# A Comparative Benchmark of Real-time Detectors for Blueberry Detection towards Precision Orchard Management

arXiv: https://arxiv.org/abs/2509.20580 · HTML: https://mlsanity.com/paper/2509.20580/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 48 references that are in the map.
- First posted on arXiv 24 Sep 2025.

## Builds on (most cited first, 17 of 17)

- [DETRs Beat YOLOs on Real-time Object Detection](https://mlsanity.com/paper/2304.08069/) (2023)
- [YOLOv10: Real-Time End-to-End Object Detection](https://mlsanity.com/paper/2405.14458/) (2024)
- [YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information](https://mlsanity.com/paper/2402.13616/) (2024)
- [Unbiased Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2102.09480/) (2021)
- [YOLOv12: Attention-Centric Real-Time Object Detectors](https://mlsanity.com/paper/2502.12524/) (2025)
- [A Survey on Deep Semi-supervised Learning](https://mlsanity.com/paper/2103.00550/) (2021)
- [Unbiased Mean Teacher for Cross-domain Object Detection](https://mlsanity.com/paper/2003.00707/) (2020)
- [RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformer](https://mlsanity.com/paper/2407.17140/) (2024)
- [YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception](https://mlsanity.com/paper/2506.17733/) (2025)
- [Deep Fruit Detection in Orchards](https://mlsanity.com/paper/1610.03677/) (2016)
- [Semi-DETR: Semi-Supervised Object Detection with Detection Transformers](https://mlsanity.com/paper/2307.08095/) (2023)
- [RF-DETR Object Detection vs YOLOv12 : A Study of Transformer-based and CNN-based Architectures for Single-Class and Multi-Class Greenfruit Detection in Complex Orchard Environments Under Label Ambiguity](https://mlsanity.com/paper/2504.13099/) (2025)
- [Weakly and Semi-Supervised Detection, Segmentation and Tracking of Table Grapes with Limited and Noisy Data](https://mlsanity.com/paper/2208.13001/) (2022)
- [Vision Transformers in Precision Agriculture: A Comprehensive Survey](https://mlsanity.com/paper/2504.21706/) (2025)
- [Semi-Supervised Object Detection: A Survey on Progress from CNN to Transformer](https://mlsanity.com/paper/2407.08460/) (2024)
- [Semi-Supervised Weed Detection in Vegetable Fields: In-domain and Cross-domain Experiments](https://mlsanity.com/paper/2502.17673/) (2025)
- [S3AD: Semi-supervised Small Apple Detection in Orchard Environments](https://mlsanity.com/paper/2311.05029/) (2023)

## Built on by (most cited first, 2 of 2)

- [Detection of On-Ground Chestnuts Using Artificial Intelligence Toward Automated Picking](https://mlsanity.com/paper/2602.14140/) (2026)
- [AerialYield-B2D: A Greenhouse Blueberry Dataset with Five-Stage Ripeness Masks and Fruit Counts](https://mlsanity.com/paper/2608.16973/) (2026)

## Abstract (arXiv)

Blueberry detection in natural environments remains challenging due to variable lighting, occlusions, and motion blur due to environmental factors and imaging devices. Deep learning-based object detectors promise to address these challenges, but they demand a large-scale, diverse dataset that captures the real-world complexities. Moreover, deploying these models in practical scenarios often requires the right accuracy/speed/memory trade-off in model selection. This study presents a novel comparative benchmark analysis of advanced real-time object detectors, including YOLO (You Only Look Once) (v8-v12) and RT-DETR (Real-Time Detection Transformers) (v1-v2) families, consisting of 36 model variants, evaluated on a newly curated dataset for blueberry detection. This dataset comprises 661 canopy images collected with smartphones during the 2022-2023 seasons, consisting of 85,879 labelled instances (including 36,256 ripe and 49,623 unripe blueberries) across a wide range of lighting conditions, occlusions, and fruit maturity stages. Among the YOLO models, YOLOv12m achieved the best accuracy with a mAP@50 of 93.3%, while RT-DETRv2-X obtained a mAP@50 of 93.6%, the highest among all the RT-DETR variants. The inference time varied with the model scale and complexity, and the mid-sized models appeared to offer a good accuracy-speed balance. To further enhance detection performance, all the models were fine-tuned using Unbiased Mean Teacher-based semi-supervised learning (SSL) on a separate set of 1,035 unlabeled images acquired by a ground-based machine vision platform in 2024. This resulted in accuracy gains ranging from -1.4% to 2.9%, with RT-DETR-v2-X achieving the best mAP@50 of 94.8%. More in-depth research into SSL is needed to better leverage cross-domain unlabeled data. Both the dataset and software programs of this study are made publicly available to support further research.