改进的卷积神经网络在树种识别中的应用

Improved Convolutional Neural Network for Tree Species Recognition

为了提高树木种类识别的正确率和效率,减缓过拟合的发生,提升树木识别技术的实用性,本文提出一种基于改进的卷积神经网络的树木识别方法。该方法首先在Xception框架中,压缩信道进一步利用全局特征映射的平均池化,改变混合注意力连接方式为并行连接;其次在特征图中随机抽取一部分,对该部分进行规范化处理,使用注意力特征图裁剪的方法后,重新进入神经网络;最后进行消融实验,在树木种类数据集中,使学习率为0.1、迭代50次时,树木识别的准确率高达98.90%。研究表明,提出的改进卷积神经网络在树木识别上具有更好的识别效果。使卷积神经网络架构的内存缩小到133.9 MB,耗时仅为458 ms。采用改进的卷积神经网络不仅提高了树木识别的准确率,同时也降低了时间成本。

In order to improve the correctness and efficiency of tree species recognition,to slow down the occurrence of overfitting,and to enhance the practicality of tree recognition techniques,this paper proposed a tree recognition method based on an improved convolutional neural network.The approach started with compressing the channel in the Xception framework to further exploit the average pool of global feature mapping,and changing the hybrid attention connection to parallel connection.Next,a randomly selected part of the feature map was normalized and re-entered into the neural network after using the attentional feature map cropping method.Finally,ablation experiment was performed and the accuracy of tree species recognition was up to 98.90% in the tree dataset when the learning rate was 0.1 and the iteration was 50 times.The study showed that the proposed improved convolutional neural network had better recognition effect on tree recognition.And the memory of the convolutional neural network architecture was reduced to 133.9 MB and the time consumed was only 458 ms.Using the improved convolutional neural network not only improved the accuracy of tree recognition,but also reduced the time cost.