本文選題：行人導航定位 + 神經(jīng)網(wǎng)絡(luò)(BP)　； 參考：《重慶郵電大學學報(自然科學版)》2016年02期

【摘要】：目前大多行人導航系統(tǒng)的研究都以手持手機、綁在腰間等單一姿態(tài)為前提,并未考慮行人使用手機過程中同時存在接電話、放在上衣口袋等多種姿態(tài)的情況。分析了行人使用手機的4種常見姿態(tài),基于行人航跡推算(pedestrian dead reckoning,PDR)算法設(shè)計了一種改進的行人導航算法。利用神經(jīng)網(wǎng)絡(luò)(back propagation,BP)模型對手機姿態(tài)進行智能識別,設(shè)計了一種新的步態(tài)檢測算法來對多姿態(tài)下的步態(tài)進行有效檢測,并將行人行走過程分為單一姿態(tài)與姿態(tài)切換過程,對2個過程的航向進行了修正。軟件測試結(jié)果表明,多姿態(tài)下實現(xiàn)系統(tǒng)定位精度在20‰以內(nèi),達標率在85%以上,應(yīng)用于導航系統(tǒng)能夠提供準確、可靠、持續(xù)的位置信息。
[Abstract]:At present, most of the research on pedestrian navigation system is based on handheld mobile phone, tied to the waist and other single posture, and does not consider that there are many gestures such as answering the phone and putting it in the coat pocket in the process of using the mobile phone. Based on the analysis of four common postures of mobile phones, an improved pedestrian navigation algorithm is designed based on the pedestrian trajectory estimation algorithm. A new gait detection algorithm is designed based on the neural network back propagation (BP) model to detect the mobile phone posture effectively, and the walking process is divided into a single posture and attitude switching process. The course of the two processes is modified. The software test results show that the positioning accuracy of the system is less than 20 鈥，

本文編號：1856162