When developing eCognition, Gerd Binnig, the 1986 Nobel Laureate for Physics, and his team made a radical departure from conventional, pixel-based image analysis game. Their unique technology does not simply identify the “objects of interest” but all of the intermediate objects together with their interrelationships (context). This difference in approach is profound. The contextual information contained in the eCognition objects facilitates the automated extraction of information – in exactly the same way as a human being makes sense of the image.
Fast forward 20 years, and eCognition has transformed from a pioneering object-based analysis technique for raster data to a software technology that can integrate and extract information from any geospatial data––automatically. It has truly offered a radical departure from conventional approaches to data analysis and it continues to push the envelope of data fusion and integrated analyses.
What’s been most rewarding and inspiring is to watch and learn just how much impact eCognition has had on geospatial users. As we celebrate the technology’s 20+ years in the business, we wanted to take stock of all that it has helped users achieve. Most importantly, we wanted to hear from users, new and old, about what eCognition has meant for them: how they’ve challenged it and how it has challenged them.
We asked a number of users 20 questions about eCognition such as: What has been the most significant eCognition development? What is their most loved feature? and, What about the software gets them out of bed? Their answers have been honest, thoughtful and entertaining––and worth sharing.
So, with this 20+ years theme in mind, we’re creating a “20 Questions” blog series to share users’ achievements and experiences. Given the software’s influence, it seemed appropriate to start with this question:
When did you know eCognition would be a game changer for you?
Here are some of our users’ answers. We would be delighted if you’d share yours with us in the eCognition Community.
2003. I was in graduate school and working on routines to automate the mapping of riparian buffers. I was throwing every possible approach using pixel-based classifiers (the standard at the time) with disastrous results. I found an article online from a professor in Germany who had compared pixel-based to object-based approaches and I wrote to him for advice. He replied with one line, “get a copy of eCognition,” so I did. It completely changed the way I approached automated feature extraction, allowing me to replicate the way, I, as a human, extract features from remotely sensed data.
Jarlath O’Neil Dunne
The first time I segmented an aerial photo of a broken marsh, I was hooked. WOW! I thought, look at the way the image objects trace the coastline, cleanly and precisely. I knew this was the way forward.
Whitney Broussard III, PhD, GISP
Senior Scientist, JESCO Inc
It was in 2004. All of a sudden we had a tool that could create information from images in a better way than the old raster solutions. Today it has become a very powerful tool.
Nils Erik Jørgensen
In 2005, I obtained a demo license of eCognition. After a challenging yet relatively short learning curve, I was sold on eCognition’s OBIA capabilities. I was impressed with how it could make smart class decisions based on spectral information and segmented object’s relationships to neighbors, ancillary data, multi-level geometry, and texture. Imagery’s sum of possibilities is greater than the whole when using OBIA.
Director of Imagery Analysis, Land Info Worldwide Mapping
I started to work with eCognition as a student in 2002. At this time, the approach of object-based image analysis in combination with fuzzy classification techniques was very fascinating and completely different to any other image analysis software.
Associate Professor Dr. Dirk Tiede
Head EO Analytics, University of Salzburg