GPU based extraction of moving objects without shadows under intensity changes
GPU based extraction of moving objects without shadows under intensity changes
复制标题
DOI：
10.1109/cec.2008.4631366
复制
发表时间：
2008-06
期刊：
影响因子：
--
通讯作者：
S. Fukui;Y. Iwahori;R. Woodham
中科院分区：
文献类型：
--
作者：
S. Fukui;Y. Iwahori;R. Woodham
本文提出了一种基于GPU的实时提取运动物体的算法。该方法的整个过程都是在 GPU 上处理的。 GPU 用于加速，所提出的方法极大地提高了处理速度。该方法使用CIELAB色彩空间的a*分量和b*分量，而不将阴影区域提取为移动对象。它对强度变化具有鲁棒性，因为生成了估计的背景图像，并且使用估计的背景图像和观察到的图像的背景减法来提取移动对象。所提出的方法减少了将计算结果从GPU传输到CPU以及相反传输的次数。减少传输时间有助于加速所提出的方法。结果通过真实数据的实验得到证明。
This paper proposes a GPU based algorithm for extracting moving objects in real time. The whole process of the proposed approach is handled on GPU. GPU is used for acceleration and the proposed approach increases processing speed dramatically. The method uses a* component and b* component of CIELAB color space without extracting shadow areas as moving objects. It is robust to intensity changes because an estimated background image is generated and moving objects are extracted using background subtraction of the estimated background image and the observed image. The proposed method reduces the times for transferring calculation results from GPU into CPU and the opposite transfer. Reducing the transfer times contributes to speeding up of the proposed method. Results are demonstrated with experiments on real data.