Create time-series datacubes for supervised machine learning with ICEYE SAR images.

Related tags

Deep Learningicecube
Overview

ICEcube is a Python library intended to help organize SAR images and annotations for supervised machine learning applications. The library generates multidimensional SAR image and labeled data arrays.

The datacubes stack SAR time-series images in range and azimuth and can preserve the geospatial content, intensity, and complex SAR signal from the ICEYE SAR images. You can use the datacubes with ICEYE Ground Range Detected (GRD) geotifs and ICEYE Single Look Complex (SLC) .hdf5 product formats.

alt text

This work is sponsored by ESA Φ-lab as part of the AI4SAR initiative.


Getting Started

You need Python 3.8 or later to use the ICEcube library.

The installation options depend on whether you want to use the library in your Python scripts or you want to contribute to it. For more information, see Installation.


ICEcube Examples

To test the Jupyter notebooks and for information on how to use the library, see the ICEcube Documentation.


AI4SAR Project Updates

For the latest project updates, see SAR for AI Development.

Comments
  • 'RPC' does not exist

    'RPC' does not exist

    Trying to read an SLC .h5 downloaded from ICEYE archive (id 10499) and get 'RPC does not exist':

    cube_config = CubeConfig()
    slc_datacube = SLCDatacube.build(cube_config, '/Users/sstrong/bin/test_data_icecube/slcs')
    
    ---------------------------------------------------------------------------
    KeyError                                  Traceback (most recent call last)
    /var/folders/7r/fyfh8zx51ls6yt8t_jppnz3c0000gq/T/ipykernel_11546/2087236712.py in <module>
          1 cube_config = CubeConfig()
    ----> 2 slc_datacube = SLCDatacube.build(cube_config, '/Users/sstrong/bin/test_data_icecube/slcs')
    
    ~/Documents/github/icecube/icecube/bin/sar_cube/slc_datacube.py in build(cls, cube_config, raster_dir)
         52     def build(cls, cube_config: CubeConfig, raster_dir: str) -> SARDatacube:
         53         slc_datacube = SLCDatacube(cube_config, RASTER_DTYPE)
    ---> 54         ds = slc_datacube.create(cls.PRODUCT_TYPE, raster_dir)
         55         slc_datacube.xrdataset = ds
         56         return slc_datacube
    
    ~/Documents/github/icecube/icecube/utils/common_utils.py in time_it(*args, **kwargs)
        111     def time_it(*args, **kwargs):
        112         time_started = time.time()
    --> 113         return_value = func(*args, **kwargs)
        114         time_elapsed = time.time()
        115         logger.info(
    
    ~/Documents/github/icecube/icecube/bin/sar_cube/sar_datacube.py in create(self, product_type, raster_dir)
         43         """
         44         metadata_object = SARDatacubeMetadata(self.cube_config)
    ---> 45         metadata_object = metadata_object.compute_metdatadf_from_folder(
         46             raster_dir, product_type
         47         )
    
    ~/Documents/github/icecube/icecube/bin/sar_cube/sar_datacube_metadata.py in compute_metdatadf_from_folder(self, raster_dir, product_type)
        116         )
        117 
    --> 118         self.metadata_df = self._crawl_metadata(raster_dir, product_type)
        119         logger.debug(f"length metadata from the directory {len(self.metadata_df)}")
        120 
    
    ~/Documents/github/icecube/icecube/bin/sar_cube/sar_datacube_metadata.py in _crawl_metadata(self, raster_dir, product_type)
         68 
         69     def _crawl_metadata(self, raster_dir, product_type):
    ---> 70         return metadata_crawler(
         71             raster_dir,
         72             product_type,
    
    ~/Documents/github/icecube/icecube/utils/metadata_crawler.py in metadata_crawler(raster_dir, product_type, variables, recursive)
         36     _, raster_paths = DirUtils.get_dir_files(raster_dir, fext=fext)
         37 
    ---> 38     return metadata_crawler_list(raster_paths, variables)
         39 
         40 
    
    ~/Documents/github/icecube/icecube/utils/metadata_crawler.py in metadata_crawler_list(raster_paths, variables)
         43 
         44     for indx, raster_path in enumerate(raster_paths):
    ---> 45         metadata = IO.load_ICEYE_metadata(raster_path)
         46         parsed_metadata = _parse_data_row(metadata, variables)
         47         parsed_metadata["product_fpath"] = raster_path
    
    ~/Documents/github/icecube/icecube/utils/analytics_IO.py in load_ICEYE_metadata(path)
        432         are converted from bytedata and read into the dict for compatability reasons.
        433         """
    --> 434         return read_SLC_metadata(h5py.File(path, "r"))
        435 
        436     elif path.endswith(".tif") or path.endswith(".tiff"):
    
