基於多重攝影機定位之人物軌跡分析

Abstract

在以視覺為基礎的監控系統中，人物的定位以及追蹤一直是個重要而且具有挑戰性的工作，也不斷發展出相關的技術與應用。近年來，有許多利用多台攝影機的研究方法被提出來，以處理人物之間互相遮蔽的問題。在本論文中我們提出了一個有效的追蹤系統，利用整合多重攝影機所截取的畫面，在人群擁擠且互相遮蔽的情況下也能夠準確地定位以及追蹤人物。對於影像的前景區域，我們以消失點為基礎建立二維樣本線段，並將之投影於地面，而後透過分析線段相交密集處找出可能的立足點，有效限縮人物位置在地面的可能範圍。利用二維前景影像區塊，我們可以對人物立足點可能區域做進一步的篩選與驗證，有效率地估計出人物的位置與高度。接著我們利用估測出來的位置，使用常見的人物移動的速度及方向之假設，對人物移動軌跡進行追蹤。實驗結果顯示，追蹤的結果確實可以進一步提升人物定位的準確性。

People localization and tracking has always been an important and challenging task in vision-based surveillance system, and the growing number of developed techniques has created a lot of applications. In recent years, a lot of approaches of people localization and tracking have been proposed to deal with occlusion problem using multiple cameras. In this study, we propose an effective system which is capable of locating and tracking a crowd of dense people, using multiple cameras. For each camera view, line samples, originated from a vanishing point, of foreground objects are projected on the ground plane. Ground regions containing a high density of projected lines are then used to find possible people locations, which greatly reduce the computation complexity. Furthermore, people heights can also be estimated. The detected locations are then tracked using common assumptions on motion direction and velocity. Experimental results show that with the help of the tracking process, the accuracy of people locations can also be improved.