视觉拐弯:转角视野盲区无线感知监测算法

doi:10.19665/j.issn1001-2400.2023.02.020

西安电子科技大学学报 ›› 2023, Vol. 50 ›› Issue (2): 197-204.doi: 10.19665/j.issn1001-2400.2023.02.020

• 网络空间安全与其他 • 上一篇

视觉拐弯:转角视野盲区无线感知监测算法

王潮^1,^2,³(),周梦^1,^2,³(),丁寅凡^1,^2,³(),汤霖^1,^2,³()

1.上海大学特种光纤与光接入网重点实验室,上海 200444
2.上海大学特种光纤与先进通信国际合作联合实验室,上海 200444
3.上海大学上海先进通信与数据科学研究院,上海 200444

收稿日期:2022-05-16 出版日期:2023-04-20 发布日期:2023-05-12
通讯作者: 汤霖(1981—),男,上海大学博士研究生,E-mail:bollytom@163.com
作者简介:王潮(1971—),男,教授,博士,E-mail:wangchao@shu.edu.cn;|周梦(1997—),女,上海大学硕士研究生,E-mail:zmyshu@163.com;|丁寅凡(1998—),男,上海大学硕士研究生,E-mail:393051725@qq.com

Visual turning:research on the wireless sensing monitoring algorithm for the corner field of the view blind area

WANG Chao^1,^2,³(),ZHOU Meng^1,^2,³(),DING Yinfan^1,^2,³(),TANG Lin^1,^2,³()

1. Joint Laboratory for International Cooperation of the Special Optical Fiber and Advanced Communication, Shanghai University,Shanghai 200444,China
2. Key Laboratory of the Special Optical Fiber and Optical Access Network,Shanghai University,Shanghai 200444,China
3. Shanghai Institute of Advanced Communication and Data Sciences,Shanghai University,Shanghai 200444,China

Received:2022-05-16 Online:2023-04-20 Published:2023-05-12

摘要/Abstract

摘要：

驾驶人视野盲区是交通事故频发的一个关键问题。现有的摄像头、转角镜以及传感器在感知环境时容易受到天气或光线不足的影响,从而导致意外事故的发生。因此,基于Wi-Fi网络低功耗、低成本、全天时的泛在感知能力,提出一种基于无线信道状态智能化感知的盲区动态对象监测系统。在类似转角或拐弯的场景下,通过无线感知技术与模式识别,提前监测是否有行人即将进入与行进方向垂直的车辆视野盲区的行为,实现“视觉拐弯”,从而预警来往车辆,避免事故的发生。实验结果表明,所提出的盲区监测系统在5 m范围内的视野盲区中实现行人检测的平均精确度可达到96%,具有鲁棒性与普适性等优势。与传统的监测方式相比,该系统在黑暗环境下能良好地工作,同时不会侵犯人们的隐私,在复杂城市交通网络中具备应用潜力,对社会改善交通状况、保障行人出行安全具有重要意义。

关键词: 无线网络, 无线感知, 信道状态信息, 视野盲区, 模式识别

Abstract:

The blind area of a driver's vision is a key problem in the frequent occurrence of traffic accidents.The existing cameras,corner mirrors and sensors are vulnerable to weather or insufficient light when sensing the environment,resulting in accidents.Therefore,based on the low power consumption,low cost and all-day ubiquitous perception capability of the Wi-Fi network,this paper proposes a blind area dynamic object monitoring system based on intelligent perception of wireless channel status.In scenes similar to corners or turns,wireless sensing technology and pattern recognition are used to monitor whether pedestrians are about to enter the blind area of vehicle vision perpendicular to the travel direction in advance,so as to realize "visual turning",warn passing vehicles and avoid accidents.Experimental results show that the proposed blind area monitoring system can achieve an average accuracy of 96% in the blind area within 5 meters,and has the advantages of robustness and universality.Compared with traditional monitoring methods,the system can work well in the dark environment without violating people's privacy so that it has application potential in the complex urban traffic network and is of great significance to improving traffic conditions and ensuring pedestrian travel safety.

Key words: Wi-Fi network, wireless sensing, channel state information, blind area of visual field, pattern recognition

中图分类号:

TN92

王潮, 周梦, 丁寅凡, 汤霖. 视觉拐弯:转角视野盲区无线感知监测算法[J]. 西安电子科技大学学报, 2023, 50(2): 197-204.

