Happy to release an eCognition Developer customized algorithm capable of analyzing time series of satellite data and classify objects based on their temporal profile.
For more information about this methodology, please refer to our published paper (open-access, click on blue title above): Csillik, O.; Belgiu, M.; Asner, G.P.; Kelly, M. Object-Based Time-Constrained Dynamic Time Warping Classification of Crops Using Sentinel-2. Remote Sensing 2019, 11, 1257.
We have used Dynamic Time Warping as a supervised classification method that uses the temporal pattern of NDVI from Sentinel-2 to classify the agricultural fields based on their similarity. The analysis was performed at the object-level, so that in the end ready-to-use spatial vector datasets of land-use/land-cover classes are generated. These kinds of approaches are needed as we move into an abundance of satellite constellations that provide increasing spatial and temporal resolution.
By downloading the ZIP file , you will get the following files: (1) an eCognition customized algorithm, (2) a User Guide with step-by-step instructions, and (3) a Demo Data folder containing a Sentinel-2 time series, the corresponding segmentation, reference and validation samples.
Let me know your feedback, if you need support or any other related questions!
Necessary cookies are absolutely essential for the website to function properly. This category only includes cookies that ensures basic functionalities and security features of the website. These cookies do not store any personal information.
Any cookies that may not be particularly necessary for the website to function and is used specifically to collect user personal data via analytics, ads, other embedded contents are termed as non-necessary cookies. It is mandatory to procure user consent prior to running these cookies on your website.