测绘学报 ›› 2020, Vol. 49 ›› Issue (6): 692-702.doi: 10.11947/j.AGCS.2020.20190305

• 地图学与地理信息 • 上一篇    下一篇

车辆轨迹数据的道路学习提取法

陆川伟, 孙群, 陈冰, 温伯威, 赵云鹏, 徐立   

  1. 信息工程大学, 河南 郑州 450001
  • 收稿日期:2019-07-16 修回日期:2019-10-11 出版日期:2020-06-20 发布日期:2020-06-28
  • 通讯作者: 孙群 E-mail:13503712102@163.com
  • 作者简介:陆川伟(1990-),男,博士生,研究方向为轨迹数据挖掘与地图更新。E-mail:19wei.90chuan@163.com
  • 基金资助:
    国家自然科学基金(41571399;41901397)

Road learning extraction method based on vehicle trajectory data

LU Chuanwei, SUN Qun, CHEN Bing, WEN Bowei, ZHAO Yunpeng, XU Li   

  1. Information Engineering University, Zhengzhou 450001, China
  • Received:2019-07-16 Revised:2019-10-11 Online:2020-06-20 Published:2020-06-28
  • Supported by:
    The National Natural Science Foundation of China (Nos. 41571399;41901397)

摘要: 车辆轨迹数据的道路信息提取是地理信息领域的热点也是难点之一,深度学习的快速发展为该问题的解决提供了一种思路与方法。本文针对车辆轨迹数据的车行道级道路提取问题,引入深度学习领域的生成式对抗网络,利用残差网络构建深层网络和多尺度感受野感知轨迹数据不同细节特征,构建了基于条件生成式对抗网络的轨迹方向约束下车行道级道路提取模型。首先提出了朝向-颜色映射栅格化转换方法,实现轨迹朝向信息向HSV颜色空间的转换;然后利用样本数据学习模型参数;最后将训练模型应用到郑州、成都、南京3个试验区域提取车行道级道路数据。试验结果表明,本文方法能够有效地提取完整的车行道级道路数据。

关键词: 深度学习, 条件生成式对抗网络, 车辆轨迹, 车行道级道路提取, 朝向-颜色映射

Abstract: Road information extraction based on vehicle trajectory data is one of the hotspots and difficulties in the field of geographic information. The rapid development of depth learning provides a new idea and method for solving this problem. Aiming at the problem of roadway-level road extraction based on vehicle trajectory data, this paper introduces the generative adversarial nets in the field of deep learning, uses residual network to construct deep network and multi-scale receptive field to perceive different details of trajectory data, and constructs roadway-level road extraction model under the constraint of trajectory direction based on conditional generative adversarial nets. Firstly, the orientation-color mapping rasterization conversion method is proposed to transform the trajectory orientation information into HSV color space. Then, the parameters of the model are learned with the sample data. Finally, the trained model is applied to three experimental areas of Zhengzhou, Chengdu and Nanjing to extract the road data at the roadway level. The experimental results showed that the proposed method can effectively extract the complete road data at the roadway level.

Key words: deep learning, conditional generative adversarial nets, vehicle trajectory, roadway-level road extraction, orientation-color mapping

中图分类号: