Towards Large Scale Urban Traffic Reference Data: Smart Infrastructure in the Test Area Autonomous Driving Baden-Württemberg

Mobile laser scanning (MLS) systems are often used to efficiently acquire reference data covering a large-scale scene. The terrestrial laser scanner (TLS) can easily collect high point density data of local scene. Localization of static TLS scans in mobile mapping point clouds can afford detailed geographic information for many specific tasks especially in autonomous driving and robotics. However, large-scale MLS reference data often have a huge amount of data and many similar scene data; significant differences may exist between MLS and TLS data. To overcome these challenges, this paper presents a novel deep neural network-based localization method in urban environment, divided by place recognition and pose refinement. Firstly, simple, reliable primitives, cylinder-like features were extracted to describe the global features of a local urban scene. Then, a probabilistic framework is applied to estimate a similarity between TLS and MLS data, under a stable decision-making strategy. Based on the results of a place recognition, we design a patch-based convolution neural network (CNN) (point-based CNN is used as kernel) for pose refinement. The input data unit is the batch consisting of several patches. One patch goes through three main blocks: feature extraction block (FEB), the patch correspondence search block and the pose estimation block. Finally, a global refinement was proposed to tune the predicted transformation parameters to realize localization. The research aim is to find the most similar scene of MLS reference data compared with the local TLS scan, and accurately estimate the transformation matrix between them. To evaluate the performance, comprehensive experiments were carried out. The experiments demonstrate that the proposed method has good performance in terms of efficiency, i.e., the runtime of processing a million points is 5 s, robustness, i.e., the success rate of place recognition is 100% in the experiments, accuracy, i.e., the mean rotation and translation error is (0.24 deg, 0.88 m) and (0.03 deg, 0.06 m) on TU Delft campus and Shanghai urban datasets, respectively, and outperformed some commonly used methods (e.g., iterative closest point (ICP), coherent point drift (CPD), random sample consensus (RANSAC)-based method).

Download Full-text

Transformer Meets Convolution: A Bilateral Awareness Network for Semantic Segmentation of Very Fine Resolution Urban Scene Images

Remote Sensing ◽

10.3390/rs13163065 ◽

2021 ◽

Vol 13 (16) ◽

pp. 3065

Author(s):

Libo Wang ◽

Rui Li ◽

Dongzhi Wang ◽

Chenxi Duan ◽

Teng Wang ◽

...

Keyword(s):

Large Scale ◽

Texture Features ◽

Semantic Segmentation ◽

Autonomous Driving ◽

Research Field ◽

Learning Approaches ◽

Fine Grained ◽

Urban Scene ◽

Fine Resolution ◽

With Memory

Semantic segmentation from very fine resolution (VFR) urban scene images plays a significant role in several application scenarios including autonomous driving, land cover classification, urban planning, etc. However, the tremendous details contained in the VFR image, especially the considerable variations in scale and appearance of objects, severely limit the potential of the existing deep learning approaches. Addressing such issues represents a promising research field in the remote sensing community, which paves the way for scene-level landscape pattern analysis and decision making. In this paper, we propose a Bilateral Awareness Network which contains a dependency path and a texture path to fully capture the long-range relationships and fine-grained details in VFR images. Specifically, the dependency path is conducted based on the ResT, a novel Transformer backbone with memory-efficient multi-head self-attention, while the texture path is built on the stacked convolution operation. In addition, using the linear attention mechanism, a feature aggregation module is designed to effectively fuse the dependency features and texture features. Extensive experiments conducted on the three large-scale urban scene image segmentation datasets, i.e., ISPRS Vaihingen dataset, ISPRS Potsdam dataset, and UAVid dataset, demonstrate the effectiveness of our BANet. Specifically, a 64.6% mIoU is achieved on the UAVid dataset.

Download Full-text

Wireless Sensor Network-Based Urban Traffic Monitoring Using Inertial Reference Data

2015 International Conference on Distributed Computing in Sensor Systems ◽

10.1109/dcoss.2015.21 ◽

2015 ◽

Cited By ~ 3

Author(s):

Mustafa Mousa ◽

Mohammed Abdulaal ◽

Stephen Boyles ◽

Christian Claudel

Keyword(s):

Wireless Sensor Network ◽

Sensor Network ◽

Reference Data ◽

Traffic Monitoring ◽

Urban Traffic ◽

Wireless Sensor

Download Full-text

Make More Connections: Urban Traffic Flow Forecasting with Spatiotemporal Adaptive Gated Graph Convolution Network

ACM Transactions on Intelligent Systems and Technology ◽

10.1145/3488902 ◽

2022 ◽

Vol 13 (2) ◽

pp. 1-25

Author(s):

Bin Lu ◽

Xiaoying Gan ◽

Haiming Jin ◽

Luoyi Fu ◽

Xinbing Wang ◽

...

