Straw detection algorithm based on semantic segmentation in complex farm scenarios

Yuan-yuan LIU; Shuo ZHANG; Hai-ye YU; Yue-yong WANG; Jia-mu WANG

doi:10.3788/OPE.20202801.0200

您当前的位置：

首页 >

文章列表页 >

Straw detection algorithm based on semantic segmentation in complex farm scenarios

Information Sciences | 更新时间：2020-08-13

- Straw detection algorithm based on semantic segmentation in complex farm scenarios
- Optics and Precision Engineering Vol. 28, Issue 1, Pages: 200-211(2020)
- 作者机构：
  
  1.吉林农业大学信息技术学院，吉林长春 130118；
  2.吉林大学工程仿生教育部重点实验室，吉林长春 130025；
  3.吉林农业大学工程技术学院，吉林长春 130118
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20202801.0200
  CLC： S24;TP751
- Received：27 August 2019，
  
  Accepted：08 October 2019，
  
  Published：25 January 2020
- 稿件说明：
移动端阅览
Yuan-yuan LIU, Shuo ZHANG, Hai-ye YU, et al. Straw detection algorithm based on semantic segmentation in complex farm scenarios[J]. Optics and precision engineering, 2020, 28(1): 200-211.
DOI：

Yuan-yuan LIU, Shuo ZHANG, Hai-ye YU, et al. Straw detection algorithm based on semantic segmentation in complex farm scenarios[J]. Optics and precision engineering, 2020, 28(1): 200-211. DOI： 10.3788/OPE.20202801.0200.

摘要

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。

Abstract

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.

关键词

Keywords

references

贺美.秸秆还田对黑土有机质变化的影响效应[D].北京: 中国农业科学院, 2016. http://cdmd.cnki.com.cn/Article/CDMD-82101-1016174502.htm

HE M. Effects of Straw Returning Methods On Black Soil Organic Matter [D].Beijing: Chinese Academy of Agricultural Sciences, 2016.(in Chinese)

宫纯文, 李建玉, 李学彬, 等.秸秆燃烧和沙尘对气溶胶光学特性的影响[J].光学精密工程, 2015, 23(10):2768-2777.

GONG CH W, LI J Y, LI X B, et al .. Influence of straw burning and dust on aerosol optical properties[J]. Opt. Precision Eng ., 2015, 23(10): 2768-2777.(in Chinese)

王丽丽, 徐岚俊, 魏舒, 等.基于Sauvola与Otsu算法的秸秆覆盖率图像检测方法[J].农业工程, 2017, 7(4):29-35.

WANG L L, XU L J, WEI SH, et al .. Straw coverage detection method based on Sauvola and Otsu segmentation algorithm[J]. Agricultural Engineering , 2017, 7(4):29-35. (in Chinese)

李洪文, 李慧, 何进, 等.基于人工神经网络的田间秸秆覆盖率检测系统[J].农业机械学报, 2009, 40(6):58-62.

LI H W, LI H, HE J, et al .. Field coverage detection system of straw based on artificial neural network[J]. Transactions of the Chinese Society for Agricultural Machinery , 2009, 40(6):58-62. (in Chinese)

刘媛媛, 王跃勇, 于海业, 等.基于多阈值图像分割算法的秸秆覆盖率检测[J].农业机械学报, 2018, 49(12):27-35, 55.

LIU Y Y, WANG Y Y, YU H Y, et al .. Detection of straw coverage rate based on multi-threshold image segmentation algorithm[J]. Transactions of the Chinese Society for Agricultural Machinery , 2018, 49(12):27-35, 55. (in Chinese)

KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM , 2017, 60(6):84-90.

潘仙张, 张石清, 郭文平.多模深度卷积神经网络应用于视频表情识别[J].光学精密工程, 2019, 27(4): 963-970.

PAN X ZH, ZHANG SH Q, GUO W P. Video-based facial expression recognition using multimodal deep convolutional neural networks[J]. Opt. Precision Eng ., 2019, 27(4): 963-970. (in Chinese)

郭保青, 王宁.基于改进深度卷积网络的铁路入侵行人分类算法[J].光学精密工程, 2018, 26(12): 3040-3050.

