Lane Boundary Detection for Intelligent Vehicles Using Deep Convolutional Neural Network Architecture
To address the limitation of 2D lane detection methods with monocular vision, which fail to capture the three-dimensional position of lane boundaries, this study proposes a convolutional neural network architecture for 3D lane detection. The deep residual network ResNet50 is employed as the feature...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | World Electric Vehicle Journal |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2032-6653/16/4/198 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849713710171422720 |
|---|---|
| author | Xuewen Chen Chenxi Xia Xiaohai Chen |
| author_facet | Xuewen Chen Chenxi Xia Xiaohai Chen |
| author_sort | Xuewen Chen |
| collection | DOAJ |
| description | To address the limitation of 2D lane detection methods with monocular vision, which fail to capture the three-dimensional position of lane boundaries, this study proposes a convolutional neural network architecture for 3D lane detection. The deep residual network ResNet50 is employed as the feature extraction backbone, augmented with a coordinate attention mechanism to facilitate shallow feature extraction, multi-scale feature map generation, and extraction of small-scale high-order feature information. The BIFPN network is utilized for bidirectional feature fusion across different scales, significantly enhancing the accuracy of lane boundary detection. By constructing an inverse perspective transformation model (IPM), the conversion from front view to aerial view is realized. A dedicated 3D lane detection head is designed for lane boundary anchor lines, enabling efficient fusion and downsampling of multi-scale feature maps. By incorporating the bias between lane boundaries and anchor lines, the 3D position of lane boundaries is effectively detected. Validation experiments on the OpenLane dataset demonstrate that the proposed method not only detects the spatial locations of lane boundaries but also identifies attributes, such as color, solid or dashed, single or double lines, and left or right dashed configurations. Additionally, the method achieves an inference speed of 64.9 FPS on an RTX 4090 GPU, showcasing its computational efficiency. |
| format | Article |
| id | doaj-art-9eff5e01edf54bfaa8ce78a20896a693 |
| institution | DOAJ |
| issn | 2032-6653 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | World Electric Vehicle Journal |
| spelling | doaj-art-9eff5e01edf54bfaa8ce78a20896a6932025-08-20T03:13:54ZengMDPI AGWorld Electric Vehicle Journal2032-66532025-04-0116419810.3390/wevj16040198Lane Boundary Detection for Intelligent Vehicles Using Deep Convolutional Neural Network ArchitectureXuewen Chen0Chenxi Xia1Xiaohai Chen2College of Automobile and Traffic Engineering, Liaoning University of Technology, Jinzhou 121001, ChinaCollege of Automobile and Traffic Engineering, Liaoning University of Technology, Jinzhou 121001, ChinaCollege of Automobile and Traffic Engineering, Liaoning University of Technology, Jinzhou 121001, ChinaTo address the limitation of 2D lane detection methods with monocular vision, which fail to capture the three-dimensional position of lane boundaries, this study proposes a convolutional neural network architecture for 3D lane detection. The deep residual network ResNet50 is employed as the feature extraction backbone, augmented with a coordinate attention mechanism to facilitate shallow feature extraction, multi-scale feature map generation, and extraction of small-scale high-order feature information. The BIFPN network is utilized for bidirectional feature fusion across different scales, significantly enhancing the accuracy of lane boundary detection. By constructing an inverse perspective transformation model (IPM), the conversion from front view to aerial view is realized. A dedicated 3D lane detection head is designed for lane boundary anchor lines, enabling efficient fusion and downsampling of multi-scale feature maps. By incorporating the bias between lane boundaries and anchor lines, the 3D position of lane boundaries is effectively detected. Validation experiments on the OpenLane dataset demonstrate that the proposed method not only detects the spatial locations of lane boundaries but also identifies attributes, such as color, solid or dashed, single or double lines, and left or right dashed configurations. Additionally, the method achieves an inference speed of 64.9 FPS on an RTX 4090 GPU, showcasing its computational efficiency.https://www.mdpi.com/2032-6653/16/4/198intelligent vehiclethree-dimensional lane boundary detectiondeep learningcoordinate attention mechanismfeature fusionsimulation |
| spellingShingle | Xuewen Chen Chenxi Xia Xiaohai Chen Lane Boundary Detection for Intelligent Vehicles Using Deep Convolutional Neural Network Architecture World Electric Vehicle Journal intelligent vehicle three-dimensional lane boundary detection deep learning coordinate attention mechanism feature fusion simulation |
| title | Lane Boundary Detection for Intelligent Vehicles Using Deep Convolutional Neural Network Architecture |
| title_full | Lane Boundary Detection for Intelligent Vehicles Using Deep Convolutional Neural Network Architecture |
| title_fullStr | Lane Boundary Detection for Intelligent Vehicles Using Deep Convolutional Neural Network Architecture |
| title_full_unstemmed | Lane Boundary Detection for Intelligent Vehicles Using Deep Convolutional Neural Network Architecture |
| title_short | Lane Boundary Detection for Intelligent Vehicles Using Deep Convolutional Neural Network Architecture |
| title_sort | lane boundary detection for intelligent vehicles using deep convolutional neural network architecture |
| topic | intelligent vehicle three-dimensional lane boundary detection deep learning coordinate attention mechanism feature fusion simulation |
| url | https://www.mdpi.com/2032-6653/16/4/198 |
| work_keys_str_mv | AT xuewenchen laneboundarydetectionforintelligentvehiclesusingdeepconvolutionalneuralnetworkarchitecture AT chenxixia laneboundarydetectionforintelligentvehiclesusingdeepconvolutionalneuralnetworkarchitecture AT xiaohaichen laneboundarydetectionforintelligentvehiclesusingdeepconvolutionalneuralnetworkarchitecture |