Object Detection
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 39
- 평가표
- 124
- 보존된 평가 기록
- 977
데이터셋
출처에 같은 태스크 이름으로 연결된 데이터셋입니다. 동명 태스크가 포함될 수 있으므로, 비교할 때는 평가 결과의 조건도 확인하세요.
Moroccan Monay dataset
A dataset of all Moroccan money
MS-EVS Dataset
The MS-EVS Dataset is the first large-scale event-based dataset for face detection. - Regular images (APS) and simulated events (EVS) - Multispectral data (RGB and/or near IR) - Very diverse faces and data quality (for robust face detection) It is divided in four subsets: - N-YoutubeFaces, 3k+ celebrity faces from Youtube videos, in color (simulated events). - N-MobiFace, 80 unedited mobile live color videos (simulated events). - N-SpectralFace, 69 multispectral videos captured in-house (simulated events). - Real-SpectralFace, a few sequences with real multispectral events (Grayscale and Infrared). | Dataset | APS | Simulated EVS | Real EVS | Data | |:---------------------:|:-------:|:-----------------:|:------------:|:--------------------------------------:| | N-YoutubeFaces | x | x | | Color (RGB) | | N-MobiFace | x | x | | Color (RGB) | | N-SpectralFace | x | x | | Multispectral (9 visible + 1 infrared) | | Real-SpectralFace | x | | x | Multispectral (1 visible + 1 infrared) |
Nomeroff Russian License Plates
Description: <a href="https://gts.ai/dataset-download/nomeroff-russian-license-plates/" target="_blank">👉 Download the dataset here</a> This dataset consists of high-resolution photographs of Russian vehicle license plates captured in diverse environments and lighting conditions. It is designed for image classification and object detection tasks, particularly aimed at automatic license plate recognition (ALPR) systems. The dataset features vehicles in urban, rural, and highway settings, with a wide range of vehicle models and plate formats that adhere to Russian vehicle registration standards. Download Dataset Dataset Overview: A collection of JPG images with varying resolutions, capturing license plates from multiple angles (frontal, side, rear) and distances. Environments include daytime and nighttime scenes, varying weather conditions (sunny, rainy, snowy), and different lighting (natural and artificial). CSV Columns: file_name: The name of the image file (str, unique values). plate_number: The alphanumeric license plate number present in the image (str). vehicle_type: The type of vehicle (e.g., sedan, SUV, truck, etc.) – this allows for classification beyond just license plate recognition (str). angle_of_view: The angle at which the image was captured (e.g., frontal, side, rear) – this provides additional context for training models to handle various perspectives (str). weather_condition: The weather conditions during image capture (e.g., sunny, rainy, snowy, etc.), offering insights into how weather impacts recognition performance (str). time_of_day: Whether the image was captured during the day, evening, or night, useful for models dealing with varying lighting conditions (str). occlusion_level: A numeric rating (0-3) representing the level of obstruction on the license plate (e.g., due to dirt, damage, or angle), helping models adapt to real-world imperfections (int). Applications: License Plate Recognition (LPR) Systems. Vehicle Tracking and Identification. Traffic Monitoring and Enforcement. Smart City Solutions and Automated Toll Systems. This dataset is sourced from Kaggle.
OCT5k
The thickness and appearance of retinal layers are essential markers for diagnosing and studying eye diseases. Despite the increasing availability of imaging devices to scan and store large amounts of data, analyzing retinal images and generating trial endpoints has remained a manual, error-prone, and time-consuming task. In particular, the lack of large amounts of high-quality labels for different diseases hinders the development of automated algorithms. Therefore, we have compiled 5016 pixel-wise manual labels for 1672 optical coherence tomography (OCT) scans featuring two different diseases as well as healthy subjects to help democratize the process of developing novel automatic techniques. We also collected 4698 bounding box annotations for a subset of 566 scans across 9 classes of disease biomarker. Due to variations in retinal morphology, intensity range, and changes in contrast and brightness, designing segmentation and detection methods that can generalize to different disease types is challenging. While machine learning-based methods can overcome these challenges, high-quality expert annotations are necessary for training. Publicly available annotated image datasets typically contain few images and/or only cover a single type of disease, and most are only annotated by a single grader. To address this gap, we present a comprehensive multi-grader and multi-disease dataset fortraining machine learning-based algorithms. The proposed dataset covers three subsets of scans (Age-related Macular Degeneration, Diabetic Macular Edema, and healthy) and annotations for two types of tasks (semantic segmentation and object detection).
