Global Localization based on Road-centric 3D Point Cloud Descriptor in Urban Environments

Accurate and reliable localization in urban environments is critical for high-level autonomous driving systems. In comparison to other localization strategies, map-based methods are more reliable and have higher localization accuracy. However, due to higher storage and update costs, dense map-based localization methods are inefficient for widespread use. In urban road environments, structural features such as road curbs that limit the road passable area and pole-like features such as streetlights, tree trunks, and traffic lights exhibit exceptional long-term stability and extraction consistency. The maps based on road curbs and pole-like features are unaffected by dynamic obstacles such as vehicles and pedestrians, making them ideal for vehicle localization in urban environments. In this paper, we design a lightweight feature map for lidar localization in urban environments based on road curbs and pole-like features and propose a novel, fast and accurate extraction strategy for these features, implementing the entire pipeline of feature extraction, map construction, and localization.We combine the orderliness of 2D range images with the spatial properties of 3D point clouds to extract road curbs and poles quickly and accurately. The proposed feature extraction methods and localization system are evaluated on datasets collected in multiple environments and times. The experimental results demonstrate that the method proposed in this paper is more efficient and robust at features extraction and vehicle localization compared with other state-of-the-art approaches.

Global localization in a prior map is an important field in virtual and augmented reality systems, but it is always a challenge to conduct point cloud based localization in the large-scale scene prior map. A large-scale prior map usually means huge amount of calculation for point cloud processing, which leads to the long time required for global localization. To deal with this problem, we propose a fast point cloud global localization method based on point clouds segmentation and learning-based descriptor. On the one hand, cylindrical filtering, ground-point removal and point cloud segmentation are adopted to eliminate a large number of useless points and retain points with rich structures, which improves the efficiency of point cloud registration. On the other hand, reliable 3D point cloud descriptor, two-phase search strategy for place recognition and geometric consistency verification are used to ensure the localization accuracy. Experiments prove that the proposed method achieves good localization effect on both KITTI and MVSEC datasets. Under the condition of ensuring the high localization accuracy, the time for point clouds to complete the global localization is greatly reduced.

This paper presents a global localization method for mobile robots based on the geometric information of structured indoor environments. With a global/local point cloud and projection map, lines are extracted from the projection maps using Hough transform. According to the directions of the obtained lines, the orientations of projection maps and point clouds are normalized. Next, the template matching algorithm is applied to the normalized global and local projection maps. Once coarse localization is completed, final accurate localization is achieved using the Iterative Closest Points (ICP) algorithm. Experimental results on several point clouds show that the proposed method can achieve high localization accuracy in real-time. The proposed method can be used for other global localization applications in structured environments.

As part of DARPA's MARS2020 program, the Jet Propulsion Laboratory developed a vision-based system for localization in urban environments that requires neither GPS nor active sensors. System hardware consists of a pair of small FireWire cameras and a standard Pentium-based computer. The inputs to the software system consist of: 1) a crude grid-based map describing the positions of buildings, 2) an initial estimate of robot location and 3) the video streams produced by each camera. At each step during the traverse the system: captures new image data, finds image features hypothesized to lie on the outside of a building, computes the range to those features, determines an estimate of the robot's motion since the previous step and combines that data with the map to update a probabilistic representation of the robot's location. This probabilistic representation allows the system to simultaneously represent multiple possible locations, For our testing, we have derived the a priori map manually using non-orthorectified overhead imagery, although this process could be automated. The software system consists of two primary components. The first is the vision system which uses binocular stereo ranging together with a set of heuristics to identify features likely to be part of building exteriors and to compute an estimate of the robot's motion since the previous step. The resulting visual features and the associated range measurements are software component, a particle-filter based localization system. This system uses the map and the then fed to the second primary most recent results from the vision system to update the estimate of the robot's location. This report summarizes the design of both the hardware and software and will include the results of applying the system to the global localization of a robot over an approximately half-kilometer traverse across JPL'S Pasadena campus.

This paper addresses the problem of mobile robot localization in urban environments. Typically, GPS is the preferred sensor for outdoor operation. However, using GPS-only localization methods leads to significant performance degradation in urban areas where nearby tall structures obstruct the clear view of the satellites. In our work, we use vision-based techniques to supplement GPS and odometry and provide accurate localization. The vision system identifies prominent linear features in the scene and matches them with a reduced model of nearby buildings, yielding improved pose estimation of the robot.

