基于先驗特征的礦下人員定位校準(zhǔn)方法
doi: 10.11999/JEIT170749
-
2.
(燕山大學(xué)電氣工程學(xué)院 秦皇島 066004) ②(河北省工業(yè)計算機控制工程重點實驗室 秦皇島 066004) ③(上海交通大學(xué)電子信息與電氣工程學(xué)院 上海 200240)
河北省自然科學(xué)基金(F2017203084),河北省博士后優(yōu)先資助項目(B2017003009)
Positioning and Calibration Method of Underground Personnel Based on Priori Features
-
2.
(School of Electrical Engineering, Yanshan University, Qinhuangdao 066004, China)
The Natural Science Foundation of Hebei Province (F2017203084), The Postdoctoral Priority Funding of Hebei Province (B2017003009)
-
摘要: 針對目前人員定位方法普遍存在易受環(huán)境影響,累計誤差大等問題,該文提出一種利用地圖先驗知識與井下人員行進(jìn)方向識別相結(jié)合的位置校正方法。該方法首先通過線性判別分析(LDA)降低傳感器特征集的維度,之后利用隨機森林(RF)與設(shè)置閾值的方法對井下人員的行進(jìn)方向分類并標(biāo)記特殊點,將特殊點與巷道結(jié)構(gòu)的先驗知識進(jìn)行匹配,修正并更新通過步行者航位推算算法(PDR)得到的井下人員的初步運動軌跡。實驗結(jié)果表明:LDA的預(yù)處理方法能夠有效提高后續(xù)分類器的精度高達(dá)6%以上。該文提出的位置估算方法能夠有效減小累積誤差,具有較高的準(zhǔn)確性和魯棒性,活動識別精度能夠達(dá)到98%,可以實現(xiàn)可靠的實時定位。Abstract: Focusing on the problem that the personnel positioning methods are seriously influenced by the indoor environment, big cumulative error and other issues, a method is proposed to correct the position, which combines the prior knowledge of the map and the heading recognition. Firstly, the dimension of the feature set is reduced by Linear Discriminant Analysis (LDA). Then, the heading of the underground personnel is classified and the special points are marked through combining Random Forest (RF) and the method of setting a threshold value. Finally, the movement trajectory of the underground personnel, which is obtained by the Pedestrian Dead Reckoning (PDR) algorithm, is corrected and updated by matching the special point with the prior knowledge of the roadway structure. The experimental results show that the pre-processing method of LDA can effectively improve the precision of the classifier by more than 6%. The proposed method can effectively reduce the cumulative error, with high accuracy and robustness. The activity recognition accuracy can reach 98%, which can achieve reliable real- time location.
-
El ASSAF A, ZAIDI S, AFFES S, et al. Accurate sensors localization in underground mines or tunnels[C]. IEEE International Conference on Ubiquitous Wireless Broadband, Montreal, Canada, 2015: 1-6. doi: 10.1109/ICUWB.2015. 7324418. 劉文遠(yuǎn), 呂倩, 王林, 等. 基于動態(tài)地標(biāo)的在線室內(nèi)平面圖生成方法[J]. 電子與信息學(xué)報, 2016, 38(6): 1519-1527. doi: 10.11999/JEIT150926. LIU Wenyuan, L Qian, WANG Lin, et al. Multidimensional fingerprints method for indoor mobile trajectory mapping with geomagnetic information[J]. Journal of Electronics Information Technology, 2016, 38(6): 1519-1527. doi: 10.11999/JEIT150926. YE Y, ZHANG L, SONG X, et al. A novel coal mine security monitoring system based on ZigBee[C]. International Conference on Intelligent Transportation, Big Data and Smart City, Halong Bay, Vietnam, 2015: 39-42. doi: 10.1109/ ICITBS.2015.16. MI J and TAKAHASHI Y. Low cost design of HF-band RFID system for mobile robot self-localization based on multiple readers and tags[C]. IEEE International Conference on Robotics and Biomimetics, Zhuhai, China, 2015: 194-199. doi: 10.1109/ROBIO.2015.7418766. LI J and LIU H P. A new weighted centroid localization algorithm in coal Mine wireless sensor networks[C]. International Conference on Computer Research and Development, Shanghai, China, 2011: 106-109. doi: 10.1109 /ICCRD.2011.5764256. WANG Jie, GAO Qinghua, YU Yan, et al. Toward robust indoor localization based on bayesian filter using chirp- spread-spectrum ranging[J]. IEEE Transactions on Industrial Electronics, 2012, 59(3): 1622-1629. doi: 10.1109/TIE.2011. 