Jul 2026· The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences· Vol XLIX-B1-2026, pp. 17-23· 0 citations· 3 references
TL;DR
A masking strategy during orthophoto generation is proposed, where U-Net is employed to detect shadow regions and Laplacian variance is used to identify blurred areas, thereby improving the reliability of orthophotos for automated pavement condition assessment.
Abstract
Abstract. Traditional pavement inspection and data collection are often constrained by traffic conditions, operational safety, and equipment costs, making it difficult to achieve both efficiency and large-scale coverage. To address these limitations, this study employs a Pavement Roughness Index and Distress Extraction System (PRIDEs), which integrates high-resolution industrial cameras, high-precision global navigation satellite system (GNSS), wheel pulse sensors, and an onboard computer to acquire high-quality images under high-speed driving conditions. Using photogrammetry and computer vision techniques, camera poses are reconstructed to generate dense point clouds, digital surface models (DSMs), and orthophotos for detailed pavement distress analysis. However, the acquired imagery is affected by dynamic shadows and lens-focusing induced blur, resulting in ghosting artifacts and inconsistent orthophoto quality. To mitigate these issues, this study proposes a masking strategy during orthophoto generation, where U-Net is employed to detect shadow regions and Laplacian variance is used to identify blurred areas. By integrating these masks, more uniform and higher-quality orthophotos can be produced. Experimental results demonstrate that the proposed approach effectively reduces false positives and false negatives of crack detection caused by shadows and blur, thereby improving the reliability of orthophotos for automated pavement condition assessment.
Under heavy traffic loads, pavement cracks have become a major factor affecting asphalt pavement performance, while conventional rehabilitation remains time-consuming and labour-intensive. Intelligent maintenance equipment offers an effective way to improve repair efficiency. Although deep learning methods have been widely used for crack detection, they often require large annotated data sets, high computational resources and retraining for different pavement conditions. In contrast, traditional image-processing methods are computationally efficient and data-independent, but their accuracy is easily affected by noise and shadows. To address these limitations, this study proposes a depth-camera-based crack localisation and tracking method that integrates multiple image-processing algorithms, including shadow removal, crack mask extraction and skeleton point identification. The proposed method was implemented on a self-developed intelligent asphalt-pavement repair robot equipped with a depth camera. Experimental results show that the method can track pavement cracks in real time during robot movement, achieving an intersection over union value of 0.80, compared with 0.42 for the conventional method. The proposed approach provides a practical balance between detection accuracy and computational efficiency.
Yuchi Lei, Liuzhen Ren, Jiangzhuo Ren et al.· Proceedings of the Instituti...· 0 citations
Introduction.
Regular road surface monitoring is essential for an objective assessment of road conditions and timely intervention to combat emerging deformations. Traditional survey methods have long been limited to visual inspection, while developing pavement microcracks could remain undetected for a long time, subsequently leading to significant repair costs. A pressing issue is the development of a road surface monitoring methodology that can detect changes in road surface geometry, including microrelief analysis.
Methods and Materials.
In modern practice, a detailed assessment of road surface conditions uses a three-dimensional representation of the surface as an array of laser reflection points obtained by terrestrial and mobile laser scanning. Road surface changes, including deformations, can be monitored and assessed by comparing point clouds obtained using stereophotogrammetry at different times. This requires minimizing the influence of external orientation errors on the clouds obtained at different times by aligning them with each other. A prototype equipped with a full-frame digital camera and a GNSS geodetic receiver was used. Between surveys conducted along two routes approximately one hour apart, changes in the asphalt surface during the specified time were simulated using specialized monitoring mockups to ensure that the survey data reflected both actual pavement deformations and simulated changes. The resulting point clouds contained over 40 million points each. To optimize the analysis, they were thinned to a density of 5 mm and cropped at the boundaries of the study area. The coordinates of the image projection centers were determined in RTK mode. The thinned point clouds were imported into Cloud Compare software (ENST, France) for analysis.
Results.
