基于泛在信号融合的室内外场景鲁棒感知算法

鄢松; 吴飞; 朱海; 陆雯霞; 胡锐; 聂大惟

doi:10.13442/j.gnss.1008-9268.2020.04.010

基于泛在信号融合的室内外场景鲁棒感知算法

上海工程技术大学电子电气工程学院,上海 201620

详细信息

作者简介:
鄢松 (1993—),男,硕士研究生,研究方向为室内定位.

通信作者:
吴飞 E-mail：fei_wu1@163.com

计量
- 文章访问数: 284
- HTML全文浏览量: 66
- PDF下载量: 41
出版历程
- 刊出日期: 2020-08-14

Robust perception algorithm for indoor and outdoor scenes based on signal of opportunity

College of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China

摘要

摘要: 针对室内外场景结合的导航应用服务需求的发展以及现有室内外场景感知方法的识别稳定性较低、准确率不高问题,本文提出一种基于泛在信号融合的室内外场景鲁棒感知算法,利用室内外场景中融合的泛在信号降低单一信号识别误差;同时为提高传统AdaBoost算法对不平衡数据集的分类精度,采用概率神经网络（PNN）作为训练的弱分类器,并引入熵权法,对迭代产生的弱分类器的权重进行修正来提高强分类器的分类准确率．现实场景下的实验表明,本文算法在采用室内外环境中的WiFi信号、全球卫星导航系统（GNSS）可用星数、光照强度这三种融合的泛在信号进行室内外场景感知时性能最佳,对于不同角度方向下的室内外场景切换,可以在误报率仅为1.7％的情况下,达到98％的识别准确率,验证了本文所提算法的准确性和鲁棒性．
- 泛在信号 /
- 室内外场景感知 /
- AdaBoost /
- PNN
Abstract: Considering that the development of navigation application service requirements for the combination of indoor and outdoor scenes and the problems of low recognition stability and the low recognition accuracy of existing indoor and outdoor scenes perception methods, this paper proposes a robust sensing algorithm for indoor and outdoor scenes based on signal of opportunity. The signal of opportunity is used to reduce the single signal recognition error. In order to improve the classification accuracy of the traditional AdaBoost algorithm for imbalanced data sets, the Probabilistic Neural Network(PNN) is used as the training weak classifier, and the entropy weight method is introduced to modify the weight of the weak classifier generated by iteration to improve the classification accuracy of the strong classifier. Experimental verification in real scenarios shows that the algorithm in this paper performs best in indoor and outdoor scene perception using signal of opportunity: WiFi signal, available GNSS stars, and light intensity in indoor and outdoor environments. For scenes switching in different angle directions, the recognition accuracy of 98％ can be achieved with a false alarm rate of only 1.7％, which verifies the accuracy and robustness of the algorithm proposed in this paper.
- signal of opportunity /
- indoor and outdoor scenes perception /
- AdaBoost /
- PNN

HTML全文

参考文献(20)

SHTAR G, SHAPIRA B, ROKACH L. Clustering Wi-Fi fingerprints for indooroutdoor detection［J］. Wireless networks, 2019, 25(3): 1341-1359.

CANOVAS O, LOPEZ-DE-TERUEL P E,RUIZ A. Detecting indoor/outdoor places using WiFi signals and adaBoost［J］. IEEE sensors journal, 2017, 17(5): 1443-1453. DOI: 10.1109/JSEN.2016.2640358.

HUANG H Z, ZENG Q H,CHEN R Z, et al. Seamless navigation methodology optimized for indoor/outdoor detection based on WiFi［C］// 2018 Ubiquitous Positioning, Indoor Navigation and Location-Based Services (UPINLBS),2018. DOI: 10.1109/UPINLBS.2018.8559940.

邹德岳. 异构无线系统室内外无缝定位技术研究［D］. 哈尔滨: 哈尔滨工业大学, 2016.

ALI M, ELBATT T, YOUSSEF M. Senseio: realistic ubiquitous indoor outdoor detection system using smartphones［J］. IEEE sensors journal, 2018, [JP2]18(9): 3684-3693. DOI: 10.1109/JSEN.2018.2810193.

陈锦华. 泛在环境下的无缝定位技术研究［D］. 北京: 北京交通大学, 2017.

蔡劲, 蔡成林, 张首刚, 等. GNSS/地磁组合的室内外无缝定位平滑过渡方法［J］. 测绘通报, 2018(2): 30-34.

郭凯旋, 卢彦霖, 冯涛, 等. 基于智能切换算法的室内外无缝定位技术研究［J］. 传感器与微系统, 2018, 37(7): 49-51,55.

GAO H, GROVES P D. Environmental context detection for adaptive navigation using GNSS measurements from a smartphone［J］. Navigation, 2018, 65(5): 99-116. DOI: 10.1002/navi.221.

ZHU Y D, LUO H Y, WANG Q, et al. A fast indoor/outdoor transition detection algorithm based on machine learning［J］. Sensors, 2019, 19(4): 786-809. DOI: 10.3390/s19040786.

CHEN K Y, TAN G. SatProbe: low-energy and fast indoor/outdoor detection based on raw GPS processing［C］//IEEE INFOCOM 2017-IEEE Conference on Computer Communications. Atlanta, GA, USA: IEEE, 2017: 1-9. DOI: 10.1109/INFOCOM.2017.8057095.

ZENG Q H, WANG J X, MENG Q, et al. Seamless pedestrian navigation methodology optimized for indoor/outdoor detection［J］. IEEE sensors journal, 2018, 18(1): 363-374. DOI: 10.1109/JSEN.2017.2764509.

LEE B, LIM C, LEE K. Classification of indoor-outdoor location using combined global positioning system (GPS) and temperature data for personal exposure assessment［J］. Environmental health and preventive medicine, 2017, 22(1):29. DOI 10.1186/s12199-017-0637-4.

ASHRAF I, HUR S J, PARK Y W. MagIO: magnetic field strength based indoor-outdoor detection with a commercial smartphone［J］. Micromachines, 2018, 9(10): 534. DOI: 10.3390/mi9100534.

ZOU H, JIANG H, LUO Y W, et al. BlueDetect: an iBeacon-Enabled scheme for accurate and energy-efficient indoor-outdoor detection and seamless location-based service［J］. Sensors, 2016, 16(2): 268. DOI: 10.3390/s16020268.

SUNG R, JUNG S-H, HAN D. Sound based indoor and outdoor environment detection for seamless positioning handover［J］. ICT express, 2015, 1(3): 106-109. DOI: 10.1016/j.icte.2016.02.001.

KELISHOMI A E, GARMABAKI A H S, BAHAGHIGHAT M, et al. Mobile user indoor-outdoor detection through physical daily activities［J］. Sensors, 2019, 19(3): 511. DOI: 10.3390/s19030511.

SAFFAR I,ALBERI-MOREL M L,SINGH K D,et al. Machine learning with partially labeled data for indoor outdoor detection［C］//2019 16th IEEE Annual Consumer Communications & Networking Conference (CCNC), 2019. DOI: 10.1109/CCNC.2019.8651736.

SAFFAR I,ALBERI-MOREL M L,SINGH K D, et al. Semi-supervised deep learning-based methods for indoor outdoor detection［C］//IEEE International Conference on Communications (ICC), 2019. DOI: 10.1109/ICC.2019.8761297.

SPECHT D F. Probabilistic neural networks for classification, mapping, or associative memory［C］//IEEE 1988 International Conference on Neural Networks,1988. DOI: 10.1109/ICNN.1988.23887.