A Framework for Remote Sensing Images Processing Using Deep Learning Techniques

Abstract

Deep learning techniques are becoming increasingly important to solve a number of image processing tasks. Among common algorithms, Convolutional Neural Networks and Recurrent Neural Networks based systems achieve state of the art results on satellite and aerial imagery in many applications. While these approaches are subject to scientific interest, there is currently no operational and generic implementation available at user-level for the remote sensing community. In this paper, we presents a framework enabling the use of deep learning techniques with remote sensing images and geospatial data. Our solution takes roots in two extensively used open-source libraries, the remote sensing image processing library Orfeo ToolBox, and the high performance numerical computation library TensorFlow. It can apply deep nets without restriction on images size and is computationally efficient, regardless hardware configuration. * R. Cresson is with the IRSTEA, UMR TETIS, BP 5095,

Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review-Part I: Evolution and Recent Trends

“…For ArcGIS, the tools are implemented in the Image Analyst extension [147] supporting TensorFlow, Keras, Pytorch and CNTK. For QGIS the established Orfeo ToolBox for ML [148] supports DL via the remote OTBTF (Orfeo ToolBox meets TensorFlow) module [149], which uses TensorFlow as backend. Another open source project which leverages QGIS is rastervision [150] which supports TensorFlow, Keras and Pytorch.…”

UAV-Based Land Cover Classification for Hoverfly (Diptera: Syrphidae) Habitat Condition Assessment: A Case Study on Mt. Stara Planina (Serbia)

“…In this study, three object-based supervised algorithms were applied: Support Vector Machine (SVM), Random Forest (RF), and knearest neighbors (k-NN). Recently, efforts have been aimed at extending OTB with deep learning algorithms [73]; however, this workflow is in the early development stage and uses image patches instead of objects. This approach will certainly be considered in future research and will also require extended image collection and labelling.…”

Sentinel-1/Sentinel-2-Derived Soil Moisture Product At Plot Scale (S2 MP)

“…It has stable API release in Python and C++, and allows development on multiple kind of platform based on Central or Graphic Processing Units. OTBTF (OTB TensorFlow) is a module developed by Cresson [9] to bind OTB capabilities with TensorFlow deep machine learning resources. OTB also contains a Python API, thus, batch processing and files manipulation have been scripted in Python.…”