運用粒子濾波器以及慣性與視覺感測器為輔助之穿戴式定位科技

Abstract

近來由於大量手機應用程式的需求，室內定位已被深入的探討研究。雖然很多研究利用無線訊號或是航位推算的方法來做位置追蹤，但是可穿戴式計算的發展帶來了新的機遇和挑戰。在本篇論文，我們提出一個運用粒子濾波器為基礎的方法，來結合人體可穿戴的慣性及視覺感測器所得到的數據以達到穿戴式定位。具體來說，濾波器採用慣性感測器訊號、無線訊號、視覺性地標以及室內地圖來做位置追蹤。慣性感測器訊號能夠推論出人體移動路徑，無線訊號能指出人體在室內建築物的粗略絕對區域，而視覺性地標提供由某一特定位置觀看室內地標的相對角度。此外，光學頭戴式顯示器提供使用者一個直覺、友善的介面讓使用者能夠直覺的得知位置資訊。我們所提出的系統也已實作出來，並且在一個U型的建築物內實驗，實驗結果顯示平均誤差大約是一公尺左右，對於人類位置追蹤上是足夠的準確度。

Indoor positioning has been intensively studied recently due to the needs of a lot of indoor mobile applications. While many works have used wireless signals or dead-reckoning in location tracking, wearable computing poses new opportunities as well as challenges to the localization problem. The paper studies the wearable localization problem by proposing a Particle filter-based scheme to fuse the input data from wearable inertial and visual sensors on human body. Specifically, the filter takes inertial signals, wireless signals, visual landmarks, and indoor floor plans as inputs for location tracking. Inertial signals imply human movement, wireless signals indicate a rough absolute region inside a building, while visual landmarks provide relative angles viewing from a particular position to certain exact markers inside a building. Further, OHMD (optical head-mounted display) provides intuitive, friendly interfaces to users. The proposed system has also been prototyped and tested in a U-shape building and the experiments show an average localization error of about one meter.