融合注意力机制的GAN病虫害图像超分辨率重建

doi:10.14088/j.cnki.issn0439-8114.2024.09.034

湖北农业科学 ›› 2024, Vol. 63 ›› Issue (9): 204-209.doi: 10.14088/j.cnki.issn0439-8114.2024.09.034

融合注意力机制的GAN病虫害图像超分辨率重建

费加杰, 杨毅, 曾晏林, 蔺瑶, 贺壹婷, 黎强, 张圣笛

云南农业大学大数据学院,昆明 650500

收稿日期:2023-02-13 出版日期:2024-09-25 发布日期:2024-09-30
通讯作者: 杨毅（1966-）,男,云南昆明人,硕士生导师,主要从事深度学习、植物病虫害防治、图形图像处理方面研究,（电话）13888222963（电子信箱）1617213828@qq.com。
作者简介:费加杰（1995-）,男,贵州六盘水人,在读硕士研究生,研究方向为图形图像处理,（电话）18184899528（电子信箱）354099126@qq.com。
基金资助:
云南省重大科技专项（A3032021043002）

Super-resolution reconstruction of GAN pest and disease images fused with attention mechanisms

FEI Jia-jie, YANG Yi, ZENG Yan-lin, LIN Yao, HE Yi-ting, LI Qiang, ZHANG Sheng-di

School of Big Data,Yunnan Agricultural University, Kunming 650500, China

Received:2023-02-13 Published:2024-09-25 Online:2024-09-30

摘要/Abstract

摘要： 收集咖啡和柑橘病虫害样本图片,利用TensorFlow深度学习框架,在原始SRGAN（Super-resolution generative adversarial networks）的超分辨率重建网络里加入了注意力模块,对重建图像视觉质量和峰值信噪比（PSNR）、结构化相似性（SSIM）指标进行分析。结果表明,设计的模型和原始SRGAN模型对比之后峰值信噪比提高了2.23,结构相似性提高了7%。在细节纹理方面可以获得更好的视觉效果,重建后的图像识别准确率提高了约4.42个百分点。因此,设计的模型可以对小样本性质的植物病虫害样本进行扩充。

关键词: 超分辨率重建, 注意力机制, 病虫害, 峰值信噪比（PSNR）, 结构化相似性（SSIM）

Abstract: The sample pictures of coffee and citrus pests and diseases were collected, and an attention module was added to the super-resolution reconstruction network of the original SRGAN by using TensorFlow deep learning framework. The visual quality, peak signal-to-noise ratio and structured similarity index of the reconstructed image were analyzed. The results showed that the peak signal-to-noise ratio of the designed model was improved by 2.23, and the structural similarity was enhanced by 7%, after comparing with the original SRGAN mode. Better visuals could be obtained in terms of detail texture, and the accuracy of the reconstructed image classification was improved by about 4.42 percentage points. Therefore, the model designed could be used for the expansion of samples of plant pests and diseases with small sample properties.

Key words: super-resolution reconstruction, attention mechanism, pests and diseases, peak signal-to-noise ratio （PSNR）, structural similarity（SSIM）

中图分类号:

费加杰, 杨毅, 曾晏林, 蔺瑶, 贺壹婷, 黎强, 张圣笛. 融合注意力机制的GAN病虫害图像超分辨率重建[J]. 湖北农业科学, 2024, 63(9): 204-209.

FEI Jia-jie, YANG Yi, ZENG Yan-lin, LIN Yao, HE Yi-ting, LI Qiang, ZHANG Sheng-di. Super-resolution reconstruction of GAN pest and disease images fused with attention mechanisms[J]. HUBEI AGRICULTURAL SCIENCES, 2024, 63(9): 204-209.

