Scene Classification

RESISC45 dataset is a dataset for Remote Sensing Image Scene Classification (RESISC). It contains 31,500 RGB images of size 256×256 divided into 45 scene classes, each class containing 700 images. Among its notable features, RESISC45 contains varying spatial resolution ranging from 20cm to more than 30m/px.

BigEarthNet consists of 590,326 Sentinel-2 image patches, each of which is a section of i) 120x120 pixels for 10m bands; ii) 60x60 pixels for 20m bands; and iii) 20x20 pixels for 60m bands. Source: BigEarthNet: A Large-Scale Benchmark Archive For Remote Sensing Image Understanding

The Remote Sensing Image Captioning Dataset (RSICD) is a dataset for remote sensing image captioning task. It contains more than ten thousands remote sensing images which are collected from Google Earth, Baidu Map, MapABC and Tianditu. The images are fixed to 224X224 pixels with various resolutions. The total number of remote sensing images is 10921, with five sentences descriptions per image. Source: https://github.com/201528014227051/RSICD_optimal Image Source: https://github.com/201528014227051/RSICD_optimal

The Places365 dataset is a scene recognition dataset. It is composed of 10 million images comprising 434 scene classes. There are two versions of the dataset: Places365-Standard with 1.8 million train and 36000 validation images from K=365 scene classes, and Places365-Challenge-2016, in which the size of the training set is increased up to 6.2 million extra images, including 69 new scene classes (leading to a total of 8 million train images from 434 scene classes). Source: Semantic-Aware Scene Recognition Image Source: Places

Million-AID is a large-scale benchmark dataset containing a million instances for RS scene classification. There are 51 semantic scene categories in Million-AID. And the scene categories are customized to match the land-use classification standards, which greatly enhance the practicability of the constructed Million-AID. Different form the existing scene classification datasets of which categories are organized with parallel or uncertain relationships, scene categories in Million-AID are organized with systematic relationship architecture, giving it superiority in management and scalability. Specifically, the scene categories in Million-AID are organized by the hierarchical category network of a three-level tree: 51 leaf nodes fall into 28 parent nodes at the second level which are grouped into 8 nodes at the first level, representing the 8 underlying scene categories of agriculture land, commercial land, industrial land, public service land, residential land, transportation land, unutilized land, and water area. The scene category network provides the dataset with excellent organization of relationship among different scene categories and also the property of scalability. The number of images in each scene category ranges from 2,000 to 45,000, endowing the dataset with the property of long tail distribution. Besides, Million-AID has superiorities over the existing scene classification datasets owing to its high spatial resolution, large scale, and global distribution. Source: DiRS: On Creating Benchmark Datasets for Remote Sensing Image Interpretation Image Source: https://captain-whu.github.io/DiRS/

AID is a new large-scale aerial image dataset, by collecting sample images from Google Earth imagery. Note that although the Google Earth images are post-processed using RGB renderings from the original optical aerial images, it has proven that there is no significant difference between the Google Earth images with the real optical aerial images even in the pixel-level land use/cover mapping. Thus, the Google Earth images can also be used as aerial images for evaluating scene classification algorithms. The new dataset is made up of the following 30 aerial scene types: airport, bare land, baseball field, beach, bridge, center, church, commercial, dense residential, desert, farmland, forest, industrial, meadow, medium residential, mountain, park, parking, playground, pond, port, railway station, resort, river, school, sparse residential, square, stadium, storage tanks and viaduct. All the images are labelled by the specialists in the field of remote sensing image interpretation, and some samples of each class are shown in Fig.1. In all, the AID dataset has a number of 10000 images within 30 classes. The images in AID are actually multi-source, as Google Earth images are from different remote imaging sensors. This brings more challenges for scene classification than the single source images like UC-Merced dataset. Moreover, all the sample images per each class in AID are carefully chosen from different countries and regions around the world, mainly in China, the United States, England, France, Italy, Japan, Germany, etc., and they are extracted at different time and seasons under different imaging conditions, which increases the intra-class diversities of the data.

The MTG-Jamendo dataset is an open dataset for music auto-tagging. The dataset contains over 55,000 full audio tracks with 195 tags categories (87 genre tags, 40 instrument tags, and 56 mood/theme tags). It is built using music available at Jamendo under Creative Commons licenses and tags provided by content uploaders. All audio is distributed in 320kbps MP3 format. A subset of the dataset is used in the Emotion and Theme Recognition in Music Task within MediaEval 2019. Source: https://mtg.github.io/mtg-jamendo-dataset/ Audio Source: https://essentia.upf.edu/datasets/mtg-jamendo/raw_30s/audio/

A dataset consisting of 180,662 triplets of dual-pol synthetic aperture radar (SAR) image patches, multi-spectral Sentinel-2 image patches, and MODIS land cover maps. Source: SEN12MS -- A Curated Dataset of Georeferenced Multi-Spectral Sentinel-1/2 Imagery for Deep Learning and Data Fusion

DCASE 2016 is a dataset for sound event detection. It consists of 20 short mono sound files for each of 11 sound classes (from office environments, like clearthroat, drawer, or keyboard), each file containing one sound event instance. Sound files are annotated with event on- and offset times, however silences between actual physical sounds (like with a phone ringing) are not marked and hence “included” in the event. Source: The NIGENS General Sound Events Database Image Source: https://arxiv.org/pdf/1911.06878.pdf

