Security personnel who must watch dozens of video feeds are easily distracted and poorly alerted to changes in threat conditions, particularly where image contrast is poor and scenes are cluttered. Conventional automated methodologies for moving target indication (MTI) also suffer from unacceptably high false alarm rates and bulky calculation schemes that require significant computational resources.
The US Army Research Lab (ARL) has developed a unique software solution using adaptive background models that enable detection of legitimate targets in a busy scene, subtracting those targets from less interesting background changes and creating an accurate change map, thus reducing human error and computer-generated false positives. The algorithm is robust and is not susceptible to “reverse polarity” where the brightness or intensity of a moving object changes throughout a video sequence. With ARL’s system, once the target is identified, it remains clearly distinct from the background. ARL’s method is also data efficient, reducing computational requirements as compared to competing methods. While initially developed for forward-looking infrared images, the algorithm is adaptable to most types of video imaging.
- Superior MTI tracking that overcomes human challenges with low light and low contrast video streams
- Reduces computational complexity and supports real-time operation
- High-functioning with visible light (color or grayscale) or infrared imaging spectra (WWIR, LWIR)
- Potential applications include tracking humans, vehicles, and wildlife
- Issued US Patent 7,460,689 is available for license
- Potential for collaboration with ARL inventor team and laboratory
Supplemental Technical Information:
For more information, contact:
Dan Swanson | firstname.lastname@example.org | (406) 994-7736
In order to apply for license to federally owned technologies, regulations require that specific information be provided regarding your company and plans for commercialization. This information will be incorporated in a license agreement which will be provided for your review prior to signature. All provided information will be considered proprietary and held confidential.