基于共轴双旋翼无人机的目标检测与薄弱位置定位系统设计

doi:10.7523/j.ucas.2022.017

中国科学院大学学报 ›› 2023, Vol. 40 ›› Issue (5): 701-709.DOI: 10.7523/j.ucas.2022.017

基于共轴双旋翼无人机的目标检测与薄弱位置定位系统设计

冯航涛^1,2, 曾少锋^1,2, 张璐^1,2, 杨旭^1,2,3, 刘智勇^1,2,3

1. 中国科学院大学人工智能学院, 北京 100049;
2. 中国科学院自动化研究所复杂系统管理与控制国家重点实验室, 北京 100190;
3. 中国科学院脑科学与智能技术卓越创新中心, 上海 200031

收稿日期:2021-11-01 修回日期:2022-03-09 发布日期:2022-03-21
通讯作者: 刘智勇,E-mail:zhiyong.liu@ia.ac.cn
基金资助:
科技部科技创新2030-“新一代人工智能”重大项目(2020AAA0108902)、中国科学院战略性先导科技专项(XDB32050100)、东莞市核心技术攻关项目(2019622101001)和国家自然科学基金(61627808)资助

Design of object detection and weak position location system base on coaxial dual-rotor drone

FENG Hangtao^1,2, ZENG Shaofeng^1,2, ZHANG Lu^1,2, YANG Xu^1,2,3, LIU Zhiyong^1,2,3

1. School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China;
2. State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China;
3. Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Shanghai 200031, China

Received:2021-11-01 Revised:2022-03-09 Published:2022-03-21

摘要/Abstract

摘要： 由自主控制算法控制的非载人无人飞行器在执行定向打击等危险任务中往往比有人机具有更大的优势。然而,在执行爆破任务的时候,无人机在不同场景下的检测算法鲁棒性往往无法得到保证,这极大地影响了无人机对目标的定位效果,导致执行任务的成功率大幅降低。为解决上述问题,提出利用基于跨域的目标检测算法提高无人机在不同场景下检测算法的鲁棒性,并通过在线GPS聚类算法提高无人机对目标定位的稳定性。同时,鉴于目标爆破位置对爆破结果的影响,提出一种薄弱部位定位算法,提高爆破的精确度和成功率。

关键词: 无人机, 目标检测, 知识蒸馏, 图像分割

Abstract: Unmanned aerial vehicles (UAV) controlled by autonomous control algorithms often have greater advantages than manned aircraft in the execution of directional strikes and other dangerous tasks. When performing blasting tasks, the robustness of the UAV detection algorithm in different scenarios is often not guaranteed, which greatly affects the UAV's positioning of the target, thus reducing the success rate of the mission. In order to solve the above problems, the crossdomain-based object detection algorithm is used to improve the robustness of the UAV detection algorithm in different scenarios, and the online GPS clustering algorithm is used to improve the robustness of object positioning. At the same time, in view of the impact of the object blasting position on the blasting result, the system uses an algorithm for locating weak parts to improve the accuracy and success rate of blasting.

Key words: unmanned aerial vehicles, object detection, knowledge distillation, image segmentation

中图分类号:

TP319.4

冯航涛, 曾少锋, 张璐, 杨旭, 刘智勇. 基于共轴双旋翼无人机的目标检测与薄弱位置定位系统设计[J]. 中国科学院大学学报, 2023, 40(5): 701-709.

FENG Hangtao, ZENG Shaofeng, ZHANG Lu, YANG Xu, LIU Zhiyong. Design of object detection and weak position location system base on coaxial dual-rotor drone[J]. Journal of University of Chinese Academy of Sciences, 2023, 40(5): 701-709.

