diff --git a/README.md b/README.md index 6e039530..24ec71f5 100644 --- a/README.md +++ b/README.md @@ -58,20 +58,10 @@ Classification is a fundamental task in remote sensing data analysis, where the - [RSI-CB](https://github.com/lehaifeng/RSI-CB) -> A Large Scale Remote Sensing Image Classification Benchmark via Crowdsource Data. See also [Remote-sensing-image-classification](https://github.com/aashishrai3799/Remote-sensing-image-classification) -- [NAIP_PoolDetection](https://github.com/annaptasznik/NAIP_PoolDetection) -> modelled as an object recognition problem, a CNN is used to identify images as being swimming pools or something else - specifically a street, rooftop, or lawn - -- [Vision Transformers Use Case: Satellite Image Classification without CNNs](https://medium.com/nerd-for-tech/vision-transformers-use-case-satellite-image-classification-without-cnns-2c4dbeb06f87) - - [WaterNet](https://github.com/treigerm/WaterNet) -> a CNN that identifies water in satellite images - [Road-Network-Classification](https://github.com/ualsg/Road-Network-Classification) -> Road network classification model using ResNet-34, road classes organic, gridiron, radial and no pattern -- [Scaling AI to map every school on the planet](https://developmentseed.org/blog/2021-03-18-ai-enabling-school-mapping) - -- [satellite-crosswalk-classification](https://github.com/rodrigoberriel/satellite-crosswalk-classification) - -- [Implementation of the 3D-CNN model for land cover classification](https://medium.com/geekculture/remote-sensing-deep-learning-for-land-cover-classification-of-satellite-imagery-using-python-6a7b4c4f570f) -> uses the Sundarbans dataset, with [repo](https://github.com/syamkakarla98/Satellite_Imagery_Analysis) - - [SSTN](https://github.com/zilongzhong/SSTN) -> Spectral-Spatial Transformer Network for Hyperspectral Image Classification: A FAS Framework - [SatellitePollutionCNN](https://github.com/arnavbansal1/SatellitePollutionCNN) -> A novel algorithm to predict air pollution levels with state-of-art accuracy using deep learning and GoogleMaps satellite images @@ -80,48 +70,26 @@ Classification is a fundamental task in remote sensing data analysis, where the - [remote-sense-quickstart](https://github.com/CarryHJR/remote-sense-quickstart) -> classification on a number of datasets, including with attention visualization -- [Satellite image classification using multiple machine learning algorithms](https://github.com/tanmay-delhikar/satellite-image-analysis-ml) - - [IGARSS2020_BWMS](https://github.com/jiankang1991/IGARSS2020_BWMS) -> Band-Wise Multi-Scale CNN Architecture for Remote Sensing Image Scene Classification with a novel CNN architecture for the feature embedding of high-dimensional RS images - [image.classification.on.EuroSAT](https://github.com/canturan10/image.classification.on.EuroSAT) -> solution in pure pytorch - [hurricane_damage](https://github.com/allankapoor/hurricane_damage) -> Post-hurricane structure damage assessment based on aerial imagery -- [openai-drivendata-challenge](https://github.com/buildwithcycy/openai-drivendata-challenge) -> Using deep learning to classify the building material of rooftops (aerial imagery from South America) - -- [BoulderAreaDetector](https://github.com/pszemraj/BoulderAreaDetector) -> CNN to classify whether a satellite image shows an area would be a good rock climbing spot or not - - [ISPRS_S2FL](https://github.com/danfenghong/ISPRS_S2FL) -> Multimodal Remote Sensing Benchmark Datasets for Land Cover Classification with A Shared and Specific Feature Learning Model - [ensemble_LCLU](https://github.com/burakekim/ensemble_LCLU) -> Deep neural network ensembles for remote sensing land cover and land use classification -- [cerraNet](https://github.com/MirandaMat/cerraNet-v2) -> contextually classify the types of use and coverage in the Brazilian Cerrado - - [Urban-Analysis-Using-Satellite-Imagery](https://github.com/mominali12/Urban-Analysis-Using-Satellite-Imagery) -> classify urban area as planned or unplanned using a combination of segmentation and classification -- [ChipClassification](https://github.com/yurithefury/ChipClassification) -> Deep learning for multi-modal classification of cloud, shadow and land cover scenes in PlanetScope and Sentinel-2 imagery - -- [DeeplearningClassficationLandsat-tImages](https://github.com/VinayarajPoliyapram/DeeplearningClassficationLandsat-tImages) -> Water/Ice/Land Classification Using Large-Scale Medium Resolution Landsat Satellite Images - -- [wildfire-detection-from-satellite-images-ml](https://github.com/shrey24/wildfire-detection-from-satellite-images-ml) -> detect whether an image contains a wildfire, with example flask web app - - [mining-discovery-with-deep-learning](https://github.com/remis/mining-discovery-with-deep-learning) -> Mining and Tailings Dam Detection in Satellite Imagery Using Deep Learning -- [e-Farmerce-platform](https://github.com/efarmerce/e-Farmerce-platform) -> classify crop type - - [sentinel2-deep-learning](https://github.com/d-smit/sentinel2-deep-learning) -> Novel Training Methodologies for Land Classification of Sentinel-2 Imagery -- [RSSC-transfer](https://github.com/risojevicv/RSSC-transfer) -> The Role of Pre-Training in High-Resolution Remote Sensing Scene Classification - -- [Classifying Geo-Referenced Photos and Satellite Images for Supporting