Wang Yang, Loe Kia-Fock, Wu Jian-Kang
School of Computer Engineering, Nanyang Technological University, 50 Nanyang Drive, Singapore.
IEEE Trans Pattern Anal Mach Intell. 2006 Feb;28(2):279-89. doi: 10.1109/TPAMI.2006.25.
This paper proposes a dynamic conditional random field (DCRF) model for foreground object and moving shadow segmentation in indoor video scenes. Given an image sequence, temporal dependencies of consecutive segmentation fields and spatial dependencies within each segmentation field are unified by a dynamic probabilistic framework based on the conditional random field (CRF). An efficient approximate filtering algorithm is derived for the DCRF model to recursively estimate the segmentation field from the history of observed images. The foreground and shadow segmentation method integrates both intensity and gradient features. Moreover, models of background, shadow, and gradient information are updated adaptively for nonstationary background processes. Experimental results show that the proposed approach can accurately detect moving objects and their cast shadows even in monocular grayscale video sequences.
本文提出了一种动态条件随机场（DCRF）模型，用于室内视频场景中的前景物体和移动阴影分割。给定一个图像序列，基于条件随机场（CRF）的动态概率框架将连续分割场的时间依赖性和每个分割场内的空间依赖性统一起来。为DCRF模型推导了一种有效的近似滤波算法，以便根据观测图像的历史递归估计分割场。前景和阴影分割方法整合了强度和梯度特征。此外，针对非平稳背景过程，自适应更新背景、阴影和梯度信息模型。实验结果表明，即使在单目灰度视频序列中，该方法也能准确检测出移动物体及其投射的阴影。
