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 S$^3$AD 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 S$^3$AD
substantially outperforms strong fully-supervised baselines, including several
small object detection systems, by up to $14.9\%$. 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.

本研究提出了一种半监督的小苹果检测系统 (S^3AD)，通过利用大型高分辨率数据集 MAD，基于上下文关注和选择性平铺的方法，解决了水果检测中小型水果检测的困难，同时限制了计算开销，并在评估中表现出了明显优势。

S$^3$AD：果园环境中的半监督小苹果检测

S$^3$AD: Semi-supervised Small Apple Detection in Orchard Environments

The framework of the seventeen sustainable development goals is a challenge
for developers and researchers applying artificial intelligence (AI). AI and
earth observations (EO) can provide reliable and disaggregated data for better
monitoring of the sustainable development goals (SDGs). In this paper, we
present an overview of SDG targets, which can be effectively measured with AI
tools. We identify indicators with the most significant contribution from the
AI and EO and describe an application of state-of-the-art machine learning
models to one of the indicators. We describe an application of U-net with SE
blocks for efficient segmentation of satellite imagery for crop detection.
Finally, we demonstrate how AI can be more effectively applied in solutions
directly contributing towards specific SDGs and propose further research on an
AI-based evaluative infrastructure for SDGs.

本文介绍了应用 AI 和地球观测数据对可持续发展目标进行监测的方法，提出了一种基于 U-net 和 SE 块的卫星图像分割模型用于作物检测，同时提出了建立评估基础设施以实现更好实现 SDGs 的未来研究方向。