Terrain Classification](https://github.com/jorgemspereira/Classifying-Geo-Referenced-Photos) -> detect floods - - [Pay-More-Attention](https://github.com/williamzhao95/Pay-More-Attention) -> Remote Sensing Image Scene Classification Based on an Enhanced Attention Module - [Remote Sensing Image Classification via Improved Cross-Entropy Loss and Transfer Learning Strategy Based on Deep Convolutional Neural Networks](https://github.com/AliBahri94/Remote-Sensing-Image-Classification-via-Improved-Cross-Entropy-Loss-and-Transfer-Learning-Strategy) -- [DenseNet40-for-HRRSISC](https://github.com/BiQiWHU/DenseNet40-for-HRRSISC) -> DenseNet40 for remote sensing image scene classification, uses UC Merced Dataset - - [SKAL](https://github.com/hw2hwei/SKAL) -> Looking Closer at the Scene: Multiscale Representation Learning for Remote Sensing Image Scene Classification - [SAFF](https://github.com/zh-hike/SAFF) -> Self-Attention-Based Deep Feature Fusion for Remote Sensing Scene Classification @@ -154,14 +122,8 @@ Classification is a fundamental task in remote sensing data analysis, where the - [flood_susceptibility_mapping](https://github.com/omarseleem92/flood_susceptibility_mapping) -> Towards urban flood susceptibility mapping using data-driven models in Berlin, Germany -- [tick-tick-bloom](https://github.com/drivendataorg/tick-tick-bloom) -> Winners of the Tick Tick Bloom: Harmful Algal Bloom Detection Challenge. Task was to predict severity of algae bloom, winners used decision trees - -- [Estimating coal power plant operation from satellite images with computer vision](https://transitionzero.medium.com/estimating-coal-power-plant-operation-from-satellite-images-with-computer-vision-b966af56919e) -> use Sentinel 2 data to identify if a coal power plant is on or off, with dataset and repo - - [Building-detection-and-roof-type-recognition](https://github.com/loosgagnet/Building-detection-and-roof-type-recognition) -> A CNN-Based Approach for Automatic Building Detection and Recognition of Roof Types Using a Single Aerial Image -- [Performance Comparison of Multispectral Channels for Land Use Classification](https://github.com/tejasri19/EuroSAT_data_analysis) -> Implemented ResNet-50, ResNet-101, ResNet-152, Vision Transformer on RGB and multispectral versions of EuroSAT dataset. - - [SNN4Space](https://github.com/AndrzejKucik/SNN4Space) -> project which investigates the feasibility of deploying spiking neural networks (SNN) in land cover and land use classification tasks - [vessel-classification](https://github.com/GlobalFishingWatch/vessel-classification) -> classify vessels and identify fishing behavior based on AIS data @@ -201,33 +163,20 @@ Image segmentation is a crucial step in image analysis and computer vision, with - [laika](https://github.com/datasciencecampus/laika) -> The goal of this repo is to research potential sources of satellite image data and to implement various algorithms for satellite image segmentation -- landcover dot io -> was a human-in-the-loop AI tool to drastically reduce the time required to produce an accurate Land Use/Land Cover (LULC) map, [blog post](http://devseed.com/blog/2021-05-17-pearl-ai-land-cover), used Microsoft Planetary Computer and ML models run locally in the browser. Code for [backelnd](https://github.com/developmentseed/pearl-backend) and [frontend](https://github.com/developmentseed/pearl-frontend) - -- [Land Cover Classification with U-Net](https://baratam-tarunkumar.medium.com/land-cover-classification-with-u-net-aa618ea64a1b) -> Satellite Image Multi-Class Semantic Segmentation Task with PyTorch Implementation of U-Net, uses DeepGlobe Land Cover Segmentation dataset, with [code](https://github.com/TarunKumar1995-glitch/land_cover_classification_unet) - -- [dubai-satellite-imagery-segmentation](https://github.com/ayushdabra/dubai-satellite-imagery-segmentation) -> due to the small dataset, image augmentation was used - [CDL-Segmentation](https://github.com/asimniazi63/CDL-Segmentation) -> Deep Learning Based Land Cover and Crop Type Classification: A Comparative Study. Compares UNet, SegNet & DeepLabv3+ - [LoveDA](https://github.com/Junjue-Wang/LoveDA) -> A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation -- [Satellite Imagery Semantic Segmentation with CNN](https://joshting.medium.com/satellite-imagery-segmentation-with-convolutional-neural-networks-f9254de3b907) -> 7 different segmentation classes, DeepGlobe Land Cover Classification Challenge dataset, with [repo](https://github.com/justjoshtings/satellite_image_segmentation) - -- [Aerial Semantic Segmentation using U-Net Deep Learning Model](https://medium.com/@rehman.aimal/aerial-semantic-segmentation-using-u-net-deep-learning-model-3356a53c915f) medium article, with [repo](https://github.com/aimalrehman92/Multiclass-Semantic-Segmentation-with-U-NET) - -- [UNet-Satellite-Image-Segmentation](https://github.com/YudeWang/UNet-Satellite-Image-Segmentation) -> A Tensorflow implentation of light UNet semantic segmentation framework - [DeepGlobe Land Cover Classification Challenge solution](https://github.com/GeneralLi95/deepglobe_land_cover_classification_with_deeplabv3plus) -- [Semantic-segmentation-with-PyTorch-Satellite-Imagery](https://github.com/JenAlchimowicz/Semantic-segmentation-with-PyTorch-Satellite-Imagery) -> predict 25 classes on RGB imagery taken to