Crop Segmentation Method of Remote Sensing Image Based on Improved DeepLabV3+ Network

doi:10.3778/j.issn.1002-8331.2108-0387

Abstract

Abstract: Aiming at the problems of low recognition accuracy, poor edge recognition effect and slow extraction speed in current remote sensing image crop extraction, a remote sensing image crop segmentation method based on improved DeepLabV3+ network is proposed. The feature extraction network is changed to a lighter MobileNetV2 network, and the ordinary convolution in the atrous spatial pyramid pooling module is changed to deep separable convolution, which greatly reduces the amount of model calculation and improves the calculation speed of the model. The double attention mechanism is added to the feature extraction module and the atrous spatial pyramid pooling module to further optimize the effect of model edge recognition and improve the accuracy of model segmentation. In addition, aiming at the imbalance of crop data sets, the weighted loss function is introduced to give different weights to corn, job’s tears and background classes, so as to improve the accuracy of crop region segmentation. Taking the UAV remote sensing image of an area in 2019 as the research object, corn and job’s tears are segmented. The experimental results show that the pixel accuracy of the improved DeepLabV3+ algorithm can reach 93.9%, the average recall can reach 90.7%, and the average intersection and merging ratio can reach 83.3%, which is better than the traditional segmentation methods commonly used for crop extraction, such as DeepLabV3+, Unet, Segnet and it has better segmentation effect on crops.

Key words: crop segmentation, dual attention mechanism, weighted loss function, unmanned aerial vehicle（UAV） remote sensing image

摘要： 针对于当前遥感影像农作物提取存在的识别精度较低、边缘识别效果较差、提取速度慢等问题，提出了一种改进DeepLabV3+网络的遥感影像农作物分割方法。将特征提取网络改为更轻量级的MobileNetV2网络，空洞空间金字塔池化模块中的普通卷积改为深度可分离卷积，大幅减少模型计算量，提高模型计算速度；在特征提取模块以及空洞空间金字塔池化模块加入双注意力机制，进一步优化模型边缘识别效果，提升模型分割精度。此外针对农作物数据集类别不平衡问题，引入加权损失函数，给予玉米、薏米与背景类不同的权重，提高模型对农作物区域分割精度。以2019年某地区的无人机遥感影像为研究对象，对玉米、薏米两种农作物进行分割。实验结果表明，改进DeepLabV3+算法像素准确率可达到93.9%，平均召回率可达到90.7%，平均交并比可达到83.3%，优于传统DeepLabV3+、Unet、Segnet等常用于农作物提取的分割方法，对农作物具有更好的分割效果。

关键词: 农作物分割, 双注意力机制, 加权损失函数, 无人机遥感影像

REN Hongjie, LIU Ping, DAI Chao, SHI Juncai. Crop Segmentation Method of Remote Sensing Image Based on Improved DeepLabV3+ Network[J]. Computer Engineering and Applications, 2022, 58(11): 215-223.

任鸿杰, 刘萍, 岱超, 史俊才. 改进DeepLabV3+网络的遥感影像农作物分割方法[J]. 计算机工程与应用, 2022, 58(11): 215-223.