Keyword(s):

Traffic Flow ◽

Road Network ◽

Large Scale ◽

Transportation Systems ◽

Urban Traffic ◽

Propagation Mechanism ◽

Urban Road ◽

The Road ◽

Traffic Flow Forecasting ◽

Gating Mechanism

Urban traffic flow forecasting is a critical issue in intelligent transportation systems. Due to the complexity and uncertainty of urban road conditions, how to capture the dynamic spatiotemporal correlation and make accurate predictions is very challenging. In most of existing works, urban road network is often modeled as a fixed graph based on local proximity. However, such modeling is not sufficient to describe the dynamics of the road network and capture the global contextual information. In this paper, we consider constructing the road network as a dynamic weighted graph through attention mechanism. Furthermore, we propose to seek both spatial neighbors and semantic neighbors to make more connections between road nodes. We propose a novel Spatiotemporal Adaptive Gated Graph Convolution Network ( STAG-GCN ) to predict traffic conditions for several time steps ahead. STAG-GCN mainly consists of two major components: (1) multivariate self-attention Temporal Convolution Network ( TCN ) is utilized to capture local and long-range temporal dependencies across recent, daily-periodic and weekly-periodic observations; (2) mix-hop AG-GCN extracts selective spatial and semantic dependencies within multi-layer stacking through adaptive graph gating mechanism and mix-hop propagation mechanism. The output of different components are weighted fused to generate the final prediction results. Extensive experiments on two real-world large scale urban traffic dataset have verified the effectiveness, and the multi-step forecasting performance of our proposed models outperforms the state-of-the-art baselines.

Download Full-text

Introducing ribosomal tandem repeat barcoding for fungi

10.1101/310540 ◽

2018 ◽

Cited By ~ 2

Author(s):

Christian Wurzbacher ◽

Ellen Larsson ◽

Johan Bengtsson-Palme ◽

Silke Van den Wyngaert ◽

Sten Svantesson ◽

...

Keyword(s):

Large Scale ◽

Tandem Repeats ◽

Reference Data ◽

Reference Sequence ◽

Herbarium Specimens ◽

Nanopore Sequencing ◽

Desktop Computer ◽

Third Generation Sequencing ◽

Ribosomal Operon ◽

Sequencing Facility

AbstractSequence analysis of the various ribosomal genetic markers is the dominant molecular method for identification and description of fungi. However, there is little agreement on what ribosomal markers should be used, and research groups utilize different markers depending on what fungal groups are targeted. New environmental fungal lineages known only from DNA data reveal significant gaps in the coverage of the fungal kingdom both in terms of taxonomy and marker coverage in the reference sequence databases. In order to integrate references covering all of the ribosomal markers, we present three sets of general primers that allow the amplification of the complete ribosomal operon from the ribosomal tandem repeats. The primers cover all ribosomal markers (ETS, SSU, ITS1, 5.8S, ITS2, LSU, and IGS) from the 5’ end of the ribosomal operon all the way to the 3’ end. We coupled these primers successfully with third generation sequencing (PacBio and Nanopore sequencing) to showcase our approach on authentic fungal herbarium specimens. In particular, we were able to generate high-quality reference data with Nanopore sequencing in a high-throughput manner, showing that the generation of reference data can be achieved on a regular desktop computer without the need for a large-scale sequencing facility. The quality of the Nanopore generated sequences was 99.85 %, which is comparable with the 99.78 % accuracy described for Sanger sequencing. With this work, we hope to stimulate the generation of a new comprehensive standard of ribosomal reference data with the ultimate aim to close the huge gaps in our reference datasets.