assess the damage after Hurricane Harvey - - [CNN_Enhanced_GCN](https://github.com/qichaoliu/CNN_Enhanced_GCN) -> CNN-Enhanced Graph Convolutional Network With Pixel- and Superpixel-Level Feature Fusion for Hyperspectral Image Classification - [LULCMapping-WV3images-CORINE-DLMethods](https://github.com/esertel/LULCMapping-WV3images-CORINE-DLMethods) -> Land Use and Land Cover Mapping Using Deep Learning Based Segmentation Approaches and VHR Worldview-3 Images - [MCANet](https://github.com/yisun98/SOLC) -> A joint semantic segmentation framework of optical and SAR images for land use classification. Uses [WHU-OPT-SAR-dataset](https://github.com/AmberHen/WHU-OPT-SAR-dataset) -- [MUnet-LUC](https://github.com/abhi170599/MUnet-LUC) - [land-cover](https://github.com/lucashu1/land-cover) -> Model Generalization in Deep Learning Applications for Land Cover Mapping @@ -238,7 +187,6 @@ Image segmentation is a crucial step in image analysis and computer vision, with - [SSLTransformerRS](https://github.com/HSG-AIML/SSLTransformerRS) -> Self-supervised Vision Transformers for Land-cover Segmentation and Classification -- [aerial-tile-segmentation](https://github.com/mrsebai/aerial-tile-segmentation) -> Large satellite image semantic segmentation into 6 classes using Tensorflow 2.0 and ISPRS benchmark dataset - [LULCMapping-WV3images-CORINE-DLMethods](https://github.com/burakekim/LULCMapping-WV3images-CORINE-DLMethods) -> Land Use and Land Cover Mapping Using Deep Learning Based Segmentation Approaches and VHR Worldview-3 Images @@ -260,7 +208,6 @@ Image segmentation is a crucial step in image analysis and computer vision, with - [M3SPADA](https://github.com/ecapliez/M3SPADA) -> Multi-Sensor Temporal Unsupervised Domain Adaptation for Land Cover Mapping with spatial pseudo labelling and adversarial learning -- [mitmul/ssai-cnn](https://github.com/mitmul/ssai-cnn) -> Semantic Segmentation for Aerial / Satellite Images with CNN, includes implementation of FCN for dense labeling of aerial imagery - [GLNet](https://github.com/VITA-Group/GLNet) -> Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images @@ -278,13 +225,11 @@ Note that deforestation detection may be treated as a segmentation task or a cha - [DetecTree](https://github.com/martibosch/detectree) -> Tree detection from aerial imagery in Python, a LightGBM classifier of tree/non-tree pixels from aerial imagery -- [Сrор field boundary detection: approaches and main challenges](https://medium.com/geekculture/%D1%81r%D0%BE%D1%80-field-boundary-detection-approaches-and-main-challenges-46e37dd276bc) -> Medium article, covering historical and modern approaches - [kenya-crop-mask](https://github.com/nasaharvest/kenya-crop-mask) -> Annual and in-season crop mapping in Kenya - LSTM classifier to classify pixels as containing crop or not, and a multi-spectral forecaster that provides a 12 month time series given a partial input. Dataset downloaded from GEE and pytorch lightning used for training - [Tree species classification from from airborne LiDAR and hyperspectral data using 3D convolutional neural networks](https://github.com/jaeeolma/tree-detection-evo) -- [crop-type-classification](https://medium.com/nerd-for-tech/crop-type-classification-cf5cc2593396) -> using Sentinel 1 & 2 data with a U-Net + LSTM, more features (i.e. bands) and higher resolution produced better results (article, no code) - [Find sports fields using Mask R-CNN and overlay on open-street-map](https://github.com/jremillard/images-to-osm) @@ -292,8 +237,6 @@ Note that deforestation detection may be treated as a segmentation task or a cha - [DeepSatModels](https://github.com/michaeltrs/DeepSatModels) -> Context-self contrastive pretraining for crop type semantic segmentation -- [Detecting Agricultural Croplands from Sentinel-2 Satellite Imagery](https://medium.com/radiant-earth-insights/detecting-agricultural-croplands-from-sentinel-2-satellite-imagery-a025735d3bd8) -> We developed UNet-Agri, a benchmark machine learning model that classifies croplands using open-access Sentinel-2 imagery at 10m spatial resolution - - [DeepTreeAttention](https://github.com/weecology/DeepTreeAttention) -> Implementation of Hang et al. 2020 "Hyperspectral Image Classification with Attention Aided CNNs" for tree species prediction - [Crop-Classification](https://github.com/bhavesh907/Crop-Classification) -> crop classification using multi temporal satellite images @@ -312,8 +255,6 @@ Note that deforestation detection may be treated as a segmentation task or a cha - [global-cropland-mapping](https://github.com/Charly-tian/global-cropland-mapping) -> global multi-temporal cropland mapping -- [U-Net for Semantic Segmentation of Soyabean Crop Fields with SAR images](https://joaootavionf007.medium.com/u-net-for-semantic-segmentation-of-soyabeans-crop-fields-with-sar-images-604232e49315) - - [Landuse_DL](https://github.com/yghlc/Landuse_DL) -> delineate landforms due to the thawing of ice-rich permafrost - [canopy](https://github.com/jonathanventura/canopy) -> A Convolutional Neural Network Classifier Identifies Tree Species in Mixed-Conifer Forest from Hyperspectral Imagery @@ -326,7 +267,6 @@ Note that deforestation detection may be treated as a segmentation task or a cha - [crop-type-detection-ICLR-2020](https://github.com/RadiantMLHub/crop-type-detection-ICLR-2020) -> Winning