Evaluation of YOLO Object Detectors for Weed Detection in Different Turfgrass Scenarios
Source abstract
Abstract
The advancement of computer vision technology has allowed for the easy detection of weeds and other stressors in turfgrasses and agriculture. This study aimed to evaluate the feasibility of single shot object detectors for weed detection in lawns, which represents a difficult task. In this study, four different YOLO (You Only Look Once) object detectors version, along with all their various scales, were trained on a public ‘Weeds’ dataset with 4203 digital images of weeds growing in lawns with a total of 11,385 annotations and tested for weed detection in turfgrasses. Different weed species were considered as one class (‘Weeds’). Trained models were tested on the test subset of the ‘Weeds’ dataset and three additional test datasets. Precision (P), recall (R), and mean average precision (mAP_0.5 and mAP_0.5:0.95) were used to evaluate the different model scales. YOLOv8l obtained the overall highest performance in the ‘Weeds’ test subset resulting in a P (0.9476), mAP_0.5 (0.9795), and mAP_0.5:0.95 (0.8123), while best R was obtained from YOLOv5m (0.9663). Despite YOLOv8l high performances, the outcomes obtained on the additional test datasets have underscored the necessity for further enhancements to address the challenges impeding accurate weed detection.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Plant Disease Management Techniques · Smart Agriculture and AI · Plant Pathogens and Fungal Diseases
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Agriculture, Food and Environment, University of Pisa, Via del Borghetto 80, 56124 Pisa, Italy
Department of Environment, Faculty of Bioscience Engineering, Ghent University, 9000 Ghent, Belgium
Departamento de Ingeniería Aeroespacial y Mecánica de Fluidos Área Agroforestal, University of Sevilla, 41013 Sevilla, Spain
References (62)
Show source-provided references
1. Use of Herbicides on Turfgrass10.1590/S0100-83582013000200024 ↗
2. Impact of European Legislation on Marketed Pesticides—A View from the Standpoint of Health Impact Assessment Studies10.1016/j.envint.2009.06.011 ↗
3. Ecological Impacts of Early 21st Century Agricultural Change in Europe—A Review10.1016/j.jenvman.2009.07.005 ↗
4. European Commission (2023, July 02). EU Pesticides Database 2022. Available online: https://food.ec.europa.eu/plants/pesticides/eu-pesticides-database_en.
5. Managing Cool-Season Turfgrass without Herbicides: Optimizing Maintenance Practices to Control Weeds10.1002/csc2.20175 ↗
6. Martelloni, L., Frasconi, C., Sportelli, M., Fontanelli, M., Raffaelli, M., and Peruzzi, A. (2020). Flaming, Glyphosate, Hot Foam and Nonanoic Acid for Weed Control: A Comparison. Agronomy, 10.10.3390/agronomy10010129 ↗
7. A Smart Sprayer for Weed Control in Bermudagrass Turf Based on the Herbicide Weed Control Spectrum10.1016/j.cropro.2023.106270 ↗
8. Deep Learning for Detecting Herbicide Weed Control Spectrum in Turfgrass10.1186/s13007-022-00929-4 ↗
9. Evaluation of Convolutional Neural Networks for Herbicide Susceptibility-Based Weed Detection in Turf10.3389/fpls.2023.1096802 ↗
10. Watchareeruetai, U., Takeuchi, Y., Matsumoto, T., Kudo, H., and Ohnishi, N. (2006, January 7–9). Computer Vision Based Methods for Detecting Weeds in Lawns. Proceedings of the 2006 IEEE Conference on Cybernetics and Intelligent Systems, Bangkok, Thailand.10.1109/ICCIS.2006.252275 ↗