Download Full-text

Large-Scale Dataset for Radio Frequency-Based Device-Free Crowd Estimation

Data ◽

10.3390/data5020052 ◽

2020 ◽

Vol 5 (2) ◽

pp. 52 ◽

Cited By ~ 1

Author(s):

Abdil Kaya ◽

Stijn Denis ◽

Ben Bellekens ◽

Maarten Weyn ◽

Rafael Berkvens

Keyword(s):

Control System ◽

Radio Frequency ◽

Large Scale ◽

Reference Data ◽

Added Value ◽

Size Estimation ◽

Music Festival ◽

Large Scale Dataset ◽

Access Control System ◽

Device Free

Organisers of events attracting many people have the important task to ensure the safety of the crowd on their venue premises. Measuring the size of the crowd is a critical first step, but often challenging because of occlusions, noise and the dynamics of the crowd. We have been working on a passive Radio Frequency (RF) sensing technique for crowd size estimation, and we now present three datasets of measurements collected at the Tomorrowland music festival in environments containing thousands of people. All datasets have reference data, either based on payment transactions or an access control system, and we provide an example analysis script. We hope that future analyses can lead to an added value for crowd safety experts.

Download Full-text

The Feasibility of Opening Communities -- Based on the Wiedemann Car-Following Model

Computer and Information Science ◽

10.5539/cis.v11n3p57 ◽

2018 ◽

Vol 11 (3) ◽

pp. 57

Author(s):

Xiao-Yan Cao ◽

Bing-Qian Liu ◽

Bao-Ru Pan ◽

Yuan-Biao Zhang

Keyword(s):

Traffic Congestion ◽

Large Scale ◽

Gated Communities ◽

Urban Traffic ◽

Average Delay ◽

Traffic Demand ◽

Car Following ◽

Car Following Model ◽

Urbanization In China ◽

The Impact

With the accelerating development of urbanization in China, the increasing traffic demand and large scale gated communities have aggravated urban traffic congestion. This paper studies the impact of communities opening on road network structure and the surrounding road capacity. Firstly, we select four indicators, namely average speed, vehicle flow, average delay time, and queue length, to measure traffic capacity. Secondly, we establish the Wiedemann car-following model, then use VISSIM software to simulate the traffic conditions of surrounding roads of communities. Finally, we take Shenzhen as an example to simulate and compare the four kinds of gated communities, axis, centripetal and intensive layout, and we also analyze the feasibility of opening communities.

Download Full-text

Large-scale urban traffic simulation with Scala and high-performance computing system

Journal of Computational Science ◽

10.1016/j.jocs.2019.06.002 ◽

2019 ◽

Vol 35 ◽

pp. 91-101 ◽

Cited By ~ 3

Author(s):

Michal Janczykowski ◽

Wojciech Turek ◽

Maciej Malawski ◽

Aleksander Byrski

Keyword(s):

High Performance Computing ◽

High Performance ◽

Large Scale ◽

Traffic Simulation ◽

Computing System ◽

Urban Traffic ◽

High Performance Computing System ◽

Performance Computing

Download Full-text

A Semiautomatic Pixel-Object Method for Detecting Landslides Using Multitemporal ALOS-2 Intensity Images

Remote Sensing ◽

10.3390/rs12030561 ◽

2020 ◽

Vol 12 (3) ◽

pp. 561 ◽

Cited By ~ 1

Author(s):

Bruno Adriano ◽

Naoto Yokoya ◽

Hiroyuki Miura ◽

Masashi Matsuoka ◽

Shunichi Koshimura

Keyword(s):

Disaster Response ◽

Large Scale ◽

Reference Data ◽

Mass Movement ◽

Recovery Planning ◽

Additional Information ◽

Digital Elevation ◽

Before And After ◽

Intensity Images ◽

Elevation Model

The rapid and accurate mapping of large-scale landslides and other mass movement disasters is crucial for prompt disaster response efforts and immediate recovery planning. As such, remote sensing information, especially from synthetic aperture radar (SAR) sensors, has significant advantages over cloud-covered optical imagery and conventional field survey campaigns. In this work, we introduced an integrated pixel-object image analysis framework for landslide recognition using SAR data. The robustness of our proposed methodology was demonstrated by mapping two different source-induced landslide events, namely, the debris flows following the torrential rainfall that fell over Hiroshima, Japan, in early July 2018 and the coseismic landslide that followed the 2018 Mw6.7 Hokkaido earthquake. For both events, only a pair of SAR images acquired before and after each disaster by the Advanced Land Observing Satellite-2 (ALOS-2) was used. Additional information, such as digital elevation model (DEM) and land cover information, was employed only to constrain the damage detected in the affected areas. We verified the accuracy of our method by comparing it with the available reference data. The detection results showed an acceptable correlation with the reference data in terms of the locations of damage. Numerical evaluations indicated that our methodology could detect landslides with an accuracy exceeding 80%. In addition, the kappa coefficients for the Hiroshima and Hokkaido events were 0.30 and 0.47, respectively.

Download Full-text