| 基于编解码器模型的车道识别与车辆检测算法 |
| |
| 引用本文： | 谢岩,刘广聪. 基于编解码器模型的车道识别与车辆检测算法[J]. 广东工业大学学报, 2019, 36(4): 36-41. DOI: 10.12052/gdutxb.180175 |
| |
| 作者姓名： | 谢岩 刘广聪 |
| |
| 作者单位： | 广东工业大学计算机学院,广东广州,510006;广东工业大学计算机学院,广东广州,510006 |
| |
| 基金项目： | 广州市科技计划项目（201508020030） |
| |
| 摘 要： | 针对无人驾驶车辆环境感知问题，通过编码器提取共享图像特征，再通过解码器来实现语义分割、分类和目标检测模块，并应用在车道识别和车辆检测上.在无人驾驶中，任务的实时性非常关键，这种共享编码器模型能一定程度上提高任务实时性.实验结果表明，该模型的语义分割在KITTI数据集上的平均精度达到93.89%，比最优性能提升0.53%，联合检测速度达到25.43 Hz.
|
| 关 键 词： | 无人驾驶 编解码器模型 语义分割 目标检测 带孔卷积 |
| 收稿时间： | 2018-12-24 |
Lane Recognition and Vehicle Detection Algorithm Based on Code-model |
| |
| Xie Yan,Liu Guang-cong. Lane Recognition and Vehicle Detection Algorithm Based on Code-model[J]. Journal of Guangdong University of Technology, 2019, 36(4): 36-41. DOI: 10.12052/gdutxb.180175 |
| |
| Authors: | Xie Yan Liu Guang-cong |
| |
| Affiliation: | School of Computers, Guangdong University of Technology, Guangzhou 510006, China |
| |
| Abstract: | Aiming at the problem of environment perception of self-driving, this paper semantic segmentation, classification and target detection module are realized by the code model, which is applied to lane recognition and vehicle detection. Shared image features are extracted by encoder, and three different functions are realized by decoder. This Shared encoder model can improve the real-time performance of tasks. In self-driving, the real-time performance of tasks is the key. Experimental results show that the average precision of semantic segmentation of this model on KITTI dataset reaches 93.89%, which is 0.53% higher than the optimal performance, and the joint detection speed reaches 25.43 Hz. |
| |
| Keywords: | self-driving code-model semantic segmentation target detection atrous convolution |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《广东工业大学学报》浏览原始摘要信息 |
|
点击此处可从《广东工业大学学报》下载免费的PDF全文 |
