Deep Object Detection of Crop Weeds: Performance of YOLOv7 on a Real Case Dataset from UAV Images

被引:88
|
作者
Gallo, Ignazio [1 ]
Rehman, Anwar Ur [1 ]
Dehkordi, Ramin Heidarian [2 ]
Landro, Nicola [1 ]
La Grassa, Riccardo [3 ]
Boschetti, Mirco [2 ]
机构
[1] Univ Insubria, Dept Theoret & Appl Sci, I-20100 Varese, Italy
[2] CNR, Inst Electromagnet Sensing Environm, I-20133 Milan, Italy
[3] Italian Natl Inst Astrophys, I-00100 Rome, Italy
关键词
Deep Learning; Convolutional Neural Network; UAV imagery; object detection; YOLOv7; CONVOLUTIONAL NETWORKS; CLASSIFICATION;
D O I
10.3390/rs15020539
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Weeds are a crucial threat to agriculture, and in order to preserve crop productivity, spreading agrochemicals is a common practice with a potential negative impact on the environment. Methods that can support intelligent application are needed. Therefore, identification and mapping is a critical step in performing site-specific weed management. Unmanned aerial vehicle (UAV) data streams are considered the best for weed detection due to the high resolution and flexibility of data acquisition and the spatial explicit dimensions of imagery. However, with the existence of unstructured crop conditions and the high biological variation of weeds, it remains a difficult challenge to generate accurate weed recognition and detection models. Two critical barriers to tackling this challenge are related to (1) a lack of case-specific, large, and comprehensive weed UAV image datasets for the crop of interest, (2) defining the most appropriate computer vision (CV) weed detection models to assess the operationality of detection approaches in real case conditions. Deep Learning (DL) algorithms, appropriately trained to deal with the real case complexity of UAV data in agriculture, can provide valid alternative solutions with respect to standard CV approaches for an accurate weed recognition model. In this framework, this paper first introduces a new weed and crop dataset named Chicory Plant (CP) and then tests state-of-the-art DL algorithms for object detection. A total of 12,113 bounding box annotations were generated to identify weed targets (Mercurialis annua) from more than 3000 RGB images of chicory plantations, collected using a UAV system at various stages of crop and weed growth. Deep weed object detection was conducted by testing the most recent You Only Look Once version 7 (YOLOv7) on both the CP and publicly available datasets (Lincoln beet (LB)), for which a previous version of YOLO was used to map weeds and crops. The YOLOv7 results obtained for the CP dataset were encouraging, outperforming the other YOLO variants by producing value metrics of 56.6%, 62.1%, and 61.3% for the mAP@0.5 scores, recall, and precision, respectively. Furthermore, the YOLOv7 model applied to the LB dataset surpassed the existing published results by increasing the mAP@0.5 scores from 51% to 61%, 67.5% to 74.1%, and 34.6% to 48% for the total mAP, mAP for weeds, and mAP for sugar beets, respectively. This study illustrates the potential of the YOLOv7 model for weed detection but remarks on the fundamental needs of large-scale, annotated weed datasets to develop and evaluate models in real-case field circumstances.
引用
收藏
页数:17
相关论文
共 38 条
  • [1] YOLOv7-sea: Object Detection of Maritime UAV Images based on Improved YOLOv7
    Zhao, Hangyue
    Zhang, Hongpu
    Zhao, Yanyun
    2023 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WORKSHOPS (WACVW), 2023, : 233 - 238
  • [2] Improved YOLOv7 for UAV Image Object Detection
    Zou, Zhentao
    Li, Zeping
    Computer Engineering and Applications, 60 (08): : 173 - 181
  • [3] Improved YOLOv7 Object Detection Algorithm for Fisheye Images
    Wu, Zhaodong
    Xu, Cheng
    Liu, Hongzhe
    Fu, Ying
    Jian, Muwei
    Computer Engineering and Applications, 2024, 60 (14) : 250 - 256
  • [4] Object Detection Based on Improved YOLOv7 for UAV Aerial Image
    Cui, Liqun
    Cao, Huawei
    Computer Engineering and Applications, 60 (20): : 189 - 197
  • [5] Cotton Disease Detection on UAV Images: A Deep Learning-Based Approach with YOLOv7
    Kinda, Zakaria
    Malo, Sadouanouan
    Bayala, Thierry Roger
    Wonni, Issa
    TOWARDS NEW E-INFRASTRUCTURE AND E-SERVICES FOR DEVELOPING COUNTRIES, AFRICOMM 2023, PT II, 2025, 588 : 234 - 249
  • [6] ATS-YOLOv7: A Real-Time Multi-Scale Object Detection Method for UAV Aerial Images Based on Improved YOLOv7
    Zhang, Heng
    Shao, Faming
    He, Xiaohui
    Chu, Weijun
    Zhao, Dewei
    Zhang, Zihan
    Bi, Shaohua
    ELECTRONICS, 2023, 12 (23)
  • [7] Small object detection model for UAV aerial image based on YOLOv7
    Jinguang Chen
    Ronghui Wen
    Lili Ma
    Signal, Image and Video Processing, 2024, 18 : 2695 - 2707
  • [8] Small object detection model for UAV aerial image based on YOLOv7
    Chen, Jinguang
    Wen, Ronghui
    Ma, Lili
    SIGNAL IMAGE AND VIDEO PROCESSING, 2024, 18 (03) : 2695 - 2707
  • [9] UAV imagery, advanced deep learning, and YOLOv7 object detection model in enhancing citrus yield estimation
    Daiaeddine, Mohamed Jibril
    Badrouss, Sara
    El Harti, Abderrazak
    Bachaoui, El Mostafa
    Biniz, Mohamed
    Sultan, Hicham Mouncif
    FOODS AND RAW MATERIALS, 2025, 13 (02) : 242 - 253
  • [10] Real-time Object Detection Performance Analysis Using YOLOv7 on Edge Devices
    Santos, Ricardo C. Camara de M.
    Silva, Mateus Coelho
    Oliveira, Ricardo A. R.
    IEEE LATIN AMERICA TRANSACTIONS, 2024, 22 (10) : 799 - 805