DroneVehicle

## Overview

DroneVehicle is a dataset for object detection tasks - it contains Vehicles annotations for 17,990 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).

In the process of UAV small target vehicle detection, it is difficult to extract the features because of the small target shape of the vehicle, the environment noise is big, the vehicles are dense and easy to miss detection. The LMAD-YOLO model is proposed, and the MultiEdgeEnhancer module is designed to enhance the edge information and enhance the feature capture through a series of operations. Large Separable Kernel Attention and SPPF are combined to form MSPF module, which can realize multi-scale perception aggregation and improve the ability of distinguishing small targets from interference. Adown module is introduced to replace the model of sampling, in order to reduce the parameters and computational complexity while enhancing the accuracy of small target detection. A Multidimensional Diffusion Fusion Pyramid Network is designed, in which Dasi and feature spread mechanism are used to fuse features to reduce the error detection and missed detection. Compared with YOLO11n model P, R, MAP50 of the improved model on DroneVehicle data set were increased by 2.4%,1.4%,2.2% respectively. The model also showed good generalization ability on the VisDrone data set.

In the process of UAV small target vehicle detection, it is difficult to extract the features because of the small target shape of the vehicle, the environment noise is big, the vehicles are dense and easy to miss detection. The LMAD-YOLO model is proposed, and the MultiEdgeEnhancer module is designed to enhance the edge information and enhance the feature capture through a series of operations. Large Separable Kernel Attention and SPPF are combined to form MSPF module, which can realize multi-scale perception aggregation and improve the ability of distinguishing small targets from interference. Adown module is introduced to replace the model of sampling, in order to reduce the parameters and computational complexity while enhancing the accuracy of small target detection. A Multidimensional Diffusion Fusion Pyramid Network is designed, in which Dasi and feature spread mechanism are used to fuse features to reduce the error detection and missed detection. Compared with YOLO11n model P, R, MAP50 of the improved model on DroneVehicle data set were increased by 2.4%,1.4%,2.2% respectively. The model also showed good generalization ability on the VisDrone data set.

Vehicle Detection Using Drone

## Overview

Vehicle Detection Using Drone is a dataset for object detection tasks - it contains Vehicle annotations for 1,286 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).

In the process of UAV small target vehicle detection, it is difficult to extract the features because of the small target shape of the vehicle, the environment noise is big, the vehicles are dense and easy to miss detection. The LMAD-YOLO model is proposed, and the MultiEdgeEnhancer module is designed to enhance the edge information and enhance the feature capture through a series of operations. Large Separable Kernel Attention and SPPF are combined to form MSPF module, which can realize multi-scale perception aggregation and improve the ability of distinguishing small targets from interference. Adown module is introduced to replace the model of sampling, in order to reduce the parameters and computational complexity while enhancing the accuracy of small target detection. A Multidimensional Diffusion Fusion Pyramid Network is designed, in which Dasi and feature spread mechanism are used to fuse features to reduce the error detection and missed detection. Compared with YOLO11n model P, R, MAP50 of the improved model on DroneVehicle data set were increased by 2.4%,1.4%,2.2% respectively. The model also showed good generalization ability on the VisDrone data set.

The dataset is derived from the DroneVehicle dataset released by Tianjin University, and the data is processed as follows: 1. The infrared image portion was selected from the dataset as the original dataset for the paper 2. MTF operations were performed on the infrared dataset to degrade the image to a blurred image3. The images were subjected to 2x down sampling and 4x down sampling, forming a paired dataset for super-resolution reconstruction

DroneVehicleIR

## Overview

DroneVehicleIR is a dataset for object detection tasks - it contains Objects annotations for 17,990 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).

The tethered drone system market is experiencing robust growth, projected to reach a value of $764 million in 2025 and maintain a Compound Annual Growth Rate (CAGR) of 7.2% from 2025 to 2033. This expansion is driven by increasing demand across diverse sectors, primarily defense and telecommunications. Defense applications leverage tethered drones for persistent surveillance, border security, and battlefield intelligence gathering, capitalizing on their extended flight times and reduced logistical complexities compared to battery-powered drones. Telecommunications companies utilize them for network inspection, maintenance, and emergency response, benefiting from the reliable connectivity provided by the tether. Other applications, such as infrastructure monitoring and search and rescue operations, are also contributing to market growth. The market segmentation reveals a strong preference for ground-fixed type systems, followed by vehicle-mounted and shipborne mobile types, reflecting the varying needs of different applications and operational environments. Key growth trends include the development of advanced sensors and payloads, miniaturization of tethered drone systems, and integration of AI-powered capabilities for enhanced data analysis. However, factors such as high initial investment costs and potential vulnerabilities to weather conditions are currently acting as restraints on market expansion. The competitive landscape comprises a mix of established players and emerging companies, with continuous innovation driving competition and product diversification. Geographic distribution indicates strong market presence in North America and Europe, while the Asia-Pacific region exhibits significant growth potential due to rising adoption in various industries. The substantial market size, coupled with the consistent CAGR, indicates a lucrative investment opportunity. Companies operating in this space are strategically focusing on enhancing product features, expanding into new applications, and forging strategic partnerships to capture a larger market share. The forecast period of 2025-2033 presents considerable opportunities for further expansion, particularly with the ongoing technological advancements and growing demand across various sectors. This growth trajectory is expected to be fueled by increasing investments in infrastructure development, rising security concerns, and the integration of tethered drone systems into existing operational workflows. The market's future prospects remain optimistic, with significant potential for expansion and diversification across diverse geographies and application domains.

