arXiv 2504.028802025-04-02eess.IVcs.AIcs.CV

全球水稻多类分割数据集（RiceSEG）：用于开发和基准测试水稻分割算法的全面且多样化的高分辨率RGB标注图像

Global Rice Multi-Class Segmentation Dataset (RiceSEG): A Comprehensive and Diverse High-Resolution RGB-Annotated Images for the Development and Benchmarking of Rice Segmentation Algorithms

Nanjing Agricultural University（南京农业大学）；The University of Tokyo（东京大学）；Professor Jayashankar Telangana Agricultural State University（贾亚尚卡尔·特伦甘纳农业州立大学）；Kyoto University（京都大学）；Huazhong University of Science and Technology（华中科技大学）；Huazhong Agricultural University（华中农业大学）；Chinese Academy of Agricultural Sciences（中国农业科学院）；Chinese Academy of Science（中国科学院）；Shenyang Agricultural University（沈阳农业大学）；Jilin Academy of Agricultural Sciences（吉林省农业科学院）；Yuan Long Ping High-Tech Agriculture Co., Ltd.（袁隆平高科技农业有限公司）

Junchi Zhou, Haozhou Wang, Yoichiro Kato, Tejasri Nampally, P. Rajalakshmi, M. Balram, Keisuke Katsura, Hao Lu, Yue Mu, Wanneng Yang, Yangmingrui Gao, Feng Xiao… 展开作者

Junchi Zhou, Haozhou Wang, Yoichiro Kato, Tejasri Nampally, P. Rajalakshmi, M. Balram, Keisuke Katsura, Hao Lu, Yue Mu, Wanneng Yang, Yangmingrui Gao, Feng Xiao, Hongtao Chen, Yuhao Chen, Wenjuan Li, Jingwen Wang, Fenghua Yu, Jian Zhou, Wensheng Wang, Xiaochun Hu, Yuanzhu Yang, Yanfeng Ding, Wei Guo, Shouyang Liu

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对水稻器官精细结构和冠层复杂光照导致分割困难且缺乏高质量数据集的问题，构建了首个包含5国近5万张图像、3078个六类标注样本的全球水稻多类语义分割数据集RiceSEG，并利用基线模型揭示了生殖阶段分割的挑战，为开发专用作物分割模型提供了重要基准。

摘要：

开发基于计算机视觉的水稻表型技术对精准田间管理和加速育种至关重要，从而持续推动水稻生产的发展。在表型任务中，区分图像组件是在器官尺度上表征植物生长发育的关键前提，能够更深入地了解生态生理过程。然而，由于水稻器官的精细结构和冠层内复杂的光照，这项任务仍然极具挑战性，凸显了对高质量训练数据集的需求。此类数据集非常稀缺，这既是因为缺乏具有代表性的大规模水稻田图像集合，也是因为标注过程非常耗时。为了填补这一空白，我们建立了首个全面的多类水稻语义分割数据集RiceSEG。我们从五个主要水稻种植国（中国、日本、印度、菲律宾和坦桑尼亚）收集了近50,000张高分辨率的地面图像，涵盖了所有生长阶段的6,000多个基因型。从这些原始图像中，选取了3,078个代表性样本，并将其标注为六个类别（背景、绿色植被、衰老植被、稻穗、杂草和浮萍），以构成RiceSEG数据集。值得注意的是，来自中国的子数据集涵盖了从东北到南方的所有主要基因型和水稻生长环境。最先进的卷积神经网络和基于transformer的语义分割模型均被用作基线。虽然这些模型在分割背景和绿色植被方面表现尚可，但在生殖阶段面临困难，此时冠层结构更加复杂且涉及多个类别。这些发现凸显了我们的数据集对于开发水稻及其他作物专用分割模型的重要性。

英文摘要：

Developing computer vision-based rice phenotyping techniques is crucial for precision field management and accelerating breeding, thereby continuously advancing rice production. Among phenotyping tasks, distinguishing image components is a key prerequisite for characterizing plant growth and development at the organ scale, enabling deeper insights into eco-physiological processes. However, due to the fine structure of rice organs and complex illumination within the canopy, this task remains highly challenging, underscoring the need for a high-quality training dataset. Such datasets are scarce, both due to a lack of large, representative collections of rice field images and the time-intensive nature of annotation. To address this gap, we established the first comprehensive multi-class rice semantic segmentation dataset, RiceSEG. We gathered nearly 50,000 high-resolution, ground-based images from five major rice-growing countries (China, Japan, India, the Philippines, and Tanzania), encompassing over 6,000 genotypes across all growth stages. From these original images, 3,078 representative samples were selected and annotated with six classes (background, green vegetation, senescent vegetation, panicle, weeds, and duckweed) to form the RiceSEG dataset. Notably, the sub-dataset from China spans all major genotypes and rice-growing environments from the northeast to the south. Both state-of-the-art convolutional neural networks and transformer-based semantic segmentation models were used as baselines. While these models perform reasonably well in segmenting background and green vegetation, they face difficulties during the reproductive stage, when canopy structures are more complex and multiple classes are involved. These findings highlight the importance of our dataset for developing specialized segmentation models for rice and other crops.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。