基于人机协作的高质量城市图像采集方法

doi:10.3969/j.issn.0255-8297.2023.05.007

摘要/Abstract

摘要： 智慧城市的很多应用都需要采集城市中的各类图像。该文将人完成图像采集任务时的情境转换为任务指令后，驱动机器人采集更多的城市图像。为了选择合适的任务参数值，评估了人与物之间的距离、人的拍照姿态和地形起伏等参数对感知效果的影响。为了解决人机协作任务指令转换的偏差问题，提出了动态阈值近似最近邻（approximate nearest neighborwith dynamic threshold,DTANN）算法以及两种优化任务指令参数的方法，包括机器人的拍照角度和位置的优化。以人机采集的图像重合度作为评估机器人完成任务的质量指标进行实验，结果表明：采用DTANN方法和任务指令优化方法后，数据的精确率和召回率都有提高，并且F1-measure值提高了8%~20%。

关键词: 人机协作, 机器人, 数据驱动, 高质量城市图像采集, 任务指令优化

Abstract: Many smart city applications require various photos collected in urbans. In this paper, contexts of sensing-task photos collected by people are converted into task instruction to drive the robot to collect more urban photos. The influence of parameters such as distance between people and objects, person’s photographing posture, and land slope on sensing effectiveness is evaluated to select appropriate task parameter values. To address deviation of task command conversion during human-machine cooperation, we present approximate nearest neighbor with dynamic threshold (DTANN) algorithm and propose two methods for optimizing task command parameters including camera posture and robot positions. The overlap of photos collected by humans and machines is used as the quality indicator to evaluate the tasks completion of the robot. Experimental results show that with the aid of DTANN method and task instruction optimization, the precision rate and recall rate both have been improved, and the F1-measure value is increased by 8% to 20%.

Key words: human-machine cooperation, robot, data driven, high quality urban photo collection, task’s instruction optimization

中图分类号:

TP391

陈荟慧, 钟委钊. 基于人机协作的高质量城市图像采集方法[J]. 应用科学学报, 2023, 41(5): 801-814.

CHEN Huihui, ZHONG Weizhao. High-Quality Urban Photos Collection Method Based on Human-Machine Cooperation[J]. Journal of Applied Sciences, 2023, 41(5): 801-814.