Oximeter Image Dataset | Medical Device Reading
This dataset is an extremely challenging set of over 2000+ original Oximeter images captured and crowdsourced from over 300+ urban and rural areas, where each image is manually reviewed and verified by computer vision professionals at Datacluster Labs. ### Dataset Features - Dataset size : 2000+ - Captured by : Over 300+ crowdsource contributors - Resolution : 100% images HD and above (1920x1080 and above) - Location : Captured with 50+ cities accross India - Diversity : Various lighting conditions like day, night, varied distances, view points etc. - Device used : Captured using mobile phones in 2020-2021 - Usage : Oximeter Reading detection, Medical Device, Healthcare system detection, etc. ### Available Annotation formats COCO, YOLO, PASCAL-VOC, Tf-Record To download full datasets or to submit a request for your dataset needs, please ping us at sales@datacluster.ai Visit www.datacluster.ai to know more. Note: All the images are manually captured and verified by a large contributor base on DataCluster platform
PALMS
Data in this study come from western Ecuador's Choco tropical forest, including \textit{Fundación para la Conservación de los Andes Tropicales Reserve and adjacent Reserva Ecológica Mache-Chindul park} (FCAT; 00$^\circ$23'28'' N, 79$^\circ$41'05'' W), \textit{Jama-Coaque Ecological Reserve} (00$^\circ$06'57'' S, 80$^\circ$07'29'' W), \textit{Canande Reserve} (0$^\circ$31'34'' N 79$^\circ$12'47'' W), and \textit{Tesoro Escondido Reserve} (0$^\circ$33'16'' N 79$^\circ$10'31'' W). FCAT is a high diversity humid tropical forest at elevation $\sim$500m, receiving $\sim$3000 mm yr$^{-1}$ precipitation with persistent fog during drier period. Jama-Coaque ranges from the boundary of the tropical moist deciduous/tropical moist evergreen forest at the lower elevations ($\sim$1000 mm precipitation yr$^{-1}$, $\sim$250 m asl) to fog-inundated wet evergreen forests above 580m to 800m. Canande (350–500 m elevation) and Tesoro Escondido ($\sim$200 m elevation) are lowland everwet Choco forests, both receiving 4000–5000 mm yr$^{-1}$ precipitation with no month experiencing drought stress or precipitation below 100 mm. These forests host several palm species with exposed canopy crowns, including the economically important \textit{Iriartea deltoidea}, \textit{Socratea exorrhiza}, and \textit{Oenocarpus bataua}, with lesser amounts of \textit{Attalea colenda} and \textit{Astrocaryum standleyanum}, and species composition varying across study sites
Pear640
Dataset contains annotated photographs of pear orchard for object detection tasks using YOLO architecture. It contains only one class "Pear fruits". This dataset is distributed under license (CC BY 4.0). Source: <a href="https://www.kaggle.com/datasets/projectlzp201910094/pear640">https://www.kaggle.com/datasets/projectlzp201910094/pear640</a> Presented in paper: Sergejs Kodors, Marks Sondors, Gunārs Lācis, Edgars Rubauskis, Ilmārs Apeināns, Imants Zarembo. "RAPID PROTOTYPING OF PEAR DETECTION NEURAL NETWORK WITH YOLO ARCHITECTURE IN PHOTOGRAPHS," In Proceedings of the International Scientific and Practical Conference "Environment. Technology. Resources.", Rezekne, Latvia, June 15-16, 2023, vol. 1, pp. 81-85, doi: <a href="https://doi.org/10.17770/etr2023vol1.7293">10.17770/etr2023vol1.7293</a>