参考文献

[1] Zhao J H, Xiao G, Zhang X C, et al. A survey on object tracking in aerial surveillance[C]//Proceedings of International Conference on Aerospace System Science and Engineering 2018, 2019:53-68. DOI:10.1007/978-981-13-6061-9_4.
[2] Vanegas F, Campbell D, Roy N, et al. UAV tracking and following a ground target under motion and localisation uncertainty[C]//2017 IEEE Aerospace Conference. March 4-11, 2017, Big Sky, MT, USA. IEEE, 2017:1-10. DOI:10.1109/AERO.2017.7943775.
[3] Tijtgat N, Van Ranst W, Volckaert B, et al. Embedded real-time object detection for a UAV warning system[C]//2017 IEEE International Conference on Computer Vision Workshops. October 22-29, 2017, Venice, Italy. IEEE, 2017:2110-2118. DOI:10.1109/ICCVW.2017.247.
[4] Du D W, Qi Y K, Yu H Y, et al. The unmanned aerial vehicle benchmark:Object detection and tracking[M]//Computer Vision-ECCV 2018. Cham:Springer International Publishing, 2018:375-391. DOI:10.1007/978-3-030-01249-6_23.
[5] Mittal P, Singh R, Sharma A. Deep learning-based object detection in low-altitude UAV datasets:a survey[J]. Image and Vision Computing, 2020, 104:104046. DOI:10.1016/j.imavis.2020.104046.
[6] Zou Z X, Shi Z W, Guo Y H, et al. Object detection in 20 years:A survey[EB/OL]. arXiv:1905.05055. (2019-05-16)[2021-11-01]. https://arxiv.org/abs/1905.05055v1.
[7] Parmar N, Vaswani A, Uszkoreit J, et al. Image transformer[EB/OL]. arXiv:1802.05751. (2018-02-15)[2021-11-01]. https://arxiv.org/abs/1802.05751.
[8] Park T, Efros A A, Zhang R, et al. Contrastive learning for unpaired image-to-image translation[C]//Computer Vision-ECCV 2020, 2020:319-345. DOI:10.1007/978-3-030-58545-7_19.
[9] Chen T, Kornblith S, Norouzi M, et al. A simple framework for contrastive learning of visual representations[EB/OL]. arXiv:2002.05709. (2020-02-13)[2021-11-01]. https://arxiv.org/abs/2002.05709.
[10] Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition. June 23-28, 2014, Columbus, OH, USA. IEEE, 2014:580-587. DOI:10.1109/CVPR.2014.81.
[11] Girshick R. Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision. December 7-13, 2015, Santiago, Chile. IEEE, 2015:1440-1448. DOI:10.1109/ICCV.2015.169.
[12] Ren S Q, He K M, Girshick R, et al. Faster R-CNN:towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6):1137-1149. DOI:10.1109/TPAMI.2016.2577031.
[13] Redmon J, Divvala S, Girshick R, et al. You only look once:unified, real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. June 27-30, 2016, Las Vegas, NV, USA. IEEE, 2016:779-788. DOI:10.1109/CVPR.2016.91.
[14] Redmon J, Farhadi A. YOLO9000:better, faster, stronger[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. July 21-26, 2017, Honolulu, HI, USA. IEEE, 2017:6517-6525. DOI:10.1109/CVPR.2017.690.
[15] Redmon J, Farhadi A. YOLOv3:an incremental improvement[EB/OL]. arXiv:1804.02767. (2018-04-08)[2021-11-01]. https://arxiv.org/abs/1804.02767v1.
[16] Bochkovskiy A, Wang C Y, Liao H Y M. YOLOv4:optimal speed and accuracy of object detection[EB/OL]. arXiv:2004.10934. (2020-04-23)[2021-11-01]. https://arxiv.org/abs/2004.10934v1.
[17] Liu W, Anguelov D, Erhan D, et al. SSD:single shot MultiBox detector[C]//Computer Vision-ECCV 2016, 2016:21-37. DOI:10.1007/978-3-319-46448-0_2.
[18] Duan K W, Bai S, Xie L X, et al. CenterNet:keypoint triplets for object detection[C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV). October 27-November 2, 2019, Seoul, Korea (South). IEEE, 2019:6568-6577. DOI:10.1109/ICCV.2019.00667.
[19] Hinton G E, Vinyals O, Dean J. Distilling the knowledge in a neural network[J]. IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, 2015, abs/1503.02531.
[20] McKinley G A. An introduction to digital image processing[J]. Clinical Microbiology Newsletter, 1990, 12(12):89-92. DOI:10.1016/0196-4399(90)90015-4.
[21] Otsu N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1979, 9(1):62-66. DOI:10.1109/TSMC.1979.4310076.
[22] Sauvola J, Pietikäinen M. Adaptive document image binarization[J]. Pattern Recognition, 2000, 33(2):225-236. DOI:10.1016/S0031-3203(99)00055-2.

