The intelligent inspection of power lines and other difficult-to-access structures and facilities has been greatly enhanced by the use of Unmanned Aerial Vehicles (UAVs), which allow inspection in a safe, efficient, and high-quality fashion. This paper analyzes the characteristics of a scene containing power equipment and the operation mode of UAVs. A low-cost virtual scene is created, and a training sample for the power-line components is generated quickly. Taking a vibration-damper as the main object, an assembled detector based on geometrical constraint (ADGC) is proposed and is used to analyze the virtual dataset. The geometric positional relationship is used as the constraint, and the Faster Region with Convolutional Neural Network (R-CNN), Deformable Part Model (DPM), and Haar cascade classifiers are combined, which allows the features of different classifiers, such as contour, shape, and texture to be fully used. By combining the characteristics of virtual data and real data using UAV images, the power components are detected by the ADGC. The result produced by the detector with relatively good performance can help expand the training set and achieve a better detection model. Moreover, this method can be smoothly transferred to other power-line facilities and other power-line scenarios.

The Façade Opening Rate (FOR) reflects a building’s capacity to withstand seismic loads, serving as a crucial foundation for seismic risk assessment and management. However, FOR data are often outdated or nonexistent in rural areas, which are particularly vulnerable to earthquake damage. This paper proposes a practical framework for estimating FORs from real-scene 3D models derived from UAV photogrammetry. The framework begins by extracting individual buildings from 3D models using annotated roof outlines. The known edges of the roof outline are then utilized to sample and generate orthogonally projected front-view images for each building façade, enabling undistorted area measurements. Next, a modified convolutional neural network is employed to automatically extract opening areas (windows and doors) from the front-view façade images. To enhance the accuracy of opening area extraction, a vanishing point correction method is applied to open-source street-view samples, aligning their style with the front-view images and leveraging street-view-labeled samples. Finally, the FOR is estimated for each building by extracting the façade wall area through simple spatial analysis. Results on two test datasets show that the proposed method achieves high accuracy in FOR estimation. Regarding the mean relative error (MRE), a critical evaluation metric which measures the relative difference between the estimated FOR and its ground truth, the proposed method outperforms the closest baseline by 5%. Moreover, on the façade images we generated, the MRE of our method was improve by 1% and 2% compared to state-of-the-art segmentation methods. These results demonstrate the effectiveness of our framework in accurately estimating FORs and highlight its potential for improving seismic risk assessment in rural areas.

In this paper, we present a novel approach to radiometric normalization for aerial images, effectively addressing both intra- and inter-image color and illumination inconsistencies caused by varying sensor technologies, atmospheric conditions, and ground reflection. We introduce a comprehensive mathematical model for radiance transfer, which addresses brightness inhomogeneities resulting from the Bidirectional Reflectance Distribution Function (BRDF) effect and vignetting effect, alongside color inconsistencies due to atmospheric and illumination variations. To enhance the model's efficiency and stability for solutions, we employ a strategy that leverages multiple polynomial models for approximation, significantly simplifying the complexity of rigorous solutions. Our efficient and robust solution leverages advanced radiometric triangulation theories, enabling effective radiometric normalization of aerial images. We validate the efficacy of our method with extensive testing on three large datasets, each containing over two hundred aerial images. The experimental results showcase our method's superiority over state-of-the-art methods, as evidenced by enhanced visual quality and improved quantitative performance in statistical assessments.

In this paper, we present a novel matching method tailored for unmanned aerial vehicle (UAV) thermal infrared images of photovoltaic (PV) panels characterized by highly repetitive textures. This method capitalizes on the integration of point and line features within the image to obtain reliable corresponding points. Furthermore, it employs multiple constraints to eliminate mismatched features and get rid of the interference of repetitive textures on feature matching. To verify the effectiveness of the proposed method, we used an UAV equipped with the DJI Zenmuse H20T thermal infrared gimbal to capture 3767 images of a PV power station in Guangzhou, China. Experiments demonstrate that, for UAV thermal infrared images of PV panels, our method outperforms the state-of-the-art techniques in terms of the density of matching points, matching success rate and matching reliability, consequently leading to robust aerial triangulation results.

In order to solve the problem that defects of different scales have different terahertz imaging characteristics in fiber reinforced composites, the fusion processing method of two terahertz images with complementary defect information was studied. To reduce the Gibbs phenomenon, Non-subsampled Shearlet Transform (NSST) with the property of shift- invariance was used to decompose source images and get their low-frequency subband and high frequency subband coefficients. Regional variance was used as connection strength factor of the Pulse Coupled Neural Network (PCNN) in the low frequency coefficient fusion, which is more according with human visual characteristics. In the fusion of high frequency coefficients, the Regional Gradient Energy of Direction Information Measure (RGEDIM) was introduced to extract the edge, texture and other details of the image and integrated them into the final image, the impact of noise on image fusion was reduced better. Finally, the fusion image was obtained through NSST inverse transform. The experimental results show that this method is superior to wavelet, Non-subsampled Contourlet Transform (NSCT) and traditional PCNN method, the fusion image has more mutual information and contains more original image information, all the defects of the source image can be clearly seen on the fusion image.

The equator’s unique combination of high humidity and temperature renders optical satellite imagery highly susceptible to persistent cloud cover. In contrast, synthetic aperture radar (SAR) offers a robust alternative due to its ability to penetrate clouds with microwave imaging. This study addresses the challenges of cloud-induced data gaps and cross-sensor geometric biases by proposing an advanced optical and SAR image-matching framework specifically designed for cloud-prone equatorial regions. We use a prompt-driven visual segmentation model with automatic prompt point generation to produce cloud masks that guide cross-modal feature-matching and joint adjustment of optical and SAR data. This process results in a comprehensive digital orthophoto map (DOM) with high geometric consistency, retaining the fine spatial detail of optical data and the all-weather reliability of SAR. We validate our approach across four equatorial regions using five satellite platforms with varying spatial resolutions and revisit intervals. Even in areas with more than 50 percent cloud cover, our method maintains sub-pixel edging accuracy under manual check points and delivers comprehensive DOM products, establishing a reliable foundation for downstream environmental monitoring and ecosystem analysis.