A marigold corolla detection model based on the improved YOLOv7 lightweight

被引:1
作者
Fan, Yixuan [1 ]
Tohti, Gulbahar [1 ,2 ]
Geni, Mamtimin [1 ]
Zhang, Guohui [1 ]
Yang, Jiayu [1 ]
机构
[1] Xinjiang Univ, Coll Mech Engn, Urumqi 830017, Xinjiang, Peoples R China
[2] Xi An Jiao Tong Univ, Xian 710049, Shaanxi, Peoples R China
关键词
Deep learning; Object detection; Marigold; YOLOv7; Lightweight;
D O I
10.1007/s11760-024-03107-2
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Marigold, as an important traditional Chinese medicinal plant renowned for its therapeutic attributes in heat dissipation, detoxification, liver protection, facial enhancement, and promotion of eye health, has witnessed a surge in demand. The demand for marigold is steadily rising, necessitating the inevitable shift toward mechanized harvesting in the industrialization of marigold cultivation. Consequently, this study endeavors to assemble a novel dataset in southern Xinjiang, China, crucial for marigold production. The focus is on improving the YOLOv7 model by lightweighting and proposing a set of detection models applicable to marigold. Through the elimination of superfluous object detection layers in the YOLOv7 model, substitution of conventional backbone network convolution with DSConv, replacement of the SPPCSPC module with Simplified SPPF, and subsequent model pruning and then retraining. This study aims to address challenges related to the deployment of mobile devices on the marigold-picking robot and the realization of high real-time detection. The experimental results demonstrate that the enhanced YOLOv7 model exhibited exceptional precision and mAP0.5 in marigold detection, achieving 93.9% and 97.7%, respectively, surpassing the performance of the original YOLOv7 model. Notably, the GFLOPs are a mere 2.3, representing only 2.2% of the computational load of the original model. Moreover, the parameter has been reduced to 15.04M, representing only 41.2% of the original model. The attained FPS, reaching 166.7, signifies a noteworthy enhancement of 26.7% compared to the original model. This showcases exceptional precision and speed in marigold detection, providing a strong technical foundation for the efficient harvesting of marigolds.
引用
收藏
页码:4703 / 4712
页数:10
相关论文
共 50 条
  • [21] YOLOv7-PSAFP: Crop pest and disease detection based on improved YOLOv7
    Du, Lujia
    Zhu, Junlong
    Liu, Muhua
    Wang, Lin
    IET IMAGE PROCESSING, 2025, 19 (01)
  • [22] Lightweight Algorithm for Apple Detection Based on an Improved YOLOv5 Model
    Sun, Yu
    Zhang, Dongwei
    Guo, Xindong
    Yang, Hua
    PLANTS-BASEL, 2023, 12 (17):
  • [23] Improved Apple Fruit Target Recognition Method Based on YOLOv7 Model
    Yang, Huawei
    Liu, Yinzeng
    Wang, Shaowei
    Qu, Huixing
    Li, Ning
    Wu, Jie
    Yan, Yinfa
    Zhang, Hongjian
    Wang, Jinxing
    Qiu, Jianfeng
    AGRICULTURE-BASEL, 2023, 13 (07):
  • [24] Lightweight Low-Light Object Detection Algorithm Based on YOLOv7
    Li Changyu
    Ge Lei
    LASER & OPTOELECTRONICS PROGRESS, 2024, 61 (14)
  • [25] EC-YOLO: Improved YOLOv7 Model for PCB Electronic Component Detection
    Luo, Shiyi
    Wan, Fang
    Lei, Guangbo
    Xu, Li
    Ye, Zhiwei
    Liu, Wei
    Zhou, Wen
    Xu, Chengzhi
    SENSORS, 2024, 24 (13)
  • [26] Tea Buds Detection in Complex Background Based on Improved YOLOv7
    Meng, Junquan
    Kang, Feng
    Wang, Yaxiong
    Tong, Siyuan
    Zhang, Chenxi
    Chen, Chongchong
    IEEE ACCESS, 2023, 11 : 88295 - 88304
  • [27] A detection method for dead caged hens based on improved YOLOv7
    Yang, Jikang
    Zhang, Tiemin
    Fang, Cheng
    Zheng, Haikun
    Ma, Chuang
    Wu, Zhenlong
    COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2024, 226
  • [28] An Enhanced Detection Method of PCB Defect Based on Improved YOLOv7
    Yang, Yujie
    Kang, Haiyan
    ELECTRONICS, 2023, 12 (09)
  • [29] Fruit Target Recognition and Maturity Detection Based on Improved YOLOv7
    Chen Q.
    Li R.
    Hu L.
    Zhang Y.
    Computer-Aided Design and Applications, 2024, 21 (S25): : 156 - 170
  • [30] Detection of whole body bone fractures based on improved YOLOv7
    Zou, Junting
    Arshad, Mohd Rizal
    BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2024, 91