Digital Map Generation and Localization for Vehicles in Urban Intersections using LiDAR and GNSS Data

Quack, Tobias; Reiter, Matthias; Abel, Dirk

doi:10.1016/j.ifacol.2017.08.042

Cited by 8 publications

(11 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among them, the feature point method is the more commonly used method, while the direct method has only been proposed in recent years [10]. In the back-end part, SLAM methods usually transform the whole problem into a maximizing a posteriori probability estimation (MAP) problem, using the data association provided by the front-end to estimate both the positional and surrounding environment maps [11]. The back-end estimation methods are generally divided into two types: filtering and optimization.…”

Section: Current Status Of Researchmentioning

confidence: 99%

[Retracted] Combined GNSS/SLAM‐Based High Accuracy Indoor Dynamic Target Localization Method

Zhang

Li³

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

As the indoor dynamic target localization does not detect and repair the circumferential jump value in time, which leads to large position and attitude errors and low-velocity stability, a combined Global Navigation Satellite System/Simultaneous Localization and Mapping- (GNSS/SLAM-) based high-precision indoor dynamic target localization method is proposed. The method uses Empirical Mode Decomposition (EMD) to decompose the noisy signal, obtains the noise energy as the dominant mode from the decomposed components, extracts the useful signal energy as the main dividing point, removes the high-frequency signal, constructs the low-frequency component to realize low-pass filtering and denoising, selects a suitable threshold processing function to make the high-frequency signal component retain the detailed signal effectively to realize high-frequency component denoising, detects and fixes the circumferential jump of the observed data, and detects and fixes the circumferential jump of each frequency. The indoor dynamic target positioning method is established by combining GNSS/SLAM to achieve high accuracy target positioning. The experimental results show that the position and attitude errors are small, and the velocity is stable, which indicates that the position information is closer to the dynamic target, i.e., the target positioning is more accurate. To address the problems of scale drift and frequent initialization due to environmental factors in monocular vision SLAM, an Ultra Wideband (UWB)/vision fusion localization model that takes into account the scale factor is proposed, which can give full play to the complementary characteristics between UWB and vision; solve the problems of visual initialization, scale ambiguity, and absolute spatial reference; and improve UWB localization accuracy and localization frequency as well as reducing the number of base stations. The model can reliably achieve 0.2 m accuracy in indoor environments with sparse texture or frequent light changes.

show abstract

Section: Current Status Of Researchmentioning

confidence: 99%

[Retracted] Combined GNSS/SLAM‐Based High Accuracy Indoor Dynamic Target Localization Method

Zhang

Li³

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…= manhole automated detection (manhole + non − manhole automated detection) • 100 (7) The manhole extraction process was applied to Areas 1, 2 and 3 of the study area. A total of 1414 manholes were extracted from area 1, while 237 manholes were extracted from area 2, and 27 manholes from area 3, as shown in Table 4.…”

Section: Feature Extractionmentioning

confidence: 99%

Automatic manhole extraction from MMS data to update basemaps

Alshaiba

Andrés

Lantada

2020

Automation in Construction

View full text Add to dashboard Cite

Basemaps are the main resource used in urban planning, building and infrastructure asset management. Therefore, they must be accurate and up to date to better serve citizens, contractors, property owners and town planning departments. Traditionally, they have been updated by aerial photogrammetry, but this is not always possible and alternatives need to be sought. In such cases, a useful option for large scales is the mobile mapping system (MMS). However, automatic extraction from MMS point clouds is limited by the complexity of the urban environment. Therefore, the influence of the urban pattern is analysed in three zones with varied urban characteristics: areas with high buildings, open areas, and areas with a low level of urbanization. In these areas, the capture and automatic extraction of 3D urban elements is performed using commercial software, which is useful for some elements but not for manholes. The objective of this study is to establish a methodology for extracting manholes automatically and completing hidden buildings' corners, in order to update urban basemaps. Shape and intensity are the main detection parameters for manholes, whereas additional information from satellite image Quickbird is used to complete the buildings. The worst rate of detection for all the extracted urban elements was found in areas of high buildings. Finally, the article analyses the computing cost for manhole extraction, and the economic cost and time consume of the entire process, including the proposed methodology using an MMS point cloud and the traditional survey in this case.

show abstract

“…Traditional obstacle clustering methods in video sequences have relied on detecting foreground pixels based on the difference between two successive frames [21,22]. Arvanitidou et al [23] realized an unsupervised moving obstacle clustering system using environmental images captured by a moving camera.…”

Section: Related Workmentioning

confidence: 99%

A Fast Spatial Clustering Method for Sparse LiDAR Point Clouds Using GPU Programming

Tian

Song

Chen³

et al. 2020

Sensors

View full text Add to dashboard Cite

Fast and accurate obstacle detection is essential for accurate perception of mobile vehicles’ environment. Because point clouds sensed by light detection and ranging (LiDAR) sensors are sparse and unstructured, traditional obstacle clustering on raw point clouds are inaccurate and time consuming. Thus, to achieve fast obstacle clustering in an unknown terrain, this paper proposes an elevation-reference connected component labeling (ER-CCL) algorithm using graphic processing unit (GPU) programing. LiDAR points are first projected onto a rasterized x–z plane so that sparse points are mapped into a series of regularly arranged small cells. Based on the height distribution of the LiDAR point, the ground cells are filtered out and a flag map is generated. Next, the ER-CCL algorithm is implemented on the label map generated from the flag map to mark individual clusters with unique labels. Finally, obstacle labeling results are inverse transformed from the x–z plane to 3D points to provide clustering results. For real-time 3D point cloud clustering, ER-CCL is accelerated by running it in parallel with the aid of GPU programming technology.

show abstract

Digital Map Generation and Localization for Vehicles in Urban Intersections using LiDAR and GNSS Data

Cited by 8 publications

References 12 publications

[Retracted] Combined GNSS/SLAM‐Based High Accuracy Indoor Dynamic Target Localization Method

[Retracted] Combined GNSS/SLAM‐Based High Accuracy Indoor Dynamic Target Localization Method

Automatic manhole extraction from MMS data to update basemaps

A Fast Spatial Clustering Method for Sparse LiDAR Point Clouds Using GPU Programming

Contact Info

Product

Resources

About