Using Convolutional Neural Networks to Automatically Analyze Aerial and Satellite Imagery
In this recording of our most recent Technical Staff Meeting, Lewis Fishgold walks us through the team's work on Raster Vision, a set of open source tools for automatically analyzing aerial and satellite imagery using convolutional neural networks.
Outline:
* a review of convolutional neural networks
* our approaches to tagging and semantic segmentation for two machine learning contests
* demo of a tool for visualizing output on an interactive map. [Seeing the results on a map can give a great sense of where the algorithms get it right, and where they get it wrong, and where they amusingly have a tough time figuring it out (e.g. a large food truck: is it a car or a building?)]
* our use of AWS Batch for running experiments
* a preview of some new work on object detection
Read more about this work in this blog post:
https://www.azavea.com/blog/2017/05/30/deep-learning-on-aerial-imagery/
Machine Learning Contest Leaderboards:
http://www2.isprs.org/potsdam-2d-semantic-labeling.html
https://www.kaggle.com/c/planet-understanding-the-amazon-from-space/leaderboard
Azavea - Advanced geospatial technology and research for civic and social impact
Visit our website: https://www.azavea.com/
Join our team: http://jobs.azavea.com/
Check out our products:
* GeoTrellis - open source, high performance geoprocessing: http://geotrellis.io/
* Cicero - database of elected officials contact information & legislative districts: https://www.cicerodata.com/
What is a B Corporation? https://www.bcorporation.net/what-are-b-corps
Видео Using Convolutional Neural Networks to Automatically Analyze Aerial and Satellite Imagery канала Azavea
Outline:
* a review of convolutional neural networks
* our approaches to tagging and semantic segmentation for two machine learning contests
* demo of a tool for visualizing output on an interactive map. [Seeing the results on a map can give a great sense of where the algorithms get it right, and where they get it wrong, and where they amusingly have a tough time figuring it out (e.g. a large food truck: is it a car or a building?)]
* our use of AWS Batch for running experiments
* a preview of some new work on object detection
Read more about this work in this blog post:
https://www.azavea.com/blog/2017/05/30/deep-learning-on-aerial-imagery/
Machine Learning Contest Leaderboards:
http://www2.isprs.org/potsdam-2d-semantic-labeling.html
https://www.kaggle.com/c/planet-understanding-the-amazon-from-space/leaderboard
Azavea - Advanced geospatial technology and research for civic and social impact
Visit our website: https://www.azavea.com/
Join our team: http://jobs.azavea.com/
Check out our products:
* GeoTrellis - open source, high performance geoprocessing: http://geotrellis.io/
* Cicero - database of elected officials contact information & legislative districts: https://www.cicerodata.com/
What is a B Corporation? https://www.bcorporation.net/what-are-b-corps
Видео Using Convolutional Neural Networks to Automatically Analyze Aerial and Satellite Imagery канала Azavea
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
When deep learning meets satellite imageryLecture 11 | Detection and SegmentationThis Canadian Genius Created Modern AIAutomated Object Based Image Feature Extraction1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jeff RoachConvolutional Neural Networks (CNNs) explainedMIT 6.S191: Convolutional Neural NetworksHands-on Satellite Imagery Analysis | SciPy 2018 Tutorial | Sara Safavi, Dana BauerHow Will Machine Learning Change The World?Real-Time Machine Learning on Satellite Imagery: How DigitalGlobe Uses Amazon SageMaker12a: Neural NetsEcology Live with Nathalie Pettorelli- Satellite imagery, time series, fusion and land cover mappingA friendly introduction to Convolutional Neural Networks and Image RecognitionThe art of neural networks | Mike Tyka | TEDxTUMFast Algorithms for Convolutional Neural Networks by Andrew Lavin and Scott GrayHow computers learn to recognize objects instantly | Joseph RedmonSkynet Machine Learning with Satellites and OpenStreetMap data | Anand ThakkerQGIS and democracy: Redistricting and reapportionment with QGISClusterNet: Detecting Small Objects in Large Scenes by Exploiting Spatio-Temporal InformationSimple explanation of convolutional neural network | Deep Learning Tutorial 23 (Tensorflow & Python)