BP神经网络的道路场景杆状地物自动分类

针对车载激光扫描数据中杆状地物分类精度不高、自动化程度低的问题，本文提出一种基于BP神经网络的分类方法。首先根据杆状地物点云特征选取10个特征值，获取杆状地物聚类单元的特征向量，构建特征矩阵；然后使用样本集训练BP神经网络模型并保存该分类模型；最后使用BP神经网络分类模型对试验区内的杆状地物进行分类。试验结果表明，该方法对杆状地物的分类精度可达95.34%，验证了文中所述方法对杆状地物分类的有效性。

Automatic classification of pole-like objects in road scene by back propagation neural network

Aiming at the problems of low accuracy and low automation of pole-like objects classification in vehicle laser scanning data, a classification method based on BP neural network is proposed. Firstly, according to the point cloud characteristics of the pole-like object, ten eigenvalues are selected to obtain the feature vectors of the pole-like object clustering unit, and then eigenmatrix is constructed. Secondly, the BP neural network model is trained by using the sample set and the classification model is saved. Finally, the BP neural network classification model is used to classify the pole-like object in the test area. The experiment showed that the classification accuracy of the method for pole-like objects could reach 95.34%, which also verifies the effectiveness of the method.