On-demand webinar: Q3 FY22 roadmap update: boosting model accuracy & quality

In this webinar from September 2022, we introduced a set of data curation & model analysis tools, beginning with Dataset Exploration. Using an approach common to many data analysts today but spun in a unique Picterra way will allow users to reveal visual patterns in the data and to quickly improve the accuracy of models by:
Finding unrepresented parts of the dataset which can be used to retrain the model.
Removing redundant training areas.
Reducing chances of false positives by adding more training areas in representative parts of the dataset.
--
Please note that some historical webinars may include references to features and functionality that are absent or are in different locations within current versions of Picterra products. Register for upcoming live webinars here: picterra.ch/re...
For more information on Picterra and to sign up for a free trial, visit our website: picterra.ch/

[@maungmoemyint857]

Do we need to do atmospheric correction of the images before training in picterra?

[@Picterra]

Hi there! As long as you can see and annotate the object, pattern, or change of interest you can create a model to detect at scale.