基于改进PCNN模型的车辆阴影消除方法

消除车辆阴影对图像分割的影响是车辆自动监控系统中亟待解决的问题。针对阴影具有方向和大小不确定性的特点,充分利用脉冲耦合神经网络模型优良的图像分割能力,结合阴影属性,提出一种基于改进的脉冲耦合神经网络模型的运动车辆阴影消除方法。此方法无需建立道路背景模型与车辆阴影模型,在消除车辆阴影的同时能较好地保留车牌、车窗以及车标等车体的重要信息,为车体定位、特征提取等处理奠定良好的基础。大量现场图像测试结果验证了该方法消除车辆阴影的有效性,可广泛地应用于自然环境中车辆阴影的消除。

Method of Vehicle Shadow Elimination Based on Improved PCNN Model

Vehicle shadow elimination is one of the urgent problems to be solved in the automatic vehicle detection system.Taking advantage of the powerful segmentation ability of the pulse coupled neural networks(PCNN) model and combing with the shadow attributes,the new shadow elimination method based on the improved PCNN model was proposed in this paper.The proposed method can overcome difficulties of uncertainty of the shadow’s direction and size.Meanwhile,there is no need to build the background model and the shadow model.Experimental results show that this method eliminates shadow effectively and retains important bodywork information well,such as the license plate,window and vehicle-logo,and can be widely applied to vehicle shadow elimination in the natural environment.