7 thoughts on “OBDTW

  1. Thanks for sharing.

    1. Hope it helps! Let me know if you’ll have questions about it.

  2. Does it work on older versions? specially Cognition v9.0 ?

    1. I used version 9.4 and usually if you want to use older versions of eCognition, some compatibility issues might arise since some features in 9.4 might not be available in 9.0. Have you tried and ended with some errors?

  3. FATİH FEHMİ ŞİMŞEK December 11, 2019 at 7:29 am

    Thank you so much Ovidiu.

    I downloaded package and i will try. If i have a question can i ask ?

    1. Sure! Try it and let me know if you have questions.

  4. Dr. U.Kumara Ganesh December 30, 2019 at 3:59 am

    Dear sir,
    I introduce myself as a professional person. For a part of my research, I planned to map landuse features using Object based image analysis.
    I am new to the object based image analysis (OBIA).
    While searching information regarding OBIA specifically for CNN, I found your’s youtube video and it helps me more to understand the same in detail.
    In this connection, I need your guidence to carry out OBIA classification for urban area. I initially tried to extract road and building using high resolution data using ecognition. But i am facing difficulties while extracting using Deep learning (convolution neural network) techniques.
    Misclassification was noticed between this two features (Building and road),
    because similar tonal signature and shadows from building and trees.
    Subsequently I tried to insert the shape of this features to discriminate (Because
    modifications are noticed in shape of this both features)in the sample file.
    But all the generated samples are only in defined shape (kernal in size (for example 10 X 10 pixels).
    Hence, I unable to define the shape of the feature too.
    I also tried to generate sample files manually in different shapes and replaced the sample files,
    but its not consider while processing.
    So kindly guide me to do further for extracting road and building using deep learning in Ecognition.

Leave a Comment

Your email address will not be published. Required fields are marked *