Graph Model-Based Lane-Marking Feature Extraction for Lane Detection
This paper presents a robust, efficient lane-marking feature extraction method using a graph model-based approach. To extract the features, the proposed hat filter with adaptive sizes is first applied to each row of an input image and local maximum values are extracted from the filter response. The...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/13/4428 |
| _version_ | 1827688570820755456 |
|---|---|
| author | Juhan Yoo Donghwan Kim |
| author_facet | Juhan Yoo Donghwan Kim |
| author_sort | Juhan Yoo |
| collection | DOAJ |
| description | This paper presents a robust, efficient lane-marking feature extraction method using a graph model-based approach. To extract the features, the proposed hat filter with adaptive sizes is first applied to each row of an input image and local maximum values are extracted from the filter response. The features with the maximum values are fed as nodes to a connected graph structure, and the edges of the graph are constructed using the proposed neighbor searching method. Nodes related to lane-markings are then selected by finding a connected subgraph in the graph. The selected nodes are fitted to line segments as the proposed features of lane-markings. The experimental results show that the proposed method not only yields at least 2.2% better performance compared to the existing methods on the KIST dataset, which includes various types of sensing noise caused by environmental changes, but also improves at least 1.4% better than the previous methods on the Caltech dataset which has been widely used for the comparison of lane marking detection. Furthermore, the proposed lane marking detection runs with an average of 3.3 ms, which is fast enough for real-time applications. |
| first_indexed | 2024-03-10T09:59:34Z |
| format | Article |
| id | doaj.art-4c8d743555254b1e8c300d440b00da86 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T09:59:34Z |
| publishDate | 2021-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-4c8d743555254b1e8c300d440b00da862023-11-22T02:03:15ZengMDPI AGSensors1424-82202021-06-012113442810.3390/s21134428Graph Model-Based Lane-Marking Feature Extraction for Lane DetectionJuhan Yoo0Donghwan Kim1Technology Research Team, Incheon International Airport Corporation, Incheon 22382, KoreaCenter for Intelligent and Interactive Robotics, Korea Institute of Science and Technology, Seoul 02792, KoreaThis paper presents a robust, efficient lane-marking feature extraction method using a graph model-based approach. To extract the features, the proposed hat filter with adaptive sizes is first applied to each row of an input image and local maximum values are extracted from the filter response. The features with the maximum values are fed as nodes to a connected graph structure, and the edges of the graph are constructed using the proposed neighbor searching method. Nodes related to lane-markings are then selected by finding a connected subgraph in the graph. The selected nodes are fitted to line segments as the proposed features of lane-markings. The experimental results show that the proposed method not only yields at least 2.2% better performance compared to the existing methods on the KIST dataset, which includes various types of sensing noise caused by environmental changes, but also improves at least 1.4% better than the previous methods on the Caltech dataset which has been widely used for the comparison of lane marking detection. Furthermore, the proposed lane marking detection runs with an average of 3.3 ms, which is fast enough for real-time applications.https://www.mdpi.com/1424-8220/21/13/4428lane marking detectionline segmentlane marking featurelane departure warning (LDW) systemlane keeping assist (LKA) systemintelligent vehicle |
| spellingShingle | Juhan Yoo Donghwan Kim Graph Model-Based Lane-Marking Feature Extraction for Lane Detection Sensors lane marking detection line segment lane marking feature lane departure warning (LDW) system lane keeping assist (LKA) system intelligent vehicle |
| title | Graph Model-Based Lane-Marking Feature Extraction for Lane Detection |
| title_full | Graph Model-Based Lane-Marking Feature Extraction for Lane Detection |
| title_fullStr | Graph Model-Based Lane-Marking Feature Extraction for Lane Detection |
| title_full_unstemmed | Graph Model-Based Lane-Marking Feature Extraction for Lane Detection |
| title_short | Graph Model-Based Lane-Marking Feature Extraction for Lane Detection |
| title_sort | graph model based lane marking feature extraction for lane detection |
| topic | lane marking detection line segment lane marking feature lane departure warning (LDW) system lane keeping assist (LKA) system intelligent vehicle |
| url | https://www.mdpi.com/1424-8220/21/13/4428 |
| work_keys_str_mv | AT juhanyoo graphmodelbasedlanemarkingfeatureextractionforlanedetection AT donghwankim graphmodelbasedlanemarkingfeatureextractionforlanedetection |