11. Comparison of Different Classification Algorithms for Weed Detection from Images Based on Shape Parameters
12. Identification of Broad-Leaved Dock (Rumex obtusifolius L.) on Grassland by Means of Digital Image Processing10.1007/s11119-006-9006-9 ↗
13. A New Algorithm for Automatic Rumex Obtusifolius Detection in Digital Images Using Colour and Texture Features and the Influence of Image Resolution10.1007/s11119-006-9024-7 ↗
14. Edge Detection for Weed Recognition in Lawns10.1016/j.compag.2020.105684 ↗
15. Recent Advances in Convolutional Neural Networks10.1016/j.patcog.2017.10.013 ↗
16. Deep Learning10.1038/nature14539 ↗
17. Weed Detection to Weed Recognition: Reviewing 50 Years of Research to Identify Constraints and Opportunities for Large-Scale Cropping Systems10.1017/wet.2022.84 ↗
18. Deep Learning for Image-Based Weed Detection in Turfgrass10.1016/j.eja.2019.01.004 ↗
19. Detection of Broadleaf Weeds Growing in Turfgrass with Convolutional Neural Networks10.1002/ps.5349 ↗
20. Weed Detection in Perennial Ryegrass with Deep Learning Convolutional Neural Network10.3389/fpls.2019.01422 ↗
21. A Deep Learning-Based Method for Classification, Detection, and Localization of Weeds in Turfgrass10.1002/ps.7102 ↗
22. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27–30). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.91 ↗
23. The Pascal Visual Object Classes Challenge: A Retrospective10.1007/s11263-014-0733-5 ↗
24. Fleet, D., Pajdla, T., Schiele, B., and Tuytelaars, T. (2014). Microsoft COCO: Common Objects in Context BT—Computer Vision—ECCV 2014, Springer International Publishing.10.1007/978-3-319-10590-1 ↗
25. Yoloweeds: A Novel Benchmark of Yolo Object Detectors for Multi-Class Weed Detection in Cotton Production Systems10.1016/j.compag.2023.107655 ↗
26. Traitement Du Signal Weed Detection in Images of Carrot Fields Based on Improved YOLO V410.18280/ts.380211 ↗
27. Weed Detection in Sesame Fields Using a YOLO Model with an Enhanced Attention Mechanism and Feature Fusion10.1016/j.compag.2022.107412 ↗
28. Drought Stress Impact on the Performance of Deep Convolutional Neural Networks for Weed Detection in Bahiagrass10.1111/gfs.12583 ↗
29. Medrano, R. (2021). Feasibility of Real-Time Weed Detection in Turfgrass on an Edge Device. [Master’s Thesis, California State Univeristy].
30. Redmon, J., and Farhadi, A. (2017, January 21–26). YOLO9000: Better, Faster, Stronger. Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.690 ↗
31. Redmon, J., and Farhadi, A. (2018). YOLOv3: An Incremental Improvement. arXiv.
32. Bochkovskiy, A., Wang, C.-Y., and Liao, H.-Y.M. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv.
33. Jocher, G. (2023, July 02). Ultralytics/Yolov5: v3.1—Bug Fixes and Performance Improvements. Zenodo 2020. Available online: https://zenodo.org/record/4154370.
34. Li, C., Li, L., Geng, Y., Jiang, H., Cheng, M., Zhang, B., Ke, Z., Xu, X., and Chu, X. (2023). YOLOv6 v3.0: A Full-Scale Reloading. arXiv.
35. Wang, C.-Y., Bochkovskiy, A., and Liao, H.-Y.M. (2022, January 18–24). YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52729.2023.00721 ↗
36. (2023, July 02). Ultralytics Yolov8 2023. Available online: https://github.com/ultralytics/ultralytics.
