以條件隨機域於相遇時合作定位

Collaborative Localization using Conditional Random Fields upon Encounter

陳奕霖(Chen, Yi Lin)

指導教授 ： 周百祥

國立清華大學/電機資訊學院/資訊工程學系/碩士(2015年)

摘要

我們提出一項綜合了行人推測航行法與相遇資訊的室內定位技術。裝置相遇可以透過近距離電磁波原理的通訊介面做為鄰近感測的機制。我們以條件隨機域(CRFs)為基礎，加上相遇時交換的軌跡與鄰近資訊， 相較於之前常用的顆粒過濾法，降低了演算的複雜度。實驗數據顯示我們不但減少運算能力的需求，更擴充了室內可定位的範圍。

關鍵字

室內定位 ； 條件隨機域 ； 相遇 ； 合作 ； 藍芽4.0 ； 軌跡合併

並列摘要

This thesis proposes a new indoor localization techniques that fuses pedestrian dead reckoning with encounter information. Encounter is detected by proximity sensing using short-range radio frequency(RF) also used for communication. Our work builds on conditional random fields(CRFs) for the lower computational complexity than the traditional particle filtering by incorporating information exchanged from the encounter, including the trajectory and proximity. Experimental results show that
we further lower the complexity and expand location coverage.

並列關鍵字

Indoor ； Localization ； Positioning ； Beacon ； BLE ； CRF ； Conditional Random Fields ； Encounter ； Proximity sensing ； Collaborative ； Trajectory merge

參考文獻

[1] ADIB, F., AND KATABI, D. See through walls with WiFi!, vol. 43. ACM, 2013.

[2] BAHL, P., AND PADMANABHAN, V. N. RADAR: An in-building RF-based user location and tracking system. In INFOCOM 2000. Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies. Proceedings. IEEE (2000), vol. 2, Ieee, pp. 775–784.

[4] BEAUREGARD, S., KLEPAL, M., ET AL. Indoor PDR performance enhancement using minimal map information and particle filters. In Position, Location and Navigation Symposium, 2008 IEEE/ION (2008), IEEE, pp. 141–147.

[8] CHAN, L.-W., CHIANG, J.-R., CHEN, Y.-C., KE, C.-N., HSU, J., AND CHU, H.-H. Collaborative localization: Enhancing WiFi-based position estimation with neighborhood links in clusters. In Pervasive Computing. Springer, 2006, pp. 50–66.

[9] CHANG, C.-M. Cooperative tracking using encounter information by particle filter.