Aircraft image dataset. Images are from airliners.

Aircraft image dataset. The dataset contains a total of 12500 aircraft instances from VHR optical remote sensing images which are acquired from Google Earth with spatial resolution ranging from 0. Expand in Data Studio Dataset for object detection of military aircraft The dataset contains 10,000 images of aircraft, with 100 images for each of 100 different aircraft model variants, most of which are airplanes. Dec 1, 2024 · For each bounding box from the labelled image dataset, there are four coordinates and one class label used for the identification of small aircraft in infrared aerial imagery. 2. It includes 3594 airplane images obtained from various public datasets, such as DIOR, UCA AOD, NWPU VHR-10, DOTA, and Google Earth. It is provided for demonstration purpose only. Apr 22, 2022 · In this study, we create a novel airplane detection dataset called High Resolution Planes (HRPlanes) by using images from Google Earth (GE) and labeling the bounding box of each plane on the images. 3 to 0. Image Mar 7, 2024 · Abstract This paper introduces FGVC-Aircraft, a new dataset containing 10,000 images of aircraft spanning 100 aircraft models, organised in a three-level hierarchy. This dataset contains 10,200 images of aircraft, with 100 images for each of 102 different aircraft model variants, most of which are airplanes. 0) is established from several airports around the world and corresponding classification criteria to provide a reference for classification of aircraft types. , “A dataset for infrared image dim-small aircraft target detection and tracking under ground/air background,” Sci. Jan 20, 2022 · 2. However, current public aircraft datasets are mainly from top-down perspective images, lacking multi 🛰️ List of satellite image training datasets with annotations for computer vision and deep learning - chrieke/awesome-satellite-imagery-datasets Training Data: Dataset of military aircraft images collected from Illia56/Military-Aircraft-Detection. 2 Metadata of the Dataset images/: code to store the open source address of the dataset and divide it into subclasses (for information only) resnet/: network framework, training code, recognition code and CBAM module using ResNet50 as the backbone network vgg/: network framework, training code, recognition code with VGG16 as the backbone network web: store the front-end web pages class_indices. 0 [54] dataset focuses on the identification of aircraft groups in remote sensing images. This dataset contains 165,340 high-resolution aircraft images collected from the internet, along with machine-generated captions. Captured from satellites, planes, and drones, these projects can help you find objects of interest in overhead photos. Sourced from a comprehensive image search, this dataset is ideal for multi-class image classification tasks. Reverie’s novel simulation platform and features 50,000 synthetic satellite images with ~630,000 aircraft annotations. GMS-5 Infrared (IR) imagery (with aircraft track overlaid on plot) collected during the ACE-1 intensive operations in Hobart, Tasmania, from the Australian Bureau of Meteorology. Reverie simulation platform and features 50,000 synthetic satellite images with over ~600,000 aircraft annotations. Hui et al. 7 or higher May 9, 2019 · This work aims to establish a universal framework to estimate the aircraft pose based on generic geometry structure features. 2019. json: stores subclass Datasets for deep learning applied to satellite and aerial imagery. Download the Aircraft labeled image dataset from images. Oct 1, 2022 · Directly augmenting images by rotation, flipping, and random cropping cannot further improve the generalization ability of existing deep models. Apr 19, 2024 · This dataset collects samples of different types of surface defects on aircraft fuselages to facilitate the identification and location of aircraft fuselage defects by computational vision and machine learning algorithms. Created by Aircraft Damage Detection 114 open source aircraft-damage images plus a pre-trained Aircraft Damage Detection model and API. This is a custom dataset created with manually clicked photographs of 3 different types of aircraft. Pre-trained Model: google/vit-base-patch16-224-in21k. Mar 4, 2025 · Key Features of the Dataset The Fighter Aircraft Image Dataset available at GTS AI presents several essential attributes that render it suitable for artificial intelligence and machine learning applications: High-Resolution Imagery: Provides intricate details of aircraft designs, leading to improved training outcomes. Airbus Defense and Space Intelligence operates the largest commercial satellite constellation combining optical imagery Military Aircraft Image Classification Project Using Custom DataSet (With Transfer Learning) This project focuses on classifying military aircraft images using Transfer Learning with the VGG16 model. PlanesNet is a labeled dataset consiting of image chips extracted from Planet satellite imagery. Improve learning efficiency. Whether you want a single datapoint, a report, an excel file, or an ongoing feed, JETNET has your aircraft data needs 2 days ago · In this study, aircraft segmentation and detection were performed using satellite imagery, with the U-Net segmentation model and the YOLO object detection model being utilized. 