基于卷积神经网络的煤炭运载车辆识别

Identification of Coal Vehicles Based on Convolutional Neural Network

为了杜绝或避免矿产品资源如煤炭、砂石矿等行业因不开票而导致偷税漏税现象的发生,利用深度卷积神经网络自动识别空车重车是一种有效途径。本文在AlexNet模型基础上,针对空车重车图像的差异性,提出5种改进思路,最终得到一种基于maxout+dropout的6层卷积神经网络的结构。对34220张空车重车图片的测试结果表明,模型在准确度、敏感度、特异性、精度等方面都取得了良好的效果。此外,模型还具有高度的鲁棒性,可以成功识别大量不同角度和不同场景的空车重车图像。

In order to prevent or avoid the occurrence of tax evasion and taxation caused by non-invoicing of mineral resources such as coal,sand and gravel,it is an effective way to use the deep convolutional neural network to automatically identify empty vehicles.Based on the AlexNet model,this paper proposes 5 kinds of improvement ideas for the difference of empty car and heavy vehicle images,and finally obtains a structure of 6-layer convolutional neural network based on maxout+dropout.The test results of the picture of the 34220 empty cars and loaded cars show that the model has achieved good results in terms of accuracy,sensitivity,specificity and precision.In addition,the model is highly robust and can successfully identify a large number of empty car images with different angles and different scenes.