Hybrid Temperature-Emissivity Separation for LWIR Imaging via Numerical Estimation and Residual Learning = 수치해석 및 잔차 학습을 이용한 이중 대역 원적외선 영상의 하이브리드 온도-방사율 분리 기법

다국어 초록 (Multilingual Abstract)

Long-Wave Infrared (LWIR) imaging is a critical sensing modality for industrial inspection, surveillance, and remote sensing due to its ability to operate independently of external illumination. However, accurate temperature retrieval from LWIR images is fundamentally challenged by the "thermal crossover" phenomenon, where the coupling between object temperature and surface emissivity creates spectral ambiguity. Conventional Temperature-Emissivity Separation (TES) methods typically rely on high-dimensional hyperspectral data, which incurs high computational costs and hardware complexity, or adopt constant emissivity assumptions that fail in heterogeneous material environments.
To address these limitations, this paper proposes a novel hybrid TES framework designed for dual-band LWIR imaging systems. The proposed method synergizes physics-based numerical estimation with data-driven residual correction to achieve parameter retrieval robust against structural biases inherent in simplified radiative models with minimal spectral information. The framework consists of two sequential stages. First, an Adaptive Hybrid Numerical Solver computes an initial estimate of temperature and emissivity based on a simplified radiative transfer model. This solver integrates the Newton-Raphson method for rapid convergence with Brent's method for global stability, ensuring reliable initialization even under non-linear radiative conditions. Second, a Residual Compensation Network, designed based on the ConvNeXt architecture, corrects the structural errors introduced by the model simplifications. By learning the residual mapping between the initial numerical estimates and the ground truth, the network recovers physically accurate parameters without the need for complex multispectral measurements.
Experimental results demonstrate that the proposed method significantly outperforms conventional single-band approaches and achieves accuracy comparable to multispectral techniques while maintaining high computational efficiency. This study presents a practical and effective solution for quantitative thermal analysis in dual-band LWIR sensing systems.

목차 (Table of Contents)

• Table of Contents
• List of figures
• List of tables
• Abstract (English)
• Chapter 1: Introduction 1
• Chapter 2: Physical Background and Related Works 11
• 2.1: Fundamentals of Thermal Radiation in the LWIR Spectrum 11
• 2.2: RadianceTemperatureEmissivity Relationship in LWIR Imaging 14
• 2.3: Related Works on TemperatureEmissivity Separation 17
• 2.3.1: Constant Emissivity Assumption 19
• 2.3.2: Classical Multispectral TES Approaches 21
• 2.3.3: Bayesian and Statistical Approaches 24
• 2.3.4: Deep learning-based TES Methods 27
• Chapter 3: Proposed TemperatureEmissivity Separation Method 30
• 3.1: Overview of the Proposed Framework 30
• 3.2: Simplified Radiative Model for Dual-Band Formulation 32
• 3.3: Dual-Band Nonlinear Formulation 36
• 3.4: Optimal Band Selection Strategy 38
• 3.5: Numerical Initial Estimation Strategy 42
• 3.5.1: Primary Strategy: Newton-Raphson Method 44
• 3.5.2: Fallback Mechanism: Brent-based Safeguarding 45
• 3.5.3: Implementation of the Adaptive Hybrid Solver 46
• 3.6: Residual Compensation Network 47
• 3.6.1: Residual Learning Framework for Structural Error Compensation 48
• 3.6.2: Network Architecture and Training Strategy 50
• 3.7: Summary of Proposed TES Process 55
• Chapter 4: Experimental Results and Analysis 57
• 4.1 Experimental Setup 57
• 4.2 Evaluation of Band Selection Strategy 60
• 4.3 Quantitative Performance Analysis 62
• 4.4 Qualitative Results 65
• Chapter 5: Conclusion 69
• References 71
• Abstract (Korean) 75
• Acknowledgement 77