PFruitlet640
Dataset contains annotated photographs of pear fruitlets for object detection tasks using YOLO architecture. It has only one class "Pear fruitlet". The digital images of pear fruitlets were collected in the experimental site of the Institute of Horticulture (LatHort) with cultivars ‘Suvenirs’, ‘Vasarine Sviestine’ and ‘Mramornaya’ on seedling rootstocks ‘Kazraushu’ with planting distances 4×5 m (500 trees per 1 ha). (Krimūnu parish, Dobeles district, Latvia: 56.610169, 23.305956). The collection of fruitlet images of ‘Suvenirs’, ‘Vasarine Sviestine’ and ‘Mramornaya’ was done at the beginning of August (79 days after full bloom). The collection of digital images was carried out using a photo camera of mobile device Huawei P 40: 50 MP Ultra Vision Camera (Wide Angle, f/1.9 aperture) + 16 MP Ultra-Wide Angle Camera (f/2.2 aperture) + 8 MP Telephoto Camera (f/2.4 aperture, OIS), the image size: 3000×4000 px; 5.0 MP. The collection of images was carried out in field conditions in 2022, in the orchard at the distance from the tree planting point 2.5 m (middle of alleyway). The whole canopy of trees was photographed as separate objects. The images were taken in the front of a tree (a tree trunk, a planting point), perpendicularly the tree row from the west side of rows (the rows of pear trees oriented from north to south) before noon (10:00–12:00) at natural light conditions. The dataset was annotated for YOLO architecture by team of Rezekne Academy of Technologies. Source: <a href="https://www.kaggle.com/datasets/projectlzp201910094/pfruitlet640">https://www.kaggle.com/datasets/projectlzp201910094/pfruitlet640</a> Presented in <a href="https://doi.org/10.15159/ar.24.012">S. Kodors, M. Sondors, I. Apeinans, I. Zarembo, G. Lacis, E. Rubauskis and K. Karklina. "Importance of mosaic augmentation for agricultural image dataset", Agronomy Research, 2024.</a> License CC BY 4.0
RF100-VL
RF100-VL is a multi-domain benchmark for object detection. The benchmark is designed to measure the extent to which model architectures can generalise to different domains, from medical imagery to defect detection to document feature identification. RF100-VL was introduced by researchers from Roboflow and Carnegie Mellon University in the paper "Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models". Roboflow 100 Vision Language (RF100-VL) is the first benchmark to ask, “How well does your VLM understand the real world?” In pursuit of this question, RF100-VL introduces 100 open source datasets containing object detection bounding boxes and multimodal few shot instruction with visual examples and rich textual descriptions across novel image domains. The dataset is comprised of 164,149 images and 1,355,491, annotations across seven domains, including aerial, biological, and industrial imagery. 1693 labeling hours were spent labeling, reviewing, and preparing the dataset. RF100-VL is a curated sample from Roboflow Universe, a repository of over 500,000+ datasets that collectively demonstrate how computer vision is being leveraged in production problems today. Current state-of-the-art models trained on web-scale data like QwenVL2.5 and GroundingDINO achieve as low as 2% AP in some categories represented in RF100-VL.
