Evaluation of Cluster Algorithms for Radar-Based Object Recognition in Autonomous and Assisted Driving

Perception systems for assisted driving and autonomy enable the identification and classification of objects through a concentration of sensors installed in vehicles, including Radio Detection and Ranging (RADAR), camera, Light Detection and Ranging (LIDAR), ultrasound, and HD maps. These sensors en...

Full description

Saved in:
Bibliographic Details
Main Authors: Daniel Carvalho de Ramos, Lucas Reksua Ferreira, Max Mauro Dias Santos, Evandro Leonardo Silva Teixeira, Leopoldo Rideki Yoshioka, João Francisco Justo, Asad Waqar Malik
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/22/7219
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850227722510401536
author Daniel Carvalho de Ramos
Lucas Reksua Ferreira
Max Mauro Dias Santos
Evandro Leonardo Silva Teixeira
Leopoldo Rideki Yoshioka
João Francisco Justo
Asad Waqar Malik
author_facet Daniel Carvalho de Ramos
Lucas Reksua Ferreira
Max Mauro Dias Santos
Evandro Leonardo Silva Teixeira
Leopoldo Rideki Yoshioka
João Francisco Justo
Asad Waqar Malik
author_sort Daniel Carvalho de Ramos
collection DOAJ
description Perception systems for assisted driving and autonomy enable the identification and classification of objects through a concentration of sensors installed in vehicles, including Radio Detection and Ranging (RADAR), camera, Light Detection and Ranging (LIDAR), ultrasound, and HD maps. These sensors ensure a reliable and robust navigation system. Radar, in particular, operates with electromagnetic waves and remains effective under a variety of weather conditions. It uses point cloud technology to map the objects in front of you, making it easy to group these points to associate them with real-world objects. Numerous clustering algorithms have been developed and can be integrated into radar systems to identify, investigate, and track objects. In this study, we evaluate several clustering algorithms to determine their suitability for application in automotive radar systems. Our analysis covered a variety of current methods, the mathematical process of these methods, and presented a comparison table between these algorithms, including Hierarchical Clustering, Affinity Propagation Balanced Iterative Reducing and Clustering using Hierarchies (BIRCH), Density-Based Spatial Clustering of Applications with Noise (DBSCAN), Mini-Batch K-Means, K-Means Mean Shift, OPTICS, Spectral Clustering, and Gaussian Mixture. We have found that K-Means, Mean Shift, and DBSCAN are particularly suitable for these applications, based on performance indicators that assess suitability and efficiency. However, DBSCAN shows better performance compared to others. Furthermore, our findings highlight that the choice of radar significantly impacts the effectiveness of these object recognition methods.
format Article
id doaj-art-11ee349807984dbda83e6a654f101f35
institution OA Journals
issn 1424-8220
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-11ee349807984dbda83e6a654f101f352025-08-20T02:04:44ZengMDPI AGSensors1424-82202024-11-012422721910.3390/s24227219Evaluation of Cluster Algorithms for Radar-Based Object Recognition in Autonomous and Assisted DrivingDaniel Carvalho de Ramos0Lucas Reksua Ferreira1Max Mauro Dias Santos2Evandro Leonardo Silva Teixeira3Leopoldo Rideki Yoshioka4João Francisco Justo5Asad Waqar Malik6Department of Electronic, Federal Technological University of Paraná, Ponta Grossa 84017-220, PR, BrazilDepartment of Electronic, Federal Technological University of Paraná, Ponta Grossa 84017-220, PR, BrazilDepartment of Electronic, Federal Technological University of Paraná, Ponta Grossa 84017-220, PR, BrazilFaculty of Science and Technology in Engineering, University of Brasilia, Gama 72444-240, DF, BrazilPolytechnic School, University of São Paulo, São Paulo 05508-010, SP, BrazilPolytechnic School, University of São Paulo, São Paulo 05508-010, SP, BrazilDepartment of Electrical and Computer