37. Wang, C.Y., Mark Liao, H.Y., Wu, Y.H., Chen, P.Y., Hsieh, J.W., and Yeh, I.H. (2020, January 14–19). CSPNet: A New Backbone That Can Enhance Learning Capability of CNN. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, USA.10.1109/CVPRW50498.2020.00203 ↗
38. Wang, K., Liew, J.H., Zou, Y., Zhou, D., and Feng, J. (November, January 27). PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.10.1109/ICCV.2019.00929 ↗
39. Nepal, U., and Eslamiat, H. (2022). Comparing YOLOv3, YOLOv4 and YOLOv5 for Autonomous Landing Spot Detection in Faulty UAVs. Sensors, 22.10.3390/s22020464 ↗
40. Xu, R., Lin, H., Lu, K., Cao, L., and Liu, Y. (2021). A Forest Fire Detection System Based on Ensemble Learning. Forests, 12.10.3390/f12020217 ↗
41. Ding, X., Zhang, X., Han, J., Ding, G., and Sun, J. (2019, January 15–20). RepVGG: Making VGG-Style ConvNets Great Again. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.
42. Liu, S. (2018, January 18–23). Path Aggregation Network for Instance Segmentation. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00913 ↗
43. Scott, M.R. (2021, January 11–17). TOOD: Task-Aligned One-Stage Object Detection. Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, BC, Canada.
44. Zhang, H., Wang, Y., Dayoub, F., and Niko, S. (2022, January 18–24). VarifocalNet: An IoU-Aware Dense Object Detector. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR46437.2021.00841 ↗
45. Loss, S., Powerful, M., For, L., and Box, B. (2022). 1 SIoU Loss: More Powerful Learning for Bounding Box Regression Zhora Gevorgyan. arXiv.
46. Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., and Savarese, S. (2019). Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression. arXiv.10.1109/CVPR.2019.00075 ↗
47. Ding, X., Chen, H., Zhang, X., Huang, K., Han, J., and Ding, G. (2023). Re-Parameterizingyouroptimizersratherthan Architectures. arXiv.
48. Changyong, S., Yifan, L., Jianfei, G., Zheng, Y., and Chunhua, S. (2021, January 11–17). Channel-Wise Knowledge Distillation for Dense Prediction. Proceedings of the IEEE/CVFInternationalConferenceonComputerVision, Montreal, BC, Canada.
49. Terven, J., and Cordova-Esparza, D. (2023). A Comprehensive Review of YOLO: From YOLOv1 to YOLOv8 and Beyond. arXiv.
50. Wang, C., Liao, H.M., Yeh, I., and Corporation, E.M. (2014). Designing Network Design Strategies Through Gradient Path Analysis. arXiv.
51. Wang, C., Yeh, I., and Liao, H.M. (2021). You Only Learn One Representation: Unified Network for Multiple Tasks. arXiv.
52. Tan, M., Pang, R., and Le, Q.V. (2020, January 13–19). EfficientDet: Scalable and Efficient Object Detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.01079 ↗
53. Tan, M., and Le, Q.V. (2019, January 10–15). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Proceedings of the International Conference on Machine Learning, Honolulu, HI, USA.
54. Agumented Startups (2023, July 02). Weeds Dataset 2021. Available online: https://universe.roboflow.com/augmented-startups/weeds-nxe1w.
55. R Core Team (2016). Team R: A Language and Environment for Statistical Computing, Team R.
56. Weisberg, S., and Fox, J. (2011). An R Companion to Applied Regression, Sage Publications.
57. Scmamp: Statistical Comparison of Multiple Algorithms in Multiple Problems10.32614/RJ-2016-017 ↗
58. Benjumea, A., Teeti, I., Cuzzolin, F., and Bradley, A. (2021). YOLO-Z: Improving Small Object Detection in YOLOv5 for Autonomous Vehicles. arXiv.
59. Goosegrass Detection in Strawberry and Tomato Using a Convolutional Neural Network10.1038/s41598-020-66505-9 ↗
60. Feature Extraction and Automatic Recognition of Plant Leaf Using Artificial Neural Network
61. Detection and Quantification of Broadleaf Weeds in Turfgrass Using Close-Range Multispectral Imagery with Pixel- and Object-Based Classification10.1080/01431161.2021.1969058 ↗
62. Application of Artificial Neural Networks in Image Recognition and Classification of Crop and Weeds