Comprehensive Performance Evaluation of YOLOv12, YOLO11, YOLOv10, YOLOv9 and YOLOv8 on Detecting and Counting Fruitlet in Complex Orchard Environments
Ranjan Sapkota, Zhichao Meng, Martin Churuvija, Xiaoqiang Du, Zenghong Ma, Manoj Karkee

TL;DR
This paper provides a comprehensive real-world evaluation of multiple YOLO versions for detecting and counting fruitlets in complex orchard environments, highlighting their accuracy and speed for practical agricultural use.
Contribution
It systematically compares various YOLO models on detection accuracy, counting precision, and computational efficiency in orchard scenarios, including sensor-specific training insights.
Findings
YOLOv12l achieved highest recall (0.900).
YOLOv9 GELAN-base and GELAN-e had the highest mAP@50 (0.935).
YOLO11n demonstrated fastest inference speed (2.4 ms).
Abstract
This study systematically conducted an extensive real-world evaluation of all configurations of You Only Look Once (YOLO)-based object detection algorithms, including YOLOv8, YOLOv9, YOLOv10, YOLO11, and YOLOv12. Models were assessed using precision, recall, mean Average Precision at 50 % Intersection over Union (mAP@50), and computational efficiency across pre-processing, inference, and post-processing stages for detecting immature green fruitlets in commercial orchards. Field-level fruitlet counting was also validated using images captured with both Intel RealSense and iPhone 14 Pro Max sensors. YOLOv12l achieved the highest recall (0.900), while YOLOv10x and YOLOv9 GELAN-c reported the top precision scores of 0.908 and 0.903, respectively. YOLOv9 GELAN-base and GELAN-e achieved the highest mAP@50 (0.935), followed by YOLO11s (0.933) and YOLOv12l (0.931). In counting validation,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsYou Only Look Once · SPEED: Separable Pyramidal Pooling EncodEr-Decoder for Real-Time Monocular Depth Estimation on Low-Resource Settings
