SLAM-based Pseudo-GNSS/INS localization system for indoor LiDAR mobile mapping systems

In the last two decades, the demand for geo-spatial data has tremendously increased. Mobile mapping Systems (MMS) are considered the main source of data for mapping and Geographic Information Systems (GIS) applications. MMS, which integrates navigation systems (such as Global Navigation Satellite Systems (GNSS) and Inertial Navigation Systems (INS)) and imaging sensors (such as cameras and laser scanners), have been an emerging trend in mapping applications because they allow the implementation of the mapping concepts from moving vehicles (e.g. cars, airplanes and trains). The main strength of MMS which makes it desirable for different mapping applications is their ability to directly georeference their mapping sensors, which means knowing their position and orientation relative to a mapping co-ordinate frame. Once geo-referenced, the mapping sensor can be used to determine the positions of points external to the platform in the same mapping co-ordinate frame. Nevertheless, the major drawback of current MMS systems is their high price due to the type of the used platform, navigation and mapping technologies. Today's smartphones are getting more sophisticated and smarter and therefore they will narrow the gap between computers and mobile phones. Current generation of smartphones are equipped with GNSS receivers, micro-electro mechanical systems (MEMS) based navigation sensors (such as gyroscopes, accelerometers, magnetometers, and barometers) and high resolution digital cameras. As a result, smartphones are now getting quite popular for data collection projects including point data mapping tasks and it is not far before we see smartphones are used as mobile mappers. This paper will present a new and innovative application of a portable MMS based on smartphones that overcome the high-cost drawback of the current land-based MMS with reasonable accuracy.

Semantic segmentation of bridge components and road infrastructure from mobile LiDAR data

The mobile 3D mapping systems (MMS) and the integration with Geographical Information Systems (GIS) represent an innovative and efficient approach to modern topography. It is recommended and useful for infrastructure analysis and urban planning. This modern technology provides accurate, fast, and detailed data, facilitating well-informed decision-making and contributing to the development of sustainable infrastructure in the 21st century. The purpose of this research was to use a mobile mapping system for land surveying measurement of an urban area, independent of pre-established ground control points. On the other hand, the research is supposed to demonstrate the usefulness of kinematic trajectory, digital imaging, and laser scanning in acquiring, storing, and processing point cloud data. This paper shows an affordable method and a modern scanning instrument used for mobile mapping scanning, to create a georeferenced point cloud (PC). The obtained result has centimetric precision of georeferenced point cloud data, even if the average speed of the car was about 30km/h. The trajectory adjustment with static GNSS measurements increases the accuracy of ground control points (GCPs) up to ±5cm for horizontal positioning and vertical positioning. Although this study was carried out while the system was mounted on a car the result followed the national accuracy requirements for land surveying and cadastre fields. In other words, the mobile mapping system is a faster and cost-effective in time alternative to static laser scanning and it is important to continue to explore and adopt these technological solutions to face the future challenges in the field of urban development and infrastructure.