Solutions from Crop Type Detection Competition at CV4A workshop, ICLR 2020 -- [Crop identification using satellite imagery](https://write.agrevolution.in/crop-identification-using-satellite-imagery-introduction-83d79344f9ee) -> Medium article, introduction to crop identification - [S4A-Models](https://github.com/Orion-AI-Lab/S4A-Models) -> Various experiments on the Sen4AgriNet dataset @@ -339,7 +279,6 @@ Note that deforestation detection may be treated as a segmentation task or a cha - [Official repository for the "Identifying trees on satellite images" challenge from Omdena](https://github.com/cienciaydatos/ai-challenge-trees) -- [TreeDetection](https://github.com/AmirNiaraki/TreeDetection) -> A color-based classifier to detect the trees in google image data along with tree visual localization and crown size calculations via OpenCV - [PTDM](https://github.com/hr8yhtzb/PTDM) -> Pomelo Tree Detection Method Based on Attention Mechanism and Cross-Layer Feature Fusion @@ -351,7 +290,6 @@ Note that deforestation detection may be treated as a segmentation task or a cha - [kbrodt biomassters solution](https://github.com/kbrodt/biomassters) -> 1st place solution -- [quqixun biomassters solution](https://github.com/quqixun/BioMassters) - [biomass-estimation](https://github.com/azavea/biomass-estimation) -> from Azavea, applied to Sentinel 1 & 2 @@ -371,7 +309,6 @@ Note that deforestation detection may be treated as a segmentation task or a cha - [cvpr-multiearth-deforestation-segmentation](https://github.com/h2oai/cvpr-multiearth-deforestation-segmentation) -> multimodal Unet entry to the CVPR Multiearth 2023 deforestation challenge -- [supervised-wheat-classification-using-pytorchs-torchgeo](https://medium.com/@sulemanhamdani10/supervised-wheat-classification-using-pytorchs-torchgeo-combining-satellite-imagery-and-python-fc7f95c82e) -> supervised wheat classification using torchgeo - [TransUNetplus2](https://github.com/aj1365/TransUNetplus2) -> TransU-Net++: Rethinking attention gated TransU-Net for deforestation mapping. Uses the Amazon and Atlantic forest dataset @@ -403,19 +340,14 @@ Note that deforestation detection may be treated as a segmentation task or a cha ### Segmentation - Water, coastlines, rivers & floods -- [pytorch-waterbody-segmentation](https://github.com/gauthamk02/pytorch-waterbody-segmentation) -> UNET model trained on the Satellite Images of Water Bodies dataset from Kaggle. The model is deployed on Hugging Face Spaces -- [Automatic Flood Detection from Satellite Images Using Deep Learning](https://medium.com/@omercaliskan99/automatic-flood-detection-from-satellite-images-using-deep-learning-f14fafd369e0) -- [Semi-Supervised Classification and Segmentation on High Resolution Aerial Images - Solving the FloodNet problem](https://sahilkhose.medium.com/paper-presentation-e9bd0f3fb0bf) - [Houston_flooding](https://github.com/Lichtphyz/Houston_flooding) -> labeling each pixel as either flooded or not using data from Hurricane Harvey. Dataset consisted of pre and post flood images, and a ground truth floodwater mask was created using unsupervised clustering (with DBScan) of image pixels with human cluster verification/adjustment - [ml4floods](https://github.com/spaceml-org/ml4floods) -> An ecosystem of data, models and code pipelines to tackle flooding with ML -- [A comprehensive guide to getting started with the ETCI Flood Detection competition](https://medium.com/cloud-to-street/jumpstart-your-machine-learning-satellite-competition-submission-2443b40d0a5a) -> using Sentinel1 SAR & pytorch -- [Map Floodwater of SAR Imagery with SageMaker](https://github.com/JayThibs/map-floodwater-sar-imagery-on-sagemaker) -> applied to Sentinel-1 dataset - [1st place solution for STAC Overflow: Map Floodwater from Radar Imagery hosted by Microsoft AI for Earth](https://github.com/sweetlhare/STAC-Overflow) -> combines Unet with Catboostclassifier, taking their maxima, not the average @@ -423,13 +355,9 @@ Note that deforestation detection may be treated as a segmentation task or a cha - [CoastSat](https://github.com/kvos/CoastSat) -> tool for mapping coastlines which has an extension [CoastSeg](https://github.com/dbuscombe-usgs/CoastSeg) using segmentation models -- [Satellite_Flood_Segmentation_of_Harvey](https://github.com/morgan-tam/Satellite_Flood_Segmentation_of_Harvey) -> explores both deep learning and traditional kmeans -- [Flood Event Detection Utilizing Satellite Images](https://github.com/KonstantinosF/Flood-Detection---Satellite-Images) -- [ETCI-2021-Competition-on-Flood-Detection](https://github.com/sidgan/ETCI-2021-Competition-on-Flood-Detection) -> Experiments on Flood Segmentation on Sentinel-1 SAR Imagery with Cyclical Pseudo Labeling and Noisy Student Training -- [FDSI](https://github.com/keillernogueira/FDSI) -> Flood Detection in Satellite Images - 2017 Multimedia Satellite Task - [deepwatermap](https://github.com/isikdogan/deepwatermap) -> a deep model that segments water on multispectral images @@ -566,7 +494,6 @@ Extracting roads is challenging due to the occlusions caused by other objects an - [Winning Solutions from SpaceNet Road Detection and Routing Challenge](https://github.com/SpaceNetChallenge/RoadDetector) -- [Detecting road and road types jupyter