Crop detection is integral for precision agriculture applications such as automated yield estimation or fruit picking. However, crop detection, e.g., apple detection in orchard environments remains challenging due to a lack of large-scale datasets and the small relative size of the crops in the image. In this work, we address these challenges by reformulating the apple detection task in a semi-supervised manner. To this end, we provide the large, high-resolution dataset MAD comprising 105 labeled images with 14,667 annotated apple instances and 4,440 unlabeled images. Utilizing this dataset, we also propose a novel Semi-Supervised Small Apple Detection system SAD based on contextual attention and selective tiling to improve the challenging detection of small apples, while limiting the computational overhead. We conduct an extensive evaluation on MAD and the MSU dataset, showing that SAD substantially outperforms strong fully-supervised baselines, including several small object detection systems, by up to . Additionally, we exploit the detailed annotations of our dataset w.r.t. apple properties to analyze the influence of relative size or level of occlusion on the results of various systems, quantifying current challenges.
View on arXiv@article{johanson2025_2311.05029,
title={ S$^3$AD: Semi-supervised Small Apple Detection in Orchard Environments },
author={ Robert Johanson and Christian Wilms and Ole Johannsen and Simone Frintrop },
journal={arXiv preprint arXiv:2311.05029},
year={ 2025 }
}