Search

The documentation of roadway factors (such as roadway geometry, lane marking retroreflectivity/classification, and lane width) through the inventory of lane markings can reduce accidents and facilitate road safety analyses. Typically, lane marking inventory is established using either imagery or Light Detection and Ranging (LiDAR) data collected by mobile mapping systems (MMS). However, it is important to consider the strengths and weaknesses of both camera and LiDAR units when establishing lane marking inventory. Images may be susceptible to weather and lighting conditions, and lane marking might be obstructed by neighboring traffic. They also lack 3D and intensity information, although color information is available. On the other hand, LiDAR data are not affected by adverse weather and lighting conditions, and they have minimal occlusions. Moreover, LiDAR data provide 3D and intensity information. Considering the complementary characteristics of camera and LiDAR units, an image-aided LiDAR framework would be highly advantageous for lane marking inventory. In this context, an image-aided LiDAR framework means that the lane markings generated from one modality (i.e., either an image or LiDAR) are enhanced by those derived from the other one (i.e., either imagery or LiDAR). In addition, a reporting mechanism that can handle multi-modal datasets from different MMS sensors is necessary for the visualization of inventory results. This study proposes an image-aided LiDAR lane marking inventory framework that can handle up to five lanes per driving direction, as well as multiple imaging and LiDAR sensors onboard an MMS. The framework utilizes lane markings extracted from images to improve LiDAR-based extraction. Thereafter, intensity profiles and lane width estimates can be derived using the image-aided LiDAR lane markings. Finally, imagery/LiDAR data, intensity profiles, and lane width estimates can be visualized through a web portal that has been developed in this study. For the performance evaluation of the proposed framework, lane markings obtained through LiDAR-based, image-based, and image-aided LiDAR approaches are compared against manually established ones. The evaluation demonstrates that the proposed framework effectively compensates for the omission errors in the LiDAR-based extraction, as evidenced by an increase in the recall from 87.6% to 91.6%.

The precise extraction of road boundaries is an essential task to obtain road infrastructure data that can support various applications, such as maintenance, autonomous driving, vehicle navigation, and the generation of high-definition maps (HD map). Despite promising outcomes in prior studies, challenges persist in road extraction, particularly in discerning diverse road types. The proposed methodology integrates state-of-the-art techniques like DBSCAN and RANSAC, aiming to establish a universally applicable approach for diverse mobile mapping systems. This effort represents a pioneering step in extracting road information from image-based point cloud data. To assess the efficacy of the proposed method, we conducted experiments using a large-scale dataset acquired by two mobile mapping systems on the Yıldız Technical University campus; one system was configured as a mobile LiDAR system (MLS), while the other was equipped with cameras to operate as a photogrammetry-based mobile mapping system (MMS). Using manually measured reference road boundary data, we evaluated the completeness, correctness, and quality parameters of the road extraction performance of our proposed method based on two datasets. The completeness rates were 93.2% and 84.5%, while the correctness rates were 98.6% and 93.6%, respectively. The overall quality of the road curb extraction was 93.9% and 84.5% for the two datasets. Our proposed algorithm is capable of accurately extracting straight or curved road boundaries and curbs from complex point cloud data that includes vehicles, pedestrians, and other obstacles in urban environment. Furthermore, our experiments demonstrate that the algorithm can be applied to point cloud data acquired from different systems, such as MLS and MMS, with varying spatial resolutions and accuracy levels.

The United States has over 8.8 million lane miles nationwide, which require regular maintenance and evaluations of sign retroreflectivity, pavement markings, and other pavement information. Pavement markings convey crucial information to drivers as well as connected and autonomous vehicles for lane delineations. Current means of evaluation are by human inspection or semi-automated dedicated vehicles, which often capture one to two pavement lines at a time. Mobile LiDAR is also frequently used by agencies to map signs and infrastructure as well as assess pavement conditions and drainage profiles. This paper presents a case study where over 70 miles of US-52 and US-41 in Indiana were assessed, utilizing both a mobile retroreflectometer and a LiDAR mobile mapping system. Comparing the intensity data from LiDAR data and the retroreflective readings, there was a linear correlation for right edge pavement markings with an R2 of 0.87 and for the center skip line a linear correlation with an R2 of 0.63. The p-values were 0.000 and 0.000, respectively. Although there are no published standards for using LiDAR to evaluate pavement marking retroreflectivity, these results suggest that mobile LiDAR is a viable tool for network level monitoring of retroreflectivity.

