基于YCbCr空间和GA神经网络的棉花图像分割算法

棉花分割是采棉机器人视觉系统的关键步骤，在强光照、阴影等复杂的棉田环境下如何准确有效地分割棉花，有助于确定其在三维空间的位置。该算法在YCbCr颜色空间下，基于棉花与背景的色调信息差，分别提取棉花与背景样本，采用BP神经网进行训练并输出其误差，得到适应度函数并进行遗传算法中的选择、交叉及变异操作，优化神经网络权值、阈值，直到输出误差达到要求或达到预定迭代次数。最后根据所获得的BP神经网络权值、阈值进行棉花图像分割。通过对136幅棉田环境中拍摄图像的分割实验表明：该方法在棉花强光照及阴影条件下也能准确地分割，分割准确率达91.9%，并且比BP算法收敛更快。

Algorithm of cotton image segmentation based on YCbCr space and ;GA neural network

Cotton segmentation is the key step of cotton picking robot vision system. The accurate and effective segmentation of cotton is useful to its position in three-dimensional space while cotton is in bright light or shadow complex field environment. It can get fitness function by training BP neural network and its output error, and then use selection, crossover and mutation operation in genetic algorithm to optimize neural network weights and threshold until the output error meets the requirement or it reaches a predetermined number of iterations. Finally, according to the obtained BP neural network weights and threshold, it segments cotton image. The experiment of image segmentation with 136 images photographed in cotton field environment shows that the algorithm can segment cotton image in bright light or shadow accurately and segmentation accuracy rate is up to 91.9%and it converges faster than BP.