    ~/Documents/github/icecube/icecube/utils/analytics_IO.py in read_SLC_metadata(h5_io)
        329 
        330     # RPCs are nested under "RPC/" in the h5 thus need to be parsed in a specific manner
    --> 331     RPC_source = h5_io["RPC"]
        332     meta_dict["RPC"] = parse_slc_rpc_to_meta_dict(
        333         RPC_source=RPC_source, meta_dict=meta_dict
    
    h5py/_objects.pyx in h5py._objects.with_phil.wrapper()
    
    h5py/_objects.pyx in h5py._objects.with_phil.wrapper()
    
    /opt/homebrew/anaconda3/envs/icecube_env/lib/python3.8/site-packages/h5py/_hl/group.py in __getitem__(self, name)
        303                 raise ValueError("Invalid HDF5 object reference")
        304         elif isinstance(name, (bytes, str)):
    --> 305             oid = h5o.open(self.id, self._e(name), lapl=self._lapl)
        306         else:
        307             raise TypeError("Accessing a group is done with bytes or str, "
    
    h5py/_objects.pyx in h5py._objects.with_phil.wrapper()
    
    h5py/_objects.pyx in h5py._objects.with_phil.wrapper()
    
    h5py/h5o.pyx in h5py.h5o.open()
    
    KeyError: "Unable to open object (object 'RPC' doesn't exist)"
    
    opened by shaystrong 3
  • scikit-image dependency  fails on OSX M1 chip

    scikit-image dependency fails on OSX M1 chip

    Can't install all requirements for icecube on an M1 chip. This may present a future problem, just documenting for awareness. scikit-image cannot seem to be compiled/installed/etc on the M1. I have not tested the conda installation, as perhaps that does work. But i use brew/pip (and conda can create conflicts with those)

    opened by shaystrong 2
  • Fix/labels coords

    Fix/labels coords

    Summary includes:

    • Making xr.dataset structure coherent for labels and SAR (added time coords for labels)
    • For labels datacube, product_fpath are used compared to previously
    • small typo fixed
    • tests added for merging sar cubes with labels cube
    • instructions/cell added to install ml requirements for notebook#5
    • release notes added to mkdocs
    • steup.py updated with ml requirements and version
    opened by muaali 1
  • Update/docs/notebooks

    Update/docs/notebooks

    Changes involve:

    • Introduced a new markdown file called "overview.md" that talks about the structure of examples under docs/
    • Added a new notebook : CreatingDatacube that walks a user how to create datacubes with different methods
    • Other notebooks updated and improved.
    opened by muaali 1
  • missing RPC metadata set to None

    missing RPC metadata set to None

    related to issue: https://github.com/iceye-ltd/icecube/issues/11 Some of old ICEYE images can have RPC information missing. If that happens RPC key will be missing and pipeline does not work. RPC is now set to None if it's missing with a user warning generated.

    opened by muaali 0
  • feat/general metadata

    feat/general metadata

    Following changes introduced:

    • metadata constraints loosen up to allow merging general SAR data (rasterio/HDF5 compatible). But this means that cube configuration is not available for such rasters
    • .tiff support added for GRDs
    • code refactoring in SARDatacubeMetadata to avoid repetitive code
    opened by muaali 0
  • Labels/subset support

    Labels/subset support

    Changes include:

    • Updating SLC metadata reader to avoid key values stored as HDF5 dataset
    • Enabling cube generation from labels.json that have masks/labels for subset rasters (i.e., number of masks ingested into labels cube don't necessarily have to be same as number of rasters)
    • CHUNK_SIZE have been reduced to provide more optimized performance for creating massive datacubes
    opened by muaali 0
  • bin module not found

    bin module not found

    After installing from github using !pip install git+https://github.com/iceye-ltd/icecube.git it imports well icecube, but it throws this error for module bin ModuleNotFoundError: No module named 'icecube.bin'

    Any advice, thanks

    opened by jaimebayes 0
  • dummy_mask_labels.json

    dummy_mask_labels.json

    FileNotFoundError: [Errno 2] No such file or directory: './resources/labels/dummy_mask_labels.json'

    Could you upload it? is it available? Thanks in advance,

    opened by jaimebayes 0
Releases(1.1.0)
Owner
ICEYE Ltd
ICEYE Ltd
ICEYE Ltd
Learning to See by Looking at Noise

Learning to See by Looking at Noise This is the official implementation of Learning to See by Looking at Noise. In this work, we investigate a suite o

Manel Baradad Jurjo 82 Dec 24, 2022
Code accompanying the paper Shared Independent Component Analysis for Multi-subject Neuroimaging

ShICA Code accompanying the paper Shared Independent Component Analysis for Multi-subject Neuroimaging Install Move into the ShICA directory cd ShICA

8 Nov 07, 2022
Deep Q-Learning Network in pytorch (not actively maintained)

pytoch-dqn This project is pytorch implementation of Human-level control through deep reinforcement learning and I also plan to implement the followin

Hung-Tu Chen 342 Jan 01, 2023
Code repository for paper `Skeleton Merger: an Unsupervised Aligned Keypoint Detector`.