Recently, light detection and ranging (LiDAR)-based mobile mapping systems (MMS) have been utilized for extracting lane markings using deep learning frameworks. However, huge datasets are required for training neural networks. Furthermore, with accurate lane markings being detected utilizing LiDAR data, an algorithm for automatically reporting their intensity information is beneficial for identifying worn-out or missing lane markings. In this paper, a transfer learning approach based on fine-tuning of a pretrained U-net model for lane marking extraction and a strategy for generating intensity profiles using the extracted results are presented. Starting from a pretrained model, a new model can be trained better and faster to make predictions on a target domain dataset with only a few training examples. An original U-net model trained on two-lane highways (source domain dataset) was fine-tuned to make accurate predictions on datasets with one-lane highway patterns (target domain dataset). Specifically, encoder- and decoder-trained U-net models are presented wherein, during retraining of the former, only weights in the encoder path of U-net were allowed to change with decoder weights frozen and vice versa for the latter. On the test data (target domain), the encoder-trained model (F1-score: 86.9%) outperformed the decoder-trained (F1-score: 82.1%). Additionally, on an independent dataset, the encoder-trained one (F1-score: 90.1%) performed better than the decoder-trained one (F1-score: 83.2%). Lastly, on the basis of lane marking results obtained from the encoder-trained U-net, intensity profiles were generated. Such profiles can be used to identify lane marking gaps and investigate their cause through RGB imagery visualization.

In recent decades, many cities have become densely populated due to increased urbanization, and the transportation infrastructure system has been heavily used. The downtime of important parts of the infrastructure, such as tunnels and bridges, seriously affects the transportation system’s efficiency. For this reason, a safe and reliable infrastructure network is necessary for the economic growth and functionality of cities. At the same time, the infrastructure is ageing in many countries, and continuous inspection and maintenance are necessary. Nowadays, detailed inspections of large infrastructure are almost exclusively performed by inspectors on site, which is both time-consuming and subject to human errors. However, the recent technological advancements in computer vision, artificial intelligence (AI), and robotics have opened up the possibilities of automated inspections. Today, semiautomatic systems such as drones and other mobile mapping systems are available to collect data and reconstruct 3D digital models of infrastructure. This significantly decreases the downtime of the infrastructure, but both damage detection and assessments of the structural condition are still manually performed, with a high impact on the efficiency and accuracy of the procedure. Ongoing research has shown that deep-learning methods, especially convolutional neural networks (CNNs) combined with other image processing techniques, can automatically detect cracks on concrete surfaces and measure their metrics (e.g., length and width). However, these techniques are still under investigation. Additionally, to use these data for automatically assessing the structure, a clear link between the metrics of the cracks and the structural condition must be established. This paper presents a review of the damage of tunnel concrete lining that is detectable with optical instruments. Thereafter, state-of-the-art autonomous tunnel inspection methods are presented with a focus on innovative mobile mapping systems for optimizing data collection. Finally, the paper presents an in-depth review of how the risk associated with cracks is assessed today in concrete tunnel lining.

In the present work, three LiDAR technologies (Faro Focus 3D X130—Terrestrial Laser Scanner, TLS-, Kaarta Stencil 2–16—Mobile mapping system, MMS-, and DJI Zenmuse L1—Airborne LiDAR sensor, ALS-) have been tested and compared in order to assess the performances in surveying built heritage in vegetated areas. Each of the mentioned devices has their limits of usability, and different methods to capture and generate 3D point clouds need to be applied. In addition, it has been necessary to apply a methodology to be able to position all the point clouds in the same reference system. While the TLS scans and the MMS data have been geo-referenced using a set of vertical markers and sphere measured by a GNSS receiver in RTK mode, the ALS model has been geo-referenced by the GNSS receiver integrated in the unmanned aerial system (UAS), which presents different characteristics and accuracies. The resulting point clouds have been analyzed and compared, focusing attention on the number of points acquired by the different systems, the density, and the nearest neighbor distance.

