Semi-supervised deep learning for target detection in imaging data
Harness the power of semi-supervised deep learning to improve target detection accuracy from raw imaging data and diagnostic test kits, with applications in medical diagnosis and aerial detection.
Overview
This solution leverages semi-supervised deep learning to enhance the detection of targets from raw imaging data and diagnostic test kit results. By integrating these data sources, our approach improves the detection accuracy and robustness for various applications, including medical diagnostics and aerial target recognition. Supported by funding from organizations such as NSF, DARPA, and others, this technology aims to provide a more efficient and accurate solution for industries that rely on precise target detection.
Technical specifications
Key features:
- Utilizes semi-supervised deep learning techniques to process raw imaging data and diagnostic test kit results.
- Acknowledges and leverages correlations between imaging channels, particularly in hyperspectral data.
- Provides leaner models with enhanced accuracy and robustness compared to traditional RGB image processing methods.
- Successfully applied to image-based medical diagnosis and aerial target detection.
Technology readiness level
This technology is at TRL 5, indicating that it has been validated in a relevant environment. Future validation plans involve tailoring methods to specific projects by collaborating with domain experts to analyze data, discuss results, and improve methodologies.
About University of Michigan
The University of Michigan is a comprehensive public research university based in Ann Arbor with additional campuses in Dearborn and Flint, known for a broad, interdisciplinary research enterprise and a major academic health system. Industry partners engage through co-located facilities, including a large north campus research complex with shared labs and incubator space, plus on-campus testbeds for rapid prototyping and validation. Proximity to Detroit’s mobility and manufacturing base, plus dedicated business engagement teams, streamlines sponsored research and access to talent. Research is supported by competitive federal funding from agencies such as NIH, NSF, DOE, and DoD, alongside state and industry sponsorship. A centralized tech transfer office manages IP, licensing, and startup support, with corporate memberships and flexible agreements.
delivered to your inbox.