A cutting-edge software system developed by Sandia National Laboratories has the remarkable capability of detecting threats beyond the range of human and sensor visibility. This innovative technology can identify and track moving objects, even those as small as a single pixel, enabling advanced surveillance and threat detection capabilities.

The groundbreaking patented software system can identify motion curves within streaming video and images from satellites, drones, and far-range security cameras. This innovative system converts these motion curves into signals, enabling the detection and tracking of even the tiniest moving objects, as small as one pixel. According to the developers, this technology has the potential to enhance the performance of various remote sensing applications significantly.

“Being able to track each pixel from a distance matters, and it is an ongoing and challenging problem,” said Tian Ma, a computer scientist and co-developer of the system. “For physical security surveillance systems, for example, the farther out you can detect a possible threat, the more time you have to prepare and respond. Often the biggest challenge is the simple fact that when objects are located far away from the sensors, their size naturally appears to be much smaller. Sensor sensitivity diminishes as the distance from the target increases.”

Photo of Robert Anderson and Tian Ma
Robert Anderson, left, and Tian Ma developed a new, patented software system at Sandia National Laboratories that gives remote sensing equipment like satellites, drones and security cameras a major performance boost in detecting small moving objects from far away. (Photo by Bret Latter)


In 2015, Ma and Robert Anderson embarked on developing the Multi-frame Moving Object Detection System (MMODS) as part of a Sandia Laboratory Directed Research and Development project. Their work has culminated in a recent publication about MMODS in Sensors.

Detecting One Moving Pixel Among Millions

Typically, remote sensing systems can only detect objects visible within a single video frame. However, as explained by Ma, MMODS introduces a novel approach by utilizing a multi-frame method to detect small objects in low visibility conditions. At a computer station, image streams from multiple sensors are processed in real time by MMODS using an image filter on a frame-by-frame basis. An advanced algorithm identifies movement in the video frames and transforms it into target signals that can be correlated and integrated across a sequence of video frames. This innovative process significantly enhances the ability to detect and track objects under challenging environmental conditions.

MMODS graphic
This image shows how running streaming data through Sandia National Laboratories’ Multi-frame Moving Object Detection System makes objects that are otherwise unseeable possible to detect and track. (Image by Eric Lundin)


This process significantly enhances the signal-to-noise ratio and overall image quality. The moving target’s signal is systematically correlated over time, steadily increasing its prominence in the image. Conversely, background noise, such as wind movements, which lack correlation and move randomly, is effectively filtered out and eliminated from the final image. This method ensures that the detected signals are more pronounced and relevant, leading to improved precision and accuracy in target detection.

Before MMODS being implemented for remote sensing improvement, Ma and Anderson conducted a demonstration of its effectiveness using simulated data. They successfully detected target objects as small as one pixel, even when the signal-to-noise ratio was close to 1:1, signifying minimal distinction between the signal and noise. This validation showcased the robustness and reliability of MMODS in identifying small targets amidst challenging conditions.

Under typical circumstances, these objects would remain undetectable to both human eyes and sensors. The baseline detector system achieved a 30% chance of detecting a moving object. However, when MMODS was integrated into the system, the detection rate significantly improved to 90% without any increase in the rate of false alarms. This substantial enhancement in detection capabilities highlights the effectiveness and reliability of MMODS in identifying previously elusive moving objects without compromising accuracy.

In another demonstration, the researchers used MMODS to detect moving objects from live data collected with a remote camera at the peak of Sandia Mountain. Without prior knowledge of Albuquerque’s roads, MMODS detected vehicles moving throughout the city.

“Given that a modern video camera has about 10 million pixels, being able to detect and track one pixel at a time is a major advance in computer vision technology,” Ma said. “MMODS has been proven to improve modern detection sensitivity by 200 to 500% and works for fast- and slow-moving objects, even in poor visibility conditions.”

Sandia National Laboratories

Sandia National Laboratories is a multimission laboratory operated by National Technology and Engineering Solutions of Sandia LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration. Sandia Labs has major research and development responsibilities in nuclear deterrence, global security, defense, energy technologies and economic competitiveness, with main facilities in Albuquerque, New Mexico, and Livermore, California. (Press Release)

To read the research paper on Ma and Anderson’s work, visit Remote Sensing Low SNR Target Detection Enhancement

Stay on top of industry news, developments, resources and articles- Sign up for a free C-UAS Hub Membership to bookmark your favorite content and receive our informative newsletters and important industry updates!

Post Image- Sandia National Laboratories’ Multi-frame Moving Object Detection System makes it possible for remote sensors to detect small moving objects that would normally be unseeable to both sensors and human eyes. (Infographic by Eric Lundin)