基于阈值或纹理分割的秸秆覆盖率检测算法, 存在准确性低、复杂度高、运行耗时长等问题, 且对含有大量干扰因素的复杂农田场景分割效果不佳。本文提出了一种检测准确度高、训练参数少且运行速度快的语义分割算法(DSRA-UNet)。该算法结合UNet的对称编-解码架构, 在浅层特征图使用标准卷积, 深层采用深度可分离卷积, 并在每一层增加残差结构来加大网络深度, 以降低参数量的同时提高精度。此外, 在跳级连接过程增加全局最大池化注意力机制, 进一步提高网络的分割精度。将算法在秸秆数据集上进行验证, 实验结果表明本文所提算法平均交并比达到94.3%, 训练参数量仅为0.76 M, 单张图片测试时间在0.05 s以下。该算法可以精准分割出秸秆和土壤, 并可在复杂环境下将干扰信息分割出, 可在一定程度上解决图像中的阴影问题。

The traditional segmentation algorithms for straw coverage detection basing on thresholds or texture features were difficult to get rid of the disadvantages of low accuracy, high complexity and time-consuming, and the effect of segmentation on complex farmland scenes containing a lot of interference factors was not good. Therefore, this paper proposed a semantic segmentation algorithm (DSRA-UNet) with high accuracy, a small mount of training parameters and high running speed. Combined with UNet′s symmetric codec architecture, this algorithm used standard convolution in shallow feature maps, and depthwise separable convolution in deep ones. Residual structure was built in each layer to increase the network depth,which can reduce the number of parameters and improve the accuracy at the same time. In addition, the global maximum pooling attention mechanism was added during the skip connection process to further improve the segmentation accuracy of the network. The algorithm was verified on the straw datasets, and the experiment results showed that the mean of intersection over union reached to 94.3% in the proposed algorithm of this paper. The number of training parameters of the algorithm was only 0.76 M, and the test time of single picture was less than 0.05 s. The algorithm could accurately segment the straw and soil, and separate the interference information in the complex environment, especially solving the shadow problem in image.