This paper presents the results of a complex three-dimensional reconstruction of the church of Nuestra Señora de la Asunción (Ávila, Spain) as an example of a successful process of verticalization from point clouds to a comprehensive computer-aided design (CAD) model. The reconstruction was carried out using the novel and advanced wearable mobile mapping system ZEB-REVO in combination with a lifting pole, in order to cover the whole geometry of the temple and, also, to model the different constructive elements. To this end, a set of good practices was followed, which allowed for passing from reality to the CAD model, such as the use of closed loops or even the use of different parametric and non-parametric strategies to capture the real geometry of the elements. As a result, this paper outlines the main guidelines for passing from point clouds to comprehensive CAD models, the former being useful for the application of smart preventive conservation processes, heritage building information models or even advanced numerical simulations.

Mobile Laser Scanning (MLS) systems have proven their usefulness in the rapid and accurate acquisition of the urban environment. From the generated point clouds, street furniture can be extracted and classified without manual intervention. However, this process of acquisition and classification is not error-free, caused mainly by disturbances. This paper analyses the effect of three disturbances (point density variation, ambient noise, and occlusions) on the classification of urban objects in point clouds. From point clouds acquired in real case studies, synthetic disturbances are generated and added. The point density reduction is generated by downsampling in a voxel-wise distribution. The ambient noise is generated as random points within the bounding box of the object, and the occlusion is generated by eliminating points contained in a sphere. Samples with disturbances are classified by a pre-trained Convolutional Neural Network (CNN). The results showed different behaviours for each disturbance: density reduction affected objects depending on the object shape and dimensions, ambient noise depending on the volume of the object, while occlusions depended on their size and location. Finally, the CNN was re-trained with a percentage of synthetic samples with disturbances. An improvement in the performance of 10–40% was reported except for occlusions with a radius larger than 1 m.

Remote sensing platforms have become an effective data acquisition tool for digital agriculture. Imaging sensors onboard unmanned aerial vehicles (UAVs) and tractors are providing unprecedented high-geometric-resolution data for several crop phenotyping activities (e.g., canopy cover estimation, plant localization, and flowering date identification). Among potential products, orthophotos play an important role in agricultural management. Traditional orthophoto generation strategies suffer from several artifacts (e.g., double mapping, excessive pixilation, and seamline distortions). The above problems are more pronounced when dealing with mid- to late-season imagery, which is often used for establishing flowering date (e.g., tassel and panicle detection for maize and sorghum crops, respectively). In response to these challenges, this paper introduces new strategies for generating orthophotos that are conducive to the straightforward detection of tassels and panicles. The orthophoto generation strategies are valid for both frame and push-broom imaging systems. The target function of these strategies is striking a balance between the improved visual appearance of tassels/panicles and their geolocation accuracy. The new strategies are based on generating a smooth digital surface model (DSM) that maintains the geolocation quality along the plant rows while reducing double mapping and pixilation artifacts. Moreover, seamline control strategies are applied to avoid having seamline distortions at locations where the tassels and panicles are expected. The quality of generated orthophotos is evaluated through visual inspection as well as quantitative assessment of the degree of similarity between the generated orthophotos and original images. Several experimental results from both UAV and ground platforms show that the proposed strategies do improve the visual quality of derived orthophotos while maintaining the geolocation accuracy at tassel/panicle locations.

