基于多尺度融合的卷积神经网络的杂草幼苗识别
Weed Seeding Recognition Based on Multi-Scale Fusion Convolutional Neutral Network

DOI: 10.12677/CSA.2020.1012255, PP. 2406-2418

Keywords: AlexNet，PL-SE，SR-SE，多尺度并行融合，轻量级，杂草识别
AlexNet, PL-SE, SR-SE, Multiscale Parallel Fusion, Lightweight Class, Weeding Identification

Full-Text   Cite this paper   Add to My Lib

Abstract:

针对传统网络ALexNet识别精度不高、内存需求量大、特征尺度单一等问题，该文提出了一种多尺度并行融合的轻量级模块PL-SE模块。该模块将上层特征经过两个不同尺度的卷积核和一个最大池化，融合之后得到新的特征信息，之后再经过一个SE模块，最后进行残差学习。同时，对于下采样部分，该文提出一种SR-SE模块代替传统网络的池化层，在降维的同时进行特征提取。使用PL-SE模块和SR-SE模块对ALexNet模型改进得到一种新的模型，用于对25种杂草幼苗进行训练识别。改进后的模型识别准确率达到了96.32%，相较于传统的ALexNet模型提高了8个百分点，参数总量减少约56.7 M (Million)。除此之外，与ResNet、GoogleNet、MobileNet等经典网络相比，改进后的模型在准确率和参数量方面都具有优势。
For the problems that the traditional network AlexNet recognition accuracy is not high, memory demand is large, the characteristic scale is single and so on, this paper presents a multi-scale parallel fusion lightweight module PL-SE module. In this module, the upper features are processed by two convolution kernels with different scales and a maximum pooling. After fusion, new feature information is obtained, followed by an SE module, and finally residual learning is conducted. At the same time, for the lower sampling part, this paper proposes a SR-SE module instead of the pooling layer of traditional network, which can extract features while reducing dimensions. Using PL-SE module and SR-SE module to improve ALexNet model, a new model was developed for training and identification of 25 weed seedlings. The improved model recognition accuracy reaches 96.32%, 8 percentage points higher than the traditional ALexNet model, and the total number of parameters is reduced by about 56.7 m (Million). In addition, compared with classic networks such as ResNet, GoogleNet and MobileNet, the improved model has advantages in accuracy and number of parameters.