Three-dimensional (3D) mapping deals with the problem of building a map of the unknown environments explored by a mobile robot. In contrast to 2D maps, 3D maps contain richer information of the visited places. Besides enabling robot navigation in 3D, a 3D map of the robot surroundings could be of great importance for higher-level robotic tasks, like scene interpretation and object interaction or manipulation, as well as for visualization purposes in general, which are required in surveillance, urban search and rescue, surveying, and others. Hence, the goal of this thesis is to develop a system which is capable of reconstructing the surrounding environment of a mobile robot as a three-dimensional map. Microsoft Kinect camera is a novel sensing sensor that captures dense depth images along with RGB images at high frame rate. Recently, it has dominated the stage of 3D robotic sensing, as it is low-cost, low-power. For this work, it is used as the exteroceptive sensor and obtains 3D point clouds of the surrounding environment. Meanwhile, the wheel odometry of the robot is used to initialize the search for correspondences between different observations. As a single 3D point cloud generated by the Microsoft Kinect sensor is composed of many tens of thousands of data points, it is necessary to compress the raw data to process them efficiently. The method chosen in this work is to use a feature-based representation which simplifies the 3D mapping procedure. The chosen features are planar surfaces and orthogonal corners, which is based on the fact that indoor environments are designed such that walls, ground floors, pillars, and other major parts of the building structures can be modeled as planar surface patches, which are parallel or perpendicular to each other. While orthogonal corners are presented as higher features which are more distinguishable in indoor environment. In this thesis, the main idea is to obtain spatial constraints between pairwise frames by building correspondences between the extracted vertical plane features and corner features. A plane matching algorithm is presented that maximizes the similarity metric between a pair of planes within a search space to determine correspondences between planes. The corner matching result is based on the plane matching results. The estimated spatial constraints form the edges of a pose graph, referred to as graph-based SLAM front-end. In order to build a map, however, a robot must be able to recognize places that it has previously visited. Limitations in sensor processing problem, coupled with environmental ambiguity, make this difficult. In this thesis, we describe a loop closure detection algorithm by compressing point clouds into viewpoint feature histograms, inspired by their strong recognition ability. The estimated roto-translation between detected loop frames is added to the graph representing this newly discovered constraint. Due to the estimation errors, the estimated edges form a non-globally consistent trajectory. With the aid of a linear pose graph optimizing algorithm, the most likely configuration of the robot poses can be estimated given the edges of the graph, referred to as SLAM back-end. Finally, the 3D map is retrieved by attaching each acquired point cloud to the corresponding pose estimate. The approach is validated through different experiments with a mobile robot in an indoor environment

In this paper, we propose a novel moving-objects detection method which, in contrast to state-of-the-art moving-objects detection methods, takes static feature points into consideration during detection. It benefits both the tracking and mapping approaches in real-time Simultaneous Localization and Mapping (SLAM) system whose localization depends on static objects primarily. Our method obtains accurate static feature point sets continuously to estimate camera poses. In return, these camera poses are employed to find inliers and outliers using succinct distinction method. More specifically, we estimate camera pose by using static map points extracted from a high accurate global map. The map is generated in a real-time stereo SLAM system, and the camera pose is estimated and optimized by using a 3D-2D projection matching search with local bundle adjustment optimization. Once we have a calculated camera pose, we begin to find inliers and outliers. Finally, combined with superpixel segmentation, we capture the moving objects and then give feedback to the whole SLAM system. Detailed results are demonstrated comparing to other moving-objects detection methods on selected KITTI datasets with moving objects.

This paper discusses a comprehensive methodology for transforming a static LiDAR (Light Detection and Ranging) system into a mobile mapping system. The initial step involves integrating various sensors, such as GNSS (Global Navigation Satellite System), IMU (Inertial Measurement Unit), and odometry sensors, into the system’s architecture to accurately estimate the position and orientation of the LiDAR sensor at any given time. Specialized algorithms compensate for the vehicle’s motion, and procedural requirements must be followed to ensure safe operation. Hardware integration is critical, requiring proper calibration and validation. Data processing workflows, including algorithms and software tools, play a crucial role in mobile LiDAR mapping systems. The quality and accuracy of the data depend on various factors, and practical considerations such as cost and time are also important. The proposed methodology provides a clear and effective way to transform a terrestrial LiDAR sensor into a mobile mapping system, increasing its flexibility and usability for various applications. However, the detailed analysis, system validation, and data processing details fall outside this paper’s scope and will be discussed in future publications.

The increasing computational capacity and the reduction of production costs of electronic devices allow the adoption of new approaches to the architectural survey. The purpose of this paper is to analyze and test different low-cost sensors able to acquire odometry, depth data and RGB images processed through SLAM (Simultaneous Localization and Mapping) algorithms to obtain metrically correct point clouds applicable in the normal workflow of the architectural survey. The advantage of these new systems is the time needed to obtain the result. The post-processing time is virtually cleared, and it is not necessary to use targets and control points during acquisition. The capabilities of these sensors are tested both qualitatively and quantitatively by comparing them with the data obtained with traditional surveying systems (laser scanning, photogrammetry, etc.) set as “ground truth”. First, the acquisition efficiency of the low-cost sensors under different conditions of use are verified. Subsequently, the different point clouds obtained using different acquisition software are compared. Lastly, pros and cons are evaluated, also from an economic point of view, in relation to traditional surveying systems. The comparisons highlight that the performance of these devices varies considerably depending on the size of the acquired environment. Therefore, they are excellent for the acquisition of small environments as they allow to obtain an accuracy of about ±3 cm in an area of 100 m2.KeywordsSimultaneous Localization and Mapping (SLAM)Mobile Mapping System (MMS)LiDARStereo cameraPoint cloud comparisonTracking

