Towards Cognitive Defect Analysis in Active Infrared Thermography with Vision-Text Cues

2026-03-11

AI Summary

This study addresses the high deployment cost and reliance on extensive labeled data in conventional AI methods for detecting internal defects in carbon fiber-reinforced polymers (CFRP) using active infrared thermography (AIRT). The work proposes a language-guided cognitive defect analysis framework that, for the first time, integrates a pretrained vision-language model (VLM) into AIRT. By incorporating a lightweight, custom-designed AIRT-VLM adapter, the method achieves zero-shot defect understanding and localization without requiring task-specific training data. It effectively bridges the domain gap between thermal and natural images, substantially enhancing defect visibility and feature alignment. Evaluated on 25 real-world CFRP test sequences, the approach improves signal-to-noise ratio by over 10 dB and attains a zero-shot detection Intersection over Union (IoU) of 70%, significantly outperforming traditional dimensionality reduction techniques.

Technology Category

• Computer Vision: Language and Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Active infrared thermography (AIRT) is currently witnessing a surge of artificial intelligence (AI) methodologies being deployed for automated subsurface defect analysis of high performance carbon fiber-reinforced polymers (CFRP). Deploying AI-based AIRT methodologies for inspecting CFRPs requires the creation of time consuming and expensive datasets of CFRP inspection sequences to train neural networks. To address this challenge, this work introduces a novel language-guided framework for cognitive defect analysis in CFRPs using AIRT and vision-language models (VLMs). Unlike conventional learning-based approaches, the proposed framework does not require developing training datasets for extensive training of defect detectors, instead it relies solely on pretrained multimodal VLM encoders coupled with a lightweight adapter to enable generative zero-shot understanding and localization of subsurface defects. By leveraging pretrained multimodal encoders, the proposed system enables generative zero-shot understanding of thermographic patterns and automatic detection of subsurface defects. Given the domain gap between thermographic data and natural images used to train VLMs, an AIRT-VLM Adapter is proposed to enhance the visibility of defects while aligning the thermographic domain with the learned representations of VLMs. The proposed framework is validated using three representative VLMs; specifically, GroundingDINO, Qwen-VL-Chat, and CogVLM. Validation is performed on 25 CFRP inspection sequences with impacts introduced at different energy levels, reflecting realistic defects encountered in industrial scenarios. Experimental results demonstrate that the AIRT-VLM adapter achieves signal-to-noise ratio (SNR) gains exceeding 10 dB compared with conventional thermographic dimensionality-reduction methods, while enabling zero-shot defect detection with intersection-over-union values reaching 70%.

Problem

• active infrared thermography
• subsurface defect analysis
• carbon fiber-reinforced polymers
• training dataset
• zero-shot detection

Innovation

• vision-language models
• zero-shot defect detection
• active infrared thermography
• domain adaptation
• cognitive defect analysis