Please wait a minute...
 
国土资源遥感  2020, Vol. 32 Issue (1): 1-6    DOI: 10.6046/gtzyyg.2020.01.01
     综述 本期目录 | 过刊浏览 | 高级检索 |
基于系留无人机的应急测绘技术应用
王永全1,2, 李清泉1, 汪驰升1,2,3(), 朱家松1,2, 王新雨1,2
1. 深圳大学城市空间信息工程广东省重点实验室,深圳 518060
2. 深圳大学海岸带地理环境监测自然资源部重点实验室,深圳 518060
3. 自然资源部城市土地资源监测与仿真重点实验室,深圳 518000
Tethered UAVs-based applications in emergency surveying and mapping
Yongquan WANG1,2, Qingquan LI1, Chisheng WANG1,2,3(), Jiasong ZHU1,2, Xinyu WANG1,2
1. Guangdong Key Laboratory of Urban Informatics, School of Architecture & Urban Planning, Shenzhen University, Shenzhen 518060, China
2. Key Laboratory for Geo-Environmental Monitoring of Coastal Zone of the Ministry of Natural Resources, Shenzhen University, Shenzhen 518060, China
3. Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Natural and Resources, Shenzhen 518000, China
全文: PDF(2651 KB)   HTML  
输出: BibTeX | EndNote (RIS)      
摘要 

传统测绘比较注重“准”,而忽视了“快”。现代应急测绘需要“既快又准”。如果使用传统的测绘技术方法将会消耗大量的时间,会影响到应急救灾的及时性。系留无人机可以采集高质量的数据,并且能够进行实时的长时间视频监测。首先,介绍了系留无人机应急测绘的应用现状、特点优势和应用场景; 然后,提出一种利用系留无人机采集高质量的影像数据和视频数据生产测绘数据产品,并通过Darknet深度学习框架对视频目标进行识别的经验和方法; 最后,在不同场景下进行模拟实验和实际应用。实验结果表明,该方法能够为救灾抢险提供及时有效的测绘保障。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
王永全
李清泉
汪驰升
朱家松
王新雨
关键词 系留无人机应急测绘Agisoft PhotoScanDarknet    
Abstract

Traditional surveying and mapping pay much attention to “accuracy”, but ignore the “speed”. Modern emergency mapping needs to be “speedy and accurate”. If traditional mapping techniques are used, it will consume a lot of time, which will affect the timeliness of emergency response. A tethered UAVs can collect high-quality data and realize real-time long-term video monitoring. This paper introduces the application status, characteristic advantages, and application scenarios of the tethered UAVs. And a kind of experience and method for using tethered UAVs to collect high quality image data and video data for producing surveying and mapping data products and identifying video targets through Darknet deep learning framework is proposed. Based on many simulation experiments and practical applications, the authors hold that this method is effective in providing timely and effective surveying and mapping guarantee for disaster relief and rescue.