Global localization is an integral part of indoor robot navigation. Traditional methods implemented at image-level still face challenges when encountering dynamic environments, illumination variation and large viewpoint changes. Methods based on 3D point cloud have low computational efficiency and high localization difficulty. In this case, an efficient global localization framework based on graph matching to solve the problem of low localization stability in object-level navigation and robot abduction is proposed. Firstly, semantic information is extracted by the instance segmentation network. An efficient 3D bounding box extraction algorithm is used to obtain the object-level map. Then the object-level map is transformed into a semantic topological graph and preprocessed. The feature matrix of the map is obtained by the tree generation and the graph kernel method. The matching method based on the voting mechanism is adopted to realize the correspondence between the local graph and the global graph. Finally, the pose of the robot is obtained by a two-stage point cloud registration method. Experiments are carried out in SceneNN dataset and three real indoor environments. Extensive experiments show that our approach reaches high accuracy and can achieve robust global localization under large viewpoint changes.

Estimating a 6-DoF camera pose in a prebuilt map is essential for spatial perception in robotics and autonomous driving. While structure-from-motion (SfM) maps provide visual context, they lack geometric precision and scale. In contrast, point cloud maps from LiDAR or depth cameras offer accurate geometry for metric-level perception. This article presents a novel camera localization method that enhances pose estimation accuracy in indoor point cloud maps that do not contain visual information. By leveraging low-level features such as edges and normals from both the query image and the point cloud, the proposed approach operates across diverse environments without scene-specific training. Specifically, we introduce an edge alignment cost that measures the edge point reprojection errors and a normal distribution cost using normalized information distance (NID) to quantify normal vector similarity. An adaptive weighting scheme integrates these costs in an optimization framework. Experiments on simulated and real-world datasets demonstrate that our method outperforms state-of-the-art feature-matching algorithms in localization accuracy.

Cities are becoming more pedestrian-friendly, reducing traffic and promoting physical activity and walking. However, prolonged exposure to the sun can cause sunburn and skin problems, so minimizing exposure to the sun while travelling is especially relevant at certain latitudes and in the summer months. This paper proposes a method for modelling urban contours and generating pedestrian maps with the location of shaded areas and accessibility barriers. The proposed method uses as input data a point cloud of an urban environment acquired with Mobile Laser Scanning. First, the input point cloud is segmented in ground points, obstacle points, and points causing shadows. Then, the three segmented point clouds are rasterized and the corresponded images are combined to obtain the navigable ground and the shaded areas. Finally, from the navigable ground, a navigation map is generated for pedestrians. To check the usefulness of this navigation map, a pathfinding algorithm is applied. The results show a correct generation of the navigable ground, and routes prioritizing the trajectory by shadow areas. Depending on the weighting between sun and shaded areas, the routes obtained show differences in distance travelled and sun exposure. The proposed method is sensitive to the existence of obstacles and noise in the point clouds.

The ability to classify urban objects in large urban scenes from point clouds efficiently and accurately still remains a challenging task today. A new methodology for the effective and accurate classification of terrestrial laser scanning (TLS) point clouds is presented in this paper. First, in order to efficiently obtain the complementary characteristics of each 3-D point, a set of point-based descriptors for recognizing urban point clouds is constructed. This includes the 3-D geometry captured using the spin-image descriptor computed on three different scales, the mean RGB colors of the point in the camera images, the LAB values of that mean RGB, and the normal at each 3-D point. The initial 3-D labeling of the categories in urban environments is generated by utilizing a linear support vector machine classifier on the descriptors. These initial classification results are then first globally optimized by the multilabel graph-cut approach. These results are further refined automatically by a local optimization approach based upon the object-oriented decision tree that uses weak priors among urban categories which significantly improves the final classification accuracy. The proposed method has been validated on three urban TLS point clouds, and the experimental results demonstrate that it outperforms the state-of-the-art method in classification accuracy for buildings, trees, pedestrians, and cars.

Urban environments still form a challenge for Global Navigation Satellite System (GNSS) positioning as they induce difficult conditions for signal propagation. Recently, Doppler measurements have been proposed as additional aiding to improve localization in urban environments. However, the performance of Doppler in urban environments has not been analyzed in depth yet. Therefore, in this paper we use real data collected from an experiment in the urban areas of Hannover to investigate the availability and signal behavior of Doppler observations. Multiple combinations of receivers with atomic clocks have been installed to study the advantages of clocks and high sensitivity receivers. Critical situations such as epochs with non-line-of-sight (NLOS) reception that affect the signal are classified to conduct a detailed analysis of the signal's behavior. Session: Signal Processing for Resilient Navigation.

Micro aerial vehicles (MAVs) are gaining importance as image acquisition tools in urban environments, where areas of interest are often close to buildings and to the ground. While GPS is still the most widely used sensor for outdoor localization, urban applications motivate the change towards visual localization. We present a framework based on metric, geo-referenced visual landmarks, which can be obtained by taking images with a consumer camera at ground level. Visual landmarks serve as prior knowledge to the MAV and allow robust, high-accuracy localization in urban environments. The issue of differing camera views in higher altitudes is reduced by incremental feature updates, a novel technique which boosts the performance by 30% in comparison to previous work, facilitates long-term operation, and results in a localization rate of 83%. We validate the visual pose estimation in-flight by comparison to IMU and GPS data, and evaluate our positioning accuracy with respect to differential GPS.

