In today’s fast-changing world, gaining an adequate understanding of the built environment is a critical prerequisite for many decision-making processes across industries. Specifically, an understanding of the location and dimensions of buildings (the “Building Footprints”) serves as foundational information for processes including insurance risk assessment, telecommunications network planning and deployment, and municipal urban planning.

In this blog post, we discuss challenges and common pitfalls we have observed over the past decade in pursuit of offering best-in-class Building Footprints at a country-scale, and highlight how Ecopia AI overcame these challenges to create and maintain the most comprehensive, accurate, and up-to-date Building…

Ecopia Vector Maps of Rayong, Thailand. These digital maps were created leveraging industry-leading artificial intelligence-based systems to extract land cover classes from their Airbus imagery.

Local governments rely on high-resolution digital maps to help them plan smart city initiatives, transportation projects, model flood risk, fairly assess properties for taxation, and more. As municipalities grow, up-to-date land use/land cover layers are increasingly important for advanced analysis and modeling.

However, the process of acquiring both the imagery and the land use/land cover layers poses a number of challenges for land administration applications across the globe.

Challenges

Obtaining the up-to-date imagery required for high-resolution digital maps can be a difficult task. Manually creating land use/land cover polygons by hand is an extremely resource-intensive process that is not scalable across…

High-Resolution Geospatial Imagery & High-Accuracy Feature Extraction

Organizations around the world depend on high-resolution geospatial imagery to make more informed decisions. After digital maps have been created or produced from the imagery, the analyses and workflows can enable efficiencies and power a wide variety of real-world use cases. For example, insurance underwriters can more accurately identify the flood risk of a property, and municipalities can better plan smart cities and sustainable infrastructure.

The faster and more accurately detailed land cover data can be extracted from imagery sources, the faster and more reliably organizations can enact meaningful change around the globe.

Rayong, Thailand. Ecopia AI (Ecopia) can rapidly extract 12+ land cover classes from high-resolution imagery as accurately as a GIS-professional.

Yet, mapping our Earth and extracting these…

Rayong, Thailand. The Airbus—Ecopia Al (Ecopia) partnership will allow Airbus customers to quickly
and easily create Ecopia Vector Maps by leveraging industry-leading artificial intelligence-based
systems to extract land cover classes from their Airbus imagery.

We sat down for a Q&A with Arnaud De Saint-Vincent, Analytics Strategy — Digital Services at Intelligence (Airbus Defence and Space), to learn more about what excites them about Ecopia AI’s technology, and what future solutions the partnership can provide their customers.

1. How did you learn about Ecopia?

We initially discovered Ecopia via web searches we made when we were looking for a partner company that could rapidly and accurately extract buildings and land use from our high-resolution satellite imagery.

2. What was it about Ecopia that prompted you to reach out and learn more about our global partnership program and technical capabilities? Why did you choose to work with Ecopia?

We had contacts with several other companies and tested their feature extraction technology capabilities. We were particularly interested in highly-detailed building and road extraction. Before Ecopia…

Where Ecopia AI has been, and where we’re going.

Introduction

As we celebrate our 8th anniversary, we reflect on the journey of how we got to where we are today, and where we’re headed next. To-date, all of our growth and accomplishments have been driven by our mission: digitizing the world using AI.

Land Cover Extraction of Indonesia. Ecopia’s Global Feature Extraction solution can extract over a dozen land cover features from geospatial imagery, including building footprints, roads, sports fields, and more.

Ecopia AI (“Ecopia”) was spun out of Ph.D. research at the University of Waterloo. Back then, Ecopia’s founders recognized that satellites, airplanes, motor vehicles, and mobile devices capture billions of high-resolution images of the Earth every day. …

Municipal Challenges with Geospatial Data

Today, the majority of municipalities face crippling inefficiencies when creating a digital twin of their region for the betterment of their community. Critical objectives — pedestrian safety, emergency services, taxation, and more — rely on accurate, up-to-date geospatial data. Without it, these objectives take too long to plan and execute, and sub-par accuracy creates organizational and logistical challenges.

Making matters worse, municipalities are routinely handicapped by their geospatial imagery renewal cycles that can often exceed several years — a result of budgetary constraints and the unavailability of the data they need. By the time GIS analysts and professionals do receive…

Maxar collected a pre-explosion image with its WorldView-3 satellite on June 9, 2020 (left), and a post-explosion image with its WorldView-2 satellite on August 5, 2020.

On August 4th, 2020, a major explosion devastated the city of Beirut, Lebanon. The cause of the explosion, as cited from the Prime Minister, was 2,750 metric tons of ammonium nitrate, a common chemical compound used in fertilizer and a component in mining explosives. As of August 7, at least 150 people have been killed and more than 5,000 people injured; another 300,000+ people have been displaced by the explosion. It is estimated that the explosion has caused as much as $5 billion in damage.

Ecopia.AI, in partnership with Maxar Technologies, has mapped a 1-kilometre radius surrounding the point of…

Acres burned by wildfire in the US have climbed year after year since the early 1980s, increasing in both frequency and intensity. In California, the Butte County Camp Fire in 2018 was the costliest wildfire in modern history, burning 153,336 acres, destroying 18,804 buildings and claiming 85 lives, stoking heightened interest amongst insurers and reinsurers to manage this risk effectively.

For insurers and reinsurers, one of the best methods to manage wildfire risk is to proactively account for it during the pricing and underwriting process. The necessary prerequisite is to ensure that all relevant risk factors are considered at the…

In the real estate market, it is often said that the three most important factors are location, location, and location. A similar argument could be made for insurance property underwriting. Of course, the attributes of the property itself are important — and there is a lot of buzz in the industry about creating comprehensive property attributes. In order for insurers to calculate the probabilities of various risks and repair/replacement costs, it is essential to have data on many specific characteristics of the property, such as square feet/meters, exterior and interior building materials, roof shape, foundation type and size, the presence…

For the second year in a row, Ecopia.AI sponsored Hack the North, which saw over 1,500 students from over 20 countries gathered at the University of Waterloo for 36 hours of hacking, collaborating and networking. Now in its sixth year, Hack the North is one of the top hackatons for high school and university students in North America! Ecopia has a strong tie to the University of Waterloo (UW), as the company was commercialized from a PhD research thesis, and two of the founders hold degrees from UW in geomatics and engineering. …

Ecopia AI

Ecopia’s HD Vector maps provide a digital representation of the real world, offering unique insight for critical decision-making at a global scale.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store