{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/dronet-efficient-convolutional-neural-network","title":"DroNet: Efficient convolutional neural network detector for real-time UAV applications","arxiv_id":"1807.06789","date":"2018-07-18","proceeding":null,"authors":["Christos Kyrkou","George Plastiras","Stylianos Venieris","Theocharis Theocharides","Christos-Savvas Bouganis"],"abstract":"Unmanned Aerial Vehicles (drones) are emerging as a promising technology for\nboth environmental and infrastructure monitoring, with broad use in a plethora\nof applications. Many such applications require the use of computer vision\nalgorithms in order to analyse the information captured from an on-board\ncamera. Such applications include detecting vehicles for emergency response and\ntraffic monitoring. This paper therefore, explores the trade-offs involved in\nthe development of a single-shot object detector based on deep convolutional\nneural networks (CNNs) that can enable UAVs to perform vehicle detection under\na resource constrained environment such as in a UAV. The paper presents a\nholistic approach for designing such systems; the data collection and training\nstages, the CNN architecture, and the optimizations necessary to efficiently\nmap such a CNN on a lightweight embedded processing platform suitable for\ndeployment on UAVs. Through the analysis we propose a CNN architecture that is\ncapable of detecting vehicles from aerial UAV images and can operate between\n5-18 frames-per-second for a variety of platforms with an overall accuracy of\n~95%. Overall, the proposed architecture is suitable for UAV applications,\nutilizing low-power embedded processors that can be deployed on commercial\nUAVs.","url_abs":"http://arxiv.org/abs/1807.06789v1","url_pdf":"http://arxiv.org/pdf/1807.06789v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"dronet-efficient-convolutional-neural-network","repo_url":"https://github.com/gplast/DroNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"dronet-efficient-convolutional-neural-network","repo_url":"https://github.com/gplast/DroNet_PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"object-detection-in-aerial-images","task_name":"Object Detection In Aerial Images"},{"task_slug":"one-shot-object-detection","task_name":"One-Shot Object Detection"},{"task_slug":"real-time-object-detection","task_name":"Real-Time Object Detection"},{"task_slug":"vehicle-detection","task_name":"vehicle detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}