2165462. WANG Jie, GAO Qinghua, Pan Miao, et al. Toward accurate device-free wireless localization with a saddle surface model[J]. IEEE Transactions on Vehicular Technology, 2016, 65(8): 6665-6677. doi: 10.1109/TVT.2015.2476495. FAN Qigao, SUN Biwen, SUN Yan, et al. Performance enhancement of MEMS-based INS/UWB integration for indoor navigation applications[J]. IEEE Sensors Journal, 2017, 17(10): 3116-3130. doi: 10.1109/JSEN.2017.2689802. 谷陽, 宋千, 李楊寰, 等. 基于慣性鞋載傳感器的人員自主定位粒子濾波方法[J]. 電子與信息學(xué)報, 2015, 37(2): 484-488. doi: 10.11999/JEIT140362. GU Yang, SONG Qian, LI Yanghuan, et al. A particle filter method for pedestrian navigation using foot-mounted inertial sensors[J]. Journal of Electronics Information Technology, 2015, 37(2): 484-488. doi: 10.11999/JEIT140362. 何堅, 萬志江, 劉金偉. 基于電源線和位置指紋的室內(nèi)定位技術(shù)[J]. 電子與信息學(xué)報, 2014, 36(12): 2902-2908. doi: 10.3724 /SP.J.1146.2013.02022. HE Jian, WAN Zhijiang, and LIU Jinwei. Indoor positioning technology based on powerline and location fingerprint[J]. Journal of Electronics Information Technology, 2014, 36(12): 2902-2908. doi: 10.3724/SP.J.1146.2013.02022. YUAN Yazhou, CHEN Cailian, GUAN Xinping, et al. An energy-efficient underground localization system based on heterogeneous wireless networks[J]. Sensors, 2015, 15(6): 12358-12376. doi: 10.3390/s150612358. INDERST F, PASCUCCI F, and RENAUDIN V. PDR and GPS trajectory parts matching for an improved self- contained personal navigation solution with handheld device[C]. Navigation Conference, Lausanne, Switzerland, 2017: 100-107. doi: 10.1109/EURONAV.2017.7954198. ROHRIG C and MULLER M. Localization of sensor nodes in a wireless sensor network using the nanoLOC TRX transceiver[C]. Vehicular Technology Conference, Barcelona, Spain, 2009: 1-5. HOF A L. Scaling gait data to body size[J]. Gait Posture, 1996, 4(3): 222-223. doi: 10.1016/0966-6362(95)01057-2 LI Yili and WONG Konmax. Riemannian distances for signal classification by power spectral density[J]. IEEE Journal of Selected Topics in Signal Processing, 2013, 7(4): 655-669. doi: 10.1109/JSTSP.2013.2260320. YANG Jian, ZHANG D, FRANGI A F, et al. Two- dimensional PCA: A new approach to appearance-based face representation and recognition.[J]. IEEE Transactions on Pattern Analysis Machine Intelligence, 2004, 26(1): 131-137. doi: 10.1109/TPAMI.2004.1261097. MARTINEZ A M and KAK A C. PCA versus LDA[J]. IEEE Transactions on Pattern Analysis Machine Intelligence, 2002, 23(2): 228-233. TORRES G A and BENITEZ V H. Finger movements classification from grasping spherical objects with surface electromyography using time domain based features[C]. Mechatronics, Adaptive and Intelligent Systems, Hermosillo, Mexico, 2016. doi: 10.1109/MAIS.2016.7761904. SVETNIK V, LIAW A, TONG C, et al. Random forest: A classification and regression tool for compound classification and QSAR modeling[J]. Journal of Chemical Information Computer Sciences, 2003, 43(6): 1947-1958. doi: 10.1021/ ci034160g. -
計量
- 文章訪問數(shù): 1462
- HTML全文瀏覽量: 187
- PDF下載量: 149
- 被引次數(shù): 0