SESYD Dataset
SESYD "Systems Evaluation SYnthetic Documents" is a database of synthetical documents with groundtruth. This database targets two main research problems in the document image analysis field (i) symbol recognition and spotting in line drawing images (floorplans and electrical diagrams) (ii) character segmentation and recognition in geographical maps. The database is composed of eleven collections for performance evaluation containing 284k images, 190k symbols and 284k characters (k for thousand). SESYD is today a key database in the document image analysis field published in 2010 and referred by one hundred of citations into research papers. Please, cite the following paper [1] if you are using this database. [1] M. Delalandre, E. Valveny, T. Pridmore and D. Karatzas. Generation of Synthetic Documents for Performance Evaluation of Symbol Recognition & Spotting Systems. International Journal on Document Analysis and Recognition (IJDAR), 13(3):187-207, 2010. http://mathieu.delalandre.free.fr/publications/IJDAR2010.pdf
ShipRSImageNet
ShipRSImageNet is a large-scale fine-grainted dataset for ship detection in high-resolution optical remote sensing images. The dataset contains 3,435 images from various sensors, satellite platforms, locations, and seasons. Each image is around 930×930 pixels and contains ships with different scales, orientations, and aspect ratios. The images are annotated by experts in satellite image interpretation, categorized into 50 object categories images. The fully annotated ShipRSImageNet contains 17,573 ship instances. There are five critical contributions of the proposed ShipRSImageNet dataset compared with other existing remote sensing image datasets. Images are collected from various remote sensors cover- ing multiple ports worldwide and have large variations in size, spatial resolution, image quality, orientation, and environment. Ships are hierarchically classified into four levels and 50 ship categories. The number of images, ship instances, and ship cate- gories is larger than that in other publicly available ship datasets. Besides, the number is still increasing. We simultaneously use both horizontal and oriented bounding boxes, and polygons to annotate images, providing detailed information about direction, background, sea environment, and location of targets. We have benchmarked several state-of-the-art object detection algorithms on ShipRSImageNet, which can be used as a baseline for future ship detection methods.
Stairs Image Dataset | Parts of House | Indoor
This dataset is an extremely challenging set of over 3000+ originally Stair images captured and crowdsourced from over 500+ urban and rural areas, where each image is manually reviewed and verified by computer vision professionals at Datacluster Labs. ### Dataset Features - Dataset size : 3000+ - Captured by : Over 500+ crowdsource contributors - Resolution : 100% images HD and above (1920x1080 and above) - Location : Captured with 500+ cities accross India - Diversity : Various lighting conditions like day, night, varied distances, view points etc. - Device used : Captured using mobile phones in 2020-2022 - Usage : Stair detection , Stair Edge detection , Computer Vision , etc. ### Available Annotation formats COCO, YOLO, PASCAL-VOC, Tf-Record To download full datasets or to submit a request for your dataset needs, please ping us at sales@datacluster.ai Visit www.datacluster.ai to know more. Note: All the images are manually captured and verified by a large contributor base on DataCluster platform
Suitcase/Luggage Dataset Indoor Object Image
This dataset is an extremely challenging set of over 7000+ original Suitcase/Luggage images captured and crowdsourced from over 800+ urban and rural areas, where each image is manually reviewed and verified by computer vision professionals at ****DC Labs. ### Dataset Features - Dataset size : 6000+ - Captured by : Over 1000+ crowdsource contributors - Resolution : 99% images HD and above (1920x1080 and above) - Location : Captured with 800+ cities accross India - Diversity : Various lighting conditions like day, night, varied distances, view points etc. - Device used : Captured using mobile phones in 2021-2022 - Usage : Luggage detection, suitcase detection, etc. ### Available Annotation formats COCO, YOLO, PASCAL-VOC, Tf-Record To download full datasets or to submit a request for your dataset needs, please ping us at sales@datacluster.ai Visit www.datacluster.ai to know more. Note: All the images are manually captured and verified by a large contributor base on DataCluster platform
Toloka Business ID Recognition
This dataset, commissioned by the Yandex Business Directory, contains 10,000 photos of organization information signs shot in the Russian Federation along with the INN (taxpayer ID) and OGRN (Primary State Registration Number) codes shown on these signs. Toloka was used for both capturing photos and recognizing INN and OGRN codes.
Toloka WaterMeters
This datase, contains 1244 images of hot and cold water meters as well as their readings and coordinates of the displays showing those readings. Each image contains exactly one water meter. The archive also includes the pictures of the results of segmentation with the masks and collages. Toloka was used for photo capturing, segmentation, and recognizing the readings.
