SPECIAL NOTICE
A -- Fiddler Program Proposer's Day
- Notice Date
- 2/7/2022 6:08:17 PM
- Notice Type
- Special Notice
- NAICS
- 541715
— Research and Development in the Physical, Engineering, and Life Sciences (except Nanotechnology and Biotechnology)
- Contracting Office
- DEF ADVANCED RESEARCH PROJECTS AGCY ARLINGTON VA 222032114 USA
- ZIP Code
- 222032114
- Solicitation Number
- DARPA-SN-22-23
- Response Due
- 3/4/2022 5:00:00 PM
- Point of Contact
- Dr. Kevin Rudd
- E-Mail Address
-
HR001122S0016@darpa.mil
(HR001122S0016@darpa.mil)
- Description
- *This notice corrects the Notice ID from a previous Special Notice posting (DARP-SN-22-23) to the correct Notice ID of DARPA-SN-22-23. All other aspects of the previous posting, including response date and time, remain unchanged. Investments by the commercial and government sectors are leading to a rapid growth in earth-observation satellites and remote-sensing data. In particular, Synthetic Aperture Radar (SAR) can produce high-resolution images of the earth at night and in all-weather conditions [1]. This unique imaging capability makes SAR particularly useful for time-critical applications including change-detection after natural disasters and identifying illegal fishing operations [2]. The objective of the Fiddler program is to improve automatic object recognition in SAR images. Object recognition often requires significant examples to train machine learning (ML) classification algorithms. Obtaining training data can be time consuming, expensive, and even impossible in dynamic conditions.� The use of machine learning and computer vision methods to generate training data in dynamic maritime environments is of particular interest to this program.� Performers will first develop methods to create object reference models directly from real SAR image examples. From these models, they will develop methods to generate or render synthetic SAR images of the object at new imaging geometries and configurations. Performers will then demonstrate generation of diverse training data to rapidly train robust SAR object detection methods from few real examples.� For more information, please see the attached Special Notice DARPA-SN-22-23. Additional Resources [1] NASA � What is SAR - https://earthdata.nasa.gov/learn/backgrounders/what-is-sar� [2] Defense Innovation Unit - xView3 Challenge - https://www.diu.mil/ai-xview-challenge#xview3
- Web Link
-
SAM.gov Permalink
(https://sam.gov/opp/94f14230d6424489a5839383e6833d24/view)
- Record
- SN06234628-F 20220209/220207230110 (samdaily.us)
- Source
-
SAM.gov Link to This Notice
(may not be valid after Archive Date)
| FSG Index | This Issue's Index | Today's SAM Daily Index Page |