UAV Data Analysis for Construction & Urban Planning
No more manual routine in construction progress monitoring. Secure data sharing with a single click
UAV Data Analysis for Construction & Urban Planning
No more manual routine in construction progress monitoring. Secure data sharing with a single click
ATLAS is an AI-driven platform that helps track and measure the progress of construction worksites and share up-to-date information with others, fostering collaboration & faster decisions making
Timely construction reporting
and no more manual routine in UAV data analysis and report generation! Share reports with your contractors and stakeholders without delays on the day of surveying.
Improve teamwork and coordination
within your team of co-workers and subcontractors. Share data in one click as direct links accessible from mobile (iOS/Android) and desktop. Increase situational awareness of all project stakeholders using very simple and visual reporting.
Sensitive data is secured
ATLAS can be installed on premises for storing, processing and exchanging the most sensitive data. By default, ATLAS platform can be accessed from the cloud at
Success story
Locating defects of the road surface
Read how Construction & Civil Engineering company from Mexico accelerates road surface analysis using AI and generates shareable web maps with detected road defects.
Main Features
ATLAS contains its own AI-engine, which learns from users activity and automates regular tasks in construction and maintenance
Track progress and compare
Keep the data of all construction assets on the timeline with easy access to different slices of the same object along with ability to compare, and receive visual reports for all changes in a specified working area. Store raw aerial photography, orthomosaics, DSM, vector data (DXF, KML, Shape), and any additional files.
Count objects, measure areas, calculate volumes
Make a territory segmentation, highlight stockpiles and calculate volumes automatically with ATLAS AI. It also allows detecting heavy vehicles and vegetation on top of a pile and remove them from DSM to make volumes more realistic.
Verification of subcontracted work
ATLAS helps you validate work of subcontractors before acceptance. Automatically detect trenches and roads on orthomosaics, calculate boundaries and area sizes.
Waste management
Track location of different wastes generated during construction process. Tires, old pallets, broken vehicles and other - all this things can be counted and segmented.
Inspect asphalt or concrete for damages
Detect cracks and scratches on concrete and asphalt surfaces on both raw imagery and orthomosaics. Resulting report can be used by repair & maintenance teams to localize defect position and estimate required materials and human resources.
Elevation mapping
ATLAS provides tools to clean DSM from artificial objects to make accurate elevation profiles and slope measurements.
Smart geospatial analysis
Automate the time-consuming manual analysis of UAV & Satellite data
Detect objects
Train AI to search for regular objects (cars, piles) or complex ones, such as excavation areas, vegetation, etc. Use Magic Wand tool to annotate objects with uniform textures in one click.
Count objects 
Count any objects on a construction site or a city plan with utmost precision and in no time.
Measure areas
Automatic image segmentation helps calculate the size of complex objects and supply accurate data for progress monitoring and resource planning.
How ATLAS works
With 3 simple steps turn your aerial images into business insights!
1.  Upload data
Upload images or orthomosaic to the ATLAS cloud or your locally deployed ATLAS On-Premises for higher data security
2. Visualise, annotate and analyze
Visualize geospatial data, annotate objects manually or with AI detectors, measure and analyze data
3. Export and share reports
Export results in GeoJSON, CSV, PDF and other formats or share them with one click with colleagues and stakeholders
The workflow
Sign up and get $50 bonus on your ATLAS account.
No credit card required!
Quick start with your AI detector
ATLAS is simple to use not requiring GIS and data science knowledge. The webinar unfolds the process of ad-hoc training your AI-powered algorithm on annotated data following the 3 easy steps.
We care about your data
ATLAS can be used as a cloud-based solution or installed on-premises.
On-premises installation
Contact us
Cloud based solution
Sign Up
Subscribe to receive latest news about drone mapping and data analysis
By subscribing I consent that I wish to receive Newsletter in line with Privacy policy
Customers in 150+ countries use SPH Engineering solutions daily for drone mission planning, flight control, and data management
Frequently Asked Questions (FAQ)
What is a survey result?
Detections performed by AI detectors are visible on the map/image, though counting, area size, and export functions are blocked. 
Once you confirm you are satisfied with the accuracy of the detection results, you will be prompted to approve the payment amount to be added to your balance, which will unlock the display of object counts, area sizes, and export of vector results. 
Which file formats can I upload to ATLAS?
  • Images: JPEG, PNG
  • Orthomosaics: GeoTiff
  • Digital surface model (DSM): GeoTiff
  • Vector technical drawings in DXF
  • Full motion videos in MPEG-TS
Can I use infrared images?
Yes, as JPEG format
What is the file output from ATLAS?
  • Shape and DXF formats are coming soon
Does ATLAS allow you to analyze videos? I.e. counting cars, pedestrians, etc.
Yes. The video should be in Full Motion Video (MPEG-TS) with GPS coordinates. One can record such a video with the UgCS Enterprise video recording package
What image resolution is required for AI detectors to work?
The higher the image resolution - the better the detection will work. In general images with GSD of 2-5 cm/pixel should be sufficient. To detect bigger objects like cars, solar panels, vegetation areas, etc it can be sufficient with 10-15 cm/pixel GSD.
Do you have sample files I can upload to train AI detectors?
Yes. In our training materials, you can find sample datasets here:
Can I import and export AI detectors?
Yes, on paid Cloud Plan and On-Premise it is possible to export detectors as files. To run this detector locally you need ATLAS On-Premise
Do you have existing AI detectors?
We do not ship detectors out of the box, because for many tasks quality depends on many conditions. But to train your first detector you may need 30 minutes. It is really quick.
What is the accuracy of a detector?
When detection is finished we cut results below 80% of confidence. In general, a lot of things depend on the annotation quality. Please follow our guidelines
What report does a detector deliver?
Images with detected objects can be downloaded as a ZIP archive or CSV list.
From it, it is possible to download GeoJSON data for external GIS systems and PDF report with area screenshot and identified objects counts and area sizes
How do I share a project with other team members or clients?
There are two options on how to share a project.
  1. Add users and open access to a specific project
  2. Share the project as a public link, not requiring authentication.
Can I use Pix4D for flying and ATLAS for object detection?
Yes. Data can be captured with any tool and then processed into orthomosaics
Can I upload pictures and ATLAS create orthophotos?
Yes. ATLAS has also a photogrammetry engine under the hood
Can I upload mosaics created in other software?
Yes. We support GeoTiff format
Does ATLAS offer custom branding?
Yes, On-Premises installation can be branded using a customer's corporate design.
Does ATLAS provide API?
Yes. Please contact our for detailed information
Does ATLAS have the ability to label/create objects to be imported into AutoCAD Civil3D?
Yes. Now it is possible to export GeoJSON, Shortly we will support DXF export
Can ATLAS be installed on my hardware?
Yes, ATLAS can be installed on your own hardware. Please contact for On-Premises options.
Which languages are supported by ATLAS?
Currently ATLAS has English, Spanish and Chinese localisation