New system for extracting crucial information from satellite images

Analyzing drone or satellite images of a given territory.

Franck de Morsier, CTO, and Pierrick Poulenas, CEO of Picterra © 2018 Alain Herzog
Franck de Morsier, CTO, and Pierrick Poulenas, CEO of Picterra © 2018 Alain Herzog

A start-up company at EPFLPicterra, recently has developed a smart system that allows users to analyze drone or satellite images of a given territory. In other words, the system is capable of extricating data, insights, and representations of changes that have occurred in the region and all of these within few clicks.

The system is actually an artificial intelligence platform that enables anybody to extricate pivotal data from drone or satellite pictures – many of which are in public domain – in a couple of snaps. It will be displayed to the public in general and sector professionals tomorrow at GEOSummit in Bern.

The system’s basic algorithms can locate and count user-selected elements and spatiotemporal changes after quickly learning which objects to recognize. Developed by Picterra’s CTO Frank de Morsier, the algorithm intuitively and quickly compares the object’s qualities with alternate elements of the picture, or contrasts the essential picture and different pictures of the area, in order to recognize the changes.

de Morsier, also a lecturer at Geographic Information Systems Laboratory said, “Although artificial intelligence (AI) has made huge strides in the fields of ‘natural’ language and text analysis, using AI specifically to analyze terrestrial imaging is an almost virgin territory. For example, What do monitoring a national park, identifying suitable building locations and managing a vineyard have in common? All these activities and a wide range of others can be carried out more quickly and comprehensively by using aerial and satellite images.”

The system has a huge range of potential applications, for example in the agriculture, defense, finance, shipping, government, university and research sectors. Other platforms that allow users to compile and exploit aerial images exist, but Picterra has created a simple system that everyone can use for their own purposes. It, therefore, relies on human expertise, which sets the direction that machine learning then follows.

A user just simply needs to upload their aerial images stitched together to form just one large image. It has few options from a drop-down menu and then pin-points some examples of the selected elements on the image. The process can then be enhanced through the addition of other images.

Pierrick Poulenas, CEO stated, “After it was founded in 2016, Picterra tested its system – which offers 5-centimeter resolution – using several real situations, including monitoring illegal logging in several African, Asian and South-American countries, tracking vine stocks in a large vineyard and detecting trees that are dangerously close to high-voltage cables.”

“The startup has used the resulting expertise to develop a new, customizable system that anyone can use. It can observe areas of up to 2,000 km2, which corresponds to the size of a satellite image. But the coverage is global: it can scan a surface of a few hectares as well as an entire continent.”

“For example, it would be perfectly possible for a citizens’ association to use AI to analyze a beach and distinguish between organic waste and waste of human origin, or for a company to use a customized AI system to track its cargo all around the world.”