The accuracy assessment of mobile mapping system (MMS) outputs is usually reliant on manual labor to inspect the quality of a vast amount of collected geospatial data. This paper presents an automated framework for the accuracy assessment and quality inspection of point cloud data collected by MMSs operating with lightweight laser scanners and consumer-grade microelectromechanical systems (MEMS) sensors. A new, large-scale test facility has been established in a challenging navigation environment (downtown area) to support the analyses conducted in this research work. MMS point cloud data are divided into short time slices for comparison with the higher-accuracy, terrestrial laser scanner (TLS) point cloud of the test facility. MMS data quality is quantified by the results of registering the point cloud of each slice with the TLS datasets. Experiments on multiple land vehicle MMS point cloud datasets using a lightweight laser scanner and three different MEMS devices are presented to demonstrate the effectiveness of the proposed method. The mean accuracy of a consumer grade MEMS ($100) was in the range of 0.48 ± 0.23 m to 0.85 ± 0.52 m. The method presented here in can be straightforwardly implemented and adopted for the accuracy assessment of other MMSs types such as unmanned aerial vehicles (UAV)s.

Cameras and laser scanners are complementary tools for a 2D/3D information generation. Systematic and random errors cause the misalignment of the multi-sensor imagery and point cloud data. In this paper, a novel feature-based approach is proposed for imagery and point cloud fine registration. The tie points and its two neighbor pixels are matched in the overlap images, which are intersected in the object space to create the differential tie plane. A preprocessing is applied to the corresponding tie points and non-robust ones are removed. Initial coarse Exterior Orientation Parameters (EOPs), Interior Orientation Parameters (IOPs), and Additional Parameters (APs) are used to transform tie plane points to the object space. Then, the nearest points of the point cloud data to the transformed tie plane points are estimated. These estimated points are used to calculate Directional Vectors (DV) of the differential planes. As a constraint equation along with the collinearity equation, each object space tie point is forced to be located on the point cloud differential plane. Two different indoor and outdoor experimental data are used to assess the proposed approach. Achieved results show about 2.5 pixels errors on checkpoints. Such results demonstrated the robustness and practicality of the proposed approach.

Maintenance and expansion of transport and communications infrastructure requires ongoing construction work on a large scale. To plan and execute these in the best possible way, up-to-date and highly detailed digital maps are needed. For example, until recently, telecommunication companies have performed documentation and mapping of as-built urban structures for construction work manually and with great time expense. Mobile mapping systems offer a solution for documenting urban environments fast and mostly automated. In consequence, large amounts of recorded data emerge in short time, creating the need for automated processing and modeling of these data to provide reliable foundations for digital planning in reasonable time. We present (a) a procedure for fully automated processing of mobile mapping data for digital construction planning in the context of nationwide broadband network expansion and (b) an in-depth study of the performance of this procedure on real-world data. Our multi-stage pipeline segments georeferenced images and fuses segmentations with 3D data, which allows exact localization of surfaces and objects, which can then be passed via interface, e.g., to a geographic information system (GIS). The final system is able to distinguish between similar looking surfaces, such as concrete and asphalt, with a precision between 80% and 95%, regardless of setting or season.

Mechanically stabilized earth (MSE) walls rely on its weight to resist the destabilizing earth forces acting at the back of the reinforced soil area. MSE walls are a common infrastructure along national and international transportation corridors as they are low-cost and have easy-to-install precast concrete panels. The usability of such transportation corridors depends on the safety and condition of the MSE wall system. Consequently, MSE walls have to be periodically monitored according to prevailing transportation asset management criteria during the construction and serviceability life stages to ensure that their predictable performance measures are met. To date, MSE walls are monitored using qualitative approaches such as visual inspection, which provide limited information. Aside from being time-consuming, visual inspection is susceptible to bias due to human subjectivity. Manual and visual inspection in the field has been traditionally based on the use of a total station, geotechnical field instrumentation, and/or static terrestrial laser scanning (TLS). These instruments can provide highly accurate and reliable performance measures; however, their underlying data acquisition and processing strategies are time-consuming and not scalable. The proposed strategy in this research provides several global and local serviceability measures through efficient processing of point cloud data acquired by a mobile LiDAR system (MLS) for MSE walls with smooth panels without the need for installing any targets. An ultra-high-accuracy vehicle-based LiDAR data acquisition system has been used for the data acquisition. To check the viability of the proposed methodology, a case study has been conducted to evaluate the similarity of the derived serviceability measures from TLS and MLS technologies. The results of that comparison verified that the MLS-based serviceability measures are within 1 cm and 0.3° of those obtained using TLS and thus confirmed the potential for using MLS to efficiently acquire point clouds while facilitating economical, scalable, and reliable monitoring of MSE walls.

