基于城市天际线的遥感视频生产与交通信息提取

汪驰升; 王乐涵; 张涓; 叶艾温; 钟国熙; 王永全; 崔红星; 李清泉

doi:10.13203/j.whugis20210174

美国《工程索引》（EI）核心期刊
美国《剑桥科学文摘》（CSA）收录期刊
荷兰斯高帕斯数据库（Scopus）收录期刊
英国INSPEC数据库（SA）收录期刊

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

汪驰升, 王乐涵, 张涓, 叶艾温, 钟国熙, 王永全, 崔红星, 李清泉

文章导航 > 武汉大学学报 ( 信息科学版) > 2022 > 优先出版

汪驰升, 王乐涵, 张涓, 叶艾温, 钟国熙, 王永全, 崔红星, 李清泉. 基于城市天际线的遥感视频生产与交通信息提取[J]. 武汉大学学报 ( 信息科学版). doi: 10.13203/j.whugis20210174

引用本文:

Wang Chisheng, Wang Lehan, Zhang Juan, Ye Aiwen, Zhong Guoxi, Wang Yongquan, Cui Hongxing, Li Qingquan. Remote sensing video production and traffic information extraction based on urban skyline[J]. Geomatics and Information Science of Wuhan University. doi: 10.13203/j.whugis20210174

Citation:

Wang Chisheng, Wang Lehan, Zhang Juan, Ye Aiwen, Zhong Guoxi, Wang Yongquan, Cui Hongxing, Li Qingquan. Remote sensing video production and traffic information extraction based on urban skyline[J]. Geomatics and Information Science of Wuhan University. doi: 10.13203/j.whugis20210174

基于城市天际线的遥感视频生产与交通信息提取

doi: 10.13203/j.whugis20210174

汪驰升^1,2,3, ,,
王乐涵^1,2,3,
张涓^1,2,3,
叶艾温^1,2,3,
钟国熙^1,2,3,
王永全^1,2,3,
崔红星⁴,
李清泉^1,2,3

1. 深圳大学广东省城市空间信息工程重点实验室，广东，深圳， 518000
2. 深圳大学自然资源部大湾区地理环境监测重点实验室，广东，深圳， 518000
3. 深圳大学深圳市空间信息智能感知与服务重点实验室，广东，深圳， 518000
4 香港科技大学，香港

基金项目:

重点研发项目(编号:2020YFC1512001)、深圳市科创委研究项目(编号:RCYX20210706092140076、20200812164904001)、国家自然科学基金项目(批准号:41974006)

详细信息

作者简介:
汪驰升、博士、副教授，主要从事遥感数据处理和灾害监测方面的研究。wangchisheng@szu.edu.cn

通讯作者: 汪驰升、博士、副教授。wangchisheng@szu.edu.cn

Remote sensing video production and traffic information extraction based on urban skyline

Wang Chisheng^{1,2,3
, ,},
Wang Lehan^1,2,3,
Zhang Juan^1,2,3,
Ye Aiwen^1,2,3,
Zhong Guoxi^1,2,3,
Wang Yongquan^1,2,3,
Cui Hongxing⁴,
Li Qingquan^1,2,3

1. Guangdong Key Laboratory of Urban Spatial Information Engineering, Shenzhen University, Guangdong, Shenzhen, 518000
2. Natural Resources Department Dawan District Key Laboratory of Geographic Environment Monitoring, Shenzhen University, Guangdong, Shenzhen, 518000
3. Shenzhen Key Laboratory of Spatial Information Intelligent Perception and Service, Shenzhen University, Guangdong, Shenzhen, 518000
4. Hong Kong University of Science and Technology, Hong Kong

