针对现有背景建模方法对局部光照突变非常敏感的问题,提出了一种新的时间和空间中心对称局部二值模式(TSCS-LBP)算子,并基于该算子的直方图设计了一种背景建模方法。TSCS-LBP算子在中心对称局部二值模式(CS-LBP)算子的基础上加入时域信息和中心像素信息,并引入有光照因子的自适应阈值,从而在保持较低计算复杂度的基础上,具有能够快速适应光照突变的能力。在此基础之上设计的背景建模方法,能够在常用实验场景中较为准确地检测出前景,有较高的抗噪性和检测精度;同时在有局部光照突变的特殊场景中也有很好的适应能力,与已有方法相比有较高的优越性。实验结果表明了本文方法的有效性和鲁棒性。

The existing background modeling algorithms are in general quite sensitive to local illumination mutation in the scene. Therefore, a new temporal and spatial center-symmetric local binary pattern (TSCS-LBP) operator is proposed, and a background modeling algorithm based on the TSCS-LBP histogram is designed. The proposed operator extracts temporal information based on the center-symmetric local binary pattern (CS-LBP) operator. Considering the lighting environment, the pixel gray value itself has an important role. So the proposed operator includes the center pixel value information. Meanwhile, this operator uses the Niblack algorithm as the threshold of the local binary pattern. The threshold has an illumination factor, which can adjust adaptively according to the lighting situations in different regions. Owing to these techniques, the proposed operator can adapt to local illumination mutation quickly, while keeping a low computational complexity. The background modeling algorithm based on the proposed TSCS-LBP operator can detect foreground objects more accurately in the common experimental scene, and has higher noise immunity and testing accuracy. Meanwhile, the proposed algorithm has a good ability to adapt to scenes having local illumination mutation and it is better than existing algorithms. The experimental results prove the effectiveness and robustness of the proposed algorithm.