An Intelligent Transportation System (ITS) is a vital component of smart cities due to the growing number of vehicles year after year. In the last decade, vehicle detection, as a primary component of ITS, has attracted scientific attention because by knowing vehicle information (i.e., type, size, numbers, location speed, etc.), the ITS parameters can be acquired. This has led to developing and deploying numerous deep learning algorithms for vehicle detection. Single Shot Detector (SSD), Region Convolutional Neural Network (RCNN), and You Only Look Once (YOLO) are three popular deep structures for object detection, including vehicles. This study evaluated these methodologies on nine fully challenging datasets to see their performance in diverse environments. Generally, YOLO versions had the best performance in detecting and localizing vehicles compared to SSD and RCNN. Between YOLO versions (YOLOv8, v7, v6, and v5), YOLOv7 has shown better detection and classification (car, truck, bus) procedures, while slower response in computation time. The YOLO versions have achieved more than 95% accuracy in detection and 90% in Overall Accuracy (OA) for the classification of vehicles, including cars, trucks and buses. The computation time on the CPU processor was between 150 milliseconds (YOLOv8, v6, and v5) and around 800 milliseconds (YOLOv7).

In this study, we present a novel approach leveraging the segment anything model (SAM) for the efficient detection and tracking of vehicles in urban traffic surveillance systems by utilizing uncalibrated low-resolution highway cameras. This research addresses the critical need for accurate vehicle monitoring in intelligent transportation systems (ITS) and smart city infrastructure. Traditional methods often struggle with the variability and complexity of urban environments, leading to suboptimal performance. Our approach harnesses the power of SAM, an advanced deep learning-based image segmentation algorithm, to significantly enhance the detection accuracy and tracking robustness. Through extensive testing and evaluation on two datasets of 511 highway cameras from Quebec, Canada and NVIDIA AI City Challenge Track 1, our algorithm achieved exceptional performance metrics including a precision of 89.68%, a recall of 97.87%, and an F1-score of 93.60%. These results represent a substantial improvement over existing state-of-the-art methods such as the YOLO version 8 algorithm, single shot detector (SSD), region-based convolutional neural network (RCNN). This advancement not only highlights the potential of SAM in real-time vehicle detection and tracking applications, but also underscores its capability to handle the diverse and dynamic conditions of urban traffic scenes. The implementation of this technology can lead to improved traffic management, reduced congestion, and enhanced urban mobility, making it a valuable tool for modern smart cities. The outcomes of this research pave the way for future advancements in remote sensing and photogrammetry, particularly in the realm of urban traffic surveillance and management.

Accurate infrastructure monitoring of ports and harbors is a vital operation conducted by the port’s authority. To operate regularly in this highly dynamic environment, we explore the potential of the cutting-edge mobile LiDAR systems (MLS) mounted on a vessel. To generate a high-quality 3 D point cloud that would satisfy the expected accuracy required in the monitoring task, the LiDAR scanner and the positioning and orientation system (POS) must be angularly aligned also known as boresight alignment. In this research, we introduce a boresight alignment methodology adapted to the port infrastructure surveillance based on prefabricated planar targets. After an analysis of planar target simulated data, we propose a boresight alignment site design. Then, we apply this boresight alignment site design in a real-world scenario. Obtained results estimate accurately roll and yaw angles errors with standard deviations of less than 0.002 degrees and pitch angle error with standard deviation less than 0.015 degrees. Finally, we defined a validation site and described the procedure that uses these features to validate the quality of the estimated parameters. The relative comparison of the georeferenced point clouds, before and after boresight alignment demonstrates the mitigation of the boresight systematic error impact on the final point cloud.

Mobile Laser Scanner (MLS) technology enables the acquisition of high-precision three-dimensional lidar point cloud data of roadside infrastructure elements, including traffic signs and street poles. This research presents an innovative and computationally efficient algorithm for the extraction of pole-shaped objects from MLS point clouds. The methodology addresses the computational challenges associated with large-scale point cloud processing through a trajectory-based segmentation and ground point filtering. The algorithm implements geometric descriptors, specifically linearity and verticality to identify potential pole structures. Subsequently, the statistical outlier removal (SOR) filter is applied to refine the candidate pole detection results. The final classification of true pole objects is achieved through the application of ground clearance criteria. The algorithm's effectiveness was validated through empirical testing across three distinct urban and suburban environments, utilizing data acquired from two different MLS systems. The experimental results demonstrated successful performance metrics, achieving mean precision and recall rates of 97.21.

Accurate volumetric modeling of indoor spaces is essential for emerging 3D cadastral systems, yet existing workflows often rely on manual intervention or produce surface-only models, limiting precision and scalability. This study proposes and validates an integrated, largely automated workflow (named VERTICAL) that converts classified indoor point clouds into topologically consistent 3D solids served as materials for land surveyor’s cadastral analysis. The approach sequentially combines RANSAC-based plane detection, polygonal mesh reconstruction, mesh optimization stage that merges coplanar faces, repairs non-manifold edges, and regularizes boundaries and planar faces prior to CAD-based solid generation, ensuring closed and geometrically valid solids. These modules are linked through a modular prototype (called P2M) with a web-based interface and parameterized batch processing. The workflow was tested on two condominium datasets representing a range of spatial complexities, from simple orthogonal rooms to irregular interiors with multiple ceiling levels, sloped roofs, and internal columns. Qualitative evaluation ensured visual plausibility, while quantitative assessment against survey-grade reference models measured geometric fidelity. Across eight representative rooms, models meeting qualitative criteria achieved accuracies exceeding 97% for key metrics including surface area, volume, and ceiling geometry, with a height RMSE around 0.01 m. Compared with existing automated modeling solutions, the proposed workflow has the ability of dealing with complex geometries and has comparable accuracy results. These results demonstrate the workflow’s capability to produce topologically consistent solids with high geometric accuracy, supporting both boundary delineation and volume calculation. The modular, interoperable design enables integration with CAD environments, offering a practical pathway toward an automated and reliable core of 3D modeling for cadastre applications.