AI Superior, in collaboration with international humanitarian NGO World Vision, undertook a compelling project to investigate the potential correlation between land degradation and conflicts in selected countries. By analysing the NDVI index and historical conflict records, the project aimed to shed light on the relationship between these two critical factors. This article explores the methodology employed, the findings discovered, and the implications of the research.
Exploring the Relationship Between Land Degradation and Conflict Prevalence
Summary
Challenge
The customer, a system integrator executing governmental projects, required a road traffic analytics system that would identify different road entities (cars, pedestrians, bicycles, etc.), track them, and perform further analysis, e.g., identify car type, model, and make, color and other. The main challenge was to create a robust Data Science System that could be easily transferable across different camera types and points of view, as well as to work in different environments.
Solution by AI Superior
The system that we developed includes multiple analytical components:
- Road entities detection (cars, pedestrians, bicycles, trucks, buses, motorcycles)
- Object tracking
- Car speed estimation
- Car color recognition
- Car type, brand, and model recognition (7000+ unique models)
- License plate recognition and validation
- Traffic intensity analysis
- Anomaly detection (e.g., a pedestrian on a highway)
- Illegal parking analysis
The components were developed as independent modules allowing for customization of the whole system. The unique features of the system are:
- Ability to detect and classify partly occluded objects
- Identify car model production year
- Supports recognition of commercial vehicles
- It can be adjusted to different traffic environments
- Allows to be updated with new car models
- Allows more features, e.g., advanced tracking or events detection
Outcome and Implications
The Data Science System was deployed by a city’s municipality and is successfully running 24/7, covering hundreds of cameras.
English 
German 
Arabic 
French 
Dutch 
Spanish