WANG Chao, ZHOU Meng, DING Yinfan, TANG Lin. Visual turning:research on the wireless sensing monitoring algorithm for the corner field of the view blind area[J]. Journal of Xidian University, 2023, 50(2): 197-204.

图/表 4

参考文献 18

[1]	戚艳军, 孔月萍, 王佳婧, 等. 一种LSTM与CNN相结合的步态识别方法[J]. 西安电子科技大学学报, 2021, 48(5):78-85.
	QI Yanjun, KONG Yueping, WANG Jiajing, et al. A Gait Recognition Method Combining LSTM and CNN[J]. Journal of Xidian University, 2021, 48 (5):78-85.
[2]	WANG C, CHEN S W, YANG Y W, et al. Literature Review on Wireless Sensing--Wi-Fi Signal-Based Recognition of Human Activities[J]. Tsinghua Science and Technology, 2018, 23(2):203-222. doi: 10.26599/TST.2018.9010080
[3]	ZHAOM M, LI T H, ALSHEIKH M A, et al. Through-Wall Human Pose Estimation Using Radio Signals[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2018:7356-7365.
[4]	LI T H, FAN L J, ZHAO M M, et al. Making the Invisible Visible:Action Recognition Through Walls and Occlusions[C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV). Piscataway:IEEE, 2019:872-881.
[5]	YUES C, YANG Y Z, WANG H, et al. Body Compass:Monitoring Sleep Posture with Wireless Signals[J]. Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies, 2020, 4(2):1-25.
[6]	FANL J, LI T H, FANG R Y, et al. Learning Longterm Representations for Person Re-Identification Using Radio Signals[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway:IEEE, 2020:10696-10706.
[7]	YU B H, WANG Y X, NIU K, et al. WiFi-Sleep:Sleep Stage Monitoring Using Commodity Wi-Fi Devices[J]. IEEE Internet of Things Journal, 2021, 8(18):13900-13913. doi: 10.1109/JIOT.2021.3068798
[8]	ZHANG L, WANG C, MA M D, et al. WiDIGR:Direction-Independent Gait Recognition System Using Commercial Wi-Fi Devices[J]. IEEE Internet of Things Journal, 2020, 7(2):1178-1191. doi: 10.1109/JIoT.6488907
[9]	HANGT M, ZHENG Y, QIAN K, et al. WiSH:WiFi-Based Real-Time Human Detection[J]. Tsinghua Science and Technology, 2019, 24(5):615-629. doi: 10.1109/TST.5971803
[10]	王博远, 刘学林, 蔚保国, 等. WiFi指纹定位中改进的加权k近邻算法[J]. 西安电子科技大学学报, 2019, 46(5):41-47.
	WANG Boyuan, LIU Xuelin, WEI Baoguo, et al. Improved Weighted k-nearest Neighbor Algorithm for WiFi Fingerprint Location[J]. Journal of Xidian University, 2019, 46(5):41-47.
[11]	郑春弟, 李刚, 陈荟慧, 等. 二次谐波加权重构的77 GHz FMCW雷达心率监测方法[J]. 西安电子科技大学学报, 2021, 48(2):173-180.
	ZHENG Chundi, LI Gang, CHEN Huihui, et al. Heart Rate Monitoring Method for 77GHz FMCW Radar Based on Second Harmonic Weighted Reconstruction[J]. Journal of Xidian University, 2021, 48(2):173-180.
[12]	YANGS H, YUAN Z M, LI W. Error Data Analytics on RSS Range-Based Localization[J]. Big Data Mining and Analytics, 2020, 3(3):155-170. doi: 10.26599/BDMA.2020.9020001
[13]	QIAN K, WU C S, ZHOU Z M, et al. Inferring Motion Direction using Commodity Wi-Fi for Interactive Exergames[C]// Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems. New York: ACM, 2017:1961-1972.
[14]	QIAN K, WU C S, YANG Z, et al. Widar:Decimeter-Level Passive Tracking via Velocity Monitoring with Commodity Wi-Fi[C]// Proceedings of the 18th ACM International Symposium on Mobile Ad Hoc Networking and Computing. New York: ACM, 2017:1-10.
[15]	WANG W, LIU A X, SHAHZAD M, et al. Understanding and Modeling of WiFi Signal Based Human Activity Recognition[C]// Proceedings of the 21st Annual International Conference Computing and Networking. New York: ACM, 2015:65-76.
[16]	ZHU H, XIAO F, SUN L J, et al. Robust and Passive Motion Detection with COTS WiFi Devices[J]. Tsinghua Science and Technology, 2017, 22(4):345-359. doi: 10.23919/TST.2017.7986938
[17]	张玄黎, 修春娣, 王延昭, 等. 基于CSI-XGBoost的高精度WiFi室内定位算法[J]. 北京航空航天大学学报, 2018, 44(12):2536-2544.
	ZHANG Xuanli, XIU Chundi, WANG Yanzhao, et al. High Precision WiFi Indoor Location Algorithm Based on CSI-Xgboost[J]. Journal of Beijing University of Aeronautics and Astronautics, 2018, 44(12):2536-2544.
[18]	CHEN T Q, Guestrin C. XGBoost:A Scalable Tree Boosting System[C]// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2016:785-794.