notebook](https://github.com/taspinar/sidl/blob/master/notebooks/2_Detecting_road_and_roadtypes_in_sattelite_images.ipynb) - [awesome-deep-map](https://github.com/antran89/awesome-deep-map) -> A curated list of resources dedicated to deep learning / computer vision algorithms for mapping. The mapping problems include road network inference, building footprint extraction, etc. @@ -1185,7 +1112,6 @@ Orinted bounding boxes (OBB) are polygons representing rotated rectangles. For d - [GF-CSL](https://github.com/WangJian981002/GF-CSL) -> Gaussian Focal Loss: Learning Distribution Polarized Angle Prediction for Rotated Object Detection in Aerial Images -- [simplified_rbox_cnn](https://github.com/SIAnalytics/simplified_rbox_cnn) -> RBox-CNN: rotated bounding box based CNN for ship detection in remote sensing image. Uses Tensorflow object detection API - [Polar-Encodings](https://github.com/flyingshan/Learning-Polar-Encodings-For-Arbitrary-Oriented-Ship-Detection-In-SAR-Images) -> Learning Polar Encodings for Arbitrary-Oriented Ship Detection in SAR Images @@ -1314,9 +1240,6 @@ Detecting the most noticeable or important object in a scene - [How hard is it for an AI to detect ships on satellite images?](https://medium.com/earthcube-stories/how-hard-it-is-for-an-ai-to-detect-ships-on-satellite-images-7265e34aadf0) -- [Object Detection in Satellite Imagery, a Low Overhead Approach](https://medium.com/the-downlinq/object-detection-in-satellite-imagery-a-low-overhead-approach-part-i-cbd96154a1b7) - -- [Detecting Ships in Satellite Imagery](https://medium.com/dataseries/detecting-ships-in-satellite-imagery-7f0ca04e7964) using the Planet dataset and Keras - [SARfish](https://github.com/MJCruickshank/SARfish) -> Ship detection in Sentinel 1 Synthetic Aperture Radar (SAR) imagery @@ -1359,13 +1282,9 @@ Detecting the most noticeable or important object in a scene - [WakeNet](https://github.com/Lilytopia/WakeNet) -> Rethinking Automatic Ship Wake Detection: State-of-the-Art CNN-based Wake Detection via Optical Images -- [Histogram of Oriented Gradients (HOG) Boat Heading Classification](https://medium.com/the-downlinq/histogram-of-oriented-gradients-hog-heading-classification-a92d1cf5b3cc) -- [Object Detection in Satellite Imagery, a Low Overhead Approach](https://medium.com/the-downlinq/object-detection-in-satellite-imagery-a-low-overhead-approach-part-i-cbd96154a1b7) -> Medium article which demonstrates how to combine Canny edge detector pre-filters with HOG feature descriptors, random forest classifiers, and sliding windows to perform ship detection -- [simplified_rbox_cnn](https://github.com/SIAnalytics/simplified_rbox_cnn) -> RBox-CNN: rotated bounding box based CNN for ship detection in remote sensing image. Uses Tensorflow object detection API -- [Ship-Detection-based-on-YOLOv3-and-KV260](https://github.com/xlsjdjdk/Ship-Detection-based-on-YOLOv3-and-KV260) -> entry project of the Xilinx Adaptive Computing Challenge 2021. It uses YOLOv3 for ship target detection in optical remote sensing images, and deploys DPU on the KV260 platform to achieve hardware acceleration - [LEVIR-Ship](https://github.com/WindVChen/LEVIR-Ship) -> a dataset for tiny ship detection under medium-resolution remote sensing images @@ -1407,11 +1326,9 @@ Detecting the most noticeable or important object in a scene - [RSVC2021-Dataset](https://github.com/YinongGuo/RSVC2021-Dataset) -> A dataset for Vehicle Counting in Remote Sensing images, created from the DOTA & ITCVD -- [Car Localization and Counting with Overhead Imagery, an Interactive Exploration](https://medium.com/the-downlinq/car-localization-and-counting-with-overhead-imagery-an-interactive-exploration-9d5a029a596b) -> Medium article by Adam Van Etten - [Vehicle-Counting-in-Very-Low-Resolution-Aerial-Images](https://github.com/hbsszq/Vehicle-Counting-in-Very-Low-Resolution-Aerial-Images) -> Vehicle Counting in Very Low-Resolution Aerial Images via Cross-Resolution Spatial Consistency and Intraresolution Time Continuity -- [Vehicle Detection blog post](https://www.silvispace.xyz/posts/vehicle-post/) by Grant Pearse: detecting vehicles across New Zealand without collecting local training data - [detecting-trucks](https://github.com/datasciencecampus/detecting-trucks) -> detecting large vehicles in Sentinel-2 @@ -1442,13 +1359,11 @@ Detecting the most noticeable or important object in a scene - [aerial-detection](https://github.com/alexbakr/aerial-detection) -> uses Yolov5 & Icevision -- [How to choose a deep learning architecture to detect aircrafts in satellite imagery?](https://medium.com/artificialis/how-to-choose-a-deep-learning-model-to-detect-aircrafts-in-satellite-imagery-cd7d106e76ad) - [rareplanes-yolov5](https://github.com/jeffaudi/rareplanes-yolov5) -> using YOLOv5 and the RarePlanes dataset to detect and classify sub-characteristics of aircraft, with [article](https://medium.com/artificialis/detecting-aircrafts-on-airbus-pleiades-imagery-with-yolov5-5f3d464b75ad) - [OnlyPlanes](https://github.com/naivelogic/OnlyPlanes) -> Incrementally Tuning Synthetic Training Datasets for Satellite Object Detection -- [Understanding the RarePlanes Dataset and Building an Aircraft Detection Model](https://encord.com/blog/rareplane-dataset-aircraft-detection-model/) -> blog post ### Object detection - Infrastructure & utilities @@ -1470,7 +1385,6 @@ Oil is stored in tanks at many points between extraction and sale, and the volum - [Oil-Tank-Volume-Estimation](https://github.com/kheyer/Oil-Tank-Volume-Estimation) -> combines object detection and classical computer vision -- [Oil tank instance segmentation with Mask R-CNN](https://github.com/georgiosouzounis/instance-segmentation-mask-rcnn) with [accompanying article](https://medium.com/@georgios.ouzounis/oil-storage-tank-instance-segmentation-with-mask-r-cnn-77c94433045f) using Keras & Airbus Oil Storage Detection Dataset on Kaggle - [SubpixelCircleDetection](https://github.com/anttad/SubpixelCircleDetection) -> CIRCULAR-SHAPED OBJECT DETECTION IN LOW RESOLUTION SATELLITE IMAGES @@ -1478,7 +1392,6 @@ Oil is stored in tanks at many points between extraction and sale, and the volum - [oil_well_detector](https://github.com/dzubke/oil_well_detector) -> detect oil wells in the Bakken oil field based on satellite imagery -- [Oil Storage Detection on Airbus Imagery with YOLOX](https://medium.com/artificialis/oil-storage-detection-on-airbus-imagery-with-yolox-9e38eb6f7e62) -> uses the Kaggle Airbus Oil Storage Detection dataset - [AContrarioTankDetection](https://github.com/anttad/AContrarioTankDetection) -> Oil Tank Detection in Satellite Images via a Contrario Clustering @@ -1492,7 +1405,6 @@ A variety of techniques can be used to count animals, including object detection - [cownter_strike](https://github.com/IssamLaradji/cownter_strike) -> counting cows, located with point-annotations, two models: CSRNet (a density-based method) & LCFCN (a detection-based method) -- [elephant_detection](https://github.com/akharina/elephant_detection) -> Using Keras-Retinanet to detect elephants from aerial images - [CNN-Mosquito-Detection](https://github.com/sriramelango/CNN-Mosquito-Detection) -> determining the locations of potentially dangerous breeding grounds, compared YOLOv4, YOLOR & YOLOv5 @@ -1508,15 +1420,12 @@ A variety of techniques can be used to count animals, including object detection ### Object detection - Miscellaneous -- [Object detection on Satellite Imagery using RetinaNet](https://medium.com/@ije_good/object-detection-on-satellite-imagery-using-retinanet-part-1-training-e589975afbd5) -> using the Kaggle Swimming Pool and Car Detection dataset -- [Tackling the Small Object Problem in Object Detection](https://blog.roboflow.com/tackling-the-small-object-problem-in-object-detection) - [Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review](https://www.mdpi.com/2072-4292/12/10/1667) - [awesome-aerial-object-detection bu murari023](https://github.com/murari023/awesome-aerial-object-detection), [another by visionxiang](https://github.com/visionxiang/awesome-object-detection-in-aerial-images) and [awesome-tiny-object-detection](https://github.com/kuanhungchen/awesome-tiny-object-detection) list many relevant papers -- [Object Detection Accuracy as a Function of Image Resolution](https://medium.com/the-downlinq/the-satellite-utility-manifold-object-detection-accuracy-as-a-function-of-image-resolution-ebb982310e8c) -> Medium article using COWC dataset, performance rapidly degrades below 30cm imagery - [Satellite Imagery Multiscale Rapid Detection with Windowed Networks (SIMRDWN)](https://github.com/avanetten/simrdwn) -> combines some of the leading object detection algorithms into a unified framework designed to detect objects both large and small in overhead imagery. Train models and test on arbitrary image sizes with YOLO (versions 2 and 3), Faster R-CNN, SSD, or R-FCN. @@ -1532,13 +1441,11 @@ A variety of techniques can be used to count animals, including object detection - [Faster RCNN for xView satellite data challenge](https://github.com/samirsen/small-object-detection) -- [How to detect small objects in (very) large images](https://blog.ml6.eu/how-to-detect-small-objects-in-very-large-images-70234bab0f98) -> A practical guide to using Slicing-Aided Hyper Inference (SAHI) for performing inference on the DOTAv1.0 object detection dataset using the mmdetection framework - [Object Detection Satellite Imagery Multi-vehicles Dataset (SIMD)](https://github.com/asimniazi63/Object-Detection-on-Satellite-Images) -> RetinaNet,Yolov3 and Faster RCNN for multi object detection on satellite images dataset - [SNIPER/AutoFocus](https://github.com/mahyarnajibi/SNIPER) -> an efficient multi-scale object detection training/inference algorithm -- [marine_debris_ML](https://github.com/NASA-IMPACT/marine_debris_ML) -> Marine debris detection, uses 3-meter imagery product called Planetscope with bands in the red, green, blue, and near-infrared. Uses Tensorflow Object Detection API with pre-trained resnet 101 - [Electric-Pylon-Detection-in-RSI](https://github.com/qsjxyz/Electric-Pylon-Detection-in-RSI) -> a dataset which contains 1500 remote sensing images of electric pylons used to train ten deep learning models @@ -1556,7 +1463,6 @@ A variety of techniques can be used to count animals, including object detection - [Google-earth-Object-Recognition](https://github.com/InnovAIco/Google-earth-Object-Recognition) -> Code for training and evaluating on Dior Dataset (Google Earth Images) using RetinaNet and YOLOV5 -- [HIECTOR: Hierarchical object detector at scale](https://medium.com/sentinel-hub/hiector-hierarchical-object-detector-at-scale-5a61753b51a3) -> HIECTOR facilitates multiple satellite data collections of increasingly detailed spatial resolution for a cost-efficient and