CHENG Zhenzhen,CHENG Yifan,MIAO Bailing.Apple Target Detection Method in Different Scenarios Based on YOLOv3[J].Northern Horticulture,2024,(22):137-146.[doi:10.11937/bfyy.20241542]
基于YOLOv3的不同场景下苹果目标检测方法
- Title:
- Apple Target Detection Method in Different Scenarios Based on YOLOv3
- 文章编号:
- 1001-0009(2024)22-0137-10
- Keywords:
- apple; YOLOv3; target detection; deep learning
- 分类号:
- S 431.9
- 文献标志码:
- A
- 摘要:
- 苹果采摘机器人依赖于精准的苹果目标检测来达到智能采摘。然而苹果数量、光照强度、生长阶段等条件使得苹果检测变得复杂，为此以苹果为试材，采用基于YOLOv3（You Only Look Once version 3）的目标检测方法，研究了不同场景下的苹果目标检测效果。针对苹果的外形特征，调整了YOLOv3的锚点尺寸以优化苹果在不同尺度上的变化。为了验证模型有效性，试验以苹果数量、拍摄不同光照的角度、苹果不同生长阶段为变量，对所提出的算法与YOLOv2（You Only Look Once version 2）、SSD（Single Shot MultiBox Detector）2种现有算法在目标识别效果进行了比较分析。结果表明：在不同条件下，所提出的方法在苹果目标检测的F1值上均达到了88%以上，可为苹果采摘机器人的开发提供技术支持。
- Abstract:
- Apple-picking robots relied on precise apple target detection to achieve intelligent picking.However，conditions such as the number of apples，light intensity，and growth stages made apple detection complex.To address this，apples were used as test materials，and the YOLOv3 (You Only Look Once version 3) object detection method was employed to study the effectiveness of apple target detection in different scenarios.The anchor sizes of YOLOv3 were adjusted to optimize the variations in apple size according to the specific characteristics of apple shapes.To verify the effectiveness of the model，experiments were conducted using variables such as the number of apples，different lighting angles，and different growth stages of apples.The proposed algorithm was compared and analyzed with two existing algorithms，YOLOv2 (You Only Look Once version 2) and SSD (Single Shot MultiBox Detector)，in terms of target recognition effectiveness.The results indicated that under different conditions，the proposed method achieved F1 scores of over 88% in apple target detection，providing technical support for the development of apple-picking robots.
参考文献/References:
［1］邱美娟,刘布春,刘园,等.中国北方主产地苹果始花期模拟及晚霜冻风险评估［J］.农业工程学报,2020,36(21):154-163.［2］陈青,殷程凯,郭自良,等.苹果采摘机器人关键技术研究现状与发展趋势［J］.农业工程学报,2023,39(4):1-15.［3］张彦斐,刘茗洋,宫金良,等.基于两级分割与区域标记梯度Hough圆变换的苹果识别［J］.农业工程学报,2022,38(19):110-121.［4］KAPACH K，BARNEA E，MAIRON R，et al.Computer vision for fruit harvesting robots-state of the art and challenges ahead［J］.International Journal of Computational Vision and Robotics，2012，3(1/2):4.［5］JI W，ZHAO D，CHENG F，et al.Automatic recognition vision system guided for apple harvesting robot［J］.Computers & Electrical Engineering，2012，38(5)：1186-1195.［6］RAKUN J，STAJNKO D，ZAZULA D.Detecting fruits in natural scenes by using spatial-frequency based texture analysis and multiview geometry［J］.Computers and Electronics in Agriculture，2011，76(1)：80-88.［7］田玉宇.复杂环境下苹果采摘机器人的目标识别算法［D］.济南：山东师范大学,2020.［8］周桂红,马帅,梁芳芳.基于改进YOLOv4模型的全景图像苹果识别［J］.农业工程学报,2022,38(21):159-168.［9］GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation［C］//Proceedings of the IEEE conference on computer vision and pattern recognition,2014:580-587.［10］GIRSHICK R.Fast R-CNN［C］//International conference on computer vision.IEEE computer society,2015:1440-1448.［11］REN S,HE K,GIRSHICK R,et al.Faster R-CNN: Towards real-time object detection with region proposal networks［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,39(6):1137-1149.［12］熊俊涛，刘振，汤林越，等.自然环境下绿色柑橘视觉检测技术研究［J］.农业机械学报，2018，49(4)：45-52.［13］LIU W，ANGUELOV D，ERHAN D，et al.Ssd：Single shot MultiBox detector［M］.Cham:Springer International Publishing,2016.［14］薛月菊，黄宁，涂淑琴，等.未成熟芒果的改进YOLOv2识别方法［J］.农业工程学报，2018，34(7)：173-179.［15］REDUMON J,FARHADI A.YOLO9000:better,faster,stronger［C］//Proceedings of the IEEE conference on computer vision and pattern recognition,2017:7263-7271.［16］RUSSELL B C，TORRALBA A，MURPHY K P，et al.LabelMe：A database and web-based tool for image annotation［J］.International Journal of Computer Vision，2008，77(1)：157-173.
