31 May 2013 Reliable ISR algorithms for a very-low-power approximate computer
Author Affiliations +
The Office of Naval Research (ONR) is looking for methods to perform higher levels of sensor processing onboard UAVs to alleviate the need to transmit full motion video to ground stations over constrained data links. Charles River Analytics is particularly interested in performing intelligence, surveillance, and reconnaissance (ISR) tasks using UAV sensor feeds. Computing with approximate arithmetic can provide 10,000x improvement in size, weight, and power (SWAP) over desktop CPUs, thereby enabling ISR processing onboard small UAVs. Charles River and Singular Computing are teaming on an ONR program to develop these low-SWAP ISR capabilities using a small, low power, single chip machine, developed by Singular Computing, with many thousands of cores. Producing reliable results efficiently on massively parallel approximate machines requires adapting the core kernels of algorithms. We describe a feature-aided tracking algorithm adapted for the novel hardware architecture, which will be suitable for use onboard a UAV. Tests have shown the algorithm produces results equivalent to state-of-the-art traditional approaches while achieving a 6400x improvement in speed/power ratio.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ross S. Eaton, Ross S. Eaton, Jonah C. McBride, Jonah C. McBride, Joseph Bates, Joseph Bates, "Reliable ISR algorithms for a very-low-power approximate computer", Proc. SPIE 8713, Airborne Intelligence, Surveillance, Reconnaissance (ISR) Systems and Applications X, 871312 (31 May 2013); doi: 10.1117/12.2016009; https://doi.org/10.1117/12.2016009


Real-time video exploitation system for small UAVs
Proceedings of SPIE (August 20 2013)
Aerial video mosaicking using binary feature tracking
Proceedings of SPIE (May 18 2015)
A nearly real-time UAV video flow mosaic method
Proceedings of SPIE (December 08 2014)
Video inpainting using scene model and object tracking
Proceedings of SPIE (February 18 2013)
Vehicle classification in video using virtual detection lines
Proceedings of SPIE (December 23 2013)

Back to Top