This deep learning model is used to detect cars in high resolution drone or aerial imagery. Car detection can be used for applications such as traffic management and analysis, parking lot utilization, urban planning, etc. It can also be used as a proxy for deriving economic indicators and estimating retail sales. High resolution aerial and drone imagery can be used for car detection due to its high spatio-temporal coverage.Using the modelFollow the guide to use the model. Before using this model, ensure that the supported deep learning libraries are installed. For more details, check Deep Learning Libraries Installer for ArcGIS.Fine-tuning the modelThis model can be fine-tuned using the Train Deep Learning Model tool. Follow the guide to fine-tune this model.InputHigh resolution RGB imagery (5 - 20 centimeter spatial resolution).OutputFeature class containing detected cars.Applicable geographiesThe model is expected to work well in the United States.Model architectureThis model uses the MaskRCNN model architecture implemented in ArcGIS API for Python.Accuracy metricsThis model has an average precision score of 0.81.Training dataThis model has been trained on an Esri proprietary car detection dataset.Sample resultsHere are a few results from the model. To view more, see this story.

Vehicle_Detection_NIGHT

## Overview

Vehicle_Detection_NIGHT is a dataset for object detection tasks - it contains Auto Bus Car Motorbike Truck annotations for 1,487 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Yolo V8 Car Detection Set

## Overview

Yolo V8 Car Detection Set is a dataset for object detection tasks - it contains Vehicles Yolov8 annotations for 1,874 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Aerial Multi-Vehicle Detection Dataset: Efficient road traffic monitoring is playing a fundamental role in successfully resolving traffic congestion in cities. Unmanned Aerial Vehicles (UAVs) or drones equipped with cameras are an attractive proposition to provide flexible and infrastructure-free traffic monitoring. Due to the affordability of such drones, computer vision solutions for traffic monitoring have been widely used. Therefore, this dataset provide images that can be used for either training or evaluating Traffic Monitoring applications. More specifically, it can be used for training an aerial vehicle detection algorithm, benchmark an already trained vehicle detection algorithm, enhance an existing dataset and aid in traffic monitoring and analysis of road segments.

The dataset construction involved manually collecting all aerial images of vehicles using UAV drones and manually annotated into three classes 'Car', 'Bus', and ''Truck'.The aerial images were collected through manual flights in road segments in Nicosia or Limassol, Cyprus, during busy hours. The images are in High Quality, Full HD (1080p) to 4k (2160p) but are usually resized before training. All images were manually annotated and inspected afterward with the vehicles that indicate 'Car' for small to medium sized vehicles, 'Bus' for busses, and 'Truck' for large sized vehicles and trucks. All annotations were converted into VOC and COCO formats for training in numerous frameworks. The data collection took part in different periods, covering busy road segments in the cities of Nicosia and Limassol in Cyprus. The altitude of the flights varies between 150 to 250 meters high, with a top view perspective. Some of the images found in this dataset are taken from Harpy Data dataset [1]

The dataset includes a total of 9048 images of which 904 are split for validation, 905 for testing, and the rest 7239 for training.

It is advised to further enhance the dataset so that random augmentations are probabilistically applied to each image prior to adding it to the batch for training. Specifically, there are a number of possible transformations such as geometric (rotations, translations, horizontal axis mirroring, cropping, and zooming), as well as image manipulations (illumination changes, color shifting, blurring, sharpening, and shadowing).

[1] Makrigiorgis, R., 2021. Harpy Data Dataset. [online] Kios.ucy.ac.cy. Available at: <https://www.kios.ucy.ac.cy/harpydata/> [Accessed 22 September 2022].

**NOTE** If you use this dataset in your research/publication please cite us using the following :

Rafael Makrigiorgis, Panayiotis Kolios, & Christos Kyrkou. (2022). Aerial Multi-Vehicle Detection Dataset (1.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.7053442

Red Car Detection

## Overview

Red Car Detection is a dataset for object detection tasks - it contains Red Car annotations for 468 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

This repository has VME dataset (images and annotations files). Also, it has the script for constructing CDSI dataset.

VME is a satellite imagery dataset built for vehicle detection in the Middle East. VME images (satellite_images folder) are under https://creativecommons.org/licenses/by-nc-nd/4.0/" target="_blank" rel="noopener">CC BY-NC-ND 4.0 license, whereas the rest of folders (annotations_HBB, annotations_OBB, CDSI_construction_scripts) are under https://creativecommons.org/licenses/by/4.0/" target="_blank" rel="noopener">CC BY 4.0 license.