tomato detection
Plant factories are an advanced form of facility agriculture that enable efficient plant cultivation through controllable environmental conditions, making them highly suitable for the automation and intelligent application of machinery. Tomato cultivation in plant factories has significant economic and agricultural value and can be utilized for various applications such as seedling cultivation, breeding, and genetic engineering. However, manual completion is still required for operations such as detection, counting, and classification of tomato fruits, and the application of machine detection is currently inefficient. Furthermore, research on the automation of tomato harvesting in plant factory environments is limited due to the lack of a suitable dataset. To address this issue, a tomato fruit dataset was constructed for plant factory environments, named as TomatoPlantfactoryDataset, which can be quickly applied to multiple tasks, including the detection of control systems, harvesting robots, yield estimation, and rapid classification and statistics. This dataset features a micro tomato variety and was captured under different artificial lighting conditions, including changes in tomato fruit, complex lighting environment changes, distance changes, occlusion, and blurring. By facilitating the intelligent application of plant factories and the widespread adoption of tomato planting machinery, this dataset can contribute to the detection of intelligent control systems, operation robots, and fruit maturity and yield estimation. The dataset is publicly available for free and can be utilized for research and communication purposes.
tomato fruits detection
Plant factories are an advanced form of facility agriculture that enable efficient plant cultivation through controllable environmental conditions, making them highly suitable for the automation and intelligent application of machinery. Tomato cultivation in plant factories has significant economic and agricultural value and can be utilized for various applications such as seedling cultivation, breeding, and genetic engineering. However, manual completion is still required for operations such as detection, counting, and classification of tomato fruits, and the application of machine detection is currently inefficient. Furthermore, research on the automation of tomato harvesting in plant factory environments is limited due to the lack of a suitable dataset. To address this issue, a tomato fruit dataset was constructed for plant factory environments, named as TomatoPlantfactoryDataset, which can be quickly applied to multiple tasks, including the detection of control systems, harvesting robots, yield estimation, and rapid classification and statistics. This dataset features a micro tomato variety and was captured under different artificial lighting conditions, including changes in tomato fruit, complex lighting environment changes, distance changes, occlusion, and blurring. By facilitating the intelligent application of plant factories and the widespread adoption of tomato planting machinery, this dataset can contribute to the detection of intelligent control systems, operation robots, and fruit maturity and yield estimation. The dataset is publicly available for free and can be utilized for research and communication purposes. Access :https://data.mendeley.com/datasets/8h3s6jkyff/1
Transparent Object Images | Indoor Object Dataset
This dataset is an extremely challenging set of over 3000+ original Transparent object images such as glasses and mirrors are captured and crowdsourced from over 500+ urban and rural areas, where each image is manually reviewed and verified by computer vision professionals at Datacluster Labs. ### Dataset Features - Dataset size : 3000+ - Captured by : Over 500+ crowdsource contributors - Resolution : 99% images HD and above (1920x1080 and above) - Location : Captured with 600+ cities accross India - Diversity : Diversity in object type, lighting, camera type etc. - Device used : Captured using mobile phones in 2020-2022 - Usage : Glass detection | Mirror detection | Transparent Cups detection | Home automation etc. ### Available Annotation formats COCO, YOLO, PASCAL-VOC, Tf-Record To download full datasets or to submit a request for your dataset needs, please ping us at sales@datacluster.ai Visit www.datacluster.ai to know more. Note: All the images are manually captured and verified by a large contributor base on DataCluster platform
VolleyVision
This dataset is part of my bachelor thesis project. It was created by combining multiple open-source datasets from RoboFlow Universe as well as manual annotation. ### Code You can find the code, models, metrics, everything related to this dataset in practical terms - GitHub Link ###Author Shakhansho Sabzaliev
WalnutData
With the gradual maturity of UAV technology, it can provide extremely powerful support for smart agriculture and precise monitoring. Currently, there is no dataset related to green walnuts in the field of agricultural computer vision. Therefore, in order to promote the algorithm design in the field of agricultural computer vision, we used UAV to collect remote sensing data from 8 walnut sample plots. Considering that green walnuts have the characteristics of being affected by various lighting conditions and being occluded, we constructed a large-scale dataset with a higher fine-grained target feature - WalnutData. This dataset contains a total of 30,240 images and 7,062,080 instances, and there are 4 target categories: illuminated from the front and not occluded (A1), backlit and not occluded (A2), illuminated from the front and occluded (B1), and backlit and occluded (B2).
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.