11. The classes in the dataset include: Airbus, ATR, Boeing, C130, F16, Grob, KAI, and Sukhoi. Crack Dent Scratch Paint-peel-off Missing-head (rivets, fastners, screws etc) The dataset consists of total 372 images with distribution as follows: Hawker Hunter - 276 HT2 - 70 Pushpak - 76 The dataset has 1115 open source different-surface-defects images plus a pre-trained aircraft-skin-defects-new-dataset model and API. Initially, we used 80 percent images for training the deep learning-based object detectors and 20 percent for performance evaluation. net (more info). In our method, line features are extracted to describe the structure of an aircraft in single images and the generic geometry features are exploited to form line groups for aircraft structure recognition. Each image is meticulously annotated with 22,341 instances, including both horizontal and oriented bounding boxes. This comprehensive dataset contains a diverse collection of ship images, ensuring robustness and accuracy in AI model training. This dataset is a demonstration version of larger and more advanced deep learning datasets created from Airbus satellite imagery. Enjoy high-quality, annotated Aircraft images ideal for image classification, object detection, and segmentation. e Dec 17, 2024 · The problem is that existing aircraft detection datasets rarely simultaneously consider the diversity of target features and the complexity of environmental factors, which has become an important factor restricting the effectiveness and reliability of aircraft detection algorithms. Our Airplane Image Dataset consists of 3,371 high-quality images of airplanes, categorized into 10 distinct classes. Deep-learning (DL) methods can achieve promising detection performance with sufficient and labeled samples. Model Architecture: Vision Transformer (ViT) for image classification. txt " format. It also provides ground-truth annotations of flying airplanes in part of those images to support future research involving flying airplane detection. Aug 26, 2024 · Aircraft detection holds significant importance in both civilian and military fields, such as air transportation control and battlefield situational awareness. Data Bank, CSTR 31253. The dataset can be used for a variety of tasks, including: Discover our Flying data collection dataset, meticulously curated for training AI in recognizing various types of flying vehicles such as drones, helicopters, passenger planes, and fighter jets. Created by Dibya Dillip 374 open source crack-porosity-inclusion images plus a pre-trained Turbine Blades Automatic defect model and API. Aircraft models are organized in a four-levels hierarchy. 902, Oct. from publication: Aircraft Type Recognition in Remote Sensing Images: Bilinear Discriminative Extreme Learning Jul 3, 2021 · This dataset contains satellite images of areas of interest surrounding 30 different European airports. Requirements Python 3. The captions were generated using Gemini Flash 1. It is used in the aviation industry. Created by Aircraft Engine Project Dec 17, 2024 · The problem is that existing aircraft detection datasets rarely simultaneously consider the diversity of target features and the complexity of environmental factors, which has become an important 2. Enable discovery of more object classes 2 days ago · In this study, aircraft segmentation and detection were performed using satellite imagery, with the U-Net segmentation model and the YOLO object detection model being utilized. It achieves a test accuracy of 75. Consequently, users can develop Mar 27, 2023 · AFGR-50 dataset is a challenging 50-class geospatial fine-grained aircraft classification dataset. Although a large amount of research has been devoted to breaking through few-sample-driven aircraft detection SynISAR consisting of ISAR images of 7 aircraft models and dataset-2, our dataset, consists of ISAR images of 5 aircraft models. Overall, the dataset is composed of 6,300 images, each being 120 x 120, with each aircraft type containing ~ 610 - 660 images. 