距离/m	静态环境	动态环境	分类识别
[0,1]	100.000	99.750	99.875
(1,3]	97.250	97.000	97.125
(3,5]	89.750	92.500	91.125
平均精确度	95.667	96.417	96.042

视觉拐弯:转角视野盲区无线感知监测算法

Visual turning:research on the wireless sensing monitoring algorithm for the corner field of the view blind area

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 4

参考文献 18

相关文章 15

Metrics

本文评价

推荐阅读 10

[1]	杨欣,毛雅淇,王伶. 无人机辅助通信的密集无线网络MAC协议[J]. 西安电子科技大学学报, 2022, 49(3): 10-20.
[2]	杨秋,顾杰,魏平. 利用幅度重排的机载火控雷达工作模式识别方法[J]. 西安电子科技大学学报, 2021, 48(2): 42-48.
[3]	闫林,刘凯,段玫妤. 一种用于点云分类的轻量级深度神经网络[J]. 西安电子科技大学学报, 2020, 47(2): 46-53.
[4]	赵彤,李先圣,张雷,丁恩杰,胡延军. 煤矿井下区间分段视距节点合作定位算法[J]. 西安电子科技大学学报, 2019, 46(1): 166-173.
[5]	杜得荣;曾孝平;简鑫;杨凡;陈礼. 三维角度域网络干扰的空间选择特性[J]. 西安电子科技大学学报, 2018, 45(5): 157-162.
[6]	杨利英;杨胜楠;袁细国;耿芳歌;张军英. 泛癌症DNA甲基化位点聚类分析[J]. 西安电子科技大学学报, 2018, 45(4): 23-28.
[7]	孙彦景;渠倩倩;王博文;左海维;王晓琳. 一种带内全双工无线网络MAC机制及性能分析[J]. 西安电子科技大学学报, 2018, 45(3): 123-129.
[8]	范亮;王晓梅;杨东煜. 一种利用最佳路径搜索的PDU容错定界算法[J]. 西安电子科技大学学报, 2016, 43(5): 160-166.
[9]	杨利英;殷黎洋;袁细国;张军英. 富集分析框架下的致病SNP位点识别[J]. 西安电子科技大学学报, 2016, 43(3): 43-48.
[10]	黄绍城;马林华;蔡钊;张嵩;茹乐;田雨. 多跳无线网络跨层自适应协同TDMA协议[J]. 西安电子科技大学学报, 2016, 43(3): 131-136.
[11]	龙彦;李红艳. 认知无线网络中视频传输的资源分配方案[J]. 西安电子科技大学学报, 2016, 43(2): 6-12.
[12]	赵婧;李兴华;薛飞洁;马建峰. 一种非合作博弈下的无线网络接入选择方法[J]. J4, 2014, 41(5): 98-104.
[13]	李红宁;裴庆祺;李子. 认知无线网络中收敛感知算法安全性检测[J]. J4, 2014, 41(3): 157-161.
[14]	冯晓峰;祁飞;吕宗庭. 异构无线网络联合呼叫接纳控制优化算法[J]. J4, 2013, 40(5): 194-199.
[15]	刘焕云;王军宁;何迪;涂尚斌. 仿生模式识别目标自适应跟踪算法[J]. J4, 2013, 40(4): 142-148.