摘要: 传统交通信息获取方法较难获取大范围、全覆盖的实时动态交通流信息，本文研究利用城市天际线作为观测平台的城市遥感视频生产与交通信息提取方法。首先，在超高层建筑物拍摄对地观测数据；然后，对原始倾斜视频观测数据进行正射校正，与卫星影像融合生成大范围城市遥感视频数据；最后，训练深度学习模型进行车辆分类识别，基于识别结果计算区域车辆数目及密度。本文在深圳平安大厦观光层开展数据采集并处理分析。结果表明：本文所提方法可生产低成本、长时间、大范围、高质量的城市遥感视频，基于该遥感视频开展的车辆检测误识别率和漏识别率低，车辆计数准确率高，可对区域交通流量进行有效监控，准确实时地获取城市内部区域交通情况。
- 城市天际线 /
- 对地观测 /
- 遥感视频 /
- 交通流量监控 /
- 深度学习
Abstract: Objectives: It is difficult for the traditional traffic information acquisition method to obtain the real-time dynamic traffic flow information of large scope and full coverage. With urbanization, the increasing number of supertall buildings makes the city skyline a favorable platform for earth observation. This paper studies the urban remote sensing video production and traffic information extraction method using the urban skyline as the observation platform. Methods: Firstly, the earth observation data shooting is carried out in the super-tall buildings. Then, the original oblique observation data is corrected by orthography, which is further fused with the satellite image to generate a large range of remote sensing video data of the city. Finally, we train a deep learning model and use it for vehicle classification and identification. The number and density of vehicles in the area are calculated based on the identification results. Results: This paper carries out data collection and processing analysis on the sightseeing floor of Ping An Building in Shenzhen. Results show that the proposed method can produce low-cost, long-time, large-scale and high-quality urban remote sensing video. The vehicle detection based on the remote sensing video have high accuracy. Conclusions: The proposed framework can be used to effectively monitor the regional traffic flow and sever for the smart city management. Furthermore, based on its capability of long-time, high-resolution, full-coverage and real-time remote sensing, this method can also be applied to many other urban management fields, such as urban disaster emergency response, crowd monitoring, and construction site monitoring.
- Urban skyline /
- Land observation /
- Remote sensing video /
- Traffic flow monitoring /
- Deep learning

[1]	徐恩恩, 郭颖, 陈尔学, 李增元, 赵磊, 刘清旺. 基于无人机LiDAR和高空间分辨率卫星遥感数据的区域森林郁闭度估测模型 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20210001
[2]	李鹏程, 白文浩. 基于Transformer结构的遥感影像敏感目标自动隐藏方法 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20220219
[3]	林学楷, 许才军. 深度学习驱动的地震目录构建：PhaseNet和EqT模型的对比与评估 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20220197
[4]	吕亚飞, 熊伟, 张筱晗. 一种通用的跨模态遥感信息关联学习方法 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20200213
[5]	邵振峰, 孙悦鸣, 席江波, 李岩. 智能优化学习的高空间分辨率遥感影像语义分割 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20200640
[6]	郭从洲, 李可, 李贺, 童晓冲, 王习文. 遥感图像质量等级分类的深度卷积神经网络方法 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20200292
[7]	李彦胜, 张永军. 耦合知识图谱和深度学习的新一代遥感影像解译范式 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20210652
[8]	应申, 唐茉, 张馨月, 胡振宇, 郭晗. 三维城市的玻璃幕墙光污染分析 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20200492
[9]	柴华彬, 严超, 邹友峰, 陈正超. 利用PSP Net实现湖北省遥感影像土地覆盖分类 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20190296
[10]	季顺平, 罗冲, 刘瑾. 基于深度学习的立体影像密集匹配方法综述 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20200620
[11]	陈行, 罗斌. 利用动态上采样滤波深度网络进行多角度遥感影像超分辨率重建 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20200651
[12]	季顺平, 田思琦, 张驰. 利用全空洞卷积神经元网络进行城市土地覆盖分类与变化检测 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20180481
[13]	郭旦怀, 张鸣珂, 贾楠, 王彦棡. 融合深度学习技术的用户兴趣点推荐研究综述 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20200334
[14]	巨袁臻, 许强, 金时超, 李为乐, 董秀军, 郭庆华. 使用深度学习方法实现黄土滑坡自动识别 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20200132
[15]	潘银, 邵振峰, 程涛, 贺蔚. 利用深度学习模型进行城市内涝影响分析 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20170217
[16]	邵振峰, 张源, 黄昕, 朱秀丽, 吴亮, 万波. 基于多源高分辨率遥感影像的2 m不透水面一张图提取 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20180196
[17]	张兵. 遥感大数据时代与智能信息提取 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20180172
[18]	樊恒, 徐俊, 邓勇, 向金海. 基于深度学习的人体行为识别 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20140110
[19]	李德仁. 论21世纪遥感与GIS的发展 . 武汉大学学报 ( 信息科学版),
[20]	赫晓慧, 陈明扬, 李盼乐, 田智慧, 周广胜. 结合DCNN与短距条件随机场的遥感影像道路提取 . 武汉大学学报 ( 信息科学版), doi: 10.13203/j.whugis20210464