accurate object detection over large areas. [Code](https://github.com/sentinel-hub/hiector) - [Detection of Multiclass Objects in Optical Remote Sensing Images](https://github.com/WenchaoliuMUC/Detection-of-Multiclass-Objects-in-Optical-Remote-Sensing-Images) -> Detection of Multiclass Objects in Optical Remote Sensing Images @@ -1568,7 +1474,6 @@ A variety of techniques can be used to count animals, including object detection - [dior_detect](https://github.com/hm-better/dior_detect) -> benchmarks for object detection on DIOR dataset -- [Panchromatic to Multispectral: Object Detection Performance as a Function of Imaging Bands](https://medium.com/the-downlinq/panchromatic-to-multispectral-object-detection-performance-as-a-function-of-imaging-bands-51ecaaa3dc56) -> Medium article, concludes that more bands are not always beneficial, but likely varies by use case - [OPLD-Pytorch](https://github.com/yf19970118/OPLD-Pytorch) -> Learning Point-Guided Localization for Detection in Remote Sensing Images @@ -1578,7 +1483,6 @@ A variety of techniques can be used to count animals, including object detection - [SRAF-Net](https://github.com/Complicateddd/SRAF-Net) -> A Scene-Relevant Anchor-Free Object Detection Network in Remote Sensing Images -- [object_detection_in_remote_sensing_images](https://github.com/EEexplorer001/object_detection_in_remote_sensing_images) -> using CNN and attention mechanism - [SHAPObjectDetection](https://github.com/hiroki-kawauchi/SHAPObjectDetection) -> SHAP-Based Interpretable Object Detection Method for Satellite Imagery @@ -1612,7 +1516,6 @@ A variety of techniques can be used to count animals, including object detection - [Satellite-Remote-Sensing-Image-Object-Detection](https://github.com/ypw-lbj/Satellite-Remote-Sensing-Image-Object-Detection) -> using RefineDet & DOTA dataset -- [yolov5](https://github.com/leticiastachelski/yolov5) -> yolov5 detecting hurricane with Roboflow - [SFRNet](https://github.com/Ranchosky/SFRNet) -> SFRNet: Fine-Grained Oriented Object Recognition via Separate Feature Refinement @@ -1630,7 +1533,6 @@ When the object count, but not its shape is required, U-net can be used to treat - [DO-U-Net](https://github.com/ToyahJade/DO-U-Net) -> an effective approach for when the size of an object needs to be known, as well as the number of objects in the image, initially created to segment and count Internally Displaced People (IDP) camps in Afghanistan -- [Cassava Crop Counting](https://medium.com/@wongsirikuln/cassava-standing-crop-counting-869cca486ce3) - [Counting from Sky](https://github.com/gaoguangshuai/Counting-from-Sky-A-Large-scale-Dataset-for-Remote-Sensing-Object-Counting-and-A-Benchmark-Method) -> A Large-scale Dataset for Remote Sensing Object Counting and A Benchmark Method @@ -1656,7 +1558,6 @@ Regression in remote sensing involves predicting continuous variables such as wi - [HighResCanopyHeight](https://github.com/facebookresearch/HighResCanopyHeight) -> code for Meta paper: Very high resolution canopy height maps from RGB imagery using self-supervised vision transformer and convolutional decoder trained on Aerial Lidar -- [Traffic density estimation as a regression problem instead of object detection](https://omdena.com/blog/ai-road-safety/) -> inspired by paper: Traffic density estimation method from small satellite imagery: Towards frequent remote sensing of car traffic - [OpticalWaveGauging_DNN](https://github.com/OpticalWaveGauging/OpticalWaveGauging_DNN) -> Optical wave gauging using deep neural networks @@ -1833,11 +1734,9 @@ Change detection is a vital component of remote sensing analysis, enabling the m - [Unstructured-change-detection-using-CNN](https://github.com/vbhavank/Unstructured-change-detection-using-CNN) -- [Change Detection in 3D: Generating Digital Elevation Models from Dove Imagery](https://www.planet.com/pulse/publications/change-detection-in-3d-generating-digital-elevation-models-from-dove-imagery/) - [QGIS plugin for applying change detection algorithms on high resolution satellite imagery](https://github.com/dymaxionlabs/massive-change-detection) -- [LamboiseNet](https://github.com/hbaudhuin/LamboiseNet) -> Master thesis about change detection in satellite imagery using Deep Learning - [Fully Convolutional Siamese Networks for Change Detection](https://github.com/rcdaudt/fully_convolutional_change_detection) @@ -1877,11 +1776,9 @@ Change detection is a vital component of remote sensing analysis, enabling the m - [SRCDNet](https://github.com/liumency/SRCDNet) -> Super-resolution-based Change Detection Network with Stacked Attention Module for Images with Different Resolutions. SRCDNet is designed to learn and predict change maps from bi-temporal images with different resolutions -- [Land-Cover-Analysis](https://github.com/Kalit31/Land-Cover-Analysis) -> Land Cover Change Detection using Satellite Image Segmentation - [A deeply supervised image fusion network for change detection in high resolution bi-temporal remote sening images](https://github.com/GeoZcx/A-deeply-supervised-image-fusion-network-for-change-detection-in-remote-sensing-images) -- [Satellite-Image-Alignment-Differencing-and-Segmentation](https://github.com/rishi5kesh/Satellite-Image-Alignment-Differencing-and-Segmentation) - [ChangeFormer](https://github.com/wgcban/ChangeFormer) -> A Transformer-Based Siamese Network