Key wordstethered UAVs    emergency surveying and mapping    Agisoft PhotoScan    Darknet
收稿日期: 2019-01-25      出版日期: 2020-03-14
:  TP79  
基金资助:自然资源部城市土地资源监测与仿真重点实验室开放基金资助课题项目“基于时序多基线InSAR的滑坡隐患监测方法”(编号: KF-2018-03-004);深圳市科创委研究项目“基于InSAR卫星大地测量数据的地震精细目录标准化构建”(编号: JCYJ20170302144002028);“面向SAR大数据的时序InSAR分析处理关键技术研究”(编号: JCYJ20180305125101282);“基于卫星雷达测角及干涉技术的城市填埋场边坡稳定性监测研究”(编号: KQJSCX20180328093453763);地震动力学国家重点实验室开放基金项目“贝叶斯框架下多源数据地震震源特征联合反演”(编号: LED2016B03);深圳市未来产业发展专项资金项目“无人机多传感器集成专业应用示范”(编号: 201607281039561400)
通讯作者: 汪驰升
作者简介: 王永全(1994-),男,硕士研究生,主要从事系留无人机和遥感数据分析及应用方面的研究。Email: 1058309323@qq.com。
引用本文:   
王永全, 李清泉, 汪驰升, 朱家松, 王新雨. 基于系留无人机的应急测绘技术应用[J]. 国土资源遥感, 2020, 32(1): 1-6.
Yongquan WANG, Qingquan LI, Chisheng WANG, Jiasong ZHU, Xinyu WANG. Tethered UAVs-based applications in emergency surveying and mapping. Remote Sensing for Land & Resources, 2020, 32(1): 1-6.
链接本文:  
https://www.gtzyyg.com/CN/10.6046/gtzyyg.2020.01.01      或      https://www.gtzyyg.com/CN/Y2020/V32/I1/1
算法 训练集 测试集 平均精
度均值/%
FLOPS FPS Cfg Weights
SSD300 COCO trainval test-dev 41.2 - 46 link
Tiny YOLO COCO trainval test-dev 23.7 5.41 Bn 244 cfg weights
DSSD321 COCO trainval test-dev 46.1 - 12 link
R-FCN COCO trainval test-dev 51.9 - 12 link
SSD513 COCO trainval test-dev 50.4 - 8 link
DSSD513 COCO trainval test-dev 53.3 - 6 link
FPN FRCN COCO trainval test-dev 59.1 - 6 link
Retinanet-101-500 COCO trainval test-dev 53.1 - 11 link
YOLOv3-320 COCO trainval test-dev 51.5 38.97 Bn 45 cfg weights
YOLOv3-tiny COCO trainval test-dev 33.1 5.56 Bn 220 cfg weights
YOLOv3-spp COCO trainval test-dev 60.6 141.45 Bn 20 cfg weights
Tab.1  YOLO与其他算法处理COCO数据集的对比[14]
Fig.1  深圳光明新区山体垮塌区域DOM及实景三维模型
Fig.2  系留无人机系统组成
Fig.3  2019年深圳大学军训系留无人机人群识别检测
Fig.4  2016年沪宁高速常州段交通事故识别
[1] Schumacher I, Strobl E . Economic development and losses due to natural disasters:The role of hazard exposure[J]. Ecological Economics, 2011,72:97-105
[2] 朱庆, 曹振宇, 林珲 , 等. 应急测绘保障体系若干关键问题研究[J]. 武汉大学学报(信息科学版), 2014,39(5):551-555.
Zhu Q, Cao Z Y, Lin H , et al. Key technologies of emergency surveying and mapping service system[J]. Geomaticsand Information Science of Wuhan University, 2014,39(5):551-555.
[3] 刘刚, 许宏健, 马海涛 , 等. 无人机航测系统在应急服务保障中的应用与前景[J]. 测绘与空间地理信息, 2011,34(4):177-179.
Liu G, Xu H J, Ma H T , et al. Unmanned aerial system applications and prospects in the protection of emergency services[J]. Geomatics and Spatial Information Technology, 2011,34(4):177-179.
[4] 金鼎坚, 支晓栋, 王建超 , 等. 面向地质灾害调查的无人机遥感影像处理软件比较[J]. 国土资源遥感, 2016,28(1):183-189.doi: 10.6046/gtzyyg.2016.01.27.
Jin D J, Zhi X D, Wang J C , et al. Comparison of UAV remote sensing imagery processing software for geological disasters monitoring[J]. Remote Sensing for Land and Resources, 2016,28(1):183-189.doi: 10.6046/gtzyyg.2016.01.27.
[5] Pratt K S, Murphy R R, Burke J L , et al. Use of tethered small unmanned aerial system at Berkman Plaza II collapse[C]// IEEE.2008 IEEE International Workshop on Safety,Security and Rescue Robotics, 2008.
[6] Muttin F . Umbilical deployment modeling for tethered UAV detecting oil pollution from ship[J]. Applied Ocean Research, 2011,33(4), 332-343.
[7] 刘磊, 李景峰, 王烁 . 系留式无人机载通信系统[J]. 通讯世界, 2016(14):53-54.
Liu L, Li J F, Wang S . Tethered unmanned aerial vehicle communication system[J]. Telecom World, 2016(14):53-54.
[8] 杨伟强, 方鼎 . 多旋翼无人机在无线电监测中的应用[J]. 中国无线电, 2015(12):28-30.
Yang W Q, Fang D . Application of multi-rotor UAV in radio monitoring[J]. China Radio, 2015(12):28-30.
[9] 赵云景, 龚绪才, 杜文俊 , 等. PhotoScan Pro软件在无人机应急航摄中的应用[J]. 国土资源遥感, 2015,27(4):179-182.doi: 10.6046/gtzyyg.2015.04.27.
Zhao Y J, Gong X C, Du W J , et al. UAV imagery data processing for emergency response based on PhotoScan Pro[J]. Remote Sensing for Land and Resources, 2015,27(4):179-182.doi: 10.6046/gtzyyg.2015.04.27.
[10] Agisoft. 运用Agisoft PhotoScan专业版软件生成正射影像和数字高程模型(无控制点)[EB/OL].[2014-06-01]. http:/www.agisoft.ru/tutorials/photoscan/05/.
Agisoft. Orthophoto and DEM generation(without GCPs) with Agisoft photoScan Professional[EB/OL][2014-06-01]. http://www.agisoft.ru/tutorials/photoscan/05/.
[11] Agisoft. 运用Agisoft PhotoScan专业版软件进行面积与体积量算[EB/OL].[ 2014- 06- 01]. http://www.agisoft.ru/tutorials/photoscan/03/.
Agisoft. Area and volume measurements with Agisoft PhotoScan Professional[EB/OL].[ 2014- 06- 01]. http://www.agisoft.ru/tutorials/photoscan/03/.
[12] Agisoft. 运用Agisoft PhotoScan专业版软件进行密集点云分类和生成数字地面模型[EB/OL].[ 2014- 06- 01]. http://www.agisoft.ru/tutorials/photoscan/08/.
Agisoft. Dense cloud classification and DTM generation with Agisoft PhotoScan Professional[EB/OL].[ 2014- 06- 01]. http://www.agisoft.ru/tutorials/P-hotoscan/08/.
[13] Redmon J, Divvala S, Girshick R , et al. You only look once:Unified, real-time object detection[C]// IEEE.2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
[14] Redmon J C . YOLO:Real-Time Object Detection[EB/OL]. https://pjreddie.com/darknet/yolo/.
[1] 赵云景, 龚绪才, 杜文俊, 周力. PhotoScan Pro软件在无人机应急航摄中的应用[J]. 国土资源遥感, 2015, 27(4): 179-182.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
京ICP备05055290号-2
版权所有 © 2015 《自然资源遥感》编辑部
地址:北京学院路31号中国国土资源航空物探遥感中心 邮编:100083
电话:010-62060291/62060292 E-mail:zrzyyg@163.com
本系统由北京玛格泰克科技发展有限公司设计开发