点击查看大图

计量

文章访问数: 186
HTML全文浏览量: 32
PDF下载量: 4
被引次数: 0

doi: 10.13203/j.whugis20210174

1. 深圳大学广东省城市空间信息工程重点实验室，广东，深圳， 518000

2. 深圳大学自然资源部大湾区地理环境监测重点实验室，广东，深圳， 518000

3. 深圳大学深圳市空间信息智能感知与服务重点实验室，广东，深圳， 518000

4 香港科技大学，香港

基金项目:

重点研发项目(编号:2020YFC1512001)、深圳市科创委研究项目(编号:RCYX20210706092140076、20200812164904001)、国家自然科学基金项目(批准号:41974006)

作者简介:
汪驰升、博士、副教授，主要从事遥感数据处理和灾害监测方面的研究。wangchisheng@szu.edu.cn

收稿日期: 2021-04-09
网络出版日期: 2022-10-19

关键词:

摘要: 传统交通信息获取方法较难获取大范围、全覆盖的实时动态交通流信息，本文研究利用城市天际线作为观测平台的城市遥感视频生产与交通信息提取方法。首先，在超高层建筑物拍摄对地观测数据；然后，对原始倾斜视频观测数据进行正射校正，与卫星影像融合生成大范围城市遥感视频数据；最后，训练深度学习模型进行车辆分类识别，基于识别结果计算区域车辆数目及密度。本文在深圳平安大厦观光层开展数据采集并处理分析。结果表明：本文所提方法可生产低成本、长时间、大范围、高质量的城市遥感视频，基于该遥感视频开展的车辆检测误识别率和漏识别率低，车辆计数准确率高，可对区域交通流量进行有效监控，准确实时地获取城市内部区域交通情况。

English Abstract

Remote sensing video production and traffic information extraction based on urban skyline

1. Guangdong Key Laboratory of Urban Spatial Information Engineering, Shenzhen University, Guangdong, Shenzhen, 518000

2. Natural Resources Department Dawan District Key Laboratory of Geographic Environment Monitoring, Shenzhen University, Guangdong, Shenzhen, 518000

3. Shenzhen Key Laboratory of Spatial Information Intelligent Perception and Service, Shenzhen University, Guangdong, Shenzhen, 518000

4. Hong Kong University of Science and Technology, Hong Kong

Received Date: 2021-04-09
Available Online: 2022-10-19

Keywords:

Abstract: Objectives: It is difficult for the traditional traffic information acquisition method to obtain the real-time dynamic traffic flow information of large scope and full coverage. With urbanization, the increasing number of supertall buildings makes the city skyline a favorable platform for earth observation. This paper studies the urban remote sensing video production and traffic information extraction method using the urban skyline as the observation platform. Methods: Firstly, the earth observation data shooting is carried out in the super-tall buildings. Then, the original oblique observation data is corrected by orthography, which is further fused with the satellite image to generate a large range of remote sensing video data of the city. Finally, we train a deep learning model and use it for vehicle classification and identification. The number and density of vehicles in the area are calculated based on the identification results. Results: This paper carries out data collection and processing analysis on the sightseeing floor of Ping An Building in Shenzhen. Results show that the proposed method can produce low-cost, long-time, large-scale and high-quality urban remote sensing video. The vehicle detection based on the remote sensing video have high accuracy. Conclusions: The proposed framework can be used to effectively monitor the regional traffic flow and sever for the smart city management. Furthermore, based on its capability of long-time, high-resolution, full-coverage and real-time remote sensing, this method can also be applied to many other urban management fields, such as urban disaster emergency response, crowd monitoring, and construction site monitoring.

引用本文:

Citation:

Wang Chisheng, Wang Lehan, Zhang Juan, Ye Aiwen, Zhong Guoxi, Wang Yongquan, Cui Hongxing, Li Qingquan. Remote sensing video production and traffic information extraction based on urban skyline[J]. Geomatics and Information Science of Wuhan University. doi: 10.13203/j.whugis20210174