基于共轴双旋翼无人机的目标检测与薄弱位置定位系统设计

Design of object detection and weak position location system base on coaxial dual-rotor drone

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

访问统计

联系我们

[1]	申晓天, 郑明洁. 一种新的基于FrFT的动目标测速和定位方法[J]. 中国科学院大学学报, 2023, 40(1): 84-92.
[2]	高锦风, 陈玉, 魏永明, 李剑南. 基于改进的YOLOv3和Facenet的无人机影像人脸识别[J]. 中国科学院大学学报, 2023, 40(1): 93-100.
[3]	霍鑫怡, 李焱磊, 陈龙永, 张福博, 孙巍. 基于卷积注意力和胶囊网络的 SAR少样本目标识别方法[J]. 中国科学院大学学报, 2022, 39(6): 783-792.
[4]	杨帅, 计璐艳, 耿修瑞. 基于滤波张量分析的高光谱目标检测方法[J]. 中国科学院大学学报, 2022, 39(5): 684-694.
[5]	刘梦冰, 邱玲, 梁晓雯. 基于Matern硬核点过程的无人机辅助蜂窝网络吞吐量分析[J]. 中国科学院大学学报, 2022, 39(5): 704-711.
[6]	古煜民, 阎福礼. 基于不同骨架UNet++网络的建筑物提取[J]. 中国科学院大学学报, 2022, 39(4): 512-523.
[7]	宋孝成, 刘晓培, 陆疌. 未知环境中无人机实时导航的人工势场方法[J]. 中国科学院大学学报, 2022, 39(3): 393-402.
[8]	席彦新, 计璐艳, 耿修瑞. 一种多时相遥感图像多目标检测算法[J]. 中国科学院大学学报, 2021, 38(4): 503-510.
[9]	黄萍萍, 王峰, 向俞明, 尤红建. 基于V-CSK视频遥感卫星运动目标检测跟踪方法[J]. 中国科学院大学学报, 2021, 38(3): 392-401.
[10]	顾育津, 宋孝成, 刘晓培, 陆疌. 基于拉普拉斯人工势场的无人机避障控制[J]. 中国科学院大学学报, 2020, 37(5): 681-687.
[11]	陈国炜, 刘磊, 郭嘉逸, 潘宗序, 胡文龙. 基于生成对抗网络的半监督遥感图像飞机检测[J]. 中国科学院大学学报, 2020, 37(4): 539-546.
[12]	卢凯旋, 李国清, 陈正超, 昝露洋, 李柏鹏, 高建威. 基于负样本多通道优化SSD网络的钢铁厂提取[J]. 中国科学院大学学报, 2020, 37(3): 352-359.
[13]	闫凯, 沈汀, 陈正超, 闫弘轩. 基于深度学习的SSD模型尾矿库自动提取[J]. 中国科学院大学学报, 2020, 37(3): 360-367.
[14]	李志新, 王心源, 刘传胜, 骆磊. 海南东寨港海底村庄遗址遥感观测与分析[J]. 中国科学院大学学报, 2019, 36(6): 803-809.
[15]	马娇, 董勇伟, 李原, 李凌霄, 杨杰芳. 多旋翼无人机微多普勒特性分析与特征提取[J]. 中国科学院大学学报, 2019, 36(2): 235-243.