Adaptive Low-power Localization Scheme for Pedestrians Based on LSTM Scene Classification

doi:10.3969/j.issn.1006-2475.2025.02.006

Abstract

Abstract: To address the challenges of pedestrian localization accuracy and high power consumption in outdoor complex environments， this paper proposes a low-power localization scheme based on scene classification for foot-mounted pedestrian navigation systems using GNSS/INS technology. This scheme collects GNSS， temperature and humidity sensor data， uses LSTM to classify typical outdoor scenes and adjusts the clock frequency of the MCU according to different scenes. Additionally， the scheme proposes an improved Sage-Husa method to mitigate the impact of GNSS outliers on localization results. The experimental results demonstrate that this solution achieves a scene classification accuracy of 97.64% with a system power consumption of only 193.074 mW. Compared with traditional ZUPT， GNSS， GNSS/INS integration and Sage-Husa methods， the proposed scheme reduces the root mean square localization error by 83.15%， 42.88%， 21.91% and 11.49% respectively. Therefore， this scheme can improve pedestrian localization accuracy in outdoor environments with low system power consumption.

Key words: pedestrian navigation system, low power, LSTM, scene classification, Sage-Husa algorithm

CLC Number:

TP391

YU Qing1, JIANG Jinguang1, 2, 3, XIE Dongpeng1, LIU Jianghua4. Adaptive Low-power Localization Scheme for Pedestrians Based on LSTM Scene Classification[J]. Computer and Modernization, 2025, 0(02): 44-51.

References

［1］ TIAN X C， CHEN J B， HAN Y Q， et al. Pedestrian navigation system using MEMS sensors for heading drift and altitude error correction［J］. Sensor Review， 2017，37（3）：270-281.
［2］杨辉. 基于MEMS传感器的高精度行人导航算法研究［D］. 厦门：厦门大学， 2014.
［3］ GU Y， SONG Q， LI Y H， et al. An anchor-based pedestrian navigation approach using only inertial sensors［J］. Sensors， 2016，16（3）. DOI： 10.3390/s16030334.
［4］ BIRD J， ARDEN D. Indoor navigation with foot-mounted strapdown inertial navigation and magnetic sensors ［Emerging Opportunities for Localization and Tracking］［J］. IEEE Wireless Communications， 2011，18（2）：28-35.
［5］ HARLE R. A survey of indoor inertial positioning systems for pedestrians［J］. IEEE Communications Surveys & Tutorials， 2013，15（3）：1281-1293.
［6］ SKOG I， HANDEL P， NILSSON J O， et al. Zero-velocity detection—An algorithm evaluation［J］. IEEE Transactions on Biomedical Engineering， 2010，57（11）：2657-2666.
［7］ ZHANG R， YANG H， HÖFLINGER F， et al. Adaptive zero velocity update based on velocity classification for pedestrian tracking［J］. IEEE Sensors Journal， 2017，17（7）：2137-2145.
［8］周彬，赵万良，荣义杰，等. 基于MEMS-INS/GNSS组合导航抗差自适应Kalman滤波算法［J］. 导航与控制， 2018，17（4）：14-20.
［9］ XU Y， WANG K， JIANG C H， et al. Motion-constrained GNSS/INS integrated navigation method based on BP neural network［J］. Remote Sensing， 2023， 15（1）. DOI： 10.3390/rs15010154.
［10］杨元喜，宋力杰，徐天河. 大地测量相关观测抗差估计理论［J］. 测绘学报， 2002（2）：95-99.
［11］杨元喜. 自适应抗差最小二乘估计［J］. 测绘学报， 1996（3）：206-211.
［12］ YANG R， ZHANG A J， ZHANG L F， et al. A novel adaptive H-infinity cubature Kalman filter algorithm based on Sage-Husa estimator for unmanned underwater vehicle［J］. Mathematical Problems in Engineering， 2020，2020. DOI： 10.1155/2020/8057028.
［13］ LIU R X， LIU F C， LIU C N， et al. Modified Sage-Husa adaptive Kalman filter-based SINS/DVL integrated navigation system for AUV［J］. Journal of Sensors， 2021，2021. DOI： 10.1155/2021/9992041.
［14］ QIAO S H， FAN Y S， WANG G F， et al. Radar target tracking for unmanned surface vehicle based on square root Sage-Husa adaptive robust Kalman filter［J］. Sensors， 2022，22（8）. DOI： 10.3390/s22082924.
［15］朋子涵，高成发，尚睿. 顾及新息向量的Sage-Husa滤波在手机GNSS定位中的应用［J］. 导航定位学报， 2020，8（2）：76-81.
［16］ TAO X L， ZHU F， HU X， et al. An enhanced foot-mounted PDR method with adaptive ZUPT and multi-sensors fusion for seamless pedestrian navigation［J］. GPS Solutions， 2022，26. DOI 10.1007/s10291-021-01196-x.
［17］ DENG Z H， WANG P Y， LIU T， et al. Foot-mounted pedestrian navigation algorithm based on BOR/MINS integrated framework［J］. IEEE Transactions on Industrial Electronics， 2020，67（5）：3980-3989.
［18］ RODRIGUES R T， BASIRI M， AGUIAR A P， et al. Low-level active visual navigation： Increasing robustness of vision-based localization using potential fields［J］. IEEE Robotics and Automation Letters， 2018，3（3）：2079-2086.
［19］ CAMPOS C， ELVIRA R， RODRÍGUEZ J J G， et al. ORB-SLAM3： An accurate open-source library for visual， visual-inertial， and multimap SLAM［J］. IEEE Transactions on Robotics， 2021，37（6）：1874-1890.
［20］ BAE H J， CHOI L. Large-scale indoor positioning using geomagnetic field with deep neural networks［C］// 2019 IEEE International Conference on Communications （ICC 2019）. IEEE， 2019：1-6.
［21］旷俭. 基于捷联PDR和磁场特征匹配的智能手机多源室内定位算法研究［D］. 武汉：武汉大学， 2021.
［22］黄智昌，尚京威. 面向复杂机房环境的室内定位技术应用研究［J］. 计算机与现代化， 2022（11）：102-110.
［23］ YU K， WEN K， LI Y B， et al. A novel NLOS mitigation algorithm for UWB localization in harsh indoor environments［J］. IEEE Transactions on Vehicular Technology， 2019，68（1）：686-699.
［24］ KANATAS A G， CONSTANTINOU P. A narrowband land mobile satellite channel software simulator for urban environments［J］. International Journal of Satellite Communications， 2000，18（1）：17-45.
［25］王椿珊. 基于低功耗优化技术的16位MCU设计［D］. 西安：西安电子科技大学， 2016.
［26］李钢. 无线供电低功耗感测标签及系统关键技术研究［D］.成都：电子科技大学， 2023.
［27］ AGGARWAL P， SYED Z， NOURELDIN A， et al. MEMS-Based Integrated Navigation［M］. Artech House Publishers， 2010.
［28］ LECUN Y， BENGIO Y， HINTON G. Deep learning［J］. Nature， 2015，521（7553）：436-444.
［29］杨丽，吴雨茜，王俊丽，等. 循环神经网络研究综述［J］. 计算机应用， 2018，38（S2）：1-6.