Point cloud semantic segmentation in urban scenes plays a vital role in intelligent city modeling, autonomous driving, and urban planning. Point cloud semantic segmentation based on deep learning methods has achieved significant improvement. However, it is also challenging for accurate semantic segmentation in large scenes due to complex elements, variety of scene classes, occlusions, and noise. Besides, most methods need to split the original point cloud into multiple blocks before processing and cannot directly deal with the point clouds on a large scale. We propose a novel context-aware network (CAN) that can directly deal with large-scale point clouds. In the proposed network, a Local Feature Aggregation Module (LFAM) is designed to preserve rich geometric details in the raw point cloud and reduce the information loss during feature extraction. Then, in combination with a Global Context Aggregation Module (GCAM), capture long-range dependencies to enhance the network feature representation and suppress the noise. Finally, a Context-Aware Upsampling Module (CAUM) is embedded into the proposed network to capture the global perception from a broad perspective. The ensemble of low-level and high-level features facilitates the effectiveness and efficiency of 3D point cloud feature refinement. Comprehensive experiments were carried out on three large-scale point cloud datasets in both outdoor and indoor environments to evaluate the performance of the proposed network. The results show that the proposed method outperformed the state-of-the-art representative semantic segmentation networks, and the overall accuracy (OA) of Tongji-3D, Semantic3D, and S3DIS is 96.01%, 95.0%, and 88.55%, respectively.

Unmanned aerial vehicle (UAV) swarms require accurate relative localization to safeguard flight missions in the global navigation satellite system-denied environment due to a lack of absolute position information. The existing work of relative localization faces challenges, such as the ranging information loss and the low localization frequency caused by long-distance ranging and large-scale characteristic of the UAV swarm. This article proposes a clustering-based cooperative relative localization scheme for UAV swarm, which contains a two-level framework: inter/intra-cluster localization. In order to investigate the tradeoff between intracluster cooperation and intercluster packet loss, the clustering-based problem is constructed as a coalition formation game (CFG) model. Given the designed coalition value, preference relation, and the coalition formation principles, it is proved that the proposed CFG model has a Nash stable partition. The designed coalition formation algorithm includes coalition heads and beacon drones selection mechanism. Simulation results show that the proposed CFG algorithms shorten the ranging time compared with global localization and achieve better localization performance (localization error and success rate) than contrast algorithms.

In order to improve the accuracy and reliability of vehicle localization in urban environment, an algorithm based on the multiple vehicles cooperative localization technique is proposed. In this paper, considering that the relative position between the vehicle to be localized and the reference vehicles have a profound effect on the accuracy, an improved computational method for geometric position factor is proposed to select the optimal group of reference vehicles from its neighbors. Then the position of the vehicle to be localized is computed by the relative distances from itself to the other optimal reference vehicles. For further improvement on the accuracy of the localization, an improved current statistical model with the variance of regulatory factor is exploited to correct the errors including those caused in the calculated locations. Some simulation experiments are shown to evaluate the effectiveness of the proposed method. The experimental results demonstrate our method can improve the accuracy of localization and reliability significantly.

In the agricultural field, concrete headworks is the most important structure for the irrigation system. In recent years, several agricultural concrete infrastructures aging for a long-term period has been increasing. For maintenance and management, conventional inspection methods are time-consuming and costly, such as the electromagnetic wave method and elastic wave method. The detection of surface damage is more effective, safe and reliable than before since the laser scanning method provides detailed geometric information about the structure. The fundamental studies on point cloud data have been conducted in the civil engineering fields, nevertheless, the characteristics of point cloud in agricultural infrastructures, such as dam, headworks and canal, have not been discussed. In this study, 3D point clouds are generated for a concrete irrigation structure using the laser scanning method. We focused on the characteristics of surface damage, which are quantitatively evaluated using point cloud information, geometric information and intensity parameter. The types of detected damage are efflorescence and cracks. Which aligned point clouds or point clouds from a single scan is effective for high-precision detection is confirmed. The characteristics of surface damage are evaluated by geometric features. The distance between the fitted plane and points is calculated by RANSAC algorithm and roughness parameter. The amount of efflorescence is detected by the distance between the fitted plane from RANSAC algorithm and points. The crack is detected by the local plane fitting method. The types of damage are characterized by the intensity parameter which is related to the color, roughness and moisture of the object. The surface damage and condition are evaluated by both geometric information and intensity parameter. These results show the unique parameters of point clouds from laser scanning methods, such as geometric features and intensity parameter, are useful to evaluate the characteristics of surface damage.