Mobiilsete sensorite integratsioonil põhinev reaalajaline lokaliseerimine ja jälgimissüsteem
Files
Date
2018
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Nutitelefoni tõusuga ja nendesse paigaldatud anduritega on tekkinud lõputult teaduslikke uurimisvõimalusi, ilma kallist riistvara omamata. Selles töös tutvustatakse uut algoritmi, mis võimaldab jälgida ja lokaliseerida sõidukit reaalajas, kasutades Android OS nutitelefoni GPS-i, kiirendusmõõturi ja güroskoobi andmevoogusid. Loodud algoritm võib reageerida kiiruse muutustele ja auto pööretele reaalajas ilma GPS-i sisendita. See tähendab, et algoritm saab hinnata sõiduki positsiooni, kui GPS andmevoog ei ole teadmata ajahulgal saadaval. Tulemused on paljutõotavad ja näitavad, et algoritm toimib hästi nii täpsuse kui ka reaalajas reageerimisega. Isegi ilma GPS infota 30 sekundit jooksul suudab algoritm hinnata sõiduki asukohta 25 meetrilise keskmise täpsusega.
With the rise of the smartphone, new research opportunities have emerged. With a wide array of sensors that are available in today’s smartphones, the research possibilities are endless. In this work, we present a new algorithm that can track and localise a vehicle in real-time using the GPS, accelerometer and gyroscope data streams from an Android OS smartphone. The resulting algorithm can respond to speed changes, and the car turns in real-time without any info from the GPS. This means that the algorithm can estimate the vehicle position if the GPS data stream is unavailable for unknown amounts of time. Results are promising and show that the algorithm performs well both in accuracy andreal-time responsiveness. Even without 30 seconds of GPS info, the algorithm is able to estimate the vehicle location with an average accuracy of 25 meters.
With the rise of the smartphone, new research opportunities have emerged. With a wide array of sensors that are available in today’s smartphones, the research possibilities are endless. In this work, we present a new algorithm that can track and localise a vehicle in real-time using the GPS, accelerometer and gyroscope data streams from an Android OS smartphone. The resulting algorithm can respond to speed changes, and the car turns in real-time without any info from the GPS. This means that the algorithm can estimate the vehicle position if the GPS data stream is unavailable for unknown amounts of time. Results are promising and show that the algorithm performs well both in accuracy andreal-time responsiveness. Even without 30 seconds of GPS info, the algorithm is able to estimate the vehicle location with an average accuracy of 25 meters.