Search

Although point features have shown their usefulness in classification with Machine Learning, point cloud visualization enhancement methods focus mainly on lighting. The visualization of point features helps to improve the perception of the 3D environment. This paper proposes Multi Feature-Rich Synthetic Colour (MFRSC) as an alternative non-photorealistic colour approach of natural-coloured point clouds. The method is based on the selection of nine features (reflectance, return number, inclination, depth, height, point density, linearity, planarity, and scattering) associated with five human perception descriptors (edges, texture, shape, size, depth, orientation). The features are reduced to fit the RGB display channels. All feature permutations are analysed according to colour distance with the natural-coloured point cloud and Image Quality Assessment. As a result, the selected feature permutations allow a clear visualization of the scene's rendering objects, highlighting edges, planes, and volumetric objects. MFRSC effectively replaces natural colour, even with less distorted visualization according to BRISQUE, NIQUE and PIQE. In addition, the assignment of features in RGB channels enables the use of MFRSC in software that does not support colorization based on point attributes (most commercially available software). MFRSC can be combined with other non-photorealistic techniques such as Eye-Dome Lighting or Ambient Occlusion. [ABSTRACT FROM AUTHOR]

• Santiago Urban Dataset SUD was acquired with MLS and HMLS equipment. • Occlusions are reduced by the integration of MLS and HMLS data. • Point clouds are labelled by heuristic and Deep Learning methods in eight classes. • SUD is valid for comparing semantic segmentation works. • SUD is valid for urban 3D mobility studies. Santiago Urban Dataset SUD is a real dataset that combines Mobile Laser Scanning (MLS) and Handheld Mobile Laser Scanning (HMLS) point clouds. The data is composed by 2 km of streets, sited in Santiago de Compostela (Spain). Point clouds undergo a manual labelling process supported by both heuristic and Deep Learning methods, resulting in the classification of eight specific classes: road, sidewalk, curb, buildings, vehicles, vegetation, poles , and others. Three PointNet++ models were trained; the first one using MLS point clouds, the second one with HMLS point clouds and the third one with both H&MLS point clouds. In order to ascertain the quality and efficacy of each Deep Learning model, various metrics were employed, including confusion matrices, precision, recall, F1-score, and IoU. The results are consistent with other state-of-the-art works and indicate that SUD is valid for comparing point cloud semantic segmentation works. Furthermore, the survey's extensive coverage and the limited occlusions indicate the potential utility of SUD in urban mobility research. [ABSTRACT FROM AUTHOR]

Highlights • The proposed method is capable of giving stable navigation and mapping solutions. • Position accuracy is around 2 m in long GNSS (more than 300 s) outage. • The mapping results achieve the meter-level accuracy. • An approximately 60% improvement of long GNSS-denied experiments is achieved. Abstract Mobile Mapping Systems (MMS) with Inertial Navigation System / Global Navigation Satellite System (INS/GNSS) and mapping sensors have been widely developed in recent years. However current systems and results are still prone to errors, especially in GNSS-denied or multipath environments. To provide robust and stable navigation information, particularly for mapping in long-term GNSS-denied environments, we propose a semi-tightly coupled integration scheme which integrates INS/GNSS with grid-based Simultaneous Localization and Mapping (SLAM). Although traditional SLAM using LiDAR can map the GNSS-denied environment efficiently, it is only in local localization. The proposed integration scheme is based on the Extended Kalman Filter (EKF) with motion constraints. In this scheme, a measurement model for grid-based SLAM is aided by the heading and velocity information. A special innovation of this scheme is the improved fusion of GNSS/INS with the use of grid-based SLAM serves like virtual odometer and virtual compass, thus gaining reliable measurements and error models to maintain good performance during INS-only mode. In addition, the initial values for example position and heading, are given to solve global localization and loop closure problems in SLAM. Finally, a smoothing and multi-resolution map strategy are applied offline to increase the robustness and performance of the proposed grid-based SLAM. Evaluation based on experimental data shows the significant improvement by the proposed semi-tightly coupled integration scheme with low-cost INS/GNSS and LiDAR, which is able to achieve 1–2 m' accuracy in terms of positioning and mapping. An approximately 60% improvement was achieved during long-term GNSS-denied environments using the proposed integration scheme. [ABSTRACT FROM AUTHOR]

Labelled point clouds are crucial to train supervised Deep Learning (DL) methods used for semantic segmentation. The objective of this research is to quantify discordances between the labels made by different people in order to assess whether such discordances can influence the success rates of a DL based semantic segmentation algorithm. An urban point cloud of 30 m road length in Santiago de Compostela (Spain) was labelled two times by ten persons. Discordances and its significance in manual labelling between individuals and rounds were calculated. In addition, a ratio test to signify discordance and concordance was proposed. Results show that most of the points were labelled accordingly with the same class by all the people. However, there were many points that were labelled with two or more classes. Class curb presented 5.9% of discordant points and 3.2 discordances for each point with concordance by all people. In addition, the percentage of significative labelling differences of the class curb was 86.7% comparing all the people in the same round and 100% comparing rounds of each person. Analysing the semantic segmentation results with a DL based algorithm, PointNet++, the percentage of concordance points are related with F-score value in R2 = 0.765, posing that manual labelling has significant impact on results of DL-based semantic segmentation methods. [ABSTRACT FROM AUTHOR]

• Point cloud processing based on Lab space colour. • Detection and correction of sky-coloured points caused by calibration errors. • Detection of sky-coloured points in eight real case studies with an average 94.7% F1-score. • Deviation from true colour of 0.976 ± 1.280 intensity levels tested on point clouds with synthetic errors. The enrichment of the point clouds with colour images improves the visualisation of the data as well as the segmentation and recognition processes. Coloured point clouds are becoming increasingly common, however, the colour they display is not always as expected. Errors in the colouring of point clouds acquired with Mobile Laser Scanning are due to perspective in the camera image, different resolution or poor calibration between the LiDAR sensor and the image sensor. The consequences of these errors are noticeable in elements captured in images, but not in point clouds, such as the sky. This paper focuses on the correction of the sky-coloured points, without resorting to the images that were initially used to colour the whole point cloud. The proposed method consists of three stages. First the region of interest where the erroneously coloured points are accumulated, is selected. Second, the sky-coloured points are detected by calculating the colour distance in the Lab colour space to a sample of the sky-colour. And third, the colour of the sky-coloured detected points is restored from the colour of the nearby points. The method is tested in ten real case studies with their corresponding point clouds from urban and rural areas. In two case studies, sky-coloured points were assigned manually and the remaining eight case studies, the sky-coloured points are derived from the acquisition errors. The algorithm for sky-coloured points detection obtained an average F1-score of 94.7%. The results show a correct reassignment of colour, texture, and patterns, while improving the point cloud visualisation. [ABSTRACT FROM AUTHOR]