- Platform
-
Services
Labeling Data
Processing Data
Improving ML Models
-
Who We Serve
For:•
ML Engineers
•
AI Business Executives
•
Product Managers
•
Academic Researchers
Technology & Innovation
Industry & Commerce
Academia & Services
- About
- Careers
-
Resources
- Pricing
- talk to sales
Academia
Polygon Annotation for Palm Tree Detection in Aerial Imagery
Saudi Arabia
Overview
King Abdullah University of Science and Technology (KAUST) partnered with Label Your Data to advance palm tree detection models using aerial imagery.
Client
Saudi university applying AI to agricultural monitoring with aerial imagery.
Challenges
Overlapping canopies and irregular crowns made annotation slow and inconsistent.
Solutions
Polygon annotation with pilot validation and QA reviews for top-notch dataset quality.
Results
Dataset delivered with 98%+ accuracy, boosting model training efficiency.
Client
King Abdullah University of Science and Technology (KAUST) is a leading Saudi research university. The client needed annotated aerial imagery to train AI models capable of detecting palm trees for agricultural monitoring and environmental research projects.
Challenges
Large and complex aerial imagery required specialized tools
Inconsistent labels from external annotators slowed down cleaning
Manual filtering reduced research efficiency
Overlapping canopies and irregular crowns complicated labelin
Solution
Annotated a high-resolution TIF image in QGIS
Applied polygon annotation to mark palm trees across the dataset
Pilot phase: client reviewed the first 10% before scaling
A dedicated annotator ensured consistency and quality
Training
A single annotator was trained in QGIS using client-provided guidelines.
The pilot phase refined instructions through feedback loops,
ensuring alignment and accuracy before scaling to the full dataset.
Results
The project was delivered in 17 days with measurable outcomes:
98%+ accuracy, verified by the client
Dataset enabled successful palm tree detection model training
Generalized well across regions, improving research reliability
Researchers saved time by avoiding manual filtering
Start Free Pilot
fill up this form to send your pilot request
Thank you for contacting us!
We'll get back to you shortly
The collaboration with Label Your Data was seamless, allowing us to focus on palm tree detection model development instead of spending valuable time on meticulous manual labeling
PhD student of Computer
Science
Trusted by ML Professionals
Why Projects Choose Label Your Data
No Forced Commitment
Check our performance based on a free trial
Flexible Pricing
Pay per labeled object or per annotation hour
Tool-Agnostic
Working with every labeling tool, even your custom tools
Quality Backed by SLAs
We commit to accuracy and deadlines – or you don’t pay