参考文献

[1] Zhang W, Li H Y, Cui L L, et al. Research progress and development trend of surgical robot and surgical instrument arm[J]. The International Journal of Medical Robotics and Computer Assisted Surgery, 2021:e2309.
[2] 回文宇, 吴锦阳, 黄建华, 等. 机器人辅助颏成形术行截骨操作的精度评价实验研究[J]. 上海交通大学学报(医学版), 2022, 42(9):1347-1352. Hui W Y, Wu J Y, Huang J H, et al. Experimental study on the accuracy evaluation of robot-assisted osteotomy of genioplasty[J]. Journal of Shanghai Jiao Tong University (Medical Science), 2022, 42(9):1347-1352. (in Chinese)
[3] 王忠民. 灾难搜救机器人研究现状与发展趋势[J]. 现代电子技术, 2007(17):152-155. Wang Z M. Research status and development tendency of searching and rescuing robot[J]. Modern Electronics Technique, 2007(17):152-155. (in Chinese)
[4] 陶永, 高赫, 王田苗, 等. 移动工业机器人在飞机装配生产线中的应用研究[J]. 航空制造技术, 2021, 64(5):32-41, 67 Tao Y, Gao H, Wang T M, et al. Application of mobile industrial robot in aircraft assembly production line[J]. Aeronautical Manufacturing Technology, 2021, 64(5):32-41, 67. (in Chinese)
[5] 许常蕾, 王庆, 陈洪, 等. 基于体感交互的仿上肢采摘机器人系统设计与仿真[J]. 农业工程学报, 2017, 33(增刊1):49-55 Xu C L, Wang Q, Chen H, et al. Design and simulation of artificial limb picking robot based on somatosensory interaction[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2017, 33(Supp.1):49-55. (in Chinese)
[6] 黄山, 吴振升, 任志刚, 等. 电力智能巡检机器人研究综述[J]. 电测与仪表, 2020, 57(2):26-38. Huang S, Wu Z S, Ren Z G, et al. Review of electric power intelligent inspection robot[J]. Electrical Measurement and Instrumentation, 2020, 57(2):26-38. (in Chinese)
[7] Wan J, Liu J, Shao Z, et al. Mobile crowd sensing for traffic prediction in internet of vehicles[J]. Sensors, 2016, 16(1):88.
[8] 钟委钊, 陈荟慧. 基于群智感知的街景变化检测方法[J]. 计算机应用研究, 2022(10):3186-3190. Zhong W Z, Chen H H. Change detection method of street view image based on crowd sensing[J]. Application Research of Computers, 2022(10):3186-3190. (in Chinese)
[9] 吴文乐, 郭斌, 於志文. 基于群智感知的城市噪声检测与时空规律分析[J]. 计算机辅助设计与图形学学报, 2014, 26(4):638-643. Wu W L, Guo B, Yu Z W. Crowd sensing based urban noise map and temporal-spatial feature analysis[J]. Journal of Computer-Aided Design & Computer Graphics, 2014, 26(4):638-643. (in Chinese)
[10] 危双丰, 刘振彬, 赵江洪, 等. SLAM室内三维重建技术综述[J]. 测绘科学, 2018, 43(7):15-26. Wei S F, Liu Z B, Zhao J H, et al. A review of indoor 3D reconstruction with SLAM[J]. Science of Surveying and Mapping, 2018, 43(7):15-26. (in Chinese)
[11] 于乃功, 苑云鹤, 李倜, 等. 一种基于海马认知机理的仿生机器人认知地图构建方法[J]. 自动化学报, 2018, 44(1):52-73. (in Chinese) Yu N G, Yuan Y H, Li T, et al. A cognitive map building algorithm by means of cognitive mechanism of hippocampus[J]. Acta Automatica Sinica, 2018, 44(1):52-73. (in Chinese)
[12] 张卫涛, 李宏利, 于迅文, 等. 城市街景地图的采集与处理[C]//卫星导航定位与北斗系统应用, 2013:174-179. Zhang W T, Li H L, Yu X W, et al. Collection and processing of urban street view maps[C]//Satellite Navigation and Positioning and Beidou System Application, 2013:174-179.
[13] Guo B, Han Q, Chen H H, et al. The emergence of visual crowd sensing:challenges and opportunities[J]. IEEE Communications Surveys & Tutorials, 2017, 19(4):2526-2543.
[14] Guo B, Chen H H, Yu Z W, et al. FlierMeet:a mobile crowd sensing system for cross-space public information reposting, tagging, and sharing[J]. IEEE Transactions on Mobile Computing, 2014, 14(10):2020-2033.
[15] Wang Q R, Guo B, Wang L, et al. CrowdWatch:dynamic sidewalk obstacle detection using mobile crowd sensing[J]. IEEE Internet of Things Journal, 2017, 4(6):2159-2171.
[16] Chen H H, Guo B, Yu Z W, et al. Toward real-time and cooperative mobile visual sensing and sharing[C]//IEEE INFOCOM 2016-the 35th Annual IEEE International Conference on Computer Communications, 2016:1-9.
[17] Chen H H, Cao Y J, Guo B, et al. LuckyPhoto:multi-facet photographing with mobile crowdsensing[C]//Proceedings of the 2018 ACM International Conference on Pervasive and Ubiquitous Computing, 2018:29-32.
[18] Andrea C, Claudio F, Burak K, et al. A survey on mobile crowdsensing systems:challenges, solutions, and opportunities[J]. IEEE Communications Surveys & Tutorials, 2019, 21(3):2419-2465.
[19] 郭明祥. 基于警用巡逻机器人的人体运动行为意图识别方法研究[D]. 合肥:中国科学技术大学, 2020.
[20] 田佳, 刘泓滨, 王宇, 等. 一种机器视觉的安防巡逻机器人系统设计[J]. 机械设计与制造, 2020(11):254-257. Tian J, Liu H B, Wang Y, et al. Design of a robot system with machine vision for security and patrol[J]. Machinery Design & Manufacture, 2020(11):254-257. (in Chinese)
[21] Sheridan T B. Human-robot interaction:status and challenges[J]. Human Factors, 2016, 58(4):525-532.
[22] 徐善军, 任书楠, 杜婧, 等. 协作机器人在高压带电作业中的应用研究[J]. 制造业自动化, 2021, 43(9):106-110. Xu S J, Ren S N, Du J, et al. The application study of collaboration robot in high-voltage electric power live line working[J]. Manufacturing Automation, 2021, 43(9):106-110. (in Chinese)
[23] Lowe D G. Object recognition from local scale-invariant features[C]//Processions of International Conference on Computer Vision, 1999:1150-1157.
[24] Fischler M A, Bolles R C. Random sample consensus:a paradigm for model fitting with applications to image analysis and automated cartography[J]. Communications of the ACM, 1981, 24(6):381-395.
[25] Muja M, Lowe D G. Scalable nearest neighbor algorithms for high dimensional data[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(11):2227-2240.
[26] Muja M, Lowe D G. Fast approximate nearest neighbors with automatic algorithm configuration[C]//International Conference on Computer Vision Theory and Applications, 2009, 2(2):331-340.