参考文献

[1] 康士伟,孙水发,陈晓军,等.单帧图像超分辨率重建的深度神经网络综述[J].信息通信,2019(3):24-27.
[2] DONG C, LOY C C, HE K, et al.Image super-resolution using deep convolutional networks[J]. IEEE transactions on pattern analysis and machine intelligence, 2015, 38(2): 295-307.
[3] DONG C, LOY C C, TANG X O.Accelerating the super-resolution convolutional neural network[A]. European conference on computer vision[C]. Springer, Cham, 2016.391-407.
[4] SHI W, CABALLERO J, HUSZÁR F, et al. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network[A]. Proceedings of the IEEE conference on computer vision and pattern recognition[C]. 2016.1874-1883.
[5] KIM J, LEE J K, LEE K M.Accurate image super-resolution using very deep convolutional networks[A]. Proceedings of the IEEE conference on computer vision and pattern recognition[C]. 2016.1646-1654.
[6] KIM J,LEE J K,LEE K M.Deeply-recursive convolutional network for image super-resolution[A].Proceedings of the IEEE conference on computer vision and pattern recognition[C]. 2016.1637-1645.
[7] GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al.Generative adversarial nets[A]. Proceedings of the 27th international conference on neural information processing systems[C]. 2014.2672-2680.
[8] LEDIG C, THEIS L, HUSZÁR F, et al. Photo-realistic single image super-resolution using a generative adversarial network[A]. Proceedings of the IEEE conference on computer vision and pattern recognition[C]. 2017. 4681-4690.
[9] VASWANI A, SHAZEER N, PARMAR N, et al.Attention is all you need[A]. Proceedings of the 31st international conference on neural information processing systems[C], 2017.6000-6010.
[10] ZHANG Y L, LI K P, LI K, et al.Image super-resolution using very deep residual channel attention networks[A].Proceedings of the European conference on computer vision (ECCV)[C]. 2018.286-301.
[11] LIU Y, WANG Y C, LI N, et al.An attention-based approach for single image super resolution[A]. 2018 24Th international conference on pattern recognition (ICPR)[C]. IEEE, 2018. 2777-2784.
[12] 梁俊杰,韦舰晶,蒋正锋.生成对抗网络GAN综述[J].计算机科学与探索,2020,14(1):1-17.
[13] 秦铁鑫. 基于数据扩充的小样本学习算法研究[D].南京:南京大学,2021.
[14] 王俊杰,焦柯,彭子祥,等.基于变分自编码器潜变量语义提炼的样本生成方法[J].计算机系统应用,2022,31(3):255-261.
[15] 李会鹏,贺国,明廷锋.Bootstrap方法在机电设备振动状态阈值设定中的应用[J].舰船科学技术,2012,34(5):70-73,77.
[16] 杨天乐,钱寅森,武威,等.基于Python爬虫和特征匹配的水稻病害图像智能采集[J].河南农业科学,2020,49(12):159-163.
[17] 俞彬. 基于生成对抗网络的图像类别不平衡问题数据扩充方法[D].广州:华南理工大学,2018.
[18] TREISMAN A M, GELADE G.A feature-integration theory of attention[J]. Cognitive psychology, 1980, 12(1): 97-136.
[19] WOO S, PARK J, LEE J Y, et al.Cbam: Convolutional block attention module[A]. Proceedings of the European conference on computer vision (ECCV)[C]. 2018. 3-19.
[20] 佟雨兵,张其善,祁云平.基于PSNR与SSIM联合的图像质量评价模型[J].中国图象图形学报,2006(12):1758-1763.

融合注意力机制的GAN病虫害图像超分辨率重建

Super-resolution reconstruction of GAN pest and disease images fused with attention mechanisms

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	宋振帅, 周艳, 钟灵, 仪杰, 宋龙, 何磊. 果树枝条识别与修剪点坐标确定方法[J]. 湖北农业科学, 2024, 63(8): 39-46.
[2]	黄其椿, 谭颂玥, 汪妮娜, 刘福平, 刘吉敏, 胡承孝, 廖惠红, 黄宏明, 韦持章, 陈东奎, 曾志康. 喷施石硫合剂对促进沃柑果实着色的影响[J]. 湖北农业科学, 2024, 63(4): 73-77.
[3]	袁鹏, 王珂, 肖坚. 基于RMAU-Net网络模型的高分影像耕地提取[J]. 湖北农业科学, 2023, 62(8): 182-188.
[4]	李正, 李宝喜, 李志豪, 战艺芳, 王利华, 龚琦. 基于深度学习的农作物病虫害识别研究进展[J]. 湖北农业科学, 2023, 62(11): 165-169.
[5]	刘立, 丰洪才, 黄清. 基于多特征融合的水果病虫害知识视频镜头检测算法[J]. 湖北农业科学, 2022, 61(20): 195-202.
[6]	陈少容, 黄荣韶, 李良波, 姚绍嫦, 谭勇, 明如宏, 黄鼎. 牛大力主要病虫害调查及白粉病的防治技术研究[J]. 湖北农业科学, 2022, 61(15): 121-123.
[7]	袁观强, 梅贤钦, 吴正利, 包慧芳, 万中义, 陈云峰, 王会良, 黄树民, 闵勇, 龙同. 通山县枇杷病虫害调查初报及其防治策略[J]. 湖北农业科学, 2021, 60(24): 90-93.
[8]	吕亮, 常向前, 王佐乾, 杨小林, 张舒. 湖北省20份水稻主栽品种抗病虫性的田间观察[J]. 湖北农业科学, 2021, 60(10): 77-81.
[9]	余为仆, 周忠雄, 徐国华, 吴芸紫, 柳冕, 许晖, 杨洪勇, 谢磊. 再生稻植保无人机病虫害防治适宜飞行参数研究[J]. 湖北农业科学, 2020, 59(22): 125-127.
[10]	程建平, 汪本福, 章桃娟, 李阳, 张枝盛, 杨晓龙, 彭成林, 杨小红. 湖北省稻虾共作模式下水稻机插栽培技术[J]. 湖北农业科学, 2020, 59(20): 29-31.
[11]	李艳红, 樊同科. 基于深度残差的多特征多粒度农业病虫害识别研究[J]. 湖北农业科学, 2020, 59(16): 153-157.
[12]	杨妮娜, 丛胜波, 赵书军, 徐大兵, 龙同, 万鹏. 湖北长阳高山蔬菜病虫害用药现状调查及解决对策[J]. 湖北农业科学, 2019, 58(20): 90-92.
[13]	徐可. 设施草莓主要病虫害及综合治理[J]. 湖北农业科学, 2019, 58(1): 53-55.
[14]	张小凤, 郭雁君, 蒋惠, 郭丽英, 周希琴, 胡亚平, 吉前华. 橘园生草栽培的研究进展[J]. 湖北农业科学, 2018, 57(3): 5-5.
[15]	和秋菊, 易传辉, 张正旺, 任羲鹏, 林中阳. 胡蜂人工养殖现状及存在的问题[J]. 湖北农业科学, 2018, 57(18): 10-13.