基于改进Mask R-CNN的笼养死鸭识别方法

柏宗春; 吕胤春; 朱一星; 马肄恒; 段恩泽

基于改进Mask R-CNN的笼养死鸭识别方法

1. 江苏省农业科学院农业设施与装备研究所;
2. 农业农村部长江中下游设施农业工程重点实验室;
3. 江苏大学农业工程学院

基金项目:

江苏省现代农业重大核心技术创新项目(CX(22)1008)

详细信息

作者简介:
柏宗春(1981—),男,副研究员,博士,主要从事畜禽养殖技术与装备研究,E-mail:vipmaple@126.com

通讯作者:
段恩泽(1995—),男,助理研究员,博士,主要从事畜禽养殖技术与装备研究,E-mail:952510993@qq.com

中图分类号: TP391.41;S858.32
计量
- 文章访问数: 10
- HTML全文浏览量: 0
- PDF下载量: 0
出版历程
- 收稿日期: 2023-11-05
- 刊出日期: 2024-07-24

Dead Duck Recognition Method Based on Improved Mask R-CNN

1. Institute of Agricultural Facilities and Equipment, Jiangsu Academy of Agricultural Sciences;
2. Key Laboratory of Protected Agriculture Engineering in the Middle and Lower Reaches of Yangtze River,Ministry of Agriculture and Rural Affairs;
3. College of Agricultural Engineering, Jiangsu University

摘要

摘要: 针对规模化笼养肉鸭舍内死鸭识别采用人工作业方式时，存在作业效率低、劳动强度大、养殖成本高等问题，以层叠式笼养肉鸭为研究对象，提出了一种基于深度学习的笼养死鸭识别方法。为了采集数据，首先面向立体层叠式养殖环境设计了一款适用于肉鸭舍的自主巡检装备。针对笼养肉鸭舍铁丝网遮挡严重的问题，基于机器视觉对笼网进行修复，基于OpenCV对图像进行增强处理。构建了一种基于Mask R-CNN的死鸭识别模型，采用Swin Transformer对模型进行优化，解决了Mask R-CNN网络缺乏整合全局信息能力的问题。对比分析了SOLO v2、Mask R-CNN和Mask R-CNN+Swin Transformer模型识别笼内死鸭准确率。实验结果表明，在平均精度均值为90%的条件下，Mask R-CNN+Swin Transformer模型对笼内死鸭总体识别准确率可达95.8%,在自主巡检装备上的检测效果优于其他主流的目标检测算法。
- 机器视觉 /
- 笼养肉鸭 /
- 死鸭识别 /
- Mask R-CNN
Abstract: Traditional manual methods for identifying dead ducks within large-scale stacked cage poultry houses have proven to be inefficient, labor-intensive, and costly. Focusing on stacked cage housing for meat ducks, a deep learning-based method was proposed for dead duck recognition. To collect the necessary dataset, a specialized autonomous inspection system tailored for meat duck housing within three-dimensional stacked environments was initially designed. To address the issue of severe wire mesh obstruction within the cage housing, machine vision techniques were employed to repair the cage mesh and enhance images by using OpenCV. A dead duck recognition model was constructed based on Mask R-CNN, and further optimized with the Swin Transformer to overcome the limitation of Mask R-CNN’s global information integration. The accuracy of dead duck recognition among the SOLO v2, Mask R-CNN, and Mask R-CNN+Swin Transformer models was compared and analyzed. Experimental results demonstrated that under the condition of mAP value of 90%, the Mask R-CNN+Swin Transformer model achieved an overall dead duck recognition rate of 95.8% within the duck cages, outperforming other mainstream object detection algorithms on the autonomous inspection equipment.
- machine vision /
- caged ducks /
- dead duck recognition /
- Mask R-CNN

HTML全文

参考文献(26)

