arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2004.06154cs.CVcs.RO
收藏

基于无人机的人工智能实时的视觉任务框架

An Efficient UAV-based Artificial Intelligence Framework for Real-Time Visual Tasks

University of Udine(乌迪内大学);Mongolian University of Science and Technology(蒙古科技大学)

Enkhtogtokh Togootogtokh, Christian Micheloni, Gian Luca Foresti, Niki Martinel

摘要:

配备了最先进的人工智能(AI)技术的现代无人机正在向大量新颖有趣的应用开放。虽然这一领域受到了最近人工智能突破的强烈影响,但大多数提供的解决方案要么完全依赖于商业软件,要么提供了一个弱集成接口,从而拒绝了其他技术的开发。这使得我们提出了一种新颖而有效的无人机-人工智能联合技术框架。智能无人机系统面临着复杂的挑战,需要在没有人类控制的情况下加以解决。这些复杂的挑战之一是能够在实时的【形】用例中执行计算机视觉任务。在本文中,我们专注于这一挑战,并介绍了一个多层AI(MLAI)框架,以允许轻松集成ad-hoc基于视觉的AI应用程序。为了展示其功能和优势,我们实现并评估了用于目标检测、目标跟踪和目标切换的不同现代视觉深度学习模型。

英文摘要:

Modern Unmanned Aerial Vehicles equipped with state of the art artificial intelligence (AI) technologies are opening to a wide plethora of novel and interesting applications. While this field received a strong impact from the recent AI breakthroughs, most of the provided solutions either entirely rely on commercial software or provide a weak integration interface which denies the development of additional techniques. This leads us to propose a novel and efficient framework for the UAV-AI joint technology. Intelligent UAV systems encounter complex challenges to be tackled without human control. One of these complex challenges is to be able to carry out computer vision tasks in real-time use cases. In this paper we focus on this challenge and introduce a multi-layer AI (MLAI) framework to allow easy integration of ad-hoc visual-based AI applications. To show its features and its advantages, we implemented and evaluated different modern visual-based deep learning models for object detection, target tracking and target handover.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