Lane markings are one of the essential elements of road information, which is useful for a wide range of transportation applications. Several studies have been conducted to extract lane markings through intensity thresholding of Light Detection and Ranging (LiDAR) point clouds acquired by mobile mapping systems (MMS). This paper proposes an intensity thresholding strategy using unsupervised intensity normalization and a deep learning strategy using automatically labeled training data for lane marking extraction. For comparative evaluation, original intensity thresholding and deep learning using manually established labels strategies are also implemented. A pavement surface-based assessment of lane marking extraction by the four strategies is conducted in asphalt and concrete pavement areas covered by MMS equipped with multiple LiDAR scanners. Additionally, the extracted lane markings are used for lane width estimation and reporting lane marking gaps along various highways. The normalized intensity thresholding leads to a better lane marking extraction with an F1-score of 78.9% in comparison to the original intensity thresholding with an F1-score of 72.3%. On the other hand, the deep learning model trained with automatically generated labels achieves a higher F1-score of 85.9% than the one trained on manually established labels with an F1-score of 75.1%. In concrete pavement area, the normalized intensity thresholding and both deep learning strategies obtain better lane marking extraction (i.e., lane markings along longer segments of the highway have been extracted) than the original intensity thresholding approach. For the lane width results, more estimates are observed, especially in areas with poor edge lane marking, using the two deep learning models when compared with the intensity thresholding strategies due to the higher recall rates for the former. The outcome of the proposed strategies is used to develop a framework for reporting lane marking gap regions, which can be subsequently visualized in RGB imagery to identify their cause.

Lidar technology is thriving nowadays for different applications mainly for autonomous navigation, mapping, and smart city technology. Lidars vary in different aspects and can be: multi beam, single beam, spinning, solid state, full 360 field of view FOV, single or multi pulse returns, and many other geometric and radiometric aspects. Users and developers in the mapping industry are continuously looking for new released Lidars having high properties of output density, coverage, and accuracy while keeping a lower cost. Accordingly, every Lidar type should be well evaluated for the final intended mapping aim. This evaluation is not easy to implement in practice because of the need to have all the investigated Lidars available in hand and integrated into a ready to use mapping system. Furthermore, to have a fair comparison; it is necessary to ensure the test applied in the same environment at the same travelling path among other conditions. In this paper, we are evaluating two state-of-the-art multi beam Lidar types: Ouster OS-1-64 and Hesai Pandar64 for mapping applications. The evaluation of the Lidar types is applied in a simulation environment which approximates reality. The paper shows the determination of the ideal orientation angle for the two Lidars by assessing the density, coverage, and accuracy and presenting clear performance quantifications and conclusions.

LiDAR-based mobile mapping systems (MMS) are rapidly gaining popularity for a multitude of applications due to their ability to provide complete and accurate 3D point clouds for any and every scene of interest. However, an accurate calibration technique for such systems is needed in order to unleash their full potential. In this paper, we propose a fully automated profile-based strategy for the calibration of LiDAR-based MMS. The proposed technique is validated by comparing its accuracy against the expected point positioning accuracy for the point cloud based on the used sensors’ specifications. The proposed strategy was seen to reduce the misalignment between different tracks from approximately 2 to 3 m before calibration down to less than 2 cm after calibration for airborne as well as terrestrial mobile LiDAR mapping systems. In other words, the proposed calibration strategy can converge to correct estimates of mounting parameters, even in cases where the initial estimates are significantly different from the true values. Furthermore, the results from the proposed strategy are also verified by comparing them to those from an existing manually-assisted feature-based calibration strategy. The major contribution of the proposed strategy is its ability to conduct the calibration of airborne and wheel-based mobile systems without any requirement for specially designed targets or features in the surrounding environment. The above claims are validated using experimental results conducted for three different MMS − two airborne and one terrestrial − with one or more LiDAR unit.