Simultaneous Localization and Mapping (SLAM) can provide pose estimation and map information. It is widely used in Intelligent transportation systems such as smart vending vehicles. However, existing SLAM methods used for vending vehicles rarely focus on indoor environments. We proposed a real-time LiDAR-based SLAM with high accuracy in both outdoor and indoor environments. Our method takes the advantage of Inertial Measurement Unit (IMU) to reduce the distortion of raw data. Corner and planar features are extracted for point cloud registration. Besides, different optimization formulas are applied in different scenes. The proposed method achieves an average error of fewer than 1m in the KITTI Odometry benchmark and has high accuracy in different experiments.

The calibration problem of binocular stereo vision rig is critical for its practical application. However, most existing calibration methods are based on manual off-line algorithms for specific reference targets or patterns. In this paper, we propose a novel simultaneous localization and mapping (SLAM)-based self-calibration method designed to achieve real-time, automatic and accurate calibration of the binocular stereo vision (BSV) rig’s extrinsic parameters in a short period without auxiliary equipment and special calibration markers, assuming the intrinsic parameters of the left and right cameras are known in advance. The main contribution of this paper is to use the SLAM algorithm as our main tool for the calibration method. The method mainly consists of two parts: SLAM-based construction of 3D scene point map and extrinsic parameter calibration. In the first part, the SLAM mainly constructs a 3D feature point map of the natural environment, which is used as a calibration area map. To improve the efficiency of calibration, a lightweight, real-time visual SLAM is built. In the second part, extrinsic parameters are calibrated through the 3D scene point map created by the SLAM. Ultimately, field experiments are performed to evaluate the feasibility, repeatability, and efficiency of our self-calibration method. The experimental data shows that the average absolute error of the Euler angles and translation vectors obtained by our method relative to the reference values obtained by Zhang’s calibration method does not exceed 0.5˚ and 2 mm, respectively. The distribution range of the most widely spread parameter in Euler angles is less than 0.2˚ while that in translation vectors does not exceed 2.15 mm. Under the general texture scene and the normal driving speed of the mobile robot, the calibration time can be generally maintained within 10 s. The above results prove that our proposed method is reliable and has practical value.

A high efficient multi-robot simultaneous localization and mapping system using partial computing offloading assisted cloud point registration strategy

A real-time SLAM (simultaneous localization and mapping) approach to harvester localization and tree map generation in forest environments is presented in this paper. The method combines 2D laser localization and mapping with GPS information to form global tree maps. Building an incremental map while also using it for localization is the only way a mobile robot can navigate in large outdoor environments. Until recently SLAM has only been confined to small-scale, mostly indoor, environments. We try to addresses the issues of scale for practical implementations of SLAM in extensive outdoor environments. Presented algorithms are tested in real outdoor environments using an all-terrain vehicle equipped with the navigation sensors and a DGPS receiver.

Abstract. The last two decades have witnessed a huge growth in the demand for geo-spatial data. This demand has encouraged researchers around the world to develop new algorithms and design new mapping systems in order to obtain reliable sources for geo-spatial data. Mobile Mapping Systems (MMS) are one of the main sources for mapping and Geographic Information Systems (GIS) data. MMS integrate various remote sensing sensors, such as cameras and LiDAR, along with navigation sensors to provide the 3D coordinates of points of interest from moving platform (e.g. cars, air planes, etc.). Although MMS can provide accurate mapping solution for different GIS applications, the cost of these systems is not affordable for many users and only large scale companies and institutions can benefits from MMS systems. The main objective of this paper is to propose a new low cost MMS with reasonable accuracy using the available sensors in smartphones and its video camera. Using the smartphone video camera, instead of capturing individual images, makes the system easier to be used by non-professional users since the system will automatically extract the highly overlapping frames out of the video without the user intervention. Results of the proposed system are presented which demonstrate the effect of the number of the used images in mapping solution. In addition, the accuracy of the mapping results obtained from capturing a video is compared to the same results obtained from using separate captured images instead of video.

