Nextbillion.ai > Case Studies > AI Company Builds Country Scale Maps in 3 Months: A Case Study

AI Company Builds Country Scale Maps in 3 Months: A Case Study

Technology Category

Drones - Drone Flight & Navigation Software
Infrastructure as a Service (IaaS) - Cloud Computing

Applicable Industries

Buildings
Marine & Shipping

Applicable Functions

Quality Assurance

Use Cases

Movement Prediction
Smart Lighting

Services

System Integration
Testing & Certification

About The Customer

The customer is a leading AI cloud computing company that was in need of a bespoke, cost-effective mapping solution. They required a solution that could efficiently map the entire UAE in a short span of three months. The company needed a large scale, end-to-end solution with custom map data attributes. They also required the map data to easily integrate with their existing routing and navigation engines. The company was looking for a solution that could effortlessly integrate with their downstream routing and navigation engines, produce map data that could be easily consumed with minimal/no assistance from map solution providers, and follow the standard schema and tagging structure along with tailored specifications provided by them.

The Challenge

A leading AI cloud computing company was faced with the challenge of creating a large scale, end-to-end mapping solution for the entire UAE within a span of three months. The company needed to build high precision, country scale maps with rapid refresh rates, a task that is both expensive and extensive. The process involved building a map at a UAE level, adding 50+ custom attributes, performing quality checks and conflict resolution, and constantly maintaining and refreshing map data. The company also needed to derive map data intelligence from multiple imagery sources, which was a time-consuming process. The data structures used by different routing and navigation engines like OSRM and others vary by routing engine type. The client needed map data that could easily integrate with their existing routing and navigation engines.

The Solution

The solution involved a specialized approach that blended AI with map expertise. A platform was built to overlay proprietary imagery data in an integrated map-editing platform. This platform was able to merge and align proprietary street level imagery, private imagery and open source imagery, integrate client’s proprietary imagery data, incorporate the derived data intelligence into one map stack, and follow the schema and tagging structure of the client’s internal routing and navigation engines. AI modules were used to efficiently extract map attributes from street and satellite imagery. A tasking platform was utilized to leverage existing OpenStreetMap (OSM) schema for lower cost and faster turnaround time. A custom QA tool was built to perform strict platform checks on attributes to ensure high quality.

Operational Impact

The outcome of the solution was a high-quality mapping solution that was tailored entirely to the customer’s unique needs and was delivered with a TAT of just 3 months. The centralization of the mapping solution with a single vendor also made the company’s day-to-day operations much simpler. The solution was able to meet the company's unique needs, including the need for a custom platform with automated tools, high-quality navigation, and a cost-effective and fast solution. The solution also allowed the company to avoid manual checks that can be expensive and inaccurate, and ensured extremely high data quality and consistency.

Quantitative Benefit