Multiple laser scanner hardware configurations can be applied to Mobile Mapping Systems. As best practice, laser scanners are rotated horizontally or inclined vertically to increase the probability of contact between the laser scan plane and any surfaces that are perpendicular to the direction of travel. Vertical inclinations also maximise the number of scan profiles striking narrow vertical features, something that can be of use when trying to recognise features. Adding a second scanner allows an MMS to capture more data and improve laser coverage of an area by filling in laser shadows. However, in any MMS the orientation of each scanner on the platform must be decided upon. Changes in the horizontal or vertical orientations of the scanner can increase the range to vertical targets and the road surface, with excessive scanner angles lowering point density significantly. Limited information is available to assist the manufacturers or operators in identifying the optimal scanner orientation for roadside surveys. The method proposed in this paper applies 3D surface normals and geometric formulae to assess the influence of scanner orientation on point distribution. It was demonstrated that by changing the orientation of the scanner the number of pulses striking a target could be greatly increased, and the number of profiles intersecting with the target could also be increased—something that is particularly important for narrow vertical features. The importance of identifying the correct trade-off between the number of profiles intersecting with the target and the point spacing was also raised.

Understanding how various Mobile Mapping System (MMS) laser hardware configurations and operating parameters exercise different influence on point density is important for assessing system performance, which in turn facilitates system design and MMS benchmarking. Point density also influences data processing, as objects that can be recognised using automated algorithms generally require a minimum point density. Although obtaining the necessary point density impacts on hardware costs, survey time and data storage requirements, a method for accurately and rapidly assessing MMS performance is lacking for generic MMSs. We have developed a method for quantifying point clouds collected by an MMS with respect to known objects at specified distances using 3D surface normals, 2D geometric formulae and line drawing algorithms. These algorithms were combined in a system called the Mobile Mapping Point Density Calculator (MIMIC) and were validated using point clouds captured by both a single scanner and a dual scanner MMS. Results from MIMIC were promising: when considering the number of scan profiles striking the target, the average error equated to less than 1 point per scan profile. These tests highlight that MIMIC is capable of accurately calculating point density for both single and dual scanner MMSs.

The current generation of Mobile Mapping Systems (MMSs) capture high density spatial data in a short time-frame. The quantity of data is difficult to predict as there is no concrete understanding of the point density that different scanner configurations and hardware settings will exhibit for objects at specific distances. Obtaining the required point density impacts survey time, processing time, data storage and is also the underlying limit of automated algorithms. This paper details a novel method for calculating point and profile information for terrestrial MMSs which are required for any point density calculation. Through application of algorithms utilising 3D surface normals and 2D geometric formulae, the theoretically optimal profile spacing and point spacing are calculated on targets. Both of these elements are a major factor in calculating point density on arbitrary objects, such as road signs, poles or buildings-all important features in asset management surveys.

A land-based mobile mapping system (MMS) is flexible and useful for the acquisition of road environment geospatial information. It integrates a set of imaging sensors and a position and orientation system (POS). The positioning quality of such systems is highly dependent on the accuracy of the utilized POS. This limitation is the major drawback due to the elevated cost associated with high-end GPS/INS units, particularly the inertial system. The potential accuracy of the direct sensor orientation depends on the architecture and quality of the GPS/INS integration process as well as the validity of the system calibration (i.e., calibration of the individual sensors as well as the system mounting parameters). In this paper, a novel single-step procedure using integrated sensor orientation with relative orientation constraint for the estimation of the mounting parameters is introduced. A comparative analysis between the proposed single-step and the traditional two-step procedure is carried out. Moreover, the estimated mounting parameters using the different methods are used in a direct geo-referencing procedure to evaluate their performance and the feasibility of the implemented system. Experimental results show that the proposed system using single-step system calibration method can achieve high 3D positioning accuracy.