References

[1] 白燕英，高聚林，张宝林.基于Landsat8影像时间序列NDVI的作物种植结构提取[J].干旱区地理，2019，42（4）：893-901.
BAI Y Y，GAO J L，ZHANG B L.Extraction of crop planting structure based on time-series NDVI of Landsat8 images[J].Arid Land Geography，2019，42（4）：893-901.
[2] 韩衍欣，蒙继华.面向地块的农作物遥感分类研究进展[J].国土资源遥感，2019，31（2）：1-9.
HAN Y X，MENG J H.A review of per-field crop classification using remote sensing[J].Remote Sensing for Land & Resources，2019，31（2）：1-9.
[3] 刘哲，刘帝佑，朱德海，等.作物遥感精细识别与自动制图研究进展与展望[J].农业机械学报，2018，49（12）：1-12.
LIU Z，LIU D Y，ZHU D H，et al.Review on crop type fine identification and automatic mapping using remote sensing[J].Transactions of the Chinese Society for Agricultural Machinery，2018，49（12）：1-12.
[4] LI H，SHUANG L Q，JIAN Z D，et al.Monitoring of wheat powdery mildew disease severity using multiangle hyperspectral remote sensing[J].IEEE Transactions on Geoscience and Remote Sensing，2021，59（2）：979-990．
[5] 刘丹，刘学军，王美珍.一种多尺度CNN的图像语义分割算法[J].遥感信息，2017，32（1）：57-64.
LIU D，LIU X J，WANG M Z.Semantic segmentation with multi-scale convolutional neural network[J].Remote Sensing Information，2017，32（1）：57-64.
[6] GUAN D Y，HUANG J X，LU S J，et al.Scale variance minimization for unsupervised domain adaptation in image segmentation[J].Pattern Recognition，2021，112（4）：107764.
[7] LONG J，SHELHAMER E，DARRELL T，et al.Fully convolutional networks for semantic segmentation[C]//IEEE Conference on Computer Vision and Pattern Recogniton，2015：3431-3440.
[8] 郑二功，田迎芳，陈涛.基于深度学习的无人机影像玉米倒伏区域提取[J].河南农业科学，2018，47（8）：155-160.
ZHENG E G，TIAN Y F，CHEN T.Region extraction of corn lodging in UAV images based on deep learning[J].Journal of Henan Agricultural Sciences，2018，47（8）：155-160.
[9] 黄云，唐林波，李震，等.采用深度学习的遥感图像花生种植区域分类技术研究[J].信号处理，2019，35（4）：617-622.
HUANG Y，TANG L B，LI Z，et al.Research on peanut planting area classification technology using remote sensing image based deep learning[J].Journal of Signal Processing，2019，35（4）：617-622.
[10] HE K M，ZHANG X Y，REN S Q，et al.Spatial pyramid pooling in deep convolutional networks for visual recognition[J].IEEE Transactions on Pattern Analysis & Machine Intelligence，2015，37（9）：1904-1916.
[11] ZHU M，YAO M H，HE Y Q，et al.Studies on high-resolution remote sensing sugarcane field extraction based on deep learning[J].IOP Conference Series：Earth and Environmental Science，2019，237（3）：032046.
[12] 杨蜀秦，宋志双，尹瀚平，等.基于深度语义分割的无人机多光谱遥感作物分类方法[J].农业机械学报，2021，52（3）：185-192.
YANG S Q，SONG Z S，YIN H P，et al.Crop classification method of UVA multispectral remote sensing based on deep semantic segmentation[J].Transactions of the Chinese Society for Agricultural Machinery，2021，52（3）：185-192.
[13] 张潜，桑军，吴伟群，等.基于Xception的细粒度图像分类[J].重庆大学学报，2018，41（5）：85-91.
ZHANG Q，SANG J，WU W Q，et al.Fine-grained image classification based on Xception[J].Journal of Chongqing University，2018，41（5）：85-91.
[14] 秦伟伟，宋泰年，刘洁瑜，等.基于轻量化YOLOv3的遥感军事目标检测算法[J].计算机工程与应用，2021，57（21）：263-269.
QIN W W，SONG T N，LIU J Y，et al.Remote sensing military target detection algorithm based on lightweight YOLOv3[J].Computer Engineering and Applications，2021，57（21）：263-269.
[15] 张汉，张德祥，陈鹏，等.并行注意力机制在图像语义分割中的应用[J].计算机工程与应用，2022，58（9）：151-160.
ZHANG H，ZHANG D X，CHEN P，et al.Application of parallel attention mechanism in image semantic segmentation[J].Computer Engineering and Applications，2022，58（9）：151-160.
[16] CHEN L C，ZHU Y，PAPANDREOU G，et al.Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//European Conference on Computer Vision，2018：833-851.
[17] XIANG X，ZHANG Y，SADDIK A E.Pavement crack detection network based on pyramid structure and attention mechanism[J].IET Image Processing，2020，14（8）：1580-1586.
[18] JIE H，LI S，GANG S.Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：7132-7141.
[19] FU J，LIU J，TIAN H，et al.Dual attention network for scene segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2019：3141-3149.
[20] NIU R，SUN X，TIAN Y，et al.Hybrid multiple attention network for semantic segmentation in aerial images[J].IEEE Transactions on Geoscience and Remote Sensing，2021，60：1-18.
[21] 袁非牛，章琳，史劲亭，等.自编码神经网络理论及应用综述[J].计算机学报，2019，42（1）：203-230.
YUAN F N，ZHANG L，SHI J T，et al.Theories and applications of auto-encoder neural networks：a literature survey[J].Chinese Journal of Computers，2019，42（1）：203-230.