QGIS plugin · Street-level imagery · Guide

02StreetView — Street-Level Imagery Lab

Street-level imagery analysis in QGIS. The plugin samples points along a street network, matches open images from Panoramax and Mapillary or your own geotagged photos, keeps the licence and attribution of every image, segments the images locally, computes the green view index, sky view factor, tree and building view factors, sky share and visual enclosure with solid-angle weighting for 360 degree panoramas, aggregates them to street segments and areas, and checks photographic sky view factor against a DSM.

Version: 0.1.0 QGIS: 3.28+ / 4.x Licence: GPL-2.0-or-later Developer: Geophilo Language: English
01 · Overview

What 02StreetView does

Street-level imagery analysis in QGIS. The plugin samples points along a street network, matches open images from Panoramax and Mapillary or your own geotagged photos, keeps the licence and attribution of every image, segments the images locally, computes the green view index, sky view factor, tree and building view factors, sky share and visual enclosure with solid-angle weighting for 360 degree panoramas, aggregates them to street segments and areas, and checks photographic sky view factor against a DSM.

Sources

Open images, licence kept

Panoramax without an account, Mapillary with your own free client token, or a local folder of geotagged JPEGs; date range, capture months, matching radius, panorama preference and heading tolerance; licence and attribution stored per image.

Segmentation

Local, no PyTorch

Built-in colour rules in NumPy (vegetation by excess green, sky by brightness and connection to the top edge) or the UperNet + ConvNeXt ADE20K model through the optional onnxruntime package, pinned by size and SHA-256.

Indicators

Solid-angle weighted

GVI, SVF, TVF, BVF, sky share and enclosure, with view factors that sum to one; an 18-view GVI after Li et al. (2015); aggregation to segments and areas with confidence half-widths; a DSM check of photo SVF with rr, MAE and bias.

02 · Install and quick start

Install, then run the demo

In QGIS, open Plugins › Manage and Install Plugins, search for 02StreetView and install it, or install a release zip with Install from ZIP.

QGIS 3.28 or later (QGIS 4 included). Only qgis.core, GDAL, NumPy and PyQt are required. The ONNX segmenter needs onnxruntime (CPU build); the Segment page shows the pip command, and the 238 MB model is downloaded from that page and checked against a pinned size and SHA-256. The services blur faces and number plates; the plugin does no de-blurring or person identification.

Open the lab

Click the 02StreetView toolbar button or Plugins › 02StreetView; the lab opens as a dock on the right.

Load the demo street

On Network, press Load demo street: four 200 m streets, each the centre line of a street canyon 20 m wide with aspect ratio H/W=0.2,0.5,0.9H/W = 0.2, 0.5, 0.9 and 1.51.5, and a rendered panorama every 20 m.

Run the chain

Press Run the whole chain. The street layer carries the closed-form truth SVFtrue=cos⁡(arctan⁡(2H/W))\mathrm{SVF}_\mathrm{true} = \cos(\arctan(2H/W)) and the planted green share; with the colour segmenter every sample's SVF is within 0.0002 and its GVI within 0.002 of the truth.

Check against the DSM

On Aggregate, Compare with DSM: with an eye height of 1.6 m the check gives r=0.9999r = 0.9999 and a bias of −0.009-0.009 (photo minus DSM). On Report, write the HTML report.

03 · The dock

The lab dock, page by page

The lab is a dock on the right of the QGIS window with an icon rail of seven pages and Help.

PageWhat it holds
1. NetworkStreet lines, optional areas and DSM, sampling interval, offset and minimum gap; a working CRS badge, Load demo street and Run the whole chain.
2. SourcesPanoramax, Mapillary (token stored in the QGIS authentication database) and a local folder; date range, capture months, matching radius; Search and match adds a layer of matched images.
3. ImagesDownload into the local cache, cache size and Clear cache; an image viewer with the segmentation overlay, a fisheye view of panoramas and the attribution line.
4. SegmentColour rules, the ONNX ADE20K model or a custom ONNX model; runtime and model cards with the pip command, licence notice and a run-time estimate.
5. IndicatorsA checklist of indicators with formula, unit and reference; elevation band; KPI gauges for mean GVI, SVF and enclosure; the sample layer styled by the chosen indicator.
6. AggregateStreet segments and areas, statistics, minimum coverage, a ranked table and the DSM check with a scatter of photo SVF against DSM SVF.
7. ReportHTML report, CSV and GeoPackage with attribution and licence fields.
Images page of the 02StreetView dock with a demo panorama and its segmentation overlay
Images page of the 02StreetView dock with a demo panorama and its segmentation overlay.
Network page with the input layers, sampling settings and network summary
Network page with the input layers, sampling settings and network summary.
Indicators page with the indicator checklist, elevation band and KPI gauges
Indicators page with the indicator checklist, elevation band and KPI gauges.
Aggregate page with the segment ranking and the DSM check
Aggregate page with the segment ranking and the DSM check.
04 · Processing

Processing provider

The plugin registers a 02StreetView provider with 10 algorithms in the Processing Toolbox, usable in models, batch mode and scripts.

GroupAlgorithm
DemoCreate demo street
SamplingSample street network
ImagerySearch and match images
ImageryDownload images to the cache
SegmentationSegment images
IndicatorsCompute view indicators
AggregationAggregate to street segments
AggregationAggregate to areas
DSM checkDSM check of photo sky view factor
LabStreet-level imagery lab (whole chain)
05 · Manual

Full manual

06 · Credits

Citation and licence

Name02StreetView - Street-Level Imagery Lab
Packagezero2streetview
Version0.1.0
QGIS3.28 or newer; QGIS 4 supported
LicenceGPL-2.0-or-later (LICENSE)
DeveloperGeophilo · Yusuf Eminoğlu (ORCID 0009-0005-6000-2934)
Sourcegitlab.com/geophilo1/zero2streetview
Issuesgitlab.com/geophilo1/zero2streetview/-/work_items
Hubplugins.qgis.org search: zero2streetview (listing pending)
RevisionNovember 2026
Eminoğlu, Y. (2026). 02StreetView - Street-Level Imagery Lab (version 0.1.0) [QGIS plugin]. https://gitlab.com/geophilo1/zero2streetview