Improving Location Accuracy by Combining Visual Tracking and Radio Positioning

無線定位技術和視訊追蹤技術具有以下幾個互補的特性。無線定位技術可以提供大範圍的定位，而在視訊追蹤系統中，只有當使用者經過攝影機的監控範圍時才能提供使用者的位置資訊。在另一方面，當使用者群聚的情況發生時，無線定位技術的定位結果會非常不準確，而在這個情形下，視訊追蹤系統卻可以取得一些準確的定位結果。因此，綜合以上兩種系統的優點，可以達到更好的定位效果。本文提出一個室內定位系統的架構，其中藉由視訊追蹤技術的輔助，以增進無線定位系統的精準度和穩定性。我們提出一個聯結方法，此方法考慮無線定位系統和視訊追蹤系統的觀測結果之軌跡和視覺影像，以決定此兩系統觀測結果之間的關聯方式，當無線節點和視訊目標間產生關聯，我們即可利用視訊追蹤的定位結果來修正此無線節點的無線定位系統結果，而其他的無線節點也根據此改變以取得更精確的結果，藉此我們可以提升整體無線定位系統的定位表現。我們所提出的系統架構可以應用在各種無線定位技術上。實驗結果証實，當使用者群聚的情況發生時，我們的系統在使用者位置固定和使用者移動的情形下，皆可以提供準確且穩定的定位結果。Radio positioning system and visual positioning system are complementary in several aspects. Radio positioning is capable of locating people in a large area, while visual positioning only monitors sub-areas covered by camera views. However, radio positioning could be completely unstable with people cluster while visual positioning can obtain some de nite observations within. As a result, taking advantage of the two systems leads to a preferable localization system. In this paper, we propose a framework that increases the accuracy and stability of the indoor radio positioning system by combining it with a supporting visual tracking system. An association method considering both trajectories and appearances is proposed to integrate the visual targets and the radio clients. Once the observations are associated, the location estimates of the radio clients are modi ed with those of the associated visual targets considered. After that, the results of the other radio clients are re ned by taking the modi cations into account. In this way, we can enhance the localization performance of the entire radio positioning system. The proposed framework can be applied to a variety of existing radio positioning techniques. The experimental results show its performance in preserving accuracy with people clusters in stationary and moving situations.1 Introduction 1 1.1 Related Work 3 1.2 System Architecture 5 2 Radio Positioning 9 2.1 ZigBee Properties 10 2.2 Fingerprinting 10 3 Visual Positioning 12 3.1 Single Camera Tracking 13 3.2 Homography Transformation 14 3.3 Color Calibration 15 4 Association Method 18 4.1 Association Matrix 19 4.2 Trajectory Similarity Matrix 19 4.3 Appearance Similarity Matrix 20 5 Radio Positioning Re nement 23 5.1 Enhancement for Visible Radio Clients 25 5.2 Enhancement for Other Radio Clients 26 6 Experimental Results 29 7 Conclusion and Future Work 36 Bibliography 3