Home / Technology / AI & IT / DARPA MTR will develop algorithms to enable SAR sensors to detect, geolocate, and image moving ground and airborne targets.

DARPA MTR will develop algorithms to enable SAR sensors to detect, geolocate, and image moving ground and airborne targets.

The aim of ground surveillance is the large scale, continuous and near real time determination of a dynamical ground picture. This task comprises detection and tracking of moving single targets and convoys, mobile weapon systems, and military equipment. The sensors of choice are airborne Ground Moving Target Indicator (GMTI) radar and synthetic aperture radar (SAR).


Moving target indication (MTI) is a mode of operation of a radar to discriminate a target against the clutter. It describes a variety of techniques used to find moving objects, like an aircraft, and filter out unmoving ones, like hills or trees. It contrasts with the modern stationary target indication (STI) technique, which uses details of the signal to directly determine the mechanical properties of the reflecting objects and thereby find targets whether they are moving or not.


Early MTI systems generally used an acoustic delay line to store a single pulse of the received signal for exactly the time between broadcasts (the pulse repetition frequency). This stored pulse will be sent to the display along with the next received pulse. The result was that the signal from any objects that did not move mixed with the stored signal and became muted out. Only signals that changed, because they moved, remained on the display. These were subject to a wide variety of noise effects that made them useful only for strong signals, generally for aircraft or ship detection.


The introduction of phase-coherent klystron transmitters, as opposed to the incoherent cavity magnetron used on earlier radars, led to the introduction of a new MTI technique. In these systems, the signal was not fed directly to the display, but first fed into a phase detector. Stationary objects did not change the phase from pulse to pulse, but moving objects did. By storing the phase signal, instead of the original analog signal, or video, and comparing the stored and current signal for changes in phase, the moving targets are revealed. This technique is far more resistant to noise, and can easily be tuned to select different velocity thresholds to filter out different types of motion.


Phase coherent signals also allowed for the direct measurement of velocity via the Doppler shift of a single received signal. This can be fed into a bandpass filter to filter out any part of the return signal that does not show a frequency shift, thereby directly extracting the moving targets. This became common in the 1970s and especially the 1980s. Modern radars generally perform all of these MTI techniques as part of a wider suite of signal processing being carried out by digital signal processors.


MTI may be specialized in terms of the type of clutter and environment: airborne MTI (AMTI), ground MTI (GMTI), etc., or may be combined mode: stationary and moving target indication (SMTI). As ground target tracking often suffers from dense target situations, high clutter, and low visibility, the integration and fusion of external background information is essential for providing precise and continuous tracks.


Synthetic aperture radar (SAR) was originally designed as an airborne ground-imaging radar technology. As an all-weather day/night imaging technology, and because of its ability to create highresolution imagery from a long standoff range, SAR has been widely used for various military purposes, including surveillance and reconnaissance. But the military is understandably interested in also being able to detect, locate, and track moving targets on the ground, a process called ground moving target indication (GMTI).


Unfortunately, due to the nature of how SAR works, it is inherently poorly suited to the task of GMTI. SAR only focuses targets and image features that remain stationary during the data collection. A moving ground target therefore does not focus in a conventional SAR image, which complicates the process of performing GMTI with SAR systems.


DARPA  launched MTR program in July 2020 to develop  algorithms and collection techniques that allow synthetic aperture radar, or SAR, sensors to “detect, geolocate, and image moving ground targets,” the announcement read. If the goals of the project are met, the MTR program will then work to develop automatic target recognition algorithms for the moving target images.


The Moving Target Recognition program from the Defense Advanced Research Projects Agency’s Strategic Technology Office is a “vital part” of DARPA’s “Mosaic Warfare” vision, in which each weapon system is one “tile” in a large force package that overwhelms the adversary.


US ADOD requirements for  moving target indication  in its sensor data

The U.S. Army is also working through the challenges associated with advanced target recognition capabilities, such as ensuring that algorithms receive adequate and sufficient data to mature and learn. “If you’re training an algorithm to recognize cats, you can get on the internet and pull up hundreds of thousands of pictures of cats,” Gen. Mike Murray, commander of Army Futures Command, said in June. “You can’t do that for a T-72 [Russian tank]. You can get a bunch of pictures, but are they at the right angles, lighting conditions, vehicle sitting camouflaged to vehicle sitting open desert?”


The U.S. Air Force Research Laboratory has awarded Descartes Labs a $2.2 million contract to generate real-time analytics with a focus on developing moving target indication data, the company announced in Oct. 2020. Under this new contract, AFRL will gain access to the company’s geospatial analytics platform, which uses artificial intelligence and computer vision to process and fuse sensor data, such as satellite imagery, for tactical use.


Descartes Labs claims the focus of this contract will involve using its platform to help the Air Force solve the challenge of generating moving target indication data for ground and airborne targets. The New Mexico-based company was recently awarded a contract from AFRL and AFWERX — an Air Force effort to spark innovation through nontraditional vendors — that gave the service access to Descartes Labs’ geospatial analytics platform for multi-sensor data fusion and situational awareness. The company has also worked with the Defense Advanced Research Projects Agency and the National Geospatial-Intelligence Agency, helping the firm further refine its approach.


“Through the implementation of multi-sensor analytics, the Air Force is creating a forward-thinking state-of-the-art national security system,” Mike Warren, Descartes Labs co-founder and chief technology officer, said in a statement. “Through increasing use of diverse types of data, the Air Force is laying the groundwork to solve tactical intelligence, surveillance and reconnaissance problems now and in the future.” This latest contract was issued through AFRL’s Space Technology Advanced Research program, which was launched in summer 2019 to develop enabling technologies for space-based capabilities, including on-orbit servicing, debris management, ground systems and more.


MTR pogram

Under the MTR program, performers will develop algorithms and collection techniques to enable SAR sensors to detect, geolocate, and image moving ground targets. Emphasis is on military vehicle targets, including slow moving vehicles whose SAR signatures are superimposed on clutter. If the goals of moving target detection, geolocation, and imaging are successfully achieved, the MTR program will proceed to develop ATR algorithms for the moving target images.


MTR will include airborne data collect experiments to test and evaluate the algorithms. Performers will be responsible for the airborne radar sensors and flight services. The Government team will be responsible for designing experiments involving moving ground vehicles, instrumented to provide ground truth.


The MTR program will be executed in two phases:

Phase 1, solicited by this BAA, will focus on SAR moving target detection, geolocation, and imaging. Phase 1 consists of a 24-month Base Period and a 6-month Option Period. Proposers to this BAA must submit proposals for the Phase 1 Base Period and Option Period. It is anticipated that awards to multiple performer teams will be made for Phase 1.

Phase 2, not solicited by this BAA, will focus on ATR for the moving target images. Prior to the end of the Phase 1 Base Period, proposal instructions for Phase 2 will be issued to the Phase 1 performers.




References and Resources also include:





About Rajesh Uppal

Check Also

Quantum-Powered AI: Unlocking the Potential of Quantum Computing in Artificial Intelligence

In the ever-evolving landscape of technology, certain combinations have the power to redefine industries. Quantum …

error: Content is protected !!