Review on aerial path planning of UAV for 3D reconstruction

doi:10.13474/j.cnki.11-2246.2022.0239

Abstract

Abstract: In the 3D reconstruction of urban scene, using UAV to collect images at low altitude has become the mainstream scheme. The UAV captures images at low altitude based on the optimal aerial path can improve the accuracy and efficiency of 3D reconstruction. Therefore, many researchers have investigated and developed the UAV aerial path planning methods in recent years. Accordingly, many viewpoint planning and flight path planning approaches have been reported. To summarize the principles of these new methods, this paper describes the working process of aerial path planning techniques, and details the modeling methods of aerial path planning based on the reconstructed 2D and 3D models of environments, as well as the unknown environment. Then the advantages and disadvantages of different path planning methods are analyzed, and the development trends are also discussed. This review can provide an important reference for the development of UAV control, aerial photography technology, and 3D reconstruction of large-scale scenes.

Key words: UAV, 3D reconstruction, oblique photography, aerial path planning, viewpoint planning

CLC Number:

P237

WU Changsong, PENG Yeping, CAO Guangzhong, YAN Yan. Review on aerial path planning of UAV for 3D reconstruction[J]. Bulletin of Surveying and Mapping, 2022, 0(8): 98-103,122.

References

[1] SNAVELY N,SEITZ S M,SZELISKI R. Photo tourism: exploring photo collections in 3D[J]. ACM Transactions on Graphics,2006,25(3): 835-846.
[2] FURUKAWA Y,PONCE J. Carved visual hulls for image-based modeling[J]. International Journal of Computer Vision,2009,81(1): 53-67.
[3] HAN Jungong,SHAO Ling,XU Dong,et al. Enhanced computer vision with Microsoft Kinect sensor: a review[J]. IEEE Transactions on Cybernetics,2013,43(5): 1318-1334.
[4] POLLEFEYS M,NISTÉR D,FRAHM J M,et al. Detailed real-time urban 3D reconstruction from video[J]. International Journal of Computer Vision,2008,78(2/3): 143-167.
[5] 张奇,徐斌,张冬,等. 倾斜摄影测量三维重建在城市规划管理中的应用[J]. 智能城市,2021,7(4):12-14.
[6] 李安福,曾政祥,吴晓明.浅析国内倾斜摄影技术的发展[J].测绘与空间地理信息,2014,37(9): 57-59.
[7] 航迹软件DroneDeploy[EB/OL].[2021-09-10].https://www.dronedeploy.com/.
[8] NESBIT P,HUGENHOLTZ C. Enhancing UAV–SfM 3D model accuracy in high-relief landscapes by incorporating oblique images[J]. Remote Sensing,2019,11(3): 239.
[9] SCOTT W R,ROTH G,RIVEST J F. View planning for automated three-dimensional object reconstruction and inspection[J]. ACM Computing Surveys,2003,35(1): 64-96.
[10] CONNOLLY C. The determination of next best views[C]//Proceedings of 1985 IEEE International Conference on Robotics and Automation.Louis,MO:IEEE,1985: 432-435.
[11] 航迹软件DJI GO PRO[EB/OL].[2021-09-10]. https://www.dji.com/cn/ground-station-pro.
[12] 吴宇豪,安籽鹏. 面向图像三维重建的无人机航线规划[J]. 电子技术应用,2019,45(3): 76-79.
[13] 盛辉,李凌昊,刘树生,等. 面向城市复杂区域的无人机倾斜摄影航线规划方法[J]. 测绘通报,2021(1):47-52.
[14] 张磊,朱励轩,张滕远,等. 适用于城市区域航拍的无人机航线规划研究[J]. 公路交通科技(应用技术版),2018,14(2): 296-299.
[15] JING Wei,POLDEN J,TAO P Y,et al. View planning for 3D shape reconstruction of buildings with unmanned aerial vehicles[C]//Proceedings of the 14th International Conference on Control,Automation,Robotics and Vision(ICARCV).Phuket:IEEE,2016:1-6.
[16] HEPP B,NIEßNER M,HILLIGES O. Plan3D: viewpoint and trajectory optimization for aerial multi-view stereo reconstruction[J]. ACM Transactions on Graphics,2017,38(1):1-17.
