Vehicles and people recognition using laser scanner based on machine learning
Moving-object tracking (estimating position and velocity of moving objects) is a key technology for autonomous driving systems and driving assistance systems in mobile robotics and vehicle automation domains. To predict and avoid collisions, the tracking system has to identify objects as accurately...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | Japanese |
| Published: |
The Japan Society of Mechanical Engineers
2018-11-01
|
| Series: | Nihon Kikai Gakkai ronbunshu |
| Subjects: | |
| Online Access: | https://www.jstage.jst.go.jp/article/transjsme/84/868/84_18-00090/_pdf/-char/en |
| _version_ | 1797989160639791104 |
|---|---|
| author | Zhenyu LIN Masafumi HASHIMOTO Kenta TAKIGAWA Kazuhiko TAKAHASHI |
| author_facet | Zhenyu LIN Masafumi HASHIMOTO Kenta TAKIGAWA Kazuhiko TAKAHASHI |
| author_sort | Zhenyu LIN |
| collection | DOAJ |
| description | Moving-object tracking (estimating position and velocity of moving objects) is a key technology for autonomous driving systems and driving assistance systems in mobile robotics and vehicle automation domains. To predict and avoid collisions, the tracking system has to identify objects as accurately as possible. This paper presents a method for recognizing vehicles (cars and bicyclists) and people using a 64-layer ground laser scanner. When laser-scanned data are captured by the laser scanner, laser-measurement points related to objects are extracted by the background subtraction method and are clustered. Eight-dimensional features are extracted from each of clustered laser-scanned data, such as distance from the laser scanner, velocity, object size, number of laser-measurement points, and distribution of the reflection intensities. The machine learning methods (support vector machine (SVM) and random forests (RF)) are applied to classify cars, bicyclists, and people from these features. The experimental results using “The Stanford Track Collection” data set show that the classification accuracy using the SVM-based method is higher than the RF-based method. In addition, they show that the use of the proposed eight-dimensional features provides better classification accuracy and shorter processing time than the use of the conventional 26-dimensional features. |
| first_indexed | 2024-04-11T08:14:44Z |
| format | Article |
| id | doaj.art-520f3672853946849994f1897209b71c |
| institution | Directory Open Access Journal |
| issn | 2187-9761 |
| language | Japanese |
| last_indexed | 2024-04-11T08:14:44Z |
| publishDate | 2018-11-01 |
| publisher | The Japan Society of Mechanical Engineers |
| record_format | Article |
| series | Nihon Kikai Gakkai ronbunshu |
| spelling | doaj.art-520f3672853946849994f1897209b71c2022-12-22T04:35:11ZjpnThe Japan Society of Mechanical EngineersNihon Kikai Gakkai ronbunshu2187-97612018-11-018486818-0009018-0009010.1299/transjsme.18-00090transjsmeVehicles and people recognition using laser scanner based on machine learningZhenyu LIN0Masafumi HASHIMOTO1Kenta TAKIGAWA2Kazuhiko TAKAHASHI3Graduate School of Doshisha UniversityFaculty of Science and Engineering, Doshisha UniversityGraduate School of Doshisha UniversityFaculty of Science and Engineering, Doshisha UniversityMoving-object tracking (estimating position and velocity of moving objects) is a key technology for autonomous driving systems and driving assistance systems in mobile robotics and vehicle automation domains. To predict and avoid collisions, the tracking system has to identify objects as accurately as possible. This paper presents a method for recognizing vehicles (cars and bicyclists) and people using a 64-layer ground laser scanner. When laser-scanned data are captured by the laser scanner, laser-measurement points related to objects are extracted by the background subtraction method and are clustered. Eight-dimensional features are extracted from each of clustered laser-scanned data, such as distance from the laser scanner, velocity, object size, number of laser-measurement points, and distribution of the reflection intensities. The machine learning methods (support vector machine (SVM) and random forests (RF)) are applied to classify cars, bicyclists, and people from these features. The experimental results using “The Stanford Track Collection” data set show that the classification accuracy using the SVM-based method is higher than the RF-based method. In addition, they show that the use of the proposed eight-dimensional features provides better classification accuracy and shorter processing time than the use of the conventional 26-dimensional features.https://www.jstage.jst.go.jp/article/transjsme/84/868/84_18-00090/_pdf/-char/enobject recognitionmultilayer laser scannermachine learningsupport vector machinerandom forestlow-dimensional featuresmulticlass classfication |
| spellingShingle | Zhenyu LIN Masafumi HASHIMOTO Kenta TAKIGAWA Kazuhiko TAKAHASHI Vehicles and people recognition using laser scanner based on machine learning Nihon Kikai Gakkai ronbunshu object recognition multilayer laser scanner machine learning support vector machine random forest low-dimensional features multiclass classfication |
| title | Vehicles and people recognition using laser scanner based on machine learning |
| title_full | Vehicles and people recognition using laser scanner based on machine learning |
| title_fullStr | Vehicles and people recognition using laser scanner based on machine learning |
| title_full_unstemmed | Vehicles and people recognition using laser scanner based on machine learning |
| title_short | Vehicles and people recognition using laser scanner based on machine learning |
| title_sort | vehicles and people recognition using laser scanner based on machine learning |
| topic | object recognition multilayer laser scanner machine learning support vector machine random forest low-dimensional features multiclass classfication |
| url | https://www.jstage.jst.go.jp/article/transjsme/84/868/84_18-00090/_pdf/-char/en |
| work_keys_str_mv | AT zhenyulin vehiclesandpeoplerecognitionusinglaserscannerbasedonmachinelearning AT masafumihashimoto vehiclesandpeoplerecognitionusinglaserscannerbasedonmachinelearning AT kentatakigawa vehiclesandpeoplerecognitionusinglaserscannerbasedonmachinelearning AT kazuhikotakahashi vehiclesandpeoplerecognitionusinglaserscannerbasedonmachinelearning |