5 AI model and are stored in separate text files matching the image filenames. The dataset contains 10,000 images of aircraft, with 100 images for each of 100 different aircraft model variants, most of which are airplanes. Images are from airliners. Download the Aircraft carrier labeled image dataset from images. Mar 24, 2025 · TartanAviation: Image, Speech, and Trajectory Datasets for Terminal Airspace Operations We introduce TartanAviation, an open-source multi-modal dataset focused on terminal-area airspace The Military Aircraft Recognition dataset offers a robust collection of 3,842 remote sensing images featuring 20 different types of military aircraft. Deep learning-based methods for aircraft detection can obtain promising detection performance with sufficient and labeled samples. 7m. The dataset comprised a total of 103 satellite images, with each image containing one or more aircraft. Enjoy high-quality, annotated Airplanes images ideal for image classification, object detection, and segmentation. It contains 10,200 images spanning 102 different aircraft variants, such as Boeing 747-400, Airbus A320, etc. Generate high-quality 2D and 3D aircraft datasets with accurate pose annotations, multiple aircraft types, and flexible export formats. Commercial aircraft jpg images for classification problemsSomething went wrong and this page crashed! If the issue persists, it's likely a problem on our side. aircraft image dataset for pose estimation. Military Aircraft Image Dataset. Download scientific diagram | Samples of 20 aircraft types in the MTARSI dataset. Eglin Air Force Base 96 th Test Wing Eglin Signature Data Center (ESDC) The ESDC is one of the larger U. - soumik-saha/SkyPulse Airbus Aircrafts Detection Sample Dataset is a dataset for an object detection task. 1 Forward Looking Infrared (FLIR) Automated Driver Assistance Systems (ADAS) Dataset The FLIR dataset for ADAS training has over 10,000 annotated thermal images of vehicles and personnel during both day and night conditions. Created by Dibya Dillip Since all images dataset provided have defects, image of a clean metal surface from the internet were used to test the prediction. These classes represent various types of aircraft from various manufacturers, both commercial, military, and training aircraft. This dataset can serve researches on infrared target characteristics, dim-small object detection and precision guidance. We name the SAR aircraft detection dataset SADD and make it public to facilitate the research of other scholars. At the finer level, differences between models are often subtle but always visually measurable, making visual recognition challenging but possible. Data Preprocessing: Random oversampling for class balance, data augmentation (rotation, flip, sharpness adjustment). There are 6 (6% of the total) unlabeled images (i. The dataset utilized is a custom collection derived from the MTARSI dataset, containing five classes of military aircraft. Jan 3, 2025 · Motivated by the inherent challenges of manual dataset annotation, such as errors, limited variability, and geographical biases, this study employs synthetic data generation techniques to create a diverse dataset by overlaying 3D models of 31 different aircraft types onto satellite imagery, creating a dataset of 5000 images containing 27,375 Sen2Fire -> A Challenging Benchmark Dataset for Wildfire Detection using Sentinel Data L1BSR -> 3740 pairs of overlapping image crops extracted from two L1B products GloSoFarID -> Global multispectral dataset for Solar Farm IDentification SICKLE -> A Multi-Sensor Satellite Imagery Dataset Annotated with Multiple Key Cropping Parameters. The HRPlanesv2 dataset contains 2120 very high-resolution Google Earth images, with a total of 14335 aircraft labeled. A benchmark is obtained by defining corresponding classification tasks and evaluation Dataset includes 22 image sequences, 30 trajectories, 16177 frames and 16944 targets. Contribute to tlkh/milair-dataset development by creating an account on GitHub. pth file is a PyTorch model trained on a dataset of aircraft images. The Ships Image Dataset is meticulously curated to aid in the development and testing of AI models for ship detection and classification. sciencedb. Apr 20, 2025 · xView Dataset The xView dataset is one of the largest publicly available datasets of overhead imagery, containing images from complex scenes around the world annotated using bounding boxes. DoD repositories of electro-optical/infrared (EO/IR) and radio frequency (RF) signature data for domestic and foreign tactical and strategic vehicles. The (main) aircraft in each image is annotated with a tight bounding box and a hierarchical airplane model label. Dataset Description We developed a dataset composed of 9 different military aircraft, as well as a dataset for various backgrounds, such as the concrete tarmac of air bases or sandy grounds for certain boneyards and air bases throughout the world. The images are of various military aircraft, including fighter jets, bombers, transport aircraft, and helicopters. This dataset has, Varied backgrounds Different resolutions Distinct