[1]	LIU Baobao, YANG Jingjing, TAO Lu, WANG Heying . DSMSC Based on Attention Mechanism for Remote Sensing Image Scene Classification [J]. Computer and Modernization, 2024, 0(12): 72-77.
[2]	GONG Yicheng1, 2, LIU Qing1, 2. Beijing Opera Binary Classification Based on RF-LCE-BiLSTM-Attention-AMSSA Model [J]. Computer and Modernization, 2024, 0(11): 7-12.
[3]	LI Junchao1, YOU Fei1, ZHANG Chao2, SU Lele2, GONG Yan2 . BiLSTM-Attention Prediction Model and Error Analysis #br# Based on Novel Multi-objective Coati Optimization Algorithm [J]. Computer and Modernization, 2024, 0(11): 70-76.
[4]	LI Jin1, WEI Yanlong1, XUE Hongxin2, LIANG Haijian2. Influenza-like Illness Prediction Based on LSTM-SIR-EAKF [J]. Computer and Modernization, 2024, 0(09): 38-44.
[5]	ZHAO Dun1, SHE Xuebing2, WU Changxing3. Named Entity Recognition in Field of Party Building Based on BERT-BiLSTM-CRF [J]. Computer and Modernization, 2024, 0(09): 91-94.
[6]	ZHENG Li-rui, XIAO Xiao-xia, ZOU Bei-ji, LIU Bin, ZHOU Zhan. Named Entity Recognition in Electronic Medical Record Based on BERT [J]. Computer and Modernization, 2024, 0(01): 87-91.
[7]	FENG Xin-xin, BU Lei, ZHANG Xiao-yu, SHI Yu-feng. Analyzing to Shield Tunnel Segments Deformation Data Based on ICEEMDAN-LSTM [J]. Computer and Modernization, 2023, 0(11): 57-61.
[8]	PAN Si-yuan, ZHANG Wei. SOC Estimation of Lithium Battery Based on Improved LSTM [J]. Computer and Modernization, 2023, 0(08): 25-30.
[9]	ZHANG Zhi-xia, XIE Bao-qiang. Natural Gas Load Forecasting Based on FCGA-LSTM and Transfer Learning [J]. Computer and Modernization, 2023, 0(07): 7-12.
[10]	WEI Xin, HE Xiao-hai, TENG Qi-zhi, QING Lin-bo, CHEN Hong-gang. Event Extraction Method Based on BERT-BiLSTM-Attention Hybrid Model [J]. Computer and Modernization, 2023, 0(04): 26-31.
[11]	ZHU Yuan-ye, NI Jian-jun, TANG Guang-yi. An RGB-D Indoor Scene Classification Method Based on Improved Convolutional Neural Network [J]. Computer and Modernization, 2023, 0(04): 73-77.
[12]	WANG Yi-ting, XING Ben-bei, LI Bin, LIU Ge, ZHANG Xiang-yu. Fuel Consumption Prediction Method of Heavy Trucks with Different Accelerating Driving Behaviors Based on Shared-LSTM [J]. Computer and Modernization, 2023, 0(03): 121-126.
[13]	ZHU Ya-jun, Yong Tso, Nyima Tashi, . Tibetan Medical Entity Recognition Based on Tibetan BERT [J]. Computer and Modernization, 2023, 0(01): 43-48.
[14]	YIN Chun-jie, XIAO Fa-da, LI Peng-fei, ZHAO Qin. Short-term Load Forecasting of Regional Microgrid Based on LSTM Neural Network [J]. Computer and Modernization, 2022, 0(04): 7-11.
[15]	OUYANG Meng-ke, SHEN Wei-kang, CHENG Hui, SHI Kai. Short-term Load Forecasting Model Based on VMD and MOGOA-LSTM [J]. Computer and Modernization, 2022, 0(03): 7-12.