Accelerating Human Detection Algorithm Development with Synthetic EO/IR Imagery in MuSES

Thursday, October 22, 2026 | 9:00 – 10:00AM ET

Developing robust human detection and recognition algorithms requires large, diverse datasets that capture the wide range of conditions encountered in real-world operations. Variations in human pose, clothing, environmental conditions, time of day, sensor perspective, and scene background can significantly impact algorithm performance. While measured data provides valuable training resources, collecting sufficient diverse datasets (particularly in the MWIR and LWIR) can be time consuming, costly, and difficult to scale.
Synthetic imagery provides a powerful alternative by enabling rapid generation of high-fidelity, pixel-aligned EO/IR datasets with controlled and repeatable variations. In this webinar, ThermoAnalytics will demonstrate how physics-based simulation using MuSES, target models, and CoTherm can be leveraged to generate diverse synthetic scenes containing human dismounts across a range of clothing configurations, poses, environmental conditions, and sensor perspectives.
This presentation will highlight how these synthetic datasets can be integrated into a modern deep-learning workflow using the YOLO11 object detection framework. Results will demonstrate the ability of synthetic EO/IR imagery to support algorithm training and evaluation while systematically exploring challenging detection conditions that may be difficult to capture through measured imagery alone.
Attendees will gain insight into how physics-based synthetic data generation can help accelerate algorithm development, expand dataset diversity, and reduce the burden of data collection for EO/IR human detection applications.

Who Should Attend

This webinar is ideal for engineers, data scientists, researchers, and defense technologists working at the intersection of simulation, AI, and threat detection.

Presenters

Jacob Hendrickson

Thermal/CFD Engineer

Jacob Hendrickson is a Thermal/CFD Engineer at ThermoAnalytics, Inc., where he works within the Engineering Services group based in Novi, Michigan. He focuses on thermal model preparation and validation, including full vehicle thermal models developed using TAITherm. Hendrickson also supports the company’s defense-side work, running EOIR simulations for target assets and their associated synthetic scene-scapes using MuSES. His human thermal modeling contributions include developing a new manikin model test bed design and creating a novel infant physiology model for TAITherm’s Human Modeling Extension. He holds a B.S. in Mechanical Engineering from Michigan Technological University and an M.B.A.

Audrey Levanen

Thermal/CFD Engineer

Audrey Levanen is a Thermal/CFD Engineer at ThermoAnalytics, Inc., where she supports defense-focused thermal and infrared modeling, synthetic data generation for AI/ML applications, and human comfort simulation projects. She has developed custom Python tools for automating image annotation and analyzing thermal comfort results, helping streamline workflows for both simulation and data science teams. Audrey joined ThermoAnalytics full-time in 2023 after interning with the company and earning her B.S. in Mechanical Engineering from Michigan Technological University.

Register for the webinar