Job title: Satellite imagery training dataset creation
Work Location: Germany / Remote
Department: Remote sensing, Computer Science, Earth Sciences
Work load: 15 Hours / Week
Job Type: Bachelor Thesis / Internship
General Description:
In the frame of prototyping a Remote sensing solution that is able to process, analyze and interpret satellite data using machine learning and AI algorithms (see images below). It is required based on the use case to train our AI model to detect, classify or predict a specific feature or phenomena for example: Trees, buildings, streets, farms, oil fields, etc.
In order to do that, our AI models shall be trained by dataset that have sufficient accuracy depending on the use case. Therefore it is required to develop a procedure to gather a generous amount of data and label it according to given specification and transfer it to Nabtaplaya Amazon AWS S3 storage.
Example of training dataset on Nabtaplaya cloud: https://drive.google.com/file/d/1A-lrvvyc4c1zjsvYLhmr2bWYr2eLyOMs/view?usp=sharing
Essential Duties and Responsibilities:
Create a labelled satellite data with features of interest based on defined specification
Export the labeled data in JSON format
Implement a generic approach and procedure for this process
Education and/or Work Experience Requirements:
Bachelor in computer science, remote sensing or related disciplines
Very good knowledge of GIS
Good knowledge of python
Very good knowledge of Linux
Good knowledge of Cloud Technology
Knowledge of Machine Learning and AI is a plus
Very good verbal and written communication skills in English
Ability to work independently and to carry out assignments to completion within parameters of instructions given, prescribed routines, and standard accepted practices
Comments