Artificial Intelligence/Machine Learning, Army STTR, Phase I
Passive Ranging for Fire Control under Day and Night Conditions
Objective
Design and build a system that can passively range to operationally relevant distances in daylight, low light, overcast and night conditions.
Description
To date much work has been invested in active ranging. However, laser-based probes are detectable and will leave the operator vulnerable, particularly at night. Commercial applications, particularly those for self-driving vehicles, use a combination of both active and passive sensors.
Low light imagers have been recently announced, that span both the VNIR, and SWIR and some are even capable of single photon detection. These low-light detectors are likely intended for the automotive market. Many, but not all have resolutions approaching HDTV. They offer, either through correlation or key-point signature comparisons a way to determine range covertly in what until now has been consider challenging situations.
Passive ranging is a desired new capability for our individual soldiers and for military platforms. It is not in any currently fielded system. Providing a measured range accuracy of +/- 20 meters at 300 meters is adequate for a proof-of-concept demonstration.
Phase I
Develop overall system design that includes specifications for ranging to distances of 100 meters, 300 meters and 1km. State the possibilities and challenges to achieving those ends including estimates of uncertainties in range.
Consider both GPS and GPS denied regions of operations. Accuracy goals should be approximately +/- 20 meters at 300 meters with a linear increase to +/- 60 meters at 1000 meters.
Phase II
Develop and demonstrate a prototype system in a realistic environment. Conduct testing to prove feasibility over extended operating conditions. Accuracy goals should be approximately +/- 20 meters at 300 meters with a linear increase to +/- 60 meters at 1000 meters.
Phase III
This system could be used in abroad range of military and civilian applications where ranging and tracking are necessary. Optimize system design for size, weight and power, to include ruggedization to survive in a military environment.
Submission Information
Please refer to the 23.B BAA for more information. Proposals must be submitted via the DoD Submission site at https://www.dodsbirsttr.mil/submissions/login
References:
- Fitzgibbon, A. (2001). Simultaneous linear estimation of multiple view geometry and lens distortion. CVPR, IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Kauai, HI Dec8-14: IEEE. doi:0.1109/CVPR.2001.990465
- Hartley, R. (2003). Multiple View Geometry in Computer Vision. Cambridge, England: Cambridge University Press. doi:isbn-13 978-0-521-54051-3
- Yang, J. (2020) Z. Lu, Y.Y. Tang, Z. Yuan and Y. Chen; Quasi Fourier-Mellin Transform for Affine Invariant Features; IEEE Transactions on Image Processing, Vol. 29, 2020
- Reilly, P. (1999) T. Klein, and H. Ilves; “Design and Demonstration of an Infrared Passive Ranger”; Johns Hopkins APL Technical Digest, Vol 20, No. 2, pp. 220-235, 1999.
- Tomasi (1992), Carlo and Kanade, Takeo; Shape and Motion from Image Streams under Orthography: a Factorization Method”; International Journal of Computer Vision; Vol 9, no 2, pp. 137-154.
- Pelegris, Gerasimos (1994); “A triangulation Method for Passive Ranging”; Master’s Thesis Naval Postgraduate School; Monterey California. DTIC AD-A284 180
- Range finders and Tracking; Summary Technical Report of Division 7, National Defense Research Committee; V. Bush, Director; J.B. Conant, Chairman; H.L. Hazen, Division 7 Chief; 1947
Objective
Design and build a system that can passively range to operationally relevant distances in daylight, low light, overcast and night conditions.
Description
To date much work has been invested in active ranging. However, laser-based probes are detectable and will leave the operator vulnerable, particularly at night. Commercial applications, particularly those for self-driving vehicles, use a combination of both active and passive sensors.
Low light imagers have been recently announced, that span both the VNIR, and SWIR and some are even capable of single photon detection. These low-light detectors are likely intended for the automotive market. Many, but not all have resolutions approaching HDTV. They offer, either through correlation or key-point signature comparisons a way to determine range covertly in what until now has been consider challenging situations.
Passive ranging is a desired new capability for our individual soldiers and for military platforms. It is not in any currently fielded system. Providing a measured range accuracy of +/- 20 meters at 300 meters is adequate for a proof-of-concept demonstration.
Phase I
Develop overall system design that includes specifications for ranging to distances of 100 meters, 300 meters and 1km. State the possibilities and challenges to achieving those ends including estimates of uncertainties in range.
Consider both GPS and GPS denied regions of operations. Accuracy goals should be approximately +/- 20 meters at 300 meters with a linear increase to +/- 60 meters at 1000 meters.
Phase II
Develop and demonstrate a prototype system in a realistic environment. Conduct testing to prove feasibility over extended operating conditions. Accuracy goals should be approximately +/- 20 meters at 300 meters with a linear increase to +/- 60 meters at 1000 meters.
Phase III
This system could be used in abroad range of military and civilian applications where ranging and tracking are necessary. Optimize system design for size, weight and power, to include ruggedization to survive in a military environment.
Submission Information
Please refer to the 23.B BAA for more information. Proposals must be submitted via the DoD Submission site at https://www.dodsbirsttr.mil/submissions/login
References:
- Fitzgibbon, A. (2001). Simultaneous linear estimation of multiple view geometry and lens distortion. CVPR, IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Kauai, HI Dec8-14: IEEE. doi:0.1109/CVPR.2001.990465
- Hartley, R. (2003). Multiple View Geometry in Computer Vision. Cambridge, England: Cambridge University Press. doi:isbn-13 978-0-521-54051-3
- Yang, J. (2020) Z. Lu, Y.Y. Tang, Z. Yuan and Y. Chen; Quasi Fourier-Mellin Transform for Affine Invariant Features; IEEE Transactions on Image Processing, Vol. 29, 2020
- Reilly, P. (1999) T. Klein, and H. Ilves; “Design and Demonstration of an Infrared Passive Ranger”; Johns Hopkins APL Technical Digest, Vol 20, No. 2, pp. 220-235, 1999.
- Tomasi (1992), Carlo and Kanade, Takeo; Shape and Motion from Image Streams under Orthography: a Factorization Method”; International Journal of Computer Vision; Vol 9, no 2, pp. 137-154.
- Pelegris, Gerasimos (1994); “A triangulation Method for Passive Ranging”; Master’s Thesis Naval Postgraduate School; Monterey California. DTIC AD-A284 180
- Range finders and Tracking; Summary Technical Report of Division 7, National Defense Research Committee; V. Bush, Director; J.B. Conant, Chairman; H.L. Hazen, Division 7 Chief; 1947