateo, California, has developed “superresolution” algorithms that allow it to reconstruct video with better and cleaner detail, increased resolution and reduced noise. All of which are ideal for the live streaming of video from the cameras attached to a UAV.

Ikena ISR features computationally intense, advanced motiontracking algorithms that provide the basis for sophisticated image stabilization and super-resolution video reconstruction. Perhaps most importantly, it can all be run on off-theshelf Windows laptops and servers.

Using NVIDIA Tesla GPUs, MotionDSP’s customers, which include a variety of military-funded research groups, are making UAVs safer and more reliable while reducing deployment costs, improving simulation accuracy and dramatically boosting performance.

Using only CPUs to execute the kind of sophisticated video postprocessing algorithms required for effective reconnaissance would result in up to six hours of processing for each one hour of video—not a viable solution when real-time results are critical. In contrast, Tesla GPUs enable MotionDSP’s Ikena ISR software to process any live video source in real-time with less than 200ms of latency. Moreover, instead of requiring expensive CPU-clustered computing systems to complete the work, Ikena can perform at full capacity on a standard workstation small enough to fit inside military vehicles.

“Super-resolution” algorithms allow MotionDSP to reconstruct video withbetter and cleaner detail, increased resolution and reduced noise.