Mobile mapping systems have been widely applied for acquiring spatial information in applications such as spatial information systems and 3D city models. Nowadays the most common technologies used for positioning and orientation of a mobile mapping system include a Global Positioning System (GPS) as the major positioning sensor and an Inertial Navigation System (INS) as the major orientation sensor. In the classical approach, the limitations of the Kalman Filter (KF) method and the overall price of multi-sensor systems have limited the popularization of most land-based mobile mapping applications. Although intelligent sensor positioning and orientation schemes consisting of Multi-layer Feed-forward Neural Networks (MFNNs), one of the most famous Artificial Neural Networks (ANNs), and KF/smoothers, have been proposed in order to enhance the performance of low cost Micro Electro Mechanical System (MEMS) INS/GPS integrated systems, the automation of the MFNN applied has not proven as easy as initially expected. Therefore, this study not only addresses the problems of insufficient automation in the conventional methodology that has been applied in MFNN-KF/smoother algorithms for INS/GPS integrated systems proposed in previous studies, but also exploits and analyzes the idea of developing alternative intelligent sensor positioning and orientation schemes that integrate various sensors in more automatic ways. The proposed schemes are implemented using one of the most famous constructive neural networks––the Cascade Correlation Neural Network (CCNNs)––to overcome the limitations of conventional techniques based on KF/smoother algorithms as well as previously developed MFNN-smoother schemes. The CCNNs applied also have the advantage of a more flexible topology compared to MFNNs. Based on the experimental data utilized the preliminary results presented in this article illustrate the effectiveness of the proposed schemes compared to smoother algorithms as well as the MFNN-smoother schemes.

Digital mobile mapping, which integrates digital imaging with direct geo-referencing, has developed rapidly over the past fifteen years. Direct geo-referencing is the determination of the time-variable position and orientation parameters for a mobile digital imager. The most common technologies used for this purpose today are satellite positioning using Global Positioning System (GPS) and Inertial Navigation System (INS) using an Inertial Measurement Unit (IMU). They are usually integrated in such a way that the GPS receiver is the main position sensor, while the IMU is the main orientation sensor. The Kalman Filter (KF) is considered as the optimal estimation tool for real-time INS/GPS integrated kinematic position and orientation determination. An intelligent hybrid scheme consisting of an Artificial Neural Network (ANN) and KF has been proposed to overcome the limitations of KF and to improve the performance of the INS/GPS integrated system in previous studies. However, the accuracy requirements of general mobile mapping applications can’t be achieved easily, even by the use of the ANN-KF scheme. Therefore, this study proposes an intelligent position and orientation determination scheme that embeds ANN with conventional Rauch-Tung-Striebel (RTS) smoother to improve the overall accuracy of a MEMS INS/GPS integrated system in post-mission mode. By combining the Micro Electro Mechanical Systems (MEMS) INS/GPS integrated system and the intelligent ANN-RTS smoother scheme proposed in this study, a cheaper but still reasonably accurate position and orientation determination scheme can be anticipated.

In this paper, we present a novel framework for detecting individual trees in densely sampled 3D point cloud data acquired in urban areas. Given a 3D point cloud, the objective is to assign point-wise labels that are both class-aware and instance-aware, a task that is known as instance-level segmentation. To achieve this, our framework addresses two successive steps. The first step of our framework is given by the use of geometric features for a binary point-wise semantic classification with the objective of assigning semantic class labels to irregularly distributed 3D points, whereby the labels are defined as “tree points” and “other points”. The second step of our framework is given by a semantic segmentation with the objective of separating individual trees within the “tree points”. This is achieved by applying an efficient adaptation of the mean shift algorithm and a subsequent segment-based shape analysis relying on semantic rules to only retain plausible tree segments. We demonstrate the performance of our framework on a publicly available benchmark dataset, which has been acquired with a mobile mapping system in the city of Delft in the Netherlands. This dataset contains 10.13 M labeled 3D points among which 17.6 % are labeled as “tree points”. The derived results clearly reveal a semantic classification of high accuracy (up to 90.77 %) and an instance-level segmentation of high plausibility, while the simplicity, applicability and efficiency of the involved methods even allow applying the complete framework on a standard laptop computer with a reasonable processing time (less than 2.5 h).