AI-powered Processing of Thermal Data
Join our online event and learn how artificial intelligence can help you capture and analyze thermal data even more effectively, recognize patterns, and reliably identify anomalies. Our experts will show you how machine learning and deep learning can optimize thermography, and how you can use thermal imaging data as additional sensor inputs for AI and image processing systems to unlock new possibilities for data processing and industrial quality assurance.
Current Appointments
- AI-powered Processing of Thermal Data (english)Virtual
Date
2026-11-10, 09:00 GMT – 11:00 GMTRegister now
Taking Data Processing, Machine Vision, and Industrial Quality Assurance to the Next Level
Compared with methods such as pyrometry, infrared thermography provides not only individual temperature values but also complex thermograms and image sequences showing the spatial and temporal distribution of those values. These contain valuable thermal information from which conclusions can be drawn about the properties and quality of materials, components, and processes. Artificial intelligence can extract and analyze this information more effectively, recognize patterns, and reliably identify anomalies.
Stable, reproducible, and high quality input data are crucial for reliable AI models. InfraTec’s infrared cameras provide the best conditions for this.
Key Features of InfraTec’s Infrared Cameras
High spatial resolution up to 1.3 µm
High thermal sensitivity up to < 0.015 K
Precise calibration
High frame rates up to 105,000 Hz per sub frame
Thus, they provide reliable and accurate measurement data, even when thermal processes occur rapidly or the signals are weak.
𝗔 𝗚𝗹𝗮𝗻𝗰𝗲 𝗮𝘁 𝘁𝗵𝗲 𝗘𝘃𝗲𝗻𝘁
Use of convolutional neural networks and predictive models for processing thermal data
Reliable AI models based on stable, reproducible, and high-quality input data from InfraTec infrared cameras
Acquisition, analysis, processing, and export of thermographic measurement data with IRBIS® 3, including NumPy-compatible formats
Application examples such as automatic ROI detection, fewer false alarms in early fire detection, and the prediction of hardness characteristics in hot forming
Practical insights from two guest speakers on the use of AI to expand the possibilities of thermography
Complementary Technical Lecture
Technical Lecture 1
Referent: Dr. Krzysztof Dziarski, Poznan University of Technology
Title: AI in Thermography – How to Analyze Faster and Save Time?
Technical Lecture 2
Referent: Sruthi Krishna Kunji Purayil, Ph.D., Bundesanstalt für Materialforschung und -prüfung, Berlin
Title: AI-Driven Multimodal NDE Using Robot-Assisted Infrared Thermography
