使用一維積分影像加速基於機率占有圖之人物定位

Acceleration of Probabilistic Occupancy Map-Based People Localization Using 1-D Integral Image

蕭晶如(Ching-Ju Hsiao)

指導教授 ： 莊仁輝

國立交通大學/資訊學院/多媒體工程研究所/碩士(2015年)

https://doi.org/10.6842/NCTU.2015.00738

摘要

隨著視覺監控系統的普及，人物定位技術所能達到的準確性與速度愈來愈受到重視。機率佔有圖(Probabilistic Occupancy Map, POM)人物定位方法因為在劇烈的光線變化和部分遮蔽的情況下能擁有好的定位結果，所以是現有方法的主流之一。然而POM方法為了推論人所在位置的機率，因此需要不斷地計算機率的二維積分影像，這導致POM方法運算速度緩慢。為了有效提升POM方法的運算速度，減少需要計算的影像像素，本論文從影像垂直消失點產生等間距的前景物體線取樣，並沿著這些線段做一維積分影像。實驗結果顯示，本論文提出的方法能有效的提升POM方法的運算速度，並維持和POM近似的定位結果。

關鍵字

人物定位 ； 線取樣 ； 機率占有圖 ； 積分影像 ； 多攝影機

並列摘要

With the popularity of vision-based surveillance system, the improvement in accuracy and efficiency of people localization has got lots of attention. Recently, using probabilistic occupancy map (POM) becomes one of main approaches to people localization because of its great localization accuracy under severe occlusions and lighting changes. To estimate the probabilities of people locations, 2-D integral images are used iteratively, which would be time-consuming during the process of the POM-based approach. To enhance the efficiency of the POM approach, we propose the use of 1-D integral images which are produced for foreground object in an image along equally-spaced line samples originated from the vanishing point of vertical lines (VPVL). Experimental results show that the proposed approach does improve the efficiency of the POM approach, with little sacrifice in the accuracy of people localization.

並列關鍵字

people localization ； line sampling ； probability occupancy map ； integral image ； multi-camera

參考文獻

[3] R. T. Collins, "Mean-shift blob tracking through scale space," in Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference on, 2003, pp. II-234-40 vol. 2.

[4] H. Wang, D. Suter, K. Schindler, and C. Shen, "Adaptive object tracking based on an effective appearance filter," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 29, pp. 1661-1667, 2007.

[6] J. Fan, W. Xu, Y. Wu, and Y. Gong, "Human tracking using convolutional neural networks," Neural Networks, IEEE Transactions on, vol. 21, pp. 1610-1623, 2010.

[9] S. Nedevschi, S. Bota, and C. Tomiuc, "Stereo-based pedestrian detection for collision-avoidance applications," Intelligent Transportation Systems, IEEE Transactions on, vol. 10, pp. 380-391, 2009.

[10] S. M. Khan and M. Shah, "Tracking multiple occluding people by localizing on multiple scene planes," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 31, pp. 505-519, 2009.