Road Markings Segmentation from LIDAR Point Clouds using Reflectivity Information

Novel Certad; Walter Morales Alvarez; Cristina Olaverri-Monreal

doi:10.1109/ICVES56941.2022.9986939

Road Markings Segmentation from LIDAR Point Clouds using Reflectivity Information

Novel Certad, Walter Morales Alvarez, Cristina Olaverri-Monreal

Department Intelligent Transport Systems

Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings › peer-review

Abstract

Lane detection algorithms are crucial for the development of autonomous vehicles technologies. The more extended approach is to use cameras as sensors. However, LIDAR sensors can cope with weather and light conditions that cameras can not. In this paper, we introduce a method to extract road markings from the reflectivity data of a 64-layers LIDAR sensor. First, a plane segmentation method along with region grow clustering was used to extract the road plane. Then we applied an adaptive thresholding based on Otsu's method and finally, we fitted line models to filter out the remaining outliers. The algorithm was tested on a test track at 60km/h and a highway at 100km/h. Results showed the algorithm was reliable and precise. There was a clear improvement when using reflectivity data in comparison to the use of the raw intensity data both of them provided by the LIDAR sensor.

Original language	English
Title of host publication	2022 IEEE International Conference on Vehicular Electronics and Safety (ICVES2022)
Publisher	IEEE
Number of pages	6
DOIs	https://doi.org/10.1109/ICVES56941.2022.9986939
Publication status	Published - Nov 2022

Fields of science

303 Health Sciences
303008 Ergonomics
201306 Traffic telematics
202031 Network engineering
202036 Sensor systems
202038 Telecommunications
202040 Transmission technology
203 Mechanical Engineering
211908 Energy research
211911 Sustainable technologies
102 Computer Sciences
102001 Artificial intelligence
102002 Augmented reality
102003 Image processing
102013 Human-computer interaction
102015 Information systems
102019 Machine learning
102021 Pervasive computing
102024 Usability research
102026 Virtual reality
102029 Practical computer science
102034 Cyber-physical systems
501026 Psychology of perception
501 Psychology
501025 Traffic psychology
201305 Traffic engineering
202 Electrical Engineering, Electronics, Information Engineering
202003 Automation
202030 Communication engineering
202034 Control engineering
202035 Robotics
202037 Signal processing
202041 Computer engineering
203004 Automotive technology
211902 Assistive technologies
211909 Energy technology
211917 Technology assessment
501030 Cognitive science

JKU Focus areas

Digital Transformation
Sustainable Development: Responsible Technologies and Management

Access to Document

10.1109/ICVES56941.2022.9986939

Interaction of autonomous and manually-controlled vehicles (IAMCV)
Certad Hernandez, N. (Researcher), Smirnov, N. (Researcher) & Olaverri-Monreal, C. (PI)
FWF
03.05.2021 → 30.04.2024
Project: Funded research › FWF - Austrian Science Fund

Cite this

@inproceedings{2c4ebab658044a9a87c7a4a52df992ee,

title = "Road Markings Segmentation from LIDAR Point Clouds using Reflectivity Information",

abstract = "Lane detection algorithms are crucial for the development of autonomous vehicles technologies. The more extended approach is to use cameras as sensors. However, LIDAR sensors can cope with weather and light conditions that cameras can not. In this paper, we introduce a method to extract road markings from the reflectivity data of a 64-layers LIDAR sensor. First, a plane segmentation method along with region grow clustering was used to extract the road plane. Then we applied an adaptive thresholding based on Otsu's method and finally, we fitted line models to filter out the remaining outliers. The algorithm was tested on a test track at 60km/h and a highway at 100km/h. Results showed the algorithm was reliable and precise. There was a clear improvement when using reflectivity data in comparison to the use of the raw intensity data both of them provided by the LIDAR sensor.",

author = "Novel Certad and {Morales Alvarez}, Walter and Cristina Olaverri-Monreal",

year = "2022",

month = nov,

doi = "10.1109/ICVES56941.2022.9986939",

language = "English",

booktitle = "2022 IEEE International Conference on Vehicular Electronics and Safety (ICVES2022)",

publisher = "IEEE",

}

TY - GEN

T1 - Road Markings Segmentation from LIDAR Point Clouds using Reflectivity Information

AU - Certad, Novel

AU - Morales Alvarez, Walter

AU - Olaverri-Monreal, Cristina

PY - 2022/11

Y1 - 2022/11

N2 - Lane detection algorithms are crucial for the development of autonomous vehicles technologies. The more extended approach is to use cameras as sensors. However, LIDAR sensors can cope with weather and light conditions that cameras can not. In this paper, we introduce a method to extract road markings from the reflectivity data of a 64-layers LIDAR sensor. First, a plane segmentation method along with region grow clustering was used to extract the road plane. Then we applied an adaptive thresholding based on Otsu's method and finally, we fitted line models to filter out the remaining outliers. The algorithm was tested on a test track at 60km/h and a highway at 100km/h. Results showed the algorithm was reliable and precise. There was a clear improvement when using reflectivity data in comparison to the use of the raw intensity data both of them provided by the LIDAR sensor.

AB - Lane detection algorithms are crucial for the development of autonomous vehicles technologies. The more extended approach is to use cameras as sensors. However, LIDAR sensors can cope with weather and light conditions that cameras can not. In this paper, we introduce a method to extract road markings from the reflectivity data of a 64-layers LIDAR sensor. First, a plane segmentation method along with region grow clustering was used to extract the road plane. Then we applied an adaptive thresholding based on Otsu's method and finally, we fitted line models to filter out the remaining outliers. The algorithm was tested on a test track at 60km/h and a highway at 100km/h. Results showed the algorithm was reliable and precise. There was a clear improvement when using reflectivity data in comparison to the use of the raw intensity data both of them provided by the LIDAR sensor.

U2 - 10.1109/ICVES56941.2022.9986939

DO - 10.1109/ICVES56941.2022.9986939

M3 - Conference proceedings

BT - 2022 IEEE International Conference on Vehicular Electronics and Safety (ICVES2022)

PB - IEEE

ER -

Road Markings Segmentation from LIDAR Point Clouds using Reflectivity Information

Abstract

Fields of science

JKU Focus areas

Access to Document

Projects

Interaction of autonomous and manually-controlled vehicles (IAMCV)

Cite this