References

[1]	Camargo, A. and Smith, J.S. (2009) Image Pattern Classification for the Identification of Disease Causing Agents in Plants. Computers and Electronics in Agriculture, 66, 121-125. https://doi.org/10.1016/j.compag.2009.01.003
[2]	Sadgrove, E.J., Falzon, G., Miron, D. and Lamb, D. (2017) Fast Object Detection in Pastoral Landscapes Using a Colour Feature Extreme Learning Machine. Computers and Elec-tronics in Agriculture, 139, 204-212. https://doi.org/10.1016/j.compag.2017.05.017
[3]	Haug, S., Michaels, A., Biber, P. and Ostermann, J. (2014) Plant Classification System for Crop/Weed Discrimination without Segmentation. IEEE Winter Conference on Applica-tions of Computer Vision, Steamboat Springs, 24-26 March 2014, 1142-1149. https://doi.org/10.1109/WACV.2014.6835733
[4]	Dos Santos Ferreira, A., Matte Freitas, D., Gon？alves da Silva, G., Pistori, H. and Theophilo Folhes, M. (2017) Weed Detection in Soybean Crops Using ConvNets. Computers and Electronics in Agriculture, 143, 314-324. https://doi.org/10.1016/j.compag.2017.10.027
[5]	Mccool, C., Perez, T. and Upcroft, B. (2017) Mixtures of Lightweight Deep Convolutional Neural Networks: Applied to Agricultural Robotics. IEEE Robotics and Automation Letters, 2, 1344-1351. https://doi.org/10.1109/LRA.2017.2667039
[6]	Sa, I., Popovi？, M., Khanna, R., Chen, Z.T., Lottes, P., Liebisch, F., Nieto, J., Stachniss, C., Walter, A. and Siegwart, R. (2018) WeedMap: A Large-Scale Semantic Weed Mapping Framework Using Aerial Multispectral Imaging and Deep Neural Network for Precision Farming. Remote Sensing, 10, 1423. https://doi.org/10.3390/rs10091423
[7]	王一鸣, 毛文华, 张小超. 基于纹理和位置特征的麦田杂草识别方法[J]. 农业机械学报, 2007, 38(4): 107-110. http://dx.chinadoi.cn/10.3969/j.issn.1000-1298.2007.04.028
[8]	何东健, 乔永亮, 李攀, 高瞻, 李海洋, 唐晶磊. 基于SVM-DS多特征融合的杂草识别[J]. 农业机械学报, 2013, 44(2): 182-187. http://dx.chinadoi.cn/10.6041/j.issn.1000-1298.2013.02.034
[9]	张新明, 涂强, 冯梦清. 基于改进概率神经网络的玉米与杂草识别[J]. 山西大学学报(自然科学版), 2015, 38(3): 432-438. http://dx.chinadoi.cn/10.13451/j.cnki.shanxi.univ(nat.sci.).2015.03.008
[10]	翟志强, 朱忠祥, 杜岳峰, 张硕, 毛恩荣. 基于Census变换的双目视觉作物行识别方法[J]. 农业工程学报, 2016, 32(11): 205-213. http://dx.chinadoi.cn/10.11975/j.issn.1002-6819.2016.11.029
[11]	王璨, 武新慧, 李志伟. 基于卷积神经网络提取多尺度分层特征识别玉米杂草[J]. 农业工程学报, 2018, 34(5): 144-151. http://dx.chinadoi.cn/10.11975/j.issn.1002-6819.2018.05.019
[12]	Leminen Madsen, S., Mathiassen, S.K., Dyrmann, M., Laursen, M.S., Paz, L.-C. and J？rgensen, R.N. (2020) Open Plant Pheno-Type Database of Common Weeds in Denmark. Remote Sensing, 12, 1246. https://doi.org/10.3390/rs12081246
[13]	Krizhevsky, A., Sutskever, I. and Hinton, G.E. (2017) ImageNet Classi-fication with Deep Convolutional Neural Networks. Communications of the ACM, 60, 84-90. https://doi.org/10.1145/3065386
[14]	Szegedy, C., Liu, W., Jia, Y.Q., Sermanet, P., Reed, S., Anguelov, D., et al. (2015) Going Deeper with Convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recog-nition, Boston, 7-12 June 2015, 1-9. https://doi.org/10.1109/CVPR.2015.7298594
[15]	Howard, A.G., Zhu, M.L., Chen, B., Kalenichenko, D., Wang, W.J., Weyand, T., Andreetto, M. and Adam, H. (2017) Mobilenets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv Preprint, arXiv:1704.04861.
[16]	Hu, J., Shen, L. and Sun, G. (2018) Squeeze-and-Excitation Networks. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-23 June 2018, 7132-7141. https://doi.org/10.1109/CVPR.2018.00745
[17]	孙俊, 何小飞, 谭文军, 武小红, 沈继锋, 陆虎. 空洞卷积结合全局池化的卷积神经网络识别作物幼苗与杂草[J]. 农业工程学报, 2018, 34(11): 159-165. http://dx.chinadoi.cn/10.11975/j.issn.1002-6819.2018.11.020
[18]	孙俊, 谭文军, 武小红, 沈继锋, 芦兵, 戴春霞. 多通道深度可分离卷积模型实时识别复杂背景下甜菜与杂草[J]. 农业工程学报, 2019, 35(12): 184-190. http://dx.chinadoi.cn/10.11975/j.issn.1002-6819.2019.12.022

Full-Text