RiceSEG
收藏资源简介:
RiceSEG是一个全面的、多样化的高分辨率RGB标注图像数据集,包含来自五个主要水稻种植国家(中国、日本、印度、菲律宾、坦桑尼亚)的近5万张地面图像,涵盖6000多个品种的水稻生长周期。数据集从原始图像中选取3078个代表性样本,并标注为六个类别(背景、绿色植被、衰老植被、稻穗、杂草、浮萍)。该数据集是公开的,旨在促进水稻分割算法的开发和评估。
RiceSEG is a comprehensive and diverse high-resolution RGB annotated image dataset. It contains nearly 50,000 ground-level images collected from five major rice-growing countries, namely China, Japan, India, the Philippines, and Tanzania, covering the growth cycles of over 6,000 rice varieties. A total of 3,078 representative samples were selected from the original images and annotated into six categories: background, green vegetation, senescent vegetation, rice panicles, weeds, and duckweed. This publicly available dataset aims to facilitate the development and evaluation of rice segmentation algorithms.

- 1Global Rice Multi-Class Segmentation Dataset (RiceSEG): A Comprehensive and Diverse High-Resolution RGB-Annotated Images for the Development and Benchmarking of Rice Segmentation Algorithms南京农业大学 · 2025年



