地球信息科学学报 ›› 2023, Vol. 25 ›› Issue (4): 852-865.doi: 10.12082/dqxxkx.2023.220941

• 街景与空间 • 上一篇    下一篇

街景图像与机器学习相结合的道路环境安全感知评价与影响因素分析

李心雨1,6(), 闫浩文2,3,4,*(), 王卓5, 王炳瑄2,3,4   

  1. 1.兰州交通大学建筑与城市规划学院,兰州 730070
    2.兰州交通大学测绘与地理信息学院,兰州 730070
    3.地理国情监测技术应用国家地方联合工程研究中心,兰州 730070
    4.甘肃省地理国情监测工程实验室,兰州 730070
    5.武汉大学资源与环境科学学院,武汉 430079
    6.甘肃大禹九洲空间信息科技有限公司院士专家工作站,兰州 730050
  • 收稿日期:2022-12-01 修回日期:2023-03-12 出版日期:2023-04-25 发布日期:2023-04-19
  • 通讯作者: *闫浩文(1969—),男,甘肃民勤人,博士,教授,主要从事微地图、地图自动综合、空间数据安全和空间关系等研究。 E-mail: yanhw@mail.lzjtu.cn
  • 作者简介:李心雨(1997—),女,湖北武汉人,硕士生,主要从事城市计算与空间分析研究。E-mail: lxy1997student@163.com
  • 基金资助:
    甘肃省高等学校产业支撑计划项目(2022CYZC-30);国家自然科学基金重点项目(41930101)

Evaluation of Road Environment Safety Perception and Analysis of Influencing Factors Combining Street View Imagery and Machine Learning

LI Xinyu1,6(), YAN Haowen2,3,4,*(), WANG Zhuo5, WANG Bingxuan2,3,4   

  1. 1. School of Architecture and Urban Planning, Lanzhou Jiaotong University, Lanzhou 730070, China
    2. Faculty of Geomatics, Lanzhou Jiaotong University, Lanzhou 730070, China
    3. National-Local Joint Engineering Research Center of Technologies and Applications for National Geographic State Monitoring, Lanzhou 730070, China
    4. Gansu Provincial Engineering Laboratory for National Geographic State Monitoring, Lanzhou 730070, China
    5. School of Resources and Environmental Sciences, Wuhan University, Wuhan 430079, China
    6. Academician Expert Workstation of Gansu Dayu Jiuzhou Space Information Technology Co., Ltd., Lanzhou 730050, China
  • Received:2022-12-01 Revised:2023-03-12 Online:2023-04-25 Published:2023-04-19
  • Contact: YAN Haowen
  • Supported by:
    The Industrial Support and Program Project of Universities in Gansu Province(2022CYZC-30);The National Nature Science Foundation of China(41930101)

摘要:

准确识别影响环境安全感知的视觉因素,对于改善城市交通环境与提升行人出行安全具有重要支撑作用。然而,既有研究难以对复杂场景下的环境安全感知进行大规模定量化研究。因此,本文利用图像语义分割和目标检测技术从街景图像中提取视觉要素,通过人工评分结合深度学习的方式构建道路安全感知数据集;再基于轻量梯度提升机和SHAP解释框架,识别出影响环境安全感知的视觉因素;最后,选取道路环境特殊的峡谷性城市兰州市安宁区高校聚集地为例进行实证研究。结果表明:① 高校及商业街的安全感知评分较高,城市道路的普遍偏低;② 天空、人行道、道路和树木的图像占比值是对环境安全感知影响最大的四类要素,其中,天空的图像占比值为线性关系,人行道和树木的图像占比值近似对数函数,道路的图像占比值则类似二次函数;③ 视觉要素占比和个数存在交互影响作用,合理的要素分布有助于形成良好的空间视线,以及营造合适的行为活动空间,从而提升环境安全感知。

关键词: 街景图像, 机器学习, 环境感知, 图像语义分割, 目标检测, LightGBM, SHAP

Abstract:

Accurate identification of visual factors affecting environmental safety perception provides important support for improving urban traffic environment and enhancing pedestrian travel safety. However, it is difficult to quantify environmental safety perception in complex scenes on a large scale in existing studies. Therefore, this study uses image semantic segmentation and object detection techniques to extract visual factors from streetscape images and constructs a road safety perception dataset by manual scoring in combination with deep learning methods. The influencing factors of environmental safety perception are also identified based on light gradient boosting machine algorithm and SHAP interpretation framework. In our study, the Anning District college cluster in Lanzhou City, a canyon city with a special road environment, is selected for the empirical study. Results show that: (1) The safety perception scores of colleges and commercial streets are high, while those of urban roads are generally low; (2) The image ratios of sky, sidewalk, road, and tree are the four factors that have the greatest influence on environmental safety perception, among which the image ratio of sky is linear, the image ratios of sidewalk and tree are similar to a logarithmic function, and the image ratio of road is similar to a quadratic function; (3) The proportion and number of visual factors have an interactive effect. A reasonable distribution of visual factors helps to create good spatial sightlines and suitable behavioral spaces, thus enhancing the perception of environmental safety.

Key words: street view image, machine learning, environment perception, semantic image segmentation, object detection, LightGBM, SHAP