For the study, photogrammetric models of the surveys were constructed, with point clouds superimposed on one another using exterior orientation parameters. The analysis revealed deviations that made it impossible to align the point cloud superposition results. Using the ICP algorithm, a reanalysis of the point clouds was performed after mutual orientation, shifting the second cloud relative to the first using a stable contour. Models placed after the initial survey showed actual changes. It was established that the accuracy of cloud construction based on the
original exterior orientation parameters of the images was insufficient, and after integrating the point clouds using ICP algorithms, display improvements were evident.
Discussion and Conclusion.
Photogrammetric survey systems exist that are relatively simple to use and relatively inexpensive, as exemplified by the presented model. It has been established that using only the coordinates of projection centers obtained using GNSS measurements as the initial data will result in insufficient point cloud orientation accuracy, specifically for deformation monitoring. However, the system is simple in design, and using modern ICP algorithms, it is possible to align two different time-lapse images, achieving millimeter-level accuracy in deformation changes. These images can be used to detect dynamic road cracks and predict road surface changes. This system, as a relatively inexpensive and simple piece of equipment, can be used for municipal needs, as well as for assessing deformations in specific areas (such as utility punctures or projectile impacts on road sections), to facilitate rapid response.
L. Pronina, V. L. Bykov, A. A. Fedorovsky et al.· The Russian Automobile and H...· 0 citations
Inspection activities on industrial assets, for instance in the aerospace or automotive industry, frequently pertain to the examination of the surface conditions of objects. Among the established techniques for surface assessment, photogrammetry has gained increasing relevance in manufacturing quality monitoring, due to its ability to provide high-fidelity 3D spatial data. However, during the photogrammetric reconstruction of a physical object, some regions may be reconstructed less accurately, for example due to an insufficient number of local photographic acquisitions; in such cases, additional photographs of these regions would be needed. This, however, requires the object to remain accessible and unchanged from the time of the initial acquisition; in practice, this condition is rarely met, as the object is often no longer accessible or is found in a different state. Therefore, photogrammetry is intrinsically tied to the acquisition moment, since it relies on images captured at a specific time and does not allow purpose-driven further inspection. This paper proposes a solution to this limitation of traditional photogrammetry, exploiting the concept of “3D scene”, defined as a high-fidelity digital representation of an object at a specific moment in time. Recent advances in radiance-field methods, particularly Gaussian Splatting (GS), enable the creation of fully navigable 3D
frozen-in-time
scenes, allowing for the extraction of digital images, i.e., renders, that can be integrated into the photogrammetric process to enhance reconstruction quality. The most significant advantage of GS-based scenes is that they are generated from exactly the same photographs used for the preliminary (and sometimes incomplete) photogrammetric reconstruction, without requiring any additional acquisitions. This combined use of photogrammetry and GS introduces the innovative paradigm of
back-in-time inspection
into manufacturing. This study addresses two main research questions: (i)
How can the combined use of photogrammetry and GS be employed for inspection tasks?
and (ii)
To what extent does GS improve reconstruction completeness and defect detectability?
A case study in the aerospace sector is proposed to demonstrate the effectiveness of this method.
M. Trombini, D. Maisano, F. Franceschini· The International Journal of...· 0 citations
Accurate 3D reconstruction of pavement textures is vital for assessing surface performance. This study systematically evaluates the factors influencing the precision of close-range photogrammetry for pavement texture characterization. Four typical mixtures, AC-13, AC-16, SMA-16, and OGFC-16, were reconstructed from 17 to 145 photographs, with high-precision laser scanning as the reference. Reconstruction quality was quantified by point cloud density, elevation deviations, and four texture parameters. Findings reveal that dense-graded yields 81–87% of points within 0–0.5 mm deviation, while open-graded achieves only 51%. Point cloud density increases with photo count but follows diminishing returns, stabilizing between 21 and 73 images. Photogrammetric texture parameters systematically underestimate laser values, yet preserve relative ranking among gradations. Ssk and Sku are highly sensitive to extreme noise, especially on fine-textured surfaces. These insights offer practical guidelines for implementing photogrammetric techniques in pavement engineering.
Lian-Guo Song, Di Yun, Le Wang et al.· Materials· 0 citations
Photogrammetric 3D city models contain detailed planimetric and elevation information that supports urban visualization and low-altitude applications. However, the direct dissemination of high-accuracy models may expose sensitive geometric measurements. Existing protection methods mainly focus on conventional encryption, coordinate scrambling, or two-dimensional data perturbation and do not adequately balance geometric accuracy degradation with the visual usability of textured 3D meshes. This study proposes a controlled geometric deformation method that processes the planimetric and elevation components independently. In the horizontal domain, a normalized Sigmoid function generates smooth, bounded, and spatially varying coordinate displacements. In the vertical domain, a normalized deformation function combines global elevation stretching with amplitude-constrained sine-wave superposition. The sine-wave parameters are generated using a seed-sensitive hybrid cascaded chaotic system, producing reproducible but model-dependent nonlinear deformation patterns. During processing, the mesh connectivity, face indices, texture coordinates, texture images, and material relationships remain unchanged. The method was evaluated using low-rise and high-rise photogrammetric 3D scenes with different horizontal extents and elevation characteristics. Under the selected 10 m planimetric and 5% elevation settings, the mean planimetric displacements were 10.474 and 10.045 m, while the relative elevation deformations were 5.01% and 5.30%, respectively. Both datasets maintained monotonic elevation relationships and achieved 100% direction consistency. Their spatial-shape coefficients deviated from the corresponding reference values by only 0.02% and 1.33%. The results demonstrate that the proposed method provides controllable and spatially continuous geometric deformation while maintaining mesh connectivity, overall morphology, and visual interpretability. It can therefore serve as a practical pre-processing approach for the risk-reduced dissemination and non-measurement-oriented visualization of photogrammetric 3D city models.
Si-Yuan Zou, Zibo Xu, Yiwen Wang et al.· Remote Sensing· 0 citations
This data article describes BD-PaveSurface, a pavement surface image dataset developed for image-level assessment of three pavement surface conditions: crack, pothole, and good pavement surface. The images were collected through systematic field surveys from selected segments of National Highways N5 and N6 in Pabna District, which form part of the Pabna-Dhaka highway route in Bangladesh. Smartphone cameras were used to capture pavement surface images under natural outdoor lighting and real traffic-environment conditions, without interrupting normal traffic movement. Data collection was conducted over an extended period across rainy-season, winter, and summer conditions to capture realistic variation in pavement appearance, illumination, surface moisture, shadows, dust, and texture. The collected images underwent manual screening and image-level labeling. Labeling was conducted by a five-member annotation team, with each image independently reviewed by a second team member. Disagreements were resolved through consensus using predefined class criteria and the dominant-condition rule for mixed crack–pothole cases, followed by independent validation by a Civil Engineering faculty member. After removal of unsuitable samples and label verification, the cleaned raw dataset contained 9000 field images, with 3000 images in each pavement condition class. To support machine-learning-based pavement condition assessment, a processed/augmented subset was prepared from the cleaned images. The preprocessing workflow converted images to RGB format and resized them to 224 × 224 pixels. The cleaned images were split into training, validation, and testing subsets before augmentation, and augmentation operations were then applied only to the training subset. The validation and testing subsets contained only standardized original images and were not augmented. The cleaned raw dataset represents 9000 unique field-acquired pavement images. The processed/augmented subset contains 12,000 derivative image files generated from these field-acquired images, comprising standardized 224 × 224 versions of all 9000 cleaned originals and 3000 newly generated training-only augmented images (1000 per class). Accordingly, the dataset contains 21,000 stored image files in total; however, these files do not represent 21,000 distinct field acquisitions or physical pavement locations. Publicly available Bangladesh-focused pavement image datasets containing both crack and pothole samples remain limited. BD-PaveSurface contributes a field-collected, multi-weather pavement image resource from a South Asian road environment and can be reused for automated pavement condition assessment, crack and pothole recognition, transfer learning, data augmentation studies, computer vision benchmarking, and low-cost camera-based road monitoring.
D. Dutta, Utsho Kundu, Nakib Aman et al.· Data in Brief· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