The tethered drone system market is experiencing robust growth, projected to reach a market size of $664.7 million in 2025 and exhibiting a Compound Annual Growth Rate (CAGR) of 6.9% from 2025 to 2033. This expansion is driven by several key factors. Increasing demand for persistent surveillance and data acquisition across various sectors, including defense, telecommunications, and critical infrastructure monitoring, fuels market growth. The enhanced safety and reliability offered by tethered systems compared to free-flying drones, along with their extended operational endurance due to continuous power supply, are significant advantages. Furthermore, advancements in tethering technology, leading to improved cable management, lighter weight systems, and increased data transmission speeds, contribute to the market's upward trajectory. The diverse application segments, encompassing ground-based, vehicle-mounted, and shipborne deployments, further broaden the market's reach and potential. Government initiatives promoting drone integration for various applications, particularly in surveillance and infrastructure inspection, also provide a strong impetus for growth. The market segmentation reveals a strong preference for ground-fixed type systems, driven by their ease of deployment and cost-effectiveness for specific applications. However, vehicle-mounted and shipborne mobile systems are gaining traction, fueled by the need for mobile surveillance and data collection in challenging terrains and maritime environments. Geographically, North America and Europe currently hold significant market share, driven by early adoption and technological advancements. However, the Asia-Pacific region is expected to witness significant growth in the coming years, owing to increasing infrastructure development and government investments in drone technology. While competitive intensity is rising with numerous players entering the market, opportunities abound for companies focusing on innovative tethering solutions, specialized applications, and efficient deployment strategies. The market's continued growth is strongly tied to technological advancements, regulatory frameworks, and expanding applications across diverse industries. This report provides a detailed analysis of the rapidly expanding tethered drone system market, projecting a value exceeding $2 billion by 2028. It delves into market concentration, key trends, dominant regions, and leading companies, offering invaluable insights for investors, industry professionals, and strategic decision-makers.

Drone_vehicle_image

## Overview

Drone_vehicle_image is a dataset for object detection tasks - it contains Vehicles annotations for 4,679 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).

The global emergency lighting tethered drone market is poised for significant growth, driven by increasing demand for enhanced safety and situational awareness during emergency rescue and response operations, particularly at night. The market's expansion is fueled by several key factors: the rising adoption of drones for improved visibility in challenging environments, advancements in tethered drone technology offering extended flight times and enhanced stability, and increasing government investments in public safety infrastructure. The market is segmented by application (emergency rescue, night emergency response, others) and type (ground fixed, vehicle-mounted mobile, shipborne mobile). Ground fixed type currently dominates due to its ease of deployment and cost-effectiveness, but the vehicle-mounted and shipborne mobile segments are experiencing rapid growth, driven by the need for mobile and adaptable solutions in diverse operational settings. Key players in the market include Fotokite, Elistair, EELTEX, XD motion, Sky Sapience Ltd, and Hoverfly Technologies, each contributing to technological innovation and market expansion through their respective product offerings and strategic partnerships. While the initial investment cost can be a restraining factor for some organizations, the long-term benefits in terms of improved safety and operational efficiency are driving widespread adoption. We project a substantial market expansion over the forecast period (2025-2033), fueled by consistent technological advancements and the increasing recognition of tethered drones as essential tools for emergency services. Geographic distribution shows significant potential in North America and Europe, driven by robust public safety infrastructure and advanced technological adoption rates. However, emerging markets in Asia-Pacific and the Middle East & Africa are expected to exhibit high growth rates, as these regions increasingly invest in modernizing their emergency response capabilities. The market is characterized by a competitive landscape with both established players and emerging startups vying for market share. The focus on developing drones with improved capabilities, such as enhanced battery life, improved payload capacity, and advanced sensor integration, will be crucial in shaping the market's future trajectory. The integration of AI and machine learning functionalities for improved decision-making during emergency situations represents a significant growth opportunity.

Model training result data: includes the data generated during the model training and validation process, including various evaluation metrics, FPS, The results of each training round.