Skeleton Merger Skeleton Merger, an Unsupervised Aligned Keypoint Detector. The paper is available at https://arxiv.org/abs/2103.10814. A map of the r

北海若 48 Nov 14, 2022
Image super-resolution (SR) is a fast-moving field with novel architectures attracting the spotlight

Revisiting RCAN: Improved Training for Image Super-Resolution Introduction Image super-resolution (SR) is a fast-moving field with novel architectures

Zudi Lin 76 Dec 01, 2022
Code for Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothing(ICCV21)

NeuralGIF Code for Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothing(ICCV21) We present Neural Generalized Implicit F

Garvita Tiwari 104 Nov 18, 2022
Stochastic gradient descent with model building

Stochastic Model Building (SMB) This repository includes a new fast and robust stochastic optimization algorithm for training deep learning models. Th

S. Ilker Birbil 22 Jan 19, 2022
Code for our CVPR2021 paper coordinate attention

Coordinate Attention for Efficient Mobile Network Design (preprint) This repository is a PyTorch implementation of our coordinate attention (will appe

Qibin (Andrew) Hou 726 Jan 05, 2023
Hide screen when boss is approaching.

BossSensor Hide your screen when your boss is approaching. Demo The boss stands up. He is approaching. When he is approaching, the program fetches fac

Hiroki Nakayama 6.2k Jan 07, 2023
The dataset of tweets pulling from Twitters with keyword: Hydroxychloroquine, location: US, Time: 2020

HCQ_Tweet_Dataset: FREE to Download. Keywords: HCQ, hydroxychloroquine, tweet, twitter, COVID-19 This dataset is associated with the paper "Understand

2 Mar 16, 2022
Brain tumor detection using Convolution-Neural Network (CNN)

Detect and Classify Brain Tumor using CNN. A system performing detection and classification by using Deep Learning Algorithms using Convolution-Neural Network (CNN).

assia 1 Feb 07, 2022
🔎 Monitor deep learning model training and hardware usage from your mobile phone 📱

Monitor deep learning model training and hardware usage from mobile. 🔥 Features Monitor running experiments from mobile phone (or laptop) Monitor har

labml.ai 1.2k Dec 25, 2022
[ICRA 2022] An opensource framework for cooperative detection. Official implementation for OPV2V.

OpenCOOD OpenCOOD is an Open COOperative Detection framework for autonomous driving. It is also the official implementation of the ICRA 2022 paper OPV

Runsheng Xu 322 Dec 23, 2022
Implementation of the paper "Fine-Tuning Transformers: Vocabulary Transfer"

Transformer-vocabulary-transfer Implementation of the paper "Fine-Tuning Transfo

LEYA 13 Nov 30, 2022
PyTorch implementation of the R2Plus1D convolution based ResNet architecture described in the paper "A Closer Look at Spatiotemporal Convolutions for Action Recognition"

R2Plus1D-PyTorch PyTorch implementation of the R2Plus1D convolution based ResNet architecture described in the paper "A Closer Look at Spatiotemporal

Irhum Shafkat 342 Dec 16, 2022
Data, model training, and evaluation code for "PubTables-1M: Towards a universal dataset and metrics for training and evaluating table extraction models".

PubTables-1M This repository contains training and evaluation code for the paper "PubTables-1M: Towards a universal dataset and metrics for training a

Microsoft 365 Jan 04, 2023
The codes for the work "Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation"

Swin-Unet The codes for the work "Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation"(https://arxiv.org/abs/2105.05537). A validatio

869 Jan 07, 2023
Learn the Deep Learning for Computer Vision in three steps: theory from base to SotA, code in PyTorch, and space-repetition with Anki

DeepCourse: Deep Learning for Computer Vision arthurdouillard.com/deepcourse/ This is a course I'm giving to the French engineering school EPITA each

Arthur Douillard 113 Nov 29, 2022
EMNLP'2021: SimCSE: Simple Contrastive Learning of Sentence Embeddings

SimCSE: Simple Contrastive Learning of Sentence Embeddings This repository contains the code and pre-trained models for our paper SimCSE: Simple Contr

Princeton Natural Language Processing 2.5k Dec 29, 2022
Trafffic prediction analysis using hybrid models - Machine Learning

Hybrid Machine learning Model Clone the Repository Create a new Directory as assests and download the model from the below link Model Link To Start th

1 Feb 08, 2022