[17] YANG C H,TSAI M H,KANG S C,et al. UAV path planning method for digital terrain model reconstruction-a debris fan example[J]. Automation in Construction,2018,93: 214-230.
[18] SAKANE S,NIEPOLD R,SATO T,et al. Illumination setup planning for a hand-eye system based on an environmental model[J]. Advanced Robotics,1991,6(4): 461-482.
[19] 王晓东,岳军红,陈兴芳. 倾斜摄影技术的单体塔式建筑物三维重建方法[J]. 全球定位系统,2021,46(2): 86-92.
[20] 周骁腾,周政,张书航,等. 面向单体建筑精细化建模的无人机三维航线规划[J]. 地矿测绘,2017,33(2): 24-27.
[21] SCHMID K,HIRSCHMVLLER H,DÖMEL A,et al. View planning for multi-view stereo 3D reconstruction using an autonomous multicopter[J]. Journal of Intelligent & Robotic Systems,2012,65(1-4): 309-323.
[22] YAN Feihu,XIA Enyong,LI Zhaoxin,et al. Sampling-based path planning for high-quality aerial 3D reconstruction of urban scenes[J]. Remote Sensing,2021,13(5): 989.
[23] ZHOU Xiaohui,XIE Ke,HUANG Kai,et al. Offsite aerial path planning for efficient urban scene reconstruction[J]. ACM Transactions on Graphics,2020,39(6): 1-16.
[24] COWAN C K,KOVESI P D. Automatic sensor placement from vision task requirements[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1988,10(3): 407-416.
[25] CHEN S Y,LI Y F. Automatic sensor placement for model-based robot vision[J]. IEEE Transactions on Systems,Man,and Cybernetics,Part B (Cybernetics),2004,34(1): 393-408.
[26] FLOOD M M. The traveling-salesman problem[J]. Operations Research,1956,4(1): 61-75.
[27] HARDOUIN G,MORAS J,MORBIDI F,et al. Next-Best-View planning for surface reconstruction of large-scale 3D environments with multiple UAVs[C]//Proceedings of 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS).Las Vegas:IEEE,2021:1567-1574.
[28] ZHENG Xiaocui,WANG Fei,LI Zhanghua. A multi-UAV cooperative route planning methodology for 3D fine-resolution building model reconstruction[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2018,146: 483-494.
[29] YAMAUCHI B. A frontier-based approach for autonomous exploration[C]//Proceedings of 1997 IEEE International Symposium on Computational Intelligence in Robotics and Automation.Monterey,CA:IEEE,1997: 146-151.
[30] BIRCHER A,KAMEL M,ALEXIS K,et al. Receding horizon“next-best-view” planner for 3D exploration[C]//Proceedings of 2016 IEEE International Conference on Robotics and Automation. Stockholm:IEEE,2016: 1462-1468.
[31] LAVALLE S M. Rapidly-exploring random trees: a new tool for path planning[J]. Department of Computer Science,1998,1:1-4.
[32] DAI Anna,PAPATHEODOROU S,FUNK N,et al. Fast frontier-based information-driven autonomous exploration with an MAV[C]//Proceedings of 2020 IEEE International Conference on Robotics and Automation. Paris:IEEE,2020: 9570-9576.
[33] SELIN M,TIGER M,DUBERG D,et al. Efficient autonomous exploration planning of large-scale 3D environments[J]. IEEE Robotics and Automation Letters,2019,4(2): 1699-1706.
[34] HEPP B,DEY D,SINHA S N,et al. Learn-to-score: efficient 3D scene exploration by predicting view utility[C]//Proceedings of 2018 Computer Vision.Cham: Springer,2018.
[35] 李爱军. 基于卷积神经网络和NBV的三维重建方法[J]. 电子测量技术,2021,44(8): 70-75.
[36] LI Haoran,ZHANG Qichao,ZHAO Dongbin. Deep reinforcement learning-based automatic exploration for navigation in unknown environment[J]. IEEE Transactions on Neural Networks and Learning Systems,2020,31(6): 2064-2076.