1.College of Engineering, Heilongjiang Bayi Agricultural University, Daqing 163319, China
2.Soybean Research Institute/Key Laboratory of Hybrid Soybean Breeding of Ministry of Agriculture and Rural Affairs, Jilin Academy of Agricultural Sciences, Changchun 130033, China
In order to build a color detection model of hybrid soybean hypocotyl, soybean plants in natural growing environment were used as research objects. This study used a self-propelled soybean phenotyping information collection platform to obtain soybean plant image data in the farmland, and built hybrid soybean hypocotyl color dataset. Color dataset of hybrid soybean hypocotyl were detected with different object detection models (SSD, Faster R-CNN, YOLOv3, YOLOv4, YOLOv5, YOLOX and YOLOv7). The model score (F1), mean of average precision (mAP), and detection speed were compared to evaluate the performance of different models in color detection of hybrid soybean hypocotyl. A color detection model of hybrid soybean hypocotyl, YOLOv7-CSW, was established by adding CARAFE feature up sampling operator, SE attention mechanism module and WIoU box loss function into the YOLOv7 network. The improved model was used to perform ablation tests on the hybrid soybean hypocotyl color dataset. The results showed that: 1) The F1 (0.92) and mAP (94.3%) of YOLOv7 model were significantly higher than those of other models; 2) The detection speed of YOLOv7 model was 58 fps, which was only lower than YOLOv5 and YOLOX, but the detection speed could meet the requirements for real-time detection tasks; 3) Compared with YOLOv7 model, the F1 and mAP of YOLOv7-CSW model were increased by 0.04 and 2.6% respectively; 4) The detection speed of YOLOv7-CSW model was 5 fps higher than YOLOv7 model, and it realized real-time detection of hybrid soybean hypocotyl color. To sum up, YOLOv7-CSW model could better obtain hypocotyl color features and accurately detect the object position, improved the object detection performance in complex farmland environments, and realized rapid and accurate detection of hypocotyl color of field hybrid soybean.
为实现田间苗期杂交大豆胚轴颜色检测,提出1种改进YOLOv7的目标检测模型YOLOv7-CSW。改进算法的核心原则是在保证模型能够正常检测目标的同时,提高目标的田间定位能力及检测准确率。利用SE(Squeeze-and-Excitation Network)注意力机制模块,在主干网络上采样前进行卷积提取特征。使用CARAFE(Content-Aware ReAssembly of FEatures)特征上采样算子替代UPSample算子,采用WIoU(Wise-IoU)损失函数替换CIoU损失函数。
GaiJ Y, DingD R, CuiZ L, QiuJ X. Development and performance of the cytoplasmic-nuclear male sterile line NJCMS1A of soybean[J]. Scientia Agricultura Sinica, 1999, 32(5): 23-27 (in Chinese)
LiX L, ZhangB, WangK, YuP. Development and application of artificial intelligence[J]. Journal of Beijing University of Technology, 2020, 46(6): 583-590 (in Chinese)
SunH, LiS, LiM Z, LiuH J, QiaoL, ZhangY. Research progress of image sensing and deep learning in agriculture[J]. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51(5): 1-17 (in Chinese)
HuangJ C, TangA, ChenG M, ZhangD, GaoF Z, ChenT. Mobile recognition solution of tea buds based on compact YOLO v4 algorithm[J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(3): 282-290 (in Chinese)
HeY T, LiB, ZhangF, TaoH B, GuL C, JiaoJ. Pig face recognition based on improved YOLOv3[J]. Journal of China Agricultural University, 2021, 26(3): 53-62 (in Chinese)
[17]
XuB, CuiX, JiW, YuanH, WangJ C. Apple grading method design and implementation for automatic grader based on improved YOLOv5[J/OL]. Agriculture,(--). DOI:doi.org/10.3390/agriculture13010124
[18]
WangY T, XingZ W, MaL F, QuA L, XueJ R. Object detection algorithm for lingwu long jujubes based on the improved ssd[J/OL]. Agriculture, (--). DOI:doi.org/10.3390/agriculture12091456