for Change Detection. Uses transformer architecture to address the limitations of CNN in handling multi-scale long-range details. Demonstrates that ChangeFormer captures much finer details compared to the other SOTA methods, achieving better performance on benchmark datasets @@ -1952,7 +1849,6 @@ Change detection is a vital component of remote sensing analysis, enabling the m - [ESCNet](https://github.com/Bobholamovic/ESCNet) -> An End-to-End Superpixel-Enhanced Change Detection Network for Very-High-Resolution Remote Sensing Images -- [ForestCoverChange](https://github.com/annusgit/ForestCoverChange) -> Detecting and Predicting Forest Cover Change in Pakistani Areas Using Remote Sensing Imagery - [deforestation-detection](https://github.com/vldkhramtsov/deforestation-detection) -> DEEP LEARNING FOR HIGH-FREQUENCY CHANGE DETECTION IN UKRAINIAN FOREST ECOSYSTEM WITH SENTINEL-2 @@ -1968,7 +1864,6 @@ Change detection is a vital component of remote sensing analysis, enabling the m - [Remote-sensing-time-series-change-detection](https://github.com/liulianni1688/Remote-sensing-time-series-change-detection) -> Graph-based block-level urban change detection using Sentinel-2 time series -- [austin-ml-change-detection-demo](https://github.com/makepath/austin-ml-change-detection-demo) -> A change detection demo for the Austin area using a pre-trained PyTorch model scaled with Dask on Planet imagery - [dfc2021-msd-baseline](https://github.com/calebrob6/dfc2021-msd-baseline) -> Multitemporal Semantic Change Detection track of the 2021 IEEE GRSS Data Fusion Competition @@ -1984,7 +1879,6 @@ Change detection is a vital component of remote sensing analysis, enabling the m - [FHD](https://github.com/ZSVOS/FHD) -> Feature Hierarchical Differentiation for Remote Sensing Image Change Detection -- [Change detection with Raster Vision](https://www.azavea.com/blog/2022/04/18/change-detection-with-raster-vision/) -> blog post with Colab notebook - [building-expansion](https://github.com/reglab/building_expansion) -> Enhancing Environmental Enforcement with Near Real-Time Monitoring: Likelihood-Based Detection of Structural Expansion of Intensive Livestock Farms @@ -2461,27 +2355,20 @@ Note that nearly all the MISR publications resulted from the [PROBA-V Super Reso - [Random Forest Super-Resolution (RFSR repo)](https://github.com/jshermeyer/RFSR) including [sample data](https://github.com/jshermeyer/RFSR/tree/master/SampleImagery) -- [Enhancing Sentinel 2 images by combining Deep Image Prior and Decrappify](https://medium.com/omdena/pushing-the-limits-of-open-source-data-enhancing-satellite-imagery-through-deep-learning-9d8a3bbc0e0a). Repo for [deep-image-prior](https://github.com/DmitryUlyanov/deep-image-prior) and article on [decrappify](https://www.fast.ai/2019/05/03/decrappify/) -- [Image Super-Resolution using an Efficient Sub-Pixel CNN](https://keras.io/examples/vision/super_resolution_sub_pixel/) -> the keras docs have a great tutorial on this light weight but well performing model - [super-resolution-using-gan](https://github.com/saraivaufc/super-resolution-using-gan) -> Super-Resolution of Sentinel-2 Using Generative Adversarial Networks -- [Super-resolution of Multispectral Satellite Images Using Convolutional Neural Networks](https://up42.com/blog/tech/super-resolution-of-multispectral-satellite-images-using-convolutional) -- [Multi-temporal Super-Resolution on Sentinel-2 Imagery](https://medium.com/sentinel-hub/multi-temporal-super-resolution-on-sentinel-2-imagery-6089c2b39ebc) using HighRes-Net, [repo](https://github.com/sentinel-hub/multi-temporal-super-resolution) - [SSPSR-Pytorch](https://github.com/junjun-jiang/SSPSR) -> A spatial-spectral prior deep network for single hyperspectral image super-resolution -- [Sentinel-2 Super-Resolution: High Resolution For All (Bands)](https://up42.com/blog/tech/sentinel-2-superresolution) - [CinCGAN](https://github.com/Junshk/CinCGAN-pytorch) -> Unsupervised Image Super-Resolution using Cycle-in-Cycle Generative Adversarial Networks - [Satellite-image-SRGAN using PyTorch](https://github.com/xjohnxjohn/Satellite-image-SRGAN) -- [EEGAN](https://github.com/kuijiang0802/EEGAN) -> Edge Enhanced GAN For Remote Sensing Image Super-Resolution, TensorFlow 1.1 -- [PECNN](https://github.com/kuijiang0802/PECNN) -> A Progressively Enhanced Network for Video Satellite Imagery Super-Resolution, minimal documentation - [hs-sr-tvtv](https://github.com/marijavella/hs-sr-tvtv) -> Enhanced Hyperspectral Image Super-Resolution via RGB Fusion and TV-TV Minimization @@ -2519,11 +2406,8 @@ Note that nearly all the MISR publications resulted from the [PROBA-V Super Reso - [SatelliteSR](https://github.com/kmalhan/SatelliteSR) -> comparison of a number of techniques on the DOTA dataset -- [Image-Super-Resolution](https://github.com/Elangoraj/Image-Super-Resolution) -> Super resolution RESNET network -- [Unsupervised Super Resolution for Sentinel-2 satellite imagery](https://github.com/savassif/Thesis) -> using Deep Image Prior (DIP), Zero-Shot Super Resolution (ΖSSR) & Degradation-Aware Super Resolution (DASR) -- [Spectral Super-Resolution of Satellite Imagery with Generative Adversarial Networks](https://github.com/ImDanielRojas/thesis) - [Super resolution using GAN / 4x Improvement](https://github.com/purijs/satellite-superresolution) -> applied to Sentinel 2