poses of aircrafts Dec 17, 2023 · End of preview. S. Perfect for computer vision research, pose estimation models, and aircraft recognition systems. The dataset is split into training, validation, and test sets. 0 [41] dataset focuses on the identification of aircraft groups in remote sensing images. Enjoy high-quality, annotated Aircraft carrier images ideal for image classification, object detection, and segmentation. The main aircraft in each image is annotated with a tight bounding box and a hierarchical airplane model label. These images JETNET monitors, collects, consolidates, transforms, and analyzes aviation data on more than 170,000 airframes. The proposed model does not require a significant amount of labeled data and alleviates the need for manual aircraft feature extraction. The purpose of PlanesNet is to serve as labeled training data to train machine learning algorithms to detect the locations of airplanes in Planet's medium resolution remote sensing imagery. Dec 17, 2024 · The OPT-Aircraft V1. Apr 1, 2020 · The data set contains 10’200 images of aircraft, with 100 images for each of 102 different aircraft model variants, most of which are airplanes [10]. It contains over 17K synthetic images of various runways, enriched with more than 1800 annotated pictures from real landing footages for comparison. Jun 21, 2013 · This paper introduces FGVC-Aircraft, a new dataset containing 10,000 images of aircraft spanning 100 aircraft models, organised in a three-level hierarchy. cv — perfect for computer vision, machine learning, and AI projects. Each target correspond a label location in the image, and each image sequence correspond a label file. Mar 21, 2024 · In this paper, we propose a binary image segmentation model to recognize aircraft by exploiting and adopting the U-Net architecture for remote sensing satellite images. jpg " file with dimensions of 4800 x 2703 pixels, and each label is saved in YOLO ". The model is designed to be lightweight and efficient for real-time applications. Benchmark dataset for the fine grained visual categorization of aircraft. Roboflow hosts the world's biggest set of open source aerial imagery datasets and pre-trained computer vision models. 26% on the FGVC Aircraft test dataset, making it a reliable choice for identifying aircraft types. A benchmark is obtained by defining corresponding classification tasks and Mar 15, 2025 · aircraft image dataset for pose estimation. However, current aircraft datasets are mainly from a single data source and lack diverse scenes and targets, making it Mar 23, 2023 · Explore the RarePlanes Dataset for aircraft detection models. Apr 3, 2024 · The OPT-Aircraft V1. Jun 9, 2020 · The accompanying synthetic dataset is generated via the novel AI. Oct 1, 2022 · The dataset contains 26 satellite images with resolution varying from 565 × 369 pixels to 1484 × 865 pixels with a total of 453 aircraft in all images. Multi-type Aircraft Remote Sensing Images (MTARSI) dataset contains 9385 images of 20 aircraft types. The dataset, comprising 12,008 images in total, was sourced from Wikimedia Commons and Google Image Search, making it a valuable resource for training and evaluating object detection models for military aircraft recognition task. Aircrafts-dataset Dataset contain more 37k images 84 models aircrafts Data Card Code (0) Discussion (1) Suggestions (0) The dataset contains 10,200 images of aircraft, with 100 images for each of 102 different aircraft model variants, most of which are airplanes. Images in the Airbus Aircraft Detection dataset have bounding box annotations. Aircraft models are organized in a three-levels hierarchy. We propose an interactive augmentation method for airplane engine damage images using a prior-guided GAN to augment training images. Each image is stored as a ". Each class represents a specific airplane model, making this dataset an excellent resource for machine learning applications such as image classification, object detection, and image recognition. This dataset is an extensive collection of high-quality images featuring various fighter aircraft, curated specifically for machine learning tasks such as classification, image recognition, and object detection. from publication: Aircraft Type Recognition in Remote Sensing Images: Bilinear Discriminative Extreme Learning . The selection of this class aims to reflect the diversity of shapes and sizes The real portion of the dataset consists of 253 Maxar WorldView-3 satellite scenes spanning 112 locations and 2,142 km^2 with 14,700 hand-annotated aircraft. Dec 17, 2024 · The problem is that existing aircraft detection datasets rarely simultaneously consider the diversity of target features and the complexity of environmental factors, which has become an important 2. 