SUIM
收藏资源简介:
SUIM数据集是专为水下图像语义分割设计的大型数据集,由明尼苏达大学交互式机器人与视觉实验室创建。该数据集包含1525张水下图像,涵盖八种对象类别,如鱼类、珊瑚礁、水生植物等,这些图像通过海洋探索和人类-机器人协作实验精心收集。数据集的创建旨在为水下机器人视觉提供一个标准平台,以促进水下场景的详细理解和自主导航。
The SUIM dataset is a large-scale dataset specifically designed for underwater image semantic segmentation, created by the Interactive Robotics and Vision Laboratory at the University of Minnesota. It contains 1525 underwater images covering eight object categories including fish, coral reefs, aquatic plants and others, which were meticulously collected through marine exploration and human-robot collaboration experiments. This dataset was developed to provide a standard benchmark platform for underwater robotic vision, facilitating in-depth understanding of underwater scenes and autonomous navigation.

- 1Semantic Segmentation of Underwater Imagery: Dataset and Benchmark交互式机器人与视觉实验室 · 2020年