Augmented Reality (AR) has increasingly benefited from the use of Simultaneous Localization and Mapping (SLAM) systems. This technology has enabled developers to create AR markerless applications, but lack semantic understanding of their environment. The inclusion of this information would empower AR applications to better react to the surroundings more realistically. To gain semantic knowledge, in recent years, focus has shifted toward fusing SLAM systems with neural networks, giving birth to the field of Semantic SLAM. Building on existing research, this paper aimed to create a SLAM system that generates a 3D map using ORB-SLAM2 and enriches it with semantic knowledge originated from the Fast-SCNN network. The key novelty of our approach is a new method for improving the predictions of neural networks, employed to balance the loss of accuracy introduced by efficient real-time models. Exploiting sensor information provided by a smartphone, GPS coordinates are utilized to query the OpenStreetMap database. The returned information is used to understand which classes are currently absent in the environment, so that they can be removed from the network’s prediction with the goal of improving its accuracy. We achieved 87.40% Pixel Accuracy with Fast-SCNN on our custom version of COCO-Stuff and showed an improvement by involving GPS data for our self-made smartphone dataset resulting in 90.24% Pixel Accuracy. Having in mind the use on smartphones, the implementation aimed to find a trade-off between accuracy and efficiency, making the system achieve an unprecedented speed. To this end, the system was carefully designed and a strong focus on lightweight neural networks is also fundamental. This enabled the creation of an above real-time Semantic SLAM system that we called EnvSLAM (Environment SLAM). Our extensive evaluation reveals the efficiency of the system features and the operability in above real-time (48.1 frames per second with an input image resolution of 640 × 360 pixels). Moreover, the GPS integration indicates an effective improvement of the network’s prediction accuracy.

Mobile mapping systems are becoming increasingly popular as they can build 3D models of the environment rapidly by using a laser scanner that is integrated with a navigation system. 3D mobile mapping has been widely used for applications such as 3D city modelling and mapping of the scanned environments. However, accurate mapping relies on not only the scanner’s performance but also on the quality of the navigation results (accuracy and robustness) . This paper discusses the potentials of using 3D mobile mapping systems for landscape change detection, that is traditionally carried out by terrestrial laser scanners that can be accurately geo-referenced at a static location to produce highly accurate dense point clouds. Yet compared to conventional surveying using terrestrial laser scanners, several advantages of mobile mapping systems can be identified. A large area can be monitored in a relatively short period, which enables high repeat frequency monitoring without having to set-up dedicated stations. However, current mobile mapping applications are limited by the quality of navigation results, especially in different environments. The change detection ability of mobile mapping systems is therefore significantly affected by the quality of the navigation results. This paper presents some data collected for the purpose of monitoring from a mobile platform. The datasets are analysed to address current potentials and difficulties. The change detection results are also presented based on the collected dataset. Results indicate the potentials of change detection using a mobile mapping system and suggestions to enhance quality and robustness.

A Simultaneous Localization and Mapping (SLAM) system must be robust to support long-term mobile vehicle and robot applications. However, camera and LiDAR based SLAM systems can be fragile when facing challenging illumination or weather conditions which degrade the utility of imagery and point cloud data. Radar, whose operating electromagnetic spectrum is less affected by environmental changes, is promising although its distinct sensor model and noise characteristics bring open challenges when being exploited for SLAM. This paper studies the use of a Frequency Modulated Continuous Wave radar for SLAM in large-scale outdoor environments. We propose a full radar SLAM system, including a novel radar motion estimation algorithm that leverages radar geometry for reliable feature tracking. It also optimally compensates motion distortion and estimates pose by joint optimization. Its loop closure component is designed to be simple yet efficient for radar imagery by capturing and exploiting structural information of the surrounding environment. Extensive experiments on three public radar datasets, ranging from city streets and residential areas to countryside and highways, show competitive accuracy and reliability performance of the proposed radar SLAM system compared to the state-of-the-art LiDAR, vision and radar methods. The results show that our system is technically viable in achieving reliable SLAM in extreme weather conditions on the RADIATE Dataset, for example, heavy snow and dense fog, demonstrating the promising potential of using radar for all-weather localization and mapping.