SongH B, MaB L, ShangY Y, WenY C, ZhangS J. Detection of young apple fruits based on YOLO v7-ECA model[J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(6): 233-242 (in Chinese)
[21]
WangC Y, BochkovskiyA, LiaoH Y M. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors [C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York:Institute of Electrical and Electronics Engineers, 2022: 7464-7475
ZhangY S, ZhaoY D, YuanM C. Insect identification and counting based on an improved Faster-RCNN model of the sticky board image[J]. Journal of China Agricultural University, 2019, 24(5): 115-122 (in Chinese)
ShangF N, ZhouX C, LiangY K, XiaoM W, ChenQ, LuoC D. Detection method for dragon fruit in natural environment based on improved YOLOX[J]. Smart Agriculture, 2022, 4(3): 120-131 (in Chinese)
[26]
LiJ Y, LiQ D, YuC T, HeY, QiL Q, ShiW Q, ZhangW. A model for identifying soybean growth periods based on multi-source sensors and improved convolutional neural network[J/OL]. Agronomy, 2022, 12(12): 2991 (--). DOI:doi.org/10.3390/agronomy12122991
WangX R, XuY, ZhouJ P, ChenJ R. Safflower picking recognition in complex environments based on an improved YOLOv7[J]. Transactions of the Chinese Society of Agricultural Engineering, 2023, 39(6): 169-176 (in Chinese)
[32]
WangJ Q, ChenK, XuR, LiuZ W, LoyC C, LinD H. Carafe: Content-aware reassembly of features [C]. Proceedings of the IEEE/CVF International Conference on Computer Vision. New York: Institute of Electrical and Electronics Engineers, 2019: 3007-3016
WangD W, HuL C, FangJ, XuZ J. Small object detection algorithm based on improved Double-Head RCNN for UAV aerial images[J/OL]. Journal of Beijing University of Aeronautics and Astronautics, (--). DOI:10.13700/j.bh.1001-5965.2022.0591 (in Chinese)
[35]
HuJ, ShenL, SunG. Squeeze-and-excitation networks [C]. Proceedings of the IEEE conference on computer vision and pattern recognition. New York: Institute of Electrical and Electronics Engineers, 2018: 7132-7141
MaR Z, HeH D, ChenY, LaiY H, JiaoR, TangH. Recognition method for maturity of pitaya based on improved YOLOv5[J]. Journal of Shenyang Agricultural University, 2023, 54(2): 196-206 (in Chinese)
[38]
程彦军. 基于监控视频的行人重识别技术研究[D]. 武汉: 华中科技大学, 2019
[39]
ChengY J. A thesis submitted in partial fulfillment of the requirements for the degree of master of engineering[D]. Wuhan: Huazhong University of Science & Technology, 2019 (in Chinese)
LiangZ Y. Research on cascaded text detection in natural scene images based on SSD[D]. Wuhan: Wuhan University, 2019 (in Chinese)
[43]
TuS Q, PangJ, LiuH F, ZhuangN, ChenY, ZhengC, WanH, XueY J. Passion fruit detection and counting based on multiple scale faster R-CNN using RGB-D images [J]. Precision Agriculture, 2020, 21(5): 1072-1091
[44]
常洪彬. 基于深度学习的航空遥感图像目标检测算法研究[D]. 长春: 吉林大学, 2022
[45]
ChangH B. Research on object detection of aerial remote sensing images based on deep learning[D]. Changchun: Jilin University, 2022 (in Chinese)
[46]
NarayanaC L, RamanaK V. An efficient real-time weed detection technique using YOLOv7[J]. International Journal of Advanced Computer Science and Applications, 2023, 14(2): 550-556
[47]
刘健. 基于深度学习的农作物病害视觉识别系统设计与开发[D]. 扬州: 扬州大学, 2022
[48]
LiuJ. Design and development of visual recognition system for crop diseases based on deep learning[D]. Yangzhou: Yangzhou University, 2022 (in Chinese)
[49]
XiaY, NguyenM, YanW Q. A real-time kiwifruit detection based on improved YOLOv7[C]. International Conference on Image and Vision Computing New Zealand. Cham: Springer, 2022: 48-61