Efficient road geometry identification from digital vector data

Andrášik, Richard; Bíl, Michal

doi:10.1007/s10109-016-0230-1

Cited by 22 publications

(16 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This work stems from a classification approach for effective identification of the road geometry introduced by Andrášik and Bíl [2]. More specifically, we applied the same idea of using a classification method to determine horizontal curves and tangents within a road network, but selected a different classification approach to allow for full automation of the entire process (construction of toolbox in ArcGIS).…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

ROCA – An ArcGIS toolbox for road alignment identification and horizontal curve radii computation

et al. 2018

Self Cite

View full text Add to dashboard Cite

We present the ROCA (ROad Curvature Analyst) software, in the form of an ESRI ArcGIS Toolbox, intended for vector line data processing. The software segments road network data into tangents and horizontal curves. Horizontal curve radii and azimuth of tangents are then automatically computed. Simultaneously, additional frequently used road section characteristics are calculated, such as the sinuosity of a road section (detour ratio), the number of turns along an individual road section and the average cumulative angle for a road section. The identification of curves is based on the naïve Bayes classifier and users are allowed to prepare their own training data files. We applied ROCA software to secondary roads within the Czech road network (9,980 km). The data processing took less than ten minutes. Approximately 43% of the road network in question consists of 42,752 horizontal curves. The ROCA software outperforms other existing automatic methods by 26% with respect to the percentage of correctly identified curves. The segmented secondary roads within the Czech road network can be viewed on the roca.cdvgis.cz/czechia web-map application. We combined data on road geometry with road crashes database to develop the crash modification factors for horizontal curves with various radii. We determined that horizontal curves with radii of 50 m are approximately 3.7 times more hazardous than horizontal curves with radii accounting for 1000 m. ROCA software can be freely downloaded for noncommercial use from https://roca.cdvinfo.cz/ website.

show abstract

Section: Methodsmentioning

confidence: 99%

“…A large amount of road network data is currently stored in GIS, with a sufficient spatial precision allowing for automated data processing. A demand for a fully automated tool for road alignment extraction from digital data therefore exists (e.g., [1, 2, 3]).…”

Section: Introductionmentioning

confidence: 99%

ROCA – An ArcGIS toolbox for road alignment identification and horizontal curve radii computation

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…The function

represents state-representation-learning approach, where driving environment images are down-sampled to only include more robust features, termed as SRL dimensionality reduction. The numbers

represent the scene size in 2 dimensions (2D), or the number of pixels in an image in 2D, experimentally chosen to retain sufficient image clarity, and multiplying by the number 3 indicates red, green, and blue (RGB) component of colors in the driving images [ 35 , 36 ]. The images in 3 dimensions (3D) are further downsampled to 2-dimensional (2D) images as this reduces processing power required while retaining robustness of features.…”

Section: System Modelmentioning

confidence: 99%

Policy-Gradient and Actor-Critic Based State Representation Learning for Safe Driving of Autonomous Vehicles

Gupta

Khwaja

Anpalagan

et al. 2020

Sensors

View full text Add to dashboard Cite

In this paper, we propose an environment perception framework for autonomous driving using state representation learning (SRL). Unlike existing Q-learning based methods for efficient environment perception and object detection, our proposed method takes the learning loss into account under deterministic as well as stochastic policy gradient. Through a combination of variational autoencoder (VAE), deep deterministic policy gradient (DDPG), and soft actor-critic (SAC), we focus on uninterrupted and reasonably safe autonomous driving without steering off the track for a considerable driving distance. Our proposed technique exhibits learning in autonomous vehicles under complex interactions with the environment, without being explicitly trained on driving datasets. To ensure the effectiveness of the scheme over a sustained period of time, we employ a reward-penalty based system where a negative reward is associated with an unfavourable action and a positive reward is awarded for favourable actions. The results obtained through simulations on DonKey simulator show the effectiveness of our proposed method by examining the variations in policy loss, value loss, reward function, and cumulative reward for `VAE+DDPG’ and `VAE+SAC’ over the learning process.

show abstract

“…Furthermore, considering that the risk of accidents increases when the radius (R) of the curve decreases (Rasdorf et al, 2012;You et al, 2012) and that the Curvature Change Rate (CCR) is a key parameter due to its influence in the operation speed (Lamm et al, 2001), this study is focused on just circular alignments (Andrasik and Bil, 2016;Misaghi and Hassan, 2005). In this sense, it is noteworthy that the geometric consistency indexes are obtained exclusively from R and CCR parameters, highlighting the relevance that they have in road safety (Montella and Imbriani, 2015).…”

Section: Step 2 Horizontal Alignment and Geometric Consistency Indexesmentioning

confidence: 99%

“…From a dual research-engineering perspective, the concept of geometric consistency in road design has a direct influence on road safety (Ng and Sayed, 2004). The studies developed have been based fundamentally on aspects such as purely geometric, models of the speed of operation, vehicle stability and the workload of the driver (Andrasik and Bil, 2016, Eftekharzadeh and Khodabakhshi, 2014. However, we must highlight the works developed by Lamm et al, (1991Lamm et al, ( , 1995Lamm et al, ( , 1999Lamm et al, ( , 2001) due to their proposal of the simultaneous triple criterion of stability: (i) in the design (Criterion I), (ii) in the speed of operation (Criterion II) and (iii) in the driving dynamics (Criterion III), which today continue to be a benchmark in the field of road safety.…”

Section: Introductionmentioning

confidence: 99%

Road safety evaluation through automatic extraction of road horizontal alignments from Mobile LiDAR System and inductive reasoning based on a decision tree

Martín-Jiménez

Zazo

Justel

et al. 2018

ISPRS Journal of Photogrammetry and Remote Sensing

View full text Add to dashboard Cite

Safe roads are a necessity for any society because of the high social costs of traffic accidents. This challenge is addressed by a novel methodology that allows us to evaluate road safety from Mobile LiDAR System data, taking advantage of the road alignment due to its influence on the accident rate. Automation is obtained through an inductive reasoning process based on a decision tree that provides a potential risk assessment. To achieve this, a 3D point cloud is classified by an iterative and incremental algorithm based on a 2.5D and 3D Delaunay triangulation, which apply different algorithms sequentially. Next, an automatic extraction process of road horizontal alignment parameters is developed to obtain geometric consistency indexes, based on a joint triple stability criterion. Likewise, this work aims to provide a powerful and effective preventive and/or predictive tool for road safety inspections. The proposed methodology was implemented on three stretches of Spanish roads, each with different traffic conditions that represent the most common road types. The developed methodology was successfully validated through as-built road projects, which were considered as "ground truth."

show abstract

Efficient road geometry identification from digital vector data

Cited by 22 publications

References 20 publications

ROCA – An ArcGIS toolbox for road alignment identification and horizontal curve radii computation

ROCA – An ArcGIS toolbox for road alignment identification and horizontal curve radii computation

Policy-Gradient and Actor-Critic Based State Representation Learning for Safe Driving of Autonomous Vehicles

Road safety evaluation through automatic extraction of road horizontal alignments from Mobile LiDAR System and inductive reasoning based on a decision tree

Contact Info

Product

Resources

About