Street-view image dataset and HRNet-OCR semantic segmentation outputs used for GVI analysis in Xinyang, China

Fuente: Zenodo
Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Jia, Xiaoli
Format: Recurso digital
Veröffentlicht: Zenodo 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866902337207926784
author Jia, Xiaoli
author_facet Jia, Xiaoli
contents <p>This dataset contains the street-view images and corresponding semantic segmentation outputs used in the study of urban green exposure in Xinyang, China. The street-view images were retrieved from the Baidu Maps Street View API along major roads within the urbanized area and were used to calculate the Green View Index (GVI). Semantic segmentation was performed using the official HRNet semantic segmentation codebase with an HRNet-W48 backbone, an OCR module, and publicly available pretrained weights. The deposited files include the processed street-view image dataset and the corresponding segmentation results used for subsequent GVI analysis. This dataset is intended to support transparency, reproducibility, and reuse in studies of street-level greenness, urban vegetation, and green exposure assessment.</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_19465724
institution Zenodo
language
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle Street-view image dataset and HRNet-OCR semantic segmentation outputs used for GVI analysis in Xinyang, China
Jia, Xiaoli
street-view imagery
Green View Index
Xinyang
HRNet-OCR
<p>This dataset contains the street-view images and corresponding semantic segmentation outputs used in the study of urban green exposure in Xinyang, China. The street-view images were retrieved from the Baidu Maps Street View API along major roads within the urbanized area and were used to calculate the Green View Index (GVI). Semantic segmentation was performed using the official HRNet semantic segmentation codebase with an HRNet-W48 backbone, an OCR module, and publicly available pretrained weights. The deposited files include the processed street-view image dataset and the corresponding segmentation results used for subsequent GVI analysis. This dataset is intended to support transparency, reproducibility, and reuse in studies of street-level greenness, urban vegetation, and green exposure assessment.</p>
title Street-view image dataset and HRNet-OCR semantic segmentation outputs used for GVI analysis in Xinyang, China
topic street-view imagery
Green View Index
Xinyang
HRNet-OCR
url https://doi.org/10.5281/zenodo.19465724