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

被引:92
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 54 条
  • [1] Performance of deep learning models for classifying and detecting common weeds in corn and soybean production systems
    Ahmad, Aanis
    Saraswat, Dharmendra
    Aggarwal, Varun
    Etienne, Aaron
    Hancock, Benjamin
    [J]. COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2021, 184 (184)
  • [2] [Anonymous], IMAGE AUGMENTATION R
  • [3] Deep Learning with Unsupervised Data Labeling for Weed Detection in Line Crops in UAV Images
    Bah, M. Dian
    Hafiane, Adel
    Canals, Raphael
    [J]. REMOTE SENSING, 2018, 10 (11)
  • [4] Opportunities for Robotic Systems and Automation in Cotton Production
    Barnes, Edward
    Morgan, Gaylon
    Hake, Kater
    Devine, Jon
    Kurtz, Ryan
    Ibendahl, Gregory
    Sharda, Ajay
    Rains, Glen
    Snider, John
    Maja, Joe Mari
    Thomasson, J. Alex
    Lu, Yuzhen
    Gharakhani, Hussein
    Griffin, James
    Kimura, Emi
    Hardin, Robert
    Raper, Tyson
    Young, Sierra
    Fue, Kadeghe
    Pelletier, Mathew
    Wanjura, John
    Holt, Greg
    [J]. AGRIENGINEERING, 2021, 3 (02): : 339 - 362
  • [5] Thermal weed control technologies for conservation agriculture-a review
    Bauer, Martin V.
    Marx, Christian
    Bauer, Fabienne V.
    Flury, Dominique M.
    Ripken, Tammo
    Streit, Bernhard
    [J]. WEED RESEARCH, 2020, 60 (04) : 241 - 250
  • [6] Bochkovskiy A, 2020, ARXIV 200410934, DOI DOI 10.48550/ARXIV.2004.10934
  • [7] Performance evaluation of deep transfer learning on multi-class identification of common weed species in cotton production systems
    Chen, Dong
    Lu, Yuzhen
    Li, Zhaojian
    Young, Sierra
    [J]. COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2022, 198
  • [8] You Only Look One-level Feature
    Chen, Qiang
    Wang, Yingming
    Yang, Tong
    Zhang, Xiangyu
    Cheng, Jian
    Sun, Jian
    [J]. 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 13034 - 13043
  • [9] Chien W., 2022, YOLOV7 REPOSITRY ALL
  • [10] Chostner B., 2017, Resour. Mag, V24, P4