This is a 21 class land use image dataset meant for research purposes. There are 100 images for each of the following classes: - agricultural - airplane - baseballdiamond - beach - buildings - chaparral - denseresidential - forest - freeway - golfcourse - harbor - intersection - mediumresidential - mobilehomepark - overpass - parkinglot - river - runway - sparseresidential - storagetanks - tenniscourt - Each image measures 256x256 pixels. The images were manually extracted from large images from the USGS National Map Urban Area Imagery collection for various urban areas around the country. The pixel resolution of this public domain imagery is 1 foot. Source: UC Merced Land Use Dataset

MLRSNet is a a multi-label high spatial resolution remote sensing dataset for semantic scene understanding. It provides different perspectives of the world captured from satellites. That is, it is composed of high spatial resolution optical satellite images. MLRSNet contains 109,161 remote sensing images that are annotated into 46 categories, and the number of sample images in a category varies from 1,500 to 3,000. The images have a fixed size of 256×256 pixels with various pixel resolutions (~10m to 0.1m). Moreover, each image in the dataset is tagged with several of 60 predefined class labels, and the number of labels associated with each image varies from 1 to 13. The dataset can be used for multi-label based image classification, multi-label based image retrieval, and image segmentation. Source: https://github.com/cugbrs/MLRSNet Image Source: Qi et al

TAU Urban Acoustic Scenes 2019 development dataset consists of 10-seconds audio segments from 10 acoustic scenes: airport, indoor shopping mall, metro station, pedestrian street, public square, street with medium level of traffic, travelling by a tram, travelling by a bus, travelling by an underground metro and urban park. Each acoustic scene has 1440 segments (240 minutes of audio). The dataset contains in total 40 hours of audio. Source: https://zenodo.org/record/2589280 Image Source: http://dcase.community/challenge2019/task-acoustic-scene-classification#citation

The TUT Acoustic Scenes 2017 dataset is a collection of recordings from various acoustic scenes all from distinct locations. For each recording location 3-5 minute long audio recordings are captured and are split into 10 seconds which act as unit of sample for this task. All the audio clips are recorded with 44.1 kHz sampling rate and 24 bit resolution. Source: Ensemble of deep neural networks for acoustic scene classification Image Source: https://www.mathworks.com/help/audio/ug/acoustic-scene-recognition-using-late-fusion.html;jsessionid=95c969bc690c06fe42a7ed17f57e

RICE is a remote sensing image dataset for cloud removal. The proposed dataset consists of two parts: RICE1 contains 500 pairs of images, each pair has images with cloud and cloudless size of 512512; RICE2 contains 450 sets of images, each set contains three 512512 size images, respectively, the reference picture without clouds, the picture of the cloud and the mask of its cloud. Source: https://github.com/BUPTLdy/RICE_DATASET

DCASE 2013 is a dataset for sound event detection. It consists of audio-only recordings where individual sound events are prominent in an acoustic scene. Source: http://dcase.community/challenge2013/index Image Source: https://link.springer.com/article/10.1186/s13636-018-0138-4

Dataset aimed to do automated aerial scene classification of disaster events from on-board a UAV. Source: Deep-Learning-Based Aerial Image Classification for Emergency Response Applications Using Unmanned Aerial Vehicles

CochlScene is a dataset for acoustic scene classification. The dataset consists of 76k samples collected from 831 participants in 13 acoustic scenes. Source: CochlScene: Acquisition of acoustic scene data using crowdsourcing Image Source: https://arxiv.org/pdf/2211.02289v1.pdf

TAU Urban Acoustic Scenes 2019 Mobile development dataset consists of 10-seconds audio segments from 10 acoustic scenes: Airport Indoor shopping mall Metro station Pedestrian street Public square Street with medium level of traffic Travelling by a tram Travelling by a bus Travelling by an underground metro Urban park Recordings were made with three devices that captured audio simultaneously. Each acoustic scene has 1440 segments (240 minutes of audio) recorded with device A (main device) and 108 segments of parallel audio (18 minutes) each recorded with devices B and C. The dataset contains in total 46 hours of audio. DCASE website Source: Zenodo Image Source: Acoustic Scene Classification

SkyEyeGPT: Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language Model

The LITIS-Rouen dataset is a dataset for audio scenes. It consists of 3026 examples of 19 scene categories. Each class is specific to a location such as a train station or an open market. The audio recordings have a duration of 30 seconds and a sampling rate of 22050 Hz. The dataset has a total duration of 1500 minutes. Source: Spatio-Temporal Attention Pooling for Audio Scene Classification Image Source: https://www.researchgate.net/figure/Summary-of-Litis-Rouen-audio-scene-dataset_tbl1_329608235

A high-resolution multi-sensor remote sensing scene classification dataset, appropriate for training and evaluating image classification models in the remote sensing domain. The dataset consists of 8400 overhead scenes, each covered by Airbus Pléiades, Airbus SPOT, and USDA NAIP imagery. The scenes are classified into 12 OpenStreetMap categories: * man_made=bridge * man_made=breakwater * building=farm * power=substation * leisure=stadium * leisure=golf_course * waterway=dam * landuse=quarry * landuse=farmland * landuse=forest * natural=water * natural=bare_rock

The dataset is collected from the Youtube videos that contains fight instances in it. Also, some non-fight sequences from regular surveillance camera videos are included. * There are 300 videos in total as 150 fight + 150 non-fight * Videos are 2-second long * Only the fight related parts are included in the samples Source: https://github.com/sayibet/fight-detection-surv-dataset Image Source: https://github.com/sayibet/fight-detection-surv-dataset

Consists of 36,785 images belonging to a diverse 92 classes. This class count is significantly higher than publicly available datasets. Maintains a low-class imbalance and a highly comprehensive data distribution for robust model training. It also provides the remote sensing community with an extra platform to validate the performance on multiple benchmarks.