•  
  •  
 

Abstract

Objective: This study is to improve the sorting efficiency of string tomatoes, and solve its false detection and false detection. Methods: First, collect the image data set of string tomatoes, expand the data and improve the generalization performance of the model through data enhancement, and 3×3 convolution is replaced by improved SVM-MHSA layer. By replacing softmax classification function in MHSA with SVM classification function which is more suitable for string tomatoes, the detection accuracy of string tomatoes is enhanced. Secondly, the remaining 3×3 convolution is replaced by deep separable convolution to reduce the number of parameters and improve the operation efficiency. Finally, random correction linear unit is introduced to improve the convergence speed of network training. Results: the test results show that the improved tiny YOLOv5l model can effectively realize the string single fruit recognition and positioning and the whole string fruit counting. The detection frame loss rate is reduced from 1.48% to 1.34%, the target loss rate is reduced from 1.98% to 1.73%, the confidence loss is reduced by 1.4%, the accuracy is increased from 97.36% to 98.89%,and the recall rate is increased from 97.35% to 98.56%. Conclusion: The tiny YOLOv5l algorithm is more accurate and lightweight. It has a high recognition accuracy in the face of challenges such as occlusion, background interference, illumination change and virtualization, and provides accurate information on the location of single fruit and the quantity of the whole string of fruit for post natal string tomato sorters.

Publication Date

12-28-2022

First Page

79

Last Page

86

DOI

10.13652/j.spjx.1003.5788.2022.80185

References

[1] 焦方圆,申金媛,郝同盟.一种基于卷积神经网络的烟叶等级识别方法[J].食品与机械,2022,38(2):222-227.JIAO F Y,SHEN J Y,HAO T M.A method of tobacco leaf grade recognition based on convolutional neural network[J].Food & Machinery,2022,38(2):222-227.
[2] MICHAEL H,CHRISTOPHER M C,SIMON D,et al.Fruit quantity and ripeness estimation using a robotic vision system[J].IEEE Robotics & Automation Letters,2018,3(4):2 995-3 002.
[3] ZHANG Q S,REN J,HUANG G,et al.Mining interpretable AOG representations from convolutional networks via active question answering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2021,43(11):3 949-3 963.
[4] 周胜安,黄耿生,张译匀,等.基于深度学习的水果缺陷实时检测方法[J].食品与机械,2021,37(11):123-129.ZHOU S A,HUANG G S,ZHANG Y J,et al.Real time detection method of fruit defects based on deep learning[J].Food & Machinery,2021,37(11):123-129.
[5] PARICOA I B,AHAMED T.Real time pear fruit detection and counting using YOLOv4 models and deep SORT[J].Sensors,2021,21(14):4 803.
[6] 高芳芳,武振超,索睿,等.基于深度学习与目标跟踪的苹果检测与视频计数方法[J].农业工程学报,2021,37(21):217-224.GAO F F,WU Z C,SUO R,et al.Apple detection and counting using real-time video based on deep learning and object tracking[J].Transactions of the Chinese Society of Agricultural Engineering,2021,37(21):217-224.
[7] WANG G,STAPPEN G V,BAETS B D.Automated detection and counting of Artemia using U-shaped fully convolutional networks and deep convolutional networks[J].Expert Systems with Applications,2021,171(4):114562.
[8] 陈科羽,时磊,刘博迪,等.改进YOLOv3的输电线路绝缘子检测方法[J].科技创新与应用,2021,11(34):79-82,86.CHEN K Y,SHI L,LIU B D,et al.Improved YOLOv3 insulator detection method for high voltage transmission and transformation lines[J].Technology Innovation and Application,2021,11(34):79-82,86.
[9] LI Y,HAN Z,XU H,et al.YOLOv3-lite:A lightweight crack detection network for aircraft structure based on depthwise separable convolutions[J].Applied Sciences,2019,9(18):3 781.
[10] CHEN B,MIAO X.Distribution line pole detection and counting based on YOLO using UAV inspection line video[J].Journal of Electrical Engineering and Technology,2020,15(1):441-448.
[11] LIU Z,WANG K,DONG H,et al.A cross-modal edge-guided salient object detection for RGB-D image[J].Neurocomputing,2021,454(5):168-177.
[12] 杨学存,和沛栋,陈丽媛,等.基于深度可分离卷积的轻量级YOLOv3输电线路鸟巢检测方法[J].智慧电力,2021,49(12):88-95.YANG X C,HE P D,CHEN L Y,et al.Birds nest detection on lightweight YOLOv3 transmission line based on deep separable convolution[J].Power Grid Analysis & Study,2021,49(12):88-95.
[13] 王静,孙紫雲,郭苹,等.改进YOLOv5的白细胞检测算法[J].计算机工程与应用,2022,58(4):134-142.WANG J,SUN Z Y,GUO P,et al.Improved leukocyte detection algorithm of YOLOv5[J].Computer Engineering and Applications,2022,58(4):134-142.
[14] ELPELTA G M,SALLAM H.Automatic prediction of COVID19 from chest images using modified ResNet50[J].Multimedia Tools and Applications,2021,80(17):26 451-26 463.
[15] 袁帅,王康,单义,等.基于多分支并行空洞卷积的多尺度目标检测算法[J].计算机辅助设计与图形学学报,2021,33(6):864-872.YUAN S,WANG K,SHAN Y,et al.Multi-scale object detection method based on multi-branch parallel dilated convolution[J].Journal of Computer-Aided Design & Computer Graphics,2021,33(6):864-872.
[16] 刘若愚,刘立波.基于改进全卷积网络模型的肺结节检测[J].激光与光电子学进展,2020,57(16):174-183.LIU R Y,LIU L B.Detection of pulmonary nodules based on improved full convolution network model[J].Laser & Optoelectronics Progress,2020,57(16):174-183.
[17] 张宏鸣,武杰,李永恒,等.多目标肉牛进食行为识别方法研究[J].农业机械学报,2020,51(10):259-267.ZHANG H M,WU J,LI Y H,et al.Recognition method of feeding behavior of multi-target beef cattle[J].Transactions of the Chinese Society of Agricultural Machinery,2020,51(10):259-267.
[18] SHEWELL C,NUGENT C,DONNELLY M,et al.Indoor localisation through object detection within multiple environments utilising a single wearable camera[J].Health & Technology,2017,7(1):51-60.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.