基于改进SPCNN模型的机场跑道胶痕检测方法

Airport runway rubber mark detection method based on improved simplified pulse-coupled neural network

针对机场跑道胶痕形态特征多样性和跑道环境复杂性导致胶痕检测效率低下的问题,提出了基于改进简化脉冲耦合神经网络模型的机场跑道胶痕图像分割算法。首先在利用邻域灰度关系优化反馈输入的基础上,将神经元点火阈值机制从传统的指数衰减改进为线性分层步长衰减。然后引入杜鹃搜索算法,结合最小交叉熵对改进模型进行参数寻优。最后根据点火映射区域的平均灰度值构建自适应迭代终止条件。实验结果表明,该算法具有更高的胶痕检测精度,且在光照条件较差和标志线影响的情况下具有更好的抗干扰性。

Aiming at the problem of low efficiency of rubber mark detection due to the diversity of morphological features of airport runway rubber mark and the complexity of the runway environment,this paper proposed a new airport runway rubber mark image segmentation algorithm based on simplified pulse coupled neural network.Firstly,on the basis of optimizing feedback input by using neighborhood gray-scale relationship,this algorithm improved the neuron ignition threshold mechanism from the traditional exponential decay to linear stratified step decay.Then,it combined the cuckoo search algorithm with the minimum cross entropy to optimize the parameters of the improved model.Finally,according to the average gray value of the ignition mapping area,it constructed an adaptive iterative termination condition.The experimental results show that the proposed algorithm has higher rubber mark detection accuracy and better anti-interference performance under the influence of poor lighting conditions and marking lines.