[1]	王明宇,王勇生.我国肉鸭养殖业发展面临的挑战[J].当代畜牧,2021(8):71-73.
[2]	祖全亮,刘宏,杨景晁.当前肉鸭产业发展形势与建议对策[J].家禽科学,2022(4):41-43.
[3]	李明阳,应诗家,戴子淳,等.新型肉鸭养殖模式生产性能及经济效益对比分析[J].中国家禽,2020,42(4):80-85.
[4]	胡惠玥,杨小玲,刘仁鑫,等.畜禽养殖机器人研究现状与展望[J].南方农机,2023,54(19):1-6,10.
[5]	薛鸿翔.基于红外热成像技术的死鸡识别系统设计与实现[D].南京:南京农业大学,2022.XUE Hongxiang.Design and implementation of dead broiler identification system based on infrared thermal imaging technology[D].Nanjing:Nanjing Agricultural University,2022.(in Chinese)
[6]	段恩泽,王粮局,雷逸群,等.基于实例分割和光流计算的死兔识别模型研究[J].农业机械学报,2022,53(2):256-264,273.DUAN Enze,WANG Liangju,LEI Yiqun,et al.Dead rabbit recognition model based on instance segmentation and optical flow computing[J].Transactions of the Chinese Society for Agricultural Machinery,2022,53(2):256-264,273.(in Chinese)
[7]	姜来,王文娣,霍晓静,等.死鸡识别机器人系统设计与试验[J].中国农机化学报,2023,44(8):81-87.JIANG Lai,WANG Wendi,HUO Xiaojing,et al.Design and experiment of dead chicken recognition robot system[J].Journal of Chinese Agricultural Mechanization,2023,44(8):81-87.(in Chinese)
[8]	赵一名,沈明霞,刘龙申,等.基于改进YOLO v5s和图像融合的笼养鸡死鸡检测方法研究[J].南京农业大学学报,2024,47(2):369-382.ZHAO Yiming,SHEN Mingxia,LIU Longshen,et al.Study on the method of detecting dead chickens in caged chicken based on improved YOLO v5s and image fusion[J].Journal of Nanjing Agricultural University,2024,47(2):369-382.(in Chinese)
[9]	GUO Y,LI C,LIU Q.R2N:a novel deep learning architecture for rain removal from single image[J].Comput.Mater.Contin.,2019,58(3):829-843.
[10]	徐旸,史金光,郑子玙,等.融合图像修复的遮挡目标检测算法[J].电光与控制,2023,30(1):21-28,86.XU Yang,SHI Jinguang,ZHENG Ziyu,et al.Occlusion target detection algorithm with image inpainting[J].Electronics Optics & Control,2023,30(1):21-28,86.(in Chinese)
[11]	孙志军,薛磊,许阳明,等.深度学习研究综述[J].计算机应用研究,2012,29(8):2806-2810.SUN Zhijun,XUE Lei,XU Yangming,et al.Overview of deep learning[J].Application Research of Computers,2012,29(8):2806-2810.(in Chinese)
[12]	周飞燕,金林鹏,董军.卷积神经网络研究综述[J].计算机学报,2017,40(6):1229-1251.ZHOU Feiyan,JIN Linpeng,DONG Jun.Review of convolutional neural network[J].Chinese Journal of Computers,2017,40(6):1229-1251.(in Chinese)
[13]	GIRSHICK R.Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision,2015:1440-1448.
[14]	李旭冬,叶茂,李涛.基于卷积神经网络的目标检测研究综述[J].计算机应用研究,2017,34(10):2881-2886,2891.LI Xudong,YE Mao,LI Tao.Review of object detection based on convolutional neural networks[J].Application Research of Computers,2017,34(10):2881-2886,2891.(in Chinese)
[15]	李彦冬,郝宗波,雷航.卷积神经网络研究综述[J].计算机应用,2016,36(9):2508-2515,2565.LI Yandong,HAO Zongbo,LEI Hang.Survey of convolutional neural network[J].Journal of Computer Applications,2016,36(9):2508-2515,2565.(in Chinese)
[16]	PARMAR N,VASWANI A,USZKOREIT J,et al.Image transformer[C]//International Conference on Machine Learning.PMLR,2018:4055-4064.
[17]	LIU Z,LIN Y,CAO Y,et al.Swin transformer:hierarchical vision transformer using shifted windows[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision,2021:10012-10022.
[18]	LIANG J,CAO J,SUN G,et al.Swinir:image restoration using swin transformer[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision,2021:1833-1844.
[19]	ZHANG H,GOODFELLOW I,METAXAS D,et al.Self-attention generative adversarial networks[C]//International Conference on Machine Learning.PMLR,2019:7354-7363.
[20]	BODENHOFER U,BONATESTA E,HOREJS-KAINRATH C,et al.MSA:an R package for multiple sequence alignment[J].Bioinformatics,2015,31(24):3997-3999.
[21]	ZHANG Z,SABUNCU M.Generalized cross entropy loss for training deep neural networks with noisy labels[J].Advances in Neural Information Processing Systems,2018,31:8792-8802.
[22]	梁建安,刘斌,梁美彦,等.基于彩色偏振图像的HSV空间目标增强方法[J].应用光学,2023,44(3):548-555.LIANG Jian'an,LIU Bin,LIANG Meiyan,et al.Target enhancement method in HSV color space based on color polarized image[J].Journal of Applied Optics,2023,44(3):548-555.(in Chinese)
[23]	WANG X,KONG T,SHEN C,et al.Solo:segmenting objects by locations[C]//Computer Vision-ECCV 2020:16th European Conference,2020:649-665.
[24]	WANG X,ZHANG R,KONG T,et al.Solov2:dynamic and fast instance segmentation[J].Advances in Neural Information Processing Systems,2020,33:17721-17732.
[25]	FANG Y,YANG S,WANG X,et al.Instances as queries[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision,2021:6910-6919.
[26]	YUE Y,FINLEY T,RADLINSKI F,et al.A support vector method for optimizing average precision[C]//Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval,2007:271-278.