SPECIAL NOTICE
70 -- Technology Licensing Opportunity for Real-Time Custom Activity Detection in Programmable Logic
- Notice Date
- 11/10/2022 12:31:38 PM
- Notice Type
- Special Notice
- NAICS
- 518210
— Data Processing, Hosting, and Related Services
- Contracting Office
- BATTELLE ENERGY ALLIANCE�DOE CNTR Idaho Falls ID 83415 USA
- ZIP Code
- 83415
- Solicitation Number
- BA-1426
- Response Due
- 11/30/2022 8:00:00 AM
- Point of Contact
- Andrew Rankin
- E-Mail Address
-
andrew.rankin@inl.gov
(andrew.rankin@inl.gov)
- Description
- TECHNOLOGY LICENSING OPPORTUNITY Real-Time Custom Activity Detection in Programmable Logic A novel video surveillance technology capable of customizable activity detection in real-time, using single frame analysis. Opportunity:�� Idaho National Laboratory (INL), managed and operated by Battelle Energy Alliance, LLC (BEA), is offering the opportunity to enter into a license and/or collaborative research agreement to commercialize the Custom Activity Detection technology. This technology transfer opportunity is part of a dedicated effort to convert government-funded research into job opportunities, businesses, and, ultimately, an improved way of life for the American people. Overview:������� Video surveillance data continues to expand, with more video coverage available daily. However, the analytics needed to alert operators on activities in real time have not kept up with the data collection rate. Object detection continues to be the state-of-the-art analytic associated with video surveillance footage. The most valuable analytical is activity detection, where the artificial intelligence system detects an activity of interest and then alerts the operator. However, the state-of-the-art for this type of analysis does not operate in real-time and requires a completed video feed for annotation. Researchers at INL have addressed these issues by designing a real-time activity detection model that brings activity detection to the camera and negates the need for central data processing. Description:��� This groundbreaking technology can enable real-time, customizable activity detection for video surveillance. It is designed specifically for deployment in inexpensive and low-power field-programmable gate arrays that can be directly integrated into a video camera, thereby bringing activity detection to the camera for the first time and negating the need to transmit large amounts of video data to a central location for processing. The activities the model can detect are also fully customizable. The single image time series representation (SITSR) provides a weighted average of several image frames in real time that can be used directly in a single CNN layer for identification and localization. The SITSR can be implemented by preprocessing the images or via layers prepended to traditional object-detection models. Prepending SITSR creation to the beginning of machine learning models has the additional benefits that the AI can learn the weights for averaging during model training and that SITSR computation does not incur increased computational costs. The SITSR is fully implementable in programmable logic for real-time deployment, along with the complete identification and localization layer. Benefits:��� ������ Allows real-time activity detection for video surveillance of high-security areas. Fully customizable to the specific detection needs of the user and includes the following: Human skeleton tracking that involves pose tracking Deep recurrent architectures Optical flow Single frame estimation Applications:�� � High-security area video surveillance. Development Status:� TRL 3, currently undergoing proof-of-concept work. INL seeks to license the above intellectual property to a company with a demonstrated ability to bring such inventions to the market. Exclusive rights in defined fields of use may be available. Added value is placed on relationships with small businesses, start-up companies, and general entrepreneurship opportunities. Please visit Technology Deployment�s website at https://inl.gov/inl-initiatives/technology-deployment for more information on working with INL and the industrial partnering and technology transfer process. Companies interested in learning more about this licensing opportunity should contact Andrew Rankin at td@inl.gov.
- Web Link
-
SAM.gov Permalink
(https://sam.gov/opp/cda9d4a99b7649ceaf7ca18379a6fcf0/view)
- Place of Performance
- Address: Idaho Falls, ID 83415, USA
- Zip Code: 83415
- Country: USA
- Zip Code: 83415
- Record
- SN06514693-F 20221112/221110230100 (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 |