Download presentation
Presentation is loading. Please wait.
1
Using Digital Trajectory
Indoor Localization Using Digital Trajectory Zhang Jingcong
2
1 2 3 4 Background & Related work My Research & Analysis OUTLINE
Experiment & Result 4 Summary & Future work
3
Using Digital Trajectory
Background & Related work Indoor Localization Using Digital Trajectory TOPIC
4
Dead Reckoning Indoor Localization Using Digital Trajectory TOPIC
No accurate Background & Related work Dead Reckoning Indoor Localization Using Digital Trajectory TOPIC
5
Indoor Localization GPS Fingerprinting Using Digital Trajectory TOPIC
No accurate Background & Related work GPS No accuracy Indoor Localization Using Digital Trajectory Fingerprinting TOPIC - Online:construction of RM - Offline:localization based on RM Wi-Fi RSS(received signal strength) AP(access point)s AP1 AP2 AP3
6
Indoor Localization GPS Fingerprinting Using Digital Trajectory TOPIC
Background & Related work GPS No accuracy Indoor Localization Using Digital Trajectory Fingerprinting TOPIC noise reflection diffraction etc. channel accuracy density of fingerprints
7
with fewer fingerprint samples
My Research & Analysis target improve the accuracy with fewer fingerprint samples use Android smartphone embedded sensors to build a digital trajectory solution
8
WI-fi fingerprinting More accurate result Trajectory construction
My Research & Analysis More accurate result WI-fi fingerprinting Particle Filter Trajectory construction
9
My Research & Analysis trajectory building-using Android
10
orientation & acceleration
My Research & Analysis trajectory building-using Android DETECTPV SENSORS orientation & acceleration ALGORITHM:DEAD RECKONING INPUT:a location fix f=(fx,fy) acceleration a=(ax,ay,az) OUTPUT:trajectory tr={(x1,y1),(x2,y2),…} while new a do |a|=sqrt(ax^2+ay^2+az^2); if detectPV(|a|)=true then calculate distance l; get theta θ; tr.add((xprev+l*sinθ,yprev+l*θ)); end using PV(peak-valley) detection to decide a step digital trajectory
11
N Particle Filter State Obser- vation Kalman Filter Estimation
My Research & Analysis Kalman Filter & Particle Filter Particle Filter State weight Obser- vation Kalman Filter Estimation variance Obser- vation N State Trajectory WiFi fingerprint
12
Experiment & Result Trajectory building
13
Experiment & Result Kalman Filter truth observed filtered
14
Generate a digital trajectory based on Android sensors
Summary & Future work summary Generate a digital trajectory based on Android sensors Use Kalman fliter to get a better estimation future work Do experiment with real scene Use Particle fliter instead of Kalman filter Improve the Android program
15
Reference Yang Liu, Marzieh Dashti, Jie Zhang.Indoor Localization on Mobile Phone Platforms Using Embedded Inertial Sensors Xiuming Zhang, Yunye Jin, Hwee-Xian Tan and Wee-Seng Soh.CIMLoc: A Crowdsourcing Indoor Digital Map Construction System for Localization
16
Q&A
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.