In November 2016, we presented COWI’s use of the Trimble eCognition software for forest monitoring. For those of you interested in learning more about this use case an additional article was published in INFORMED INFRASTRUCTURE entitled “One Forest, Multiple Perspectives”.
This article goes into more detail than what was published in the May, 2016 edition of the Trimble technology & more magazine and reviews several interesting COWI eCognition-based business cases. In both cases, the fundamental strengths of the eCognition software are clearly presented – namely, providing customers with a powerful image-object based analysis platform that allows remote sensing specialists to combine multiple data types within a single project environment. Here the user was particularly interested in combining “historical stand data with the elevation detail of LiDAR”.
Moreover, COWI was able to develop “the eCognition rule set to identify and delineate stand borders, distinguish vegetative types based on height, spectral qualities and textural features––a process similar to how the human brain distinguishes specific objects––and classify the vegetation” in just two days.
COWI is also utilizing the benefits of image analysis automation (i.e. batch processing): “the software automatically recognized stand border changes and delineated them, defined existing and new clear cuts, detected and delineated differences in the forest between 2010 and 2015 and divided unproductive areas into two classes, trees shorter or taller than four meters––a workflow that took 30 minutes.”
COWI’s customer, the Swedish forest company Orsa Besparingsskog, reported that the maps generated by COWI with eCognition were 95% accurate.