Claim · model-written summary
YOLOv5s-Im ran at 4.56 FPS on an Intel NUC11TNKi3.
- Taxon
- apple
Malus domesticat0 - Outcome
- high frame ratese6
- Value
- 4.56 FPSe6
- Qualifier
- on Intel NUC11TNKi3e6
Not reportedMaterialGeneCompoundOrgan / stageInteractorInteractor roleSecond interactorSecond interactor roleTreatmentComparatorSettingDirection
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e6“achieving high frame rates (227 FPS on NVIDIA RTX 4060 Ti, 22 FPS on Jetson Xavier, 4.56 FPS on Intel NUC11TNKi3)”
t0“apple flower detection”
Title
Optimized Yolov5s-Im for real-time apple flower detection in drone-based pollination
Shahram Hamza Manzoor; Zhao Zhang; Hongwen Li; et al. Smart Agricultural Technology 2025. doi:10.1016/j.atech.2025.101150
Other claims from this paper (18)
- Method / resource YOLOv5s-Im achieved 88% apple flower detection accuracy.
- Method / resource YOLOv5s-Im averaged 41.6 pollination attempts per flight, outperforming YOLOv5s and YOLOv5s-T (fewer than 10 attempts).
- Mechanism The advantage of YOLOv5s-Im in pollination attempts is attributed to its faster inference speed.
- Method / resource YOLOv5-Sh-V2 averaged 37.8 pollination attempts per flight with ShuffleNet version 2 backbone.
- Method / resource YOLOv5-Sh-V2 reached 80% detection accuracy (mAP).
- Method / resource YOLOv5-Sh-V2 ran at 1.0 FPS detection speed.
- Method / resource YOLOv5s-Mb-V2 averaged 30.6 pollination attempts per flight with MobileNet version 2 backbone.
- Method / resource YOLOv5s-Mb-V2 reached 82% detection accuracy (mAP).
- Method / resource YOLOv5s-Mb-V2 ran at 0.7 FPS detection speed.
- Method / resource YOLOv5s-Im reached 90.6% precision.
- Method / resource YOLOv5s-Im reached 87.7% recall.
- Method / resource YOLOv5s-Im reached 91.2% mAP50.
- Method / resource YOLOv5s-Im reached an F1-score of 89.42%.
- Method / resource YOLOv5s-Im reduced GFLOPS by 89%.
- Method / resource YOLOv5s-Im reduced model size by 85%.
- Method / resource YOLOv5s-Im ran at 227 FPS on an NVIDIA RTX 4060 Ti.
- Method / resource YOLOv5s-Im ran at 22 FPS on a Jetson Xavier.
- Method / resource YOLOv5s-Im kept 84%-88% accuracy across clear light, afternoon, angled and low-light orchard conditions.