VME_CDSI_datasets.zip has four components:

1. annotations_OBB: It holds TXT files in YOLO format with Oriented Bounding Box (OBB) annotations. Each annotation file is named after the corresponding image name
2. annotations_HBB: This component contains HBB annotation files in JSON file formatted in MS-COCO format defined by four values in pixels (x_min, y_min, width, height) of training, validation, and test splits
3. satellite_images: This folder consists of VME images of size 512x512 in PNG format
4. CDSI_construction_scripts: This directory comprises all instructions needed to build the CDSI dataset in detail: a) instructions for downloading each dataset from its repository, b) The conversion to MS-COCO format script for each dataset is under the dataset name folder, c) The combination instructions. The training, validation, and test splits are available under "CDSI_construction_scripts/data_utils" folder.

annotations_HBB, annotations_OBB, CDSI_construction_scripts, are available in our GitHub repository

Please cite our dataset & paper with the preferred format as shown in the "Citation" section

The dataset contains locations and attributes of Vehicle Detection Systems, created from a database provided by the District Department of Transportation.

Vehicle Detection From Satellite

## Overview

Vehicle Detection From Satellite is a dataset for object detection tasks - it contains Cars Trucks Vans annotations for 2,059 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Dataset

This dataset was created by mukaseevru

Contents

Car Detection Game Fixed

## Overview

Car Detection Game Fixed is a dataset for object detection tasks - it contains Car Detection Game Fixed annotations for 2,071 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

This New Zealand car detection Deep Learning Package will detect cars from high resolution imagery. This model is re-trained from the Esri Car Detection - USA Deep Learning Package and is trained to work better within the New Zealand geography.The model precision had also improved from 0.81 to 0.89. The package is trained to be more aggressive in terms of car detecting and is able to detect most cars that are fully covered in shade or partially blocked by tree canopy. This deep learning model is used to detect cars in high resolution drone or aerial imagery. Car detection can be used for applications such as traffic management and analysis, parking lot utilization, urban planning, etc. It can also be used as a proxy for deriving economic indicators and estimating retail sales. High resolution aerial and drone imagery can be used for car detection due to its high spatio-temporal coverage.Licensing requirementsArcGIS Desktop – ArcGIS Image Analyst and ArcGIS 3D Analyst extensions for ArcGIS ProArcGIS Online – ArcGIS Image for ArcGIS OnlineUsing the modelFollow the guide to use the model. Before using this model, ensure that the supported deep learning libraries are installed. For more details, check Deep Learning Libraries Installer for ArcGIS.Note: Deep learning is computationally intensive, and a powerful GPU is recommended to process large datasets.InputHigh resolution RGB imagery (7.5 centimetre spatial resolution)OutputFeature class containing detected carsApplicable geographiesThe model is expected to work well with the New Zealand localised data.Model architectureThis model uses the MaskRCNN model architecture implemented in ArcGIS Pro Arcpy.Accuracy metricsThis model has an average precision score of 0.89.Sample resultsHere are a few results from the model.(Post processing are recommended to filter out False Positive Object.e.g (confidence >= x | 0.95) |& ((shape_area/shape_length) >= x | 0.5) |& (class == Car) |& Regularize(feature)3% of detected object will need to be filtered out averagely .To learn how to use this model, see this story

If you use this dataset, please cite this paper: Puertas, E.; De-Las-Heras, G.; Fernández-Andrés, J.; Sánchez-Soriano, J. Dataset: Roundabout Aerial Images for Vehicle Detection. Data 2022, 7, 47. https://doi.org/10.3390/data7040047 This publication presents a dataset of Spanish roundabouts aerial images taken from an UAV, along with annotations in PASCAL VOC XML files that indicate the position of vehicles within them. Additionally, a CSV file is attached containing information related to the location and characteristics of the captured roundabouts. This work details the process followed to obtain them: image capture, processing and labeling. The dataset consists of 985,260 total instances: 947,400 cars, 19,596 cycles, 2,262 trucks, 7,008 buses and 2,208 empty roundabouts, in 61,896 1920x1080px JPG images. These are divided into 15,474 extracted images from 8 roundabouts with different traffic flows and 46,422 images created using data augmentation techniques. The purpose of this dataset is to help research on computer vision on the road, as such labeled images are not abundant. It can be used to train supervised learning models, such as convolutional neural networks, which are very popular in object detection. Roundabout (scenes) Frames Car Truck Cycle Bus Empty 1 (00001) 1,996 34,558 0 4229 0 0 2 (00002) 514 743 0 0 0 157 3 (00003-00017) 1,795 4822 58 0 0 0 4 (00018-00033) 1,027 6615 0 0 0 0 5 (00034-00049) 1,261 2248 0 550 0 81 6 (00050-00052) 5,501 180,342 1420 120 1376 0 7 (00053) 2,036 5,789 562 0 226 92 8 (00054) 1,344 1,733 222 0 150 222 Total 15,474 236,850 2,262 4,899 1,752 552 Data augmentation x4 x4 x4 x4 x4 x4 Total 61,896 947,400 9048 19,596 7,008 2,208

The previous fine-grained datasets mainly focus on classification and are often captured in a controlled setup, with the camera focusing on the objects. We introduce the first Fine-Grained Vehicle Detection (FGVD) dataset in the wild, captured from a moving camera mounted on a car. It contains 5502 scene images with 210 unique fine-grained labels of multiple vehicle types organized in a three-level hierarchy. While previous classification datasets also include makes for different kinds of cars, the FGVD dataset introduces new class labels for categorizing two-wheelers, autorickshaws, and trucks. The FGVD dataset is challenging as it has vehicles in complex traffic scenarios with intra-class and inter-class variations in types, scale, pose, occlusion, and lighting conditions. The current object detectors like yolov5 and faster RCNN perform poorly on our dataset due to a lack of hierarchical modeling. Along with providing baseline results for existing object detectors on FGVD Dataset, we also present the results of a combination of an existing detector and the recent Hierarchical Residual Network (HRN) classifier for the FGVD task. Finally, we show that FGVD vehicle images are the most challenging to classify among the fine-grained datasets.

