The analysis of infrared video images is becoming one of the methods used to detect thermal hazards in many large-scale engineering sites. The fusion of infrared thermal imaging and visible image data in the target area can help people to identify and locate the fault points of thermal hazards. Among them, a very important step is the registration of thermally visible images. However, the direct registration of images with large-scale differences may lead to large registration errors or even failure. This paper presents a novel two-stage thermal–visible-image registration strategy specifically designed for exceptional scenes, such as a substation. Firstly, the original image pairs that occur after binarization are quickly and roughly registered. Secondly, the adaptive downsampling unit partial-intensity invariant feature descriptor (ADU-PIIFD) algorithm is proposed to correct the small-scale differences in details and achieve finer registration. Experiments are conducted on 30 data sets containing complex power station scenes and compared with several other methods. The results show that the proposed method exhibits an excellent and stable performance in thermal–visible-image registration, and the registration error on the entire data set is within five pixels. Especially for multimodal images with poor image quality and many detailed features, the robustness of the proposed method is far better than that of other methods, which provides a more reliable image registration scheme for the field of fire safety.

To address the challenge of robotic inspection and maintenance in unmanned environments, this paper presents an integrated approach combining Conv2D-PSE-iTransformer for equipment state prediction, Dynamic Analytic Hierarchy Process (D-AHP) for health assessment, and deep reinforcement learning for optimized path planning. The Conv2D-PSE-iTransformer accurately predicts the operational state of electrical equipment, which serves as a critical input for the D-AHP evaluation. Based on the predicted state, D-AHP dynamically assesses the health of the equipment, enabling the identification of high-risk components that require immediate attention. Based on these evaluations, the DRL-based path planning generates optimized inspection routes that prioritize these high-risk areas while ensuring complete coverage with minimal inspection time. Experimental results demonstrate the effectiveness of this integrated method, highlighting its ability to reduce inspection time and enhance the overall efficiency, safety, and reliability of robotic inspections in complex, high-risk environments.