Engineering, Mississippi State University, 406 Hardy Road 216 Simrall Hall Mississippi State, Starkville, MS 39762, USAPerception systems for assisted driving and autonomy enable the identification and classification of objects through a concentration of sensors installed in vehicles, including Radio Detection and Ranging (RADAR), camera, Light Detection and Ranging (LIDAR), ultrasound, and HD maps. These sensors ensure a reliable and robust navigation system. Radar, in particular, operates with electromagnetic waves and remains effective under a variety of weather conditions. It uses point cloud technology to map the objects in front of you, making it easy to group these points to associate them with real-world objects. Numerous clustering algorithms have been developed and can be integrated into radar systems to identify, investigate, and track objects. In this study, we evaluate several clustering algorithms to determine their suitability for application in automotive radar systems. Our analysis covered a variety of current methods, the mathematical process of these methods, and presented a comparison table between these algorithms, including Hierarchical Clustering, Affinity Propagation Balanced Iterative Reducing and Clustering using Hierarchies (BIRCH), Density-Based Spatial Clustering of Applications with Noise (DBSCAN), Mini-Batch K-Means, K-Means Mean Shift, OPTICS, Spectral Clustering, and Gaussian Mixture. We have found that K-Means, Mean Shift, and DBSCAN are particularly suitable for these applications, based on performance indicators that assess suitability and efficiency. However, DBSCAN shows better performance compared to others. Furthermore, our findings highlight that the choice of radar significantly impacts the effectiveness of these object recognition methods.https://www.mdpi.com/1424-8220/24/22/7219perception systemsdriving assistanceautonomous vehiclesobject identificationcluster algorithmsradar sensor
spellingShingle Daniel Carvalho de Ramos
Lucas Reksua Ferreira
Max Mauro Dias Santos
Evandro Leonardo Silva Teixeira
Leopoldo Rideki Yoshioka
João Francisco Justo
Asad Waqar Malik
Evaluation of Cluster Algorithms for Radar-Based Object Recognition in Autonomous and Assisted Driving
Sensors
perception systems
driving assistance
autonomous vehicles
object identification
cluster algorithms
radar sensor
title Evaluation of Cluster Algorithms for Radar-Based Object Recognition in Autonomous and Assisted Driving
title_full Evaluation of Cluster Algorithms for Radar-Based Object Recognition in Autonomous and Assisted Driving
title_fullStr Evaluation of Cluster Algorithms for Radar-Based Object Recognition in Autonomous and Assisted Driving
title_full_unstemmed Evaluation of Cluster Algorithms for Radar-Based Object Recognition in Autonomous and Assisted Driving
title_short Evaluation of Cluster Algorithms for Radar-Based Object Recognition in Autonomous and Assisted Driving
title_sort evaluation of cluster algorithms for radar based object recognition in autonomous and assisted driving
topic perception systems
driving assistance
autonomous vehicles
object identification
cluster algorithms
radar sensor
url https://www.mdpi.com/1424-8220/24/22/7219
work_keys_str_mv AT danielcarvalhoderamos evaluationofclusteralgorithmsforradarbasedobjectrecognitioninautonomousandassisteddriving
AT lucasreksuaferreira evaluationofclusteralgorithmsforradarbasedobjectrecognitioninautonomousandassisteddriving
AT maxmaurodiassantos evaluationofclusteralgorithmsforradarbasedobjectrecognitioninautonomousandassisteddriving
AT evandroleonardosilvateixeira evaluationofclusteralgorithmsforradarbasedobjectrecognitioninautonomousandassisteddriving
AT leopoldoridekiyoshioka evaluationofclusteralgorithmsforradarbasedobjectrecognitioninautonomousandassisteddriving
AT joaofranciscojusto evaluationofclusteralgorithmsforradarbasedobjectrecognitioninautonomousandassisteddriving
AT asadwaqarmalik evaluationofclusteralgorithmsforradarbasedobjectrecognitioninautonomousandassisteddriving