114 open source aircraft-damage images plus a pre-trained Aircraft Damage Detection model and API. B. Aircraft detection in remote-sensing images is significant in both military and civilian fields, such as air traffic control and battlefield dynamic monitoring. Background Airbus Defense and Space Intelligence operates the largest commercial satellite constellation combining optical imagery from Pléiades, SPOT, Vision-1 and DMC as well Landing Approach Runway Detection (LARD) is a dataset of aerial front view images of runways designed for aircraft landing phase. SAR Aircraft Detection Dataset Data Description Since there is no publicly available aircraft detection dataset in SAR images, we collect and construct an aircraft slice dataset to investigate the detection performance of our method. The real portion of the dataset consists of 253 Maxar WorldView-3 satellite scenes spanning 112 locations and 2,142 km^2 with 14,700 hand-annotated aircraft. The goal of the xView dataset is to accelerate progress in four computer vision frontiers: Reduce minimum resolution for detection. The images are labelled for 5 different classes of surface defects on aircraft skin viz. The dataset consists of 109 images with 3425 labeled objects belonging to 2 different classes including airplane and truncated_airplane. This dataset is part of the work entitled "Measuring economic activity from space: a case study using flying airplanes and COVID-19" published The aircraft_classifier. This is due to some of the images of aircraft parts seem to be of metal or steel surfaces. Aircraft Damage Detection (v8, dataset-v2-aug-800-pad), created by Aircraft Damage Detection Download the Airplanes labeled image dataset from images. Most of the Jan 25, 2024 · TartanAviation is an open-source multi-modal dataset focused on terminal-area airspace operations and provides a holistic view of the airport environment by concurrently collecting image, speech, and ADS-B trajectory data. The dataset includes 32000 20x20 RGB images labeled with either a "plane" or "no-plane" classification. Created by Aircraft Damage Detection A comprehensive toolkit for generating synthetic aircraft datasets for machine learning applications. Jul 9, 2025 · The aircraft image dataset used in this study consists of 8 classes with a total of 4,520 images. The aviation engine failure dataset is crucial for ML and AI research, containing high-resolution images of turbine blades with various defect conditions. Contribute to yglee-afa/3D-Aircraft-Pose-Estimation development by creating an account on GitHub. - nhangen/aircraft-dataset-generator Mar 20, 2025 · The datasets were collected at both towered and non-towered airfields across multiple months to capture diversity in aircraft operations, seasons, aircraft types, and weather conditions. Sep 18, 2021 · Airbus Aircrafts Detection Sample Dataset This dataset is a demonstration version of larger and more advanced deep learning datasets created from Airbus satellite imagery. 0 Government Databases and Datasets 2. We also provide a synthetic image generator based on Google Earth Studio if you want to enrich your dataset, or Feb 21, 2024 · This dataset is for fine-grained image classification of aircraft types for classification or detection tasks. This level of detail supports precise training and evaluation of aircraft recognition algorithms. This repository also includes some aircraft, watercraft, and personnel imagery. The dataset contains 10,200 images of aircraft, with 100 images for each of 102 different aircraft model variants, most of which are airplanes. Learn about synthetic data's importance and analyze the dataset using Encord. Dec 1, 2024 · Finally, the used dataset consists of 1614 aircraft samples across 60 images, containing four different aircraft classes and the previously described set of semi-automated negative samples at five different airports. Jun 19, 2023 · 114 open source aircraft-damage images and annotations in multiple formats for training computer vision models. The images are systematically organized into folders, each labeled with the corresponding aircraft model name, offering a valuable resource for researchers and developers working on AI military aircraft images with aircraft type and bounding box annotations The classification dataset of aircraft types based on remote sensing images (OPT-Aircraft _v1. 1. The dataset consists of 5,601 images of four types of aircraft fuselage defects. An automated system using image recognition and machine learning to detect and classify aircraft damage, predict repair methods, and improve maintenance efficiency. Every aircraft has over 150 distinct data types, neatly organized and searchable by tail (registration) and serial number so you can find exactly what you need fast. The accompanying synthetic dataset is generated via AI. n6ld czns j6 u1d6w bjmgvbtv k4h ppjtr qeoypw tlm qh86d16