F-360iSOD是一个基于注视点的360度全景图像数据集，由法国IETR INSA Rennes创建，包含107张具有挑战性的全景图像，涵盖室内外场景。数据集通过人工标注了1,165个显著对象，每个对象都有精确的像素级标注。创建过程中，利用真实人眼注视图指导标注，确保数据集质量。F-360iSOD主要用于显著对象检测研究，特别是在虚拟现实和全景图像分析领域，旨在提高模型对全景图像中显著对象的识别

arXiv2020-05-19 更新800

Annotated Google Street View dataset for pole and tree detection

场景图像分析

基础设施检测

Dataset for machine learning training with images of sidewalks from Curitiba/PR - Brazil.

Zenodo2026-05-09 更新50

From street view imagery to the countryside: large-scale perception of rural China using deep learning

场景图像分析

深度学习

This project includes the deep learning model code about the article "From street view imagery to the countryside: large-scale perception of rural China using deep learning," which introduces a Pair-C

DataCite Commons2025-03-23 更新960

SVRDD

道路损坏检测

场景图像分析

The usage of Baidu street-view Imagery must respect the Baidu Maps Open Platform Terms of Service. This work is licensed under CC BY 4.0.

NIAID Data Ecosystem90