Person Tracking

Updated 09/03/15 - New videos cleared for release.

Deep Vision's technology provides robust, adaptable, real-time person tracking.

Deep Vision's technology is independent of the sensing platform, type of sensor or other targets within the sensor's data. Therefore, it can track people independent of sensor modality, sensor motion, and target motion. With no dependence on environmental factors, the technology can be deployed for person tracking from both aerial and ground-based systems. The solution is suited for both integration with existing sensor suites or for development of new products.

With and without prior knowledge of the person, or their characteristics, Deep Vision's people tracking technology delivers a highly robust, real-time target locking solution.

Technology Highlights
  • Runtime target designation
  • Automatic target detection
  • Continuous and accurate tracking of the target
  • Passive ranging to the target
  • 3D velocity vector relative to the sensor
  • Moving target moving platform
  • Instantaneous learning of newly acquired targets for future detection
Technology Details
  • Maintenance of a 30+ fps detection/tracking rate
  • Independent of sensor resolution: 640x480, 1024x768, 15MP, etc.
  • Implemented in C/C++
  • Developed in GNU/Linux, but operating system agnostic
  • Small memory footprint
  • Customisable to meet current and future product/programme requirements
  • Support for mobile devices, such as the Android operating system
  • Support for embedded platforms such as: Gumstix, SheevaPlug, etc.


An evading human target being chased down in the woods. Real-time tracking in a cluttered natural environment with chaotic sensor motion. The target moves unpredictably through a wooded area, leaving and entering the field of view. The target is continuously reacquired as it re-enters, even when it is partially obscured and only visible for a fraction of a second. This video was recorded using legacy interlacing - very noisy.

Another evading human target being chased down in the woods but this time recorded using progressive scan. Note how extreme sensor motion, changes in perspective and scale and wildly unpredictable behaviour of the target, including obsfucation to the point of loss, has little affect, if any, on tracking capability.

Designation and tracking of a human target. The target is tracked whilst the camera experiences high degrees of motion. The tracking is independent of target/platform motion, scale/pose of the target, in addition to changing target/background composition and dynamic reacquisition.

The operator designates a target at runtime and that target is tracked within the field of view, independent of target/platform motion, target scale/pose, and target/background composition. Note the extent of camouflage and track persistence through loss of focus.

Designation of a person in one sensor and handover that target for acquisition by another. Target information is immediately transmitted to all members of the distributed system.

Designation of a person in one area and reacquisition of the target in another area by another sensor. Target information is immediately transmitted to all members of the distributed system.