基於物體移動資訊及外觀資訊於擁擠環境中有效率的行人偵測

在監視系統影片分析的系統裡，於擁擠環境中偵測行人一直是一個具挑戰性且對於分析很有幫助的一個問題。我們提出整合外觀資訊以及物體移動資訊的一個有效率的偵測行人方法。首先將移動的像素利用背景去除的方法取出來，接著使用一個過濾的步驟來減少模板的比對區塊。此外，我們使用了積分圖片(Integral Image)的方式快速地計算每個影格中的邊緣分佈來分析形狀，並提出一個能夠偵測部份與完整身形的機率分析方法。我們以稀疏輪廓(Sparse contour)來表示代表性的身形模板，並利用資料點分佈模型(Point Distribution Model)概念產生身形的稀疏輪廓。我們進而提出了以回歸方法幫助適性調整模板比對視窗的大小。在多尺寸模板方法以及前景比例過濾方法的幫助下，實驗證明了我們的方法不但可以更有效率的偵測行人還可以增加整個偵測結果的準確度。

關鍵字

行人偵測；監視影片；稀疏輪廓；模板比對；積分圖片； GPU加速；擁擠環境

並列摘要

Detecting human in crowded environment is profitable but challenging in video surveillance. We propose an efficient human detection method by combining both motion and appearance clues. Moving pixels are first extracted by background subtraction, and then a filtering step is used to narrow the range for human template matching. We utilize integral images to fast generate shape information from edge maps of each frame and define the matching probability to be capable of detecting both full-body and partial-body. Representative human templates are constructed by sparse contours on the basis of the point distribution model (PDM). Moreover, linear regression analysis is also applied to adaptively adjust the template sizes. With the aid of the proposed foreground ratio filtering and the multi-sized template matching techniques, experimental results show that our method not only can efficiently detect human in a crowded environment but also largely enhance the resultant detection accuracy.

並列關鍵字

Human detection ； pedestrian detection ； surveillance video ； sparse human contour ； template matching ； integral image ； GPU acceleration ； crowded scene

參考文獻

[1] C. R. Wren, A. Azarbayejani, T. Darrell and A. P. Pentland, "Pfinder: Real-time tracking of the human body," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 780-785, 1997.

[2] C. Stauffer and W. E. L. Grimson, "Adaptive background mixture models for real-time tracking," in Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, pp. 246-252, 1999.

[3] B. Wu and R. Nevatia, "Detection of multiple, partially occluded humans in a single image by bayesian combination of edgelet part detectors," in Proc. IEEE Int. Conf. on Computer Vision, pp. 90-97, 2005.

[7] N. Dalal and B. Triggs, "Histograms of oriented gradients for human detection," in Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, pp. 886-893, 2005.

[8] D. M. Gavrila and J. Giebel, "Shape-based pedestrian detection and tracking," in Proc. IEEE Intelligent Vehicle Symposium, pp. 8-14, 2002.

國際替代計量

基於物體移動資訊及外觀資訊於擁擠環境中有效率的行人偵測

全文下載

主題瀏覽