Car Motorcycle Detection

## Overview

Car Motorcycle Detection is a dataset for object detection tasks - it contains Cars And Motorcycle annotations for 3,533 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

This dataset is a subset of 74 videos from the multimodal in-the-wild dataset MuSe-CAR. It contains 1 124 video frames showing human-vehicle interactions across all MuSe topics and 6 146 labels (bounding boxes). The pre-defined training, development and test partitions are also provided.

The purpose of this dataset is to support research in the field of automatic recognition and detection of automotive parts in a natural context. It provides labels for 29 interior and exterior vehicle regions during human-vehicle interaction. It also enables benchmarking and cross-corpus transfer learning, as demonstrated in GoCarD (A Generic, Optical Car Part Recognition and Detection). The footage captures many "in-the-wild" characteristics, including a range of shot sizes, camera motion, moving objects, a wide variety of backgrounds and different interactions.

The MuSe data set can only be used for research purposes (see below).

Description:

👉 Download the dataset here

Our bicycle image dataset is a rich collection of over 5,000 images specifically curated to aid in the development of advanced computer vision algorithms. This dataset is uniquely diverse, with images captured from real-world environments, making it a valuable resource for researchers and developers working on bicycle detection and vehicle classification.

Dataset Overview

This dataset comprises high-quality images of bicycles in various orientations, lighting conditions, and environments. Each image has been manually verified by experts to ensure consistency and quality, making it suitable for a wide range of AI applications.

Download Dataset

Key Dataset Features

Dataset Size: 5,000+ high-resolution images

Contributors: Sourced from over 3,000 crowdsourcing participants globally

Resolution: HD and above, with most images at 1920×1080 resolution and higher

Geographic Diversity: Images collected from more than 3,000 distinct locations worldwide

Device Variety: Captured using smartphones, DSLR cameras, and other devices

Environmental Variations: Includes images in different lighting conditions (day/night, artificial/natural light), weather conditions, and perspectives (e.g., front view, side view, close-up, and distant shots)

Data Applications

This dataset is ideal for:

Bicycle Detection: Training AI models to recognize bicycles in urban, rural, and off-road environments

Vehicle Classification: Differentiating between two-wheelers and other vehicles

Autonomous Systems: Improving the detection algorithms for autonomous driving systems

Urban Planning: Analyzing bicycle traffic patterns and supporting city infrastructure development

Transportation Research: Understanding bicycle movement in different contexts, including city traffic, pedestrian paths, and remote areas

Unique Dataset Benefits

This dataset stands out due to its:

Crowdsourced Accuracy: Every image is carefully reviewed by computer vision professionals, ensuring high annotation quality and relevance.

Wide Variety of Scenarios: From busy urban streets to quiet country roads, this dataset covers an array of scenarios that challenge detection algorithms.

Scalability: The large number of contributors and varied locations make this dataset an invaluable resource for scalable machine learning models.

How It Can Be Used

This dataset is perfect for training deep learning models to recognize bicycles and other two-wheeled vehicles in complex environments. It’s a powerful tool for industries focused on smart cities, traffic management, autonomous vehicles, and public transportation.

This dataset is sourced from Kaggle.

Discover the Persian Car Plate Detection Dataset with 263 annotated plates optimized for YOLOv8.

This dataset is collected by DataCluster Labs. To download full dataset or to submit a request for your new data collection needs, please drop a mail to: sales@datacluster.ai This dataset is an extremely challenging set of over 50,000+ original Vehicle images captured and crowdsourced from over 1000+ urban and rural areas, where each image is manually reviewed and verified by computer vision professionals at Datacluster Labs.

Dataset Features

Dataset size : 50,000+ images Captured by : Over 1000+ crowdsource contributors Resolution : 100% images are HD and above (1920x1080 and above) Location : Captured with 1000+ 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 : Vehicle Detection, Automobile detection, Construction vehicle detection, Self driving systems, etc.

Vehicle Classes

Indian Auto Indian Truck Bus Truck Tempo Traveller Tractor Car Two Wheelers

Available Annotation formats COCO, YOLO, PASCAL-VOC, Tf-Record

*To download full datasets or to submit a request for your dataset needs, please drop a mail on sales@datacluster.ai . Visit www.datacluster.ai to know more.

Dataset

This dataset was created by Yigit Efe Uysal

Contents

Vehicle volume counts for intersections with GridSmart cameras. Data represents volume in a specific direction for a given 15 minute interval.