Strawberry fruit recognition algorithm based on improved Faster R-CNN model

doi:10.14088/j.cnki.issn0439-8114.2023.11.032

Abstract

Abstract: In response to the problem of low recognition accuracy of the Faster R-CNN model for natural strawberries （Fragaria ananassa Duch.）, the Faster R-CNN model was improved by improving the RPN structure and replacing the backbone feature extraction network using live images of strawberries planted on ridges as the data source.The results showed that the improved Faster R-CNN model had an average precision （AP） of 0.893 0 when identifying mature strawberries and 0.820 7 when identifying immature strawberries. The accuracy of strawberry recognition reached a high level, solving the problem of difficulty in identifying immature strawberries.Meanwhile, in order to test the automatic counting performance of the model, a linear regression between automatic counting and manual counting was established based on the recognition results of the model. The correlation coefficients of mature and immature strawberries were 0.973 7 and 0.944 7, respectively. The high correlation between automatic counting and manual counting indicated that the improved Faster R-CNN model had high recognition performance and counting ability.

Key words: strawberry （Fragaria ananassa Duch.）, identification, Faster R-CNN model, ResNet50

CLC Number:

LI Jia-jun, ZHU Zi-feng, LIU Hong-xin, SU Yu-rong, WEN Chuan-wen, ZHANG Yuan-sheng, ZHANG Hui-min, DENG Li-miao. Strawberry fruit recognition algorithm based on improved Faster R-CNN model[J]. HUBEI AGRICULTURAL SCIENCES, 2023, 62(11): 183-190.

References

[1] 王鸣谦,薛莉,赵珺,等. 世界草莓生产及贸易现状[J]. 中国果树,2021(2):104-108.
[2] 肖逸尘,杨涵.南京草莓产业SWOT分析及发展策略[J].中国林业经济,2021(5):74-77.
[3] 王粮局,张立博,段运红,等. 基于视觉伺服的草莓采摘机器人果实定位方法[J]. 农业工程学报,2015,31(22):25-31.
[4] 林相泽,张俊媛,朱赛华,等.基于K-SVD和正交匹配追踪稀疏表示的稻飞虱图像分类方法[J].农业工程学报,2019,35(19):216-222.
[5] 王丹丹,何东健.基于R-FCN深度卷积神经网络的机器人疏果前苹果目标的识别[J].农业工程学报,2019,35(3):156-163.
[6] OLANIYI E O, OYEDOTUN O K, ADNAN K.Intelligent grading system for banana fruit using neural network arbitration:Intelligent grading system for banana fruit[J]. Journal of food process engineering, 2017, 40(1):e12335.
[7] 谢忠红,徐焕良,黄秋桂,等.基于高光谱图像和深度学习的菠菜新鲜度检测[J].农业工程学报,2019,35(13):277-284.
[8] JUNCHENG M, KEMING D, FEIXIANG Z, et al.A recognition method for cucumber diseases using leaf symptom images based on deep convolutional neural network[J]. Computers and electronics in agriculture, 2018, 154:18-24.
[9] 胡庆胜,符亚云,牛金星.采摘机器人视觉系统的目标识别提取研究[J].河南科技,2020,39(25):5-8.
[10] 闫勇,陈立夫,郭坤坤,等.Lab色彩模型下梯度Hough圆变换的成熟草莓识别[J].安徽农业大学学报,2020,47(3):488-493.
[11] 刘小刚,范诚,李加念,等.基于卷积神经网络的草莓识别方法[J].农业机械学报,2020,51(2):237-244.
[12] 任会,朱洪前.基于深度学习的目标橘子识别方法研究[J].计算机时代,2021(1):57-60,64.
[13] WANG T T, XU L, LI J B.Sdcrkl-gp: Scalable deep convolutional random kernel learning in gaussian process for image recognition[J].Neurocomputing, 2021, 456:288-298.
[14] 席芮,姜凯,张万枝,等.基于改进Faster R-CNN的马铃薯芽眼识别方法[J].农业机械学报,2020,51(4):216-223.
[15] 张磊,姜军生,李昕昱,等.基于快速卷积神经网络的果园果实检测试验研究[J].中国农机化学报,2020,41(10):183-190,210.
[16] ZHONG Z, JIN L,HUANG S.A new approach for text proposal generation and text detection in natural images[A].Ieee international conference on acoustics, speech and signal processing(ICASSP)[C].New Orleans,LA,USA:IEEE,2017.1208-1212.
[17] HE K M,ZHANG X Y,REN S Q,et al.Deep residual learning for image recognition[A]. Ieee conference on computer vision and pattern recognition[C].Las Vegas,NV,USA:IEEE,2016.770-778.
[18] REN S Q, HE KM, GIRSHICK, R, et al.Faster R-CCC: Towards real-time object detection with region proposal networks[J]. Ieee transactions on pattern analysis and machine intelligence,2017,39(6):1137-1149.
[19] 张文静,赵性祥,丁睿柔,等.基于Faster R-CNN算法的番茄识别检测方法[J].山东农业大学学报(自然科学版),2021,52(4):624-630.
[20] 岳有军,孙碧玉,王红君,等.基于级联卷积神经网络的番茄果实目标检测[J].科学技术与工程,2021,21(6):2387-2391.
[21] 陈怡佳. 基于Faster RCNN的目标检测系统[D]. 哈尔滨:哈尔滨理工大学,2019.
[22] 荆伟斌,李存军,竞霞,等.基于深度学习的苹果树侧视图果实识别[J].中国农业信息,2019,31(5):75-83.
[23] 闫建伟,赵源,张乐伟,等.改进Faster-RCNN自然环境下识别刺梨果实[J].农业工程学报,2019,35(18):143-150.
[24] 倪建功,李娟,邓立苗,等.基于知识蒸馏的胡萝卜外观品质等级智能检测[J].农业工程学报,2020,36(18):181-187.
[25] 成伟,张文爱,冯青春,等.基于改进YOLOv3的温室番茄果实识别估产方法[J].中国农机化学报,2021,42(4):176-182.
[26] 彭明霞,夏俊芳,彭辉. 融合FPN的Faster R-CNN复杂背景下棉田杂草高效识别方法[J]. 农业工程学报,2019,35(20):202-209.
[27] 李林升,曾平平.改进深度学习框架Faster-RCNN的苹果目标检测[J].机械设计与研究,2019,35(5):24-27.
[28] LI W Y,WANG D J,LI M,et al.Field detection of tiny pests from sticky trap images using deep learning in agricultural greenhouse[J]. Computers and electronics in agriculture,2021,183: 106048.
[29] SENGUPTA S, LEE W S.Identification and determination of the number of immature green citrus fruit in a canopy under different ambient light conditions[J]. Biosystems engineering, 2014, 117: 51-61.
[30] 赵辉,乔艳军,王红君,等.基于改进YOLOv3的果园复杂环境下苹果果实识别[J].农业工程学报,2021,37(16):127-135.