| WANG Xiaohua (王小华),LIAO Zhonghe,MA Pin,MIAO Zhonghua.[J].高技术通讯(英文),2022,28(3):272~279 |
|
| Deep learning based curb detection with Lidar |
| |
| DOI：10.3772/j.issn.1006-6748.2022.03.006 |
| 中文关键词: |
| 英文关键词: curb detection, EdgeNet, curb annotation algorithm |
| 基金项目: |
| Author Name | Affiliation | | WANG Xiaohua (王小华) | (School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, P. R. China) | | LIAO Zhonghe | (School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, P. R. China) | | MA Pin | (School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, P. R. China) | | MIAO Zhonghua | (School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, P. R. China) |
|
| Hits: 484 |
| Download times: 463 |
| 中文摘要: |
| |
| 英文摘要: |
| Curb detection provides road boundary information and is important to road detection. However, curb detection is challenging due to the problems such as various curb shapes, colour, discontinuity. In this work, a novel learning-based method for curb detection is proposed using Lidar point clouds, considering that Lidars are not sensitive to illumination and are relatively stable to weather conditions. A deep neural network, named EdgeNet, is constructed and trained, which handles point clouds in an end-to-end way. After EdgeNet is properly trained, curb points are then segmented in the neural network output. In order to train, a curb point annotation algorithm is also designed to generate training dataset. The curb detection method works well with different road scenarios including intersections. The experimental results validate the effectiveness and robustness of this curb detection method. |
|
View Full Text
View/Add Comment Download reader |
| Close |
|
|
|