GUO B Q, WANG N. Pedestrian intruding railway clearance classification algorithm based on improved deep convolutional network[J]. Opt. Precision Eng. , 2018, 26(12): 3040-3050. (in Chinese)

吕晓琪, 吴凉, 谷宇, 等.基于三维卷积神经网络的低剂量CT肺结节检测[J].光学精密工程, 2018, 26(5): 1211-1218.

LÜ X Q, WU L, GU Y, et al .. Detection of low dose CT pulmonary nodules based on 3D convolution neural network[J]. Opt. Precision Eng. , 2018, 26(5): 1211-1218. (in Chinese)

潘蓉, 孙伟.基于预分割和回归的深度学习目标检测[J].光学精密工程, 2017, 25(10s): 221-227.

PAN R, SUN W. Deep learning target detection based on pre-segmentation and regression[J]. Opt. Precision Eng ., 2017, 25(10s): 221-227. (in Chinese)

董月, 冯华君, 徐之海, 等.Attention Res-Unet:一种高效阴影检测算法[J].浙江大学学报(工学版), 2019, 53(2):373-381+406.

DONG Y, FENG H J, XU ZH H, et al .. Attention Res-Unet: an efficient shadow detection algorithm[J]. Journal of ZheJiang University ( Engineering Science ), 2019, 53(2): 373-381+406. (in Chinese)

RONNEBERGER O, FISCHER P, BROX T. U-Net: Convolutional Networks for Biomedical Image Segmentation[C]. International Conference on Medical Image Computing and Computer-assisted Intervention. Cham: Springer , 2015: 234-241.

JONATHAN L, EVAN S, TREVOR D. Fully Convolutional Networks for Semantic Segmentation[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2015: 3431- 3440.

HE K M, ZHANG X Y, REN S Q, et al .. Deep Residual Learning for Image Recognition[C]. IEEE Conference on Computer Vision and Pattern Recognition ( CVPR ), 2016: 770- 778.

FRANCOIS C.Xception: Deep Learning with Depthwise Separable Convolutions[C]. Proceedings of the IEEE conference on computer vision and pattern recognition , 2017: 1251-1258.

VASWANI A, SHAZEER N, PARMAR N, et al .. Attention is All You Need[C]. Advances in neural information processing systems , 2017: 5998-6008.

ZHAO B, WU X, FENG J, et al .. Diversified visual attention networks for fine-grained object classification[J]. IEEE Transactions on Multimedia , 2017, 19(6): 1245-1256.

JO Y J, CHO H, LEE S Y, et al .. Quantitative phase imaging and artificial intelligence: a review[J]. IEEE Journal of Selected Topics in Quantum Electronics , 2018, 25(1): 1-14.

LI H, XIONG P, AN J, et al .. Pyramid attention network for semantic segmentation[J]. arXiv preprint arXiv: 1805.10180, 2018. http://www.researchgate.net/publication/325396278_Pyramid_Attention_Network_for_Semantic_Segmentation?ev=auth_pub

LIN T Y, GOYAL P, GIRSHICK R, et al .. Focal Loss for Dense Object Detection[C]. Proceedings of the IEEE international conference on computer vision , 2017: 2980-2988.

BADRINARAYANAN V, KENDALL A, CIPOLLA R. SegNet:A deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2017, 39(12):2481-2495.

CHEN L C, ZHU Y, PAPANDREOU G, et al .. Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation[C]. Proceedings of the European conference on computer vision ( ECCV ), 2018: 801-818.

Views

366

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Concrete crack segmentation combined with linear guidance and mesh optimization

Real-time semantic segmentation based on improved BiSeNet

Real time semantic segmentation network of wire harness terminals based on multiple receptive field attention

Straw coverage detection of conservation tillage farmland based on improved U-Net model

Underwater image enhancement based on multi-branch residual attention network

Related Author

XU Shengjun

LIU Guanghui

CHEN Jian

MENG Yuebo

REN Fenglei

YANG Lu

ZHOU Haibo

ZHANG Shiyv

Related Institution

College of Information and Control Engineering，Xi'an University of Architecture and Technology

Xi'an Key Laboratory of Intelligent Technology for Building and Manufacturing

Higher Education Key Laboratory of Construction Robot in Shaanxi Province

Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control， School of Mechanical Engineering， Tianjin University of Technology

National Demonstration Center for Experimental Mechanical and Electrical Engineering Education，Tianjin University of Technology

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