Geospatial Solutions
ROW asset QA / utility inventory

QA/QC for right-of-way asset inventories before they become bad GIS layers.

Mobile-mapping vendors, public works teams, utility contractors, and asset inventory teams use this kind of review to catch wrong classes, missed assets, duplicate labels, loose centroids, and schema gaps before delivery.

01

Ingest mobile-mapping output

02

Run class-specific QA

03

Correct imagery labels

04

Clean GIS positions

05

Export client schema

8

QA records in queue

61%

export readiness

1

ready to ship

Manhole coverROW-MH-0241
Manhole cover
centroid
Source evidence

Row Asset Manhole Cover.mp4

Confirm class as manhole cover, populate utility subtype, and keep the point at the visible cover center.

Confidence

89%

Geometry

centroid

Readiness

72%

GIS QA map
AcceptedMoved pointAttribute holdRejected

Active QA decision

Manhole cover

Fix attribute

Status

Attribute hold

Category

Utility inventory

Export blocker

Missing required subtype field

Buyer risk

Wrong utility class or loose center point creates a bad buried-asset layer.

Reviewer note

Source video shows the object clearly enough for a centroid, but the export cannot move until the utility subtype is populated.

Required action

Confirm class as manhole cover, populate utility subtype, and keep the point at the visible cover center.

Review queue

Every row represents a GIS record that either ships, moves, gets fixed, or gets deleted.

Click a record to sync the table, source evidence, QA decision, and map marker.

AssetDecisionStatusReadinessBlocker
ROW-MH-0241Fix attributeAttribute hold72%Missing required subtype field
ROW-HY-0188AcceptExport ready98%None
ROW-CB-0417False negativeAdd missed asset41%Missing asset must be added
ROW-GR-0094Move centroidNeeds geolocation66%Point is still on vehicle marker
ROW-UP-0122False positiveDelete from layer18%Wrong object for ROW inventory
ROW-CAB-0063Fix attributeAttribute hold69%Mandatory attributes incomplete
ROW-BS-0208Mark duplicateDuplicate hold52%Duplicate candidate not resolved
ROW-CR-0275Fix attributeAttribute hold74%ADA fields incomplete

QA rules from the Drive evidence

The demo follows the same four review lanes documented in the ROW folder.

ROW Asset Attribute QA

Attribute QA

Reviewers verify required attributes, correct condition calls, and keep coded fields clean before delivery.

Condition: Good/Fair/PoorMandatory fieldsNo extra words in coded fields

ROW Asset False Negative QA

False negative QA

Reviewers scan the best image in a sequence, add missed assets, resize boxes, and split multiple objects.

Add missing objectFix box sizeOne correct record in best image

ROW Asset False Positive QA

False positive QA

Wrong-class, duplicate, non-ROW, low-visibility, and private-area detections are deleted before the GIS layer is trusted.

Delete wrong classRemove duplicatesApply customer correctness rules

ROW Asset Geolocation QA

Geolocation QA

Asset points are moved from the vehicle marker to the real-world location using source imagery and map context.

Vehicle image is ground truthDrag point to assetUse curb and road context
Export readiness

The handoff is not complete until the layer can survive GIS review.

The output is a cleaned asset inventory with review status, deleted records, missed additions, corrected coordinates, and notes your GIS manager can trace.

Average readiness

61%

QA lanes

4

Asset classes

8

QA-cleared GeoJSON
FileGDB or Shapefile
CSV asset register
Deleted false-positive log
False-negative additions
Reviewer QA notes
Client schema mapping
Training-data corrections

Send a sample inventory

We can review a small corridor and show exactly where the QA layer saves the dataset.

Mobile-mapping vendor

Clear backlog without letting inconsistent output reach customers.

Public works or utility team

Clean asset records before they drive maintenance and capital decisions.

GIS manager

Receive a schema-ready layer instead of a cleanup project.

Send ROW asset sample data

Share a small image sequence, extracted asset table, or GIS layer. We will respond with a pilot QA scope and delivery estimate.

Asset classes (select any)

Implementation stack

Technologies We Work With

We choose the stack around the job: browser maps for decision surfaces, spatial databases for reliable data, Python and GIS libraries for analysis, and annotation tools when imagery needs reviewer-ready labels.

QGIS

GIS Software

ESRI ArcGIS

GIS Platform

PostgreSQL

Database

PostGIS

Spatial Database

AWS

Cloud Platform

Google Cloud

Cloud Platform

DuckDB

Analytics Database

OpenAI

AI Platform

Claude AI

AI Assistant

CVAT

Annotation Tool

Python

Programming

React

Frontend

Node.js

Backend

Docker

Containerization

Kubernetes

Orchestration

Azure

Cloud Platform

TensorFlow

Machine Learning

Pandas

Data Analysis

NumPy

Scientific Computing

Jupyter

Data Science

Git

Version Control

Linux

Operating System

Ubuntu

Operating System

Mapbox

Mapping Platform

Leaflet

Web Mapping

Fastapi

API Framework

GeoPandas

Geospatial Analysis

GDAL

Geospatial Library