BP神经网络和遗传算法在货车车锁检测中的应用

Application of BP Neural Network and Genetic Algorithm in Lock Detection of Freight Train

为实现货车自动检测记录系统 ,需要根据货车的图像检测进站货车车锁是否存在 .提出一种基于 BP神经网络和遗传算法的货车车锁检测方法 .首先提取图像的投影特征、边缘图像的矩向量特征以及灰度直方图特征 ,然后用 BP神经网络进行检测和定位 ;同时引入遗传算法 ,利用遗传算法的高并行性和鲁棒性 ,可以较快地完成全局搜索 ,而不会陷入局部最优 .实验结果表明 ,该方法能有效地克服货车车锁种类多、变形大以及光照变化的影响 ,具有较高的检测速度和检测成功率 .

To realize automatic detection and recording system of freight train, it's necessary to detect from the train image whether the locks exist. First the projection feature, moment vector feature of edge image, and the feature of gray histogram are extracted, and then BP neural network is used for detecting and locating the lock. At the same time, genetic algorithm is used to speed up searching the whole image with parallel and robust processing. Experiment results show that the method can overcome the problems of variety in lock types, image deformation and variation of environmental brightness, and enhances the speed and success rate of detection.