相似文献/References:
[1]曹慧,姜倩倩,张保仁,等.节水养根处理对苹果枝叶生长发育的影响[J].北方园艺,2013,37(04):1.
[2]王贵平,王金政,薛晓敏,等.叶面喷施甜菜碱对干旱胁迫下苹果幼树[J].北方园艺,2014,38(12):10.
WANG Gui-ping,WANG Jin-zheng,XUE Xiao-min,et al.Effect of Spraying Glycinebetaine on Physiological Responses of Apple Young Trees Under Drought Stress[J].Northern Horticulture,2014,38(22):10.
[3]李 莹,任亚梅,马学敏,等.1-MCP处理结合不同贮藏条件对苹果常温货架品质的影响[J].北方园艺,2014,38(11):137.
LI Ying,REN Ya-mei,MA Xue-min,et al.Effects of 1-MCP Treatment With Different Storage Conditions on Quality of Apple During Shelf Life at Room Temperature[J].Northern Horticulture,2014,38(22):137.
[4]党建美,胡清玉,张 瑜,等.炭疽菌叶枯病在我国苹果产区的发生分布及趋势分析[J].北方园艺,2014,38(10):177.
DANG Jian-mei,HU Qing-yu,ZHANG Yu,et al.The Occurrence Trend and Distribution of Apple Glomerella Leaf Spot in China[J].Northern Horticulture,2014,38(22):177.
[5]解贝贝,沙广利,戴洪义,等.六种无融合生殖砧木对‘嘎拉’苹果果实大小和品质的影响[J].北方园艺,2013,37(17):23.
XIE Bei-bei,SHA Guang-li,DAI Hong-yi,et al.Effect of Six No Fusion Reproductive Rootstocks on the Fruit Size and Quality of ‘Gala’ Apple[J].Northern Horticulture,2013,37(22):23.
[6]冯娟娟,刘军弟,霍学喜.世界主要落叶水果主产国生产与贸易预测分析[J].北方园艺,2014,38(04):195.
[7]吕天星,王铭,伊凯.苹果杂种实生苗叶片性状遗传趋势研究[J].北方园艺,2013,37(14):8.
LV Tian-xing,WANG Ming,YI Kai.Study on Genetic Trends of Leaf Traits in Apple Hybrid Seedling[J].Northern Horticulture,2013,37(22):8.
[8]史星雲,王立新,王亚杰,等.陕西省苹果主栽品种品质差异及相关性分析[J].北方园艺,2013,37(14):11.
SHI Xing-yun,WANG Li-xin,WANG Ya-jie,et al.Quality and Correlation Analysis of the Main Apple Cultivars in Shaanxi Province[J].Northern Horticulture,2013,37(22):11.
[9]隗晓雯,郭静,王菲,等.不同矮化砧木叶片酶活性与内源激素含量的差异[J].北方园艺,2013,37(14):16.
WEI Xiao-wen,GUO Jing,WANG Fei,et al.Difference of Enzyme Activity and the Content of Endogenous Hormones in the Leaves of Different Apple Dwarfing Rootstocks[J].Northern Horticulture,2013,37(22):16.
[10]刘 君,刁永强,陈淑英,等.伊犁河谷不同苹果品种苗木冻害调查及分析[J].北方园艺,2013,37(23):34.
LIU Jun,DIAO Yong-qiang,CHEN Shu-ying,et al.An Investigation and Analysis of Freeze Injury of Different Varieties Apple Seedlings in Ili Area[J].Northern Horticulture,2013,37(22):34.
备注/Memo
第一作者简介：程浈浈(1994-)，女，博士，讲师，现主要从事图像处理与模式识别等研究工作。E-mail：2021190008@xyafu.edu.cn.责任作者：龚守富(1976-)，男，硕士，教授，现主要从事园艺作物栽培及产后加工等研究工作。E-mail: 2000230016@xyafu.edu.cn.基金项目：河南省重点研发与推广专项（科技攻关）资助项目（232102111118）。收稿日期：2024-04-11