Hybrid mobile vision for emerging applications
Hybrid mobile vision for emerging applications
复制标题
DOI：
10.1145/3508396.3512876
复制
发表时间：
2022-03
期刊：
影响因子：
--
通讯作者：
Na Wu;F. Lin;Feng Qian;Bo Han
中科院分区：
文献类型：
--
作者：
Na Wu;F. Lin;Feng Qian;Bo Han
虽然移动应用程序极大地受益于 2D 计算机视觉算法（例如对象检测和分类），但由于移动设备上深度摄像头和 LiDAR 扫描仪的可用性不断增加，探索 3D 视觉的研究仍然有限。在本文中，我们提出了一种混合移动视觉系统，该系统智能地结合了 2D 和 3D 视觉，以提高增强和混合现实以及体积内容分析等新兴应用程序的性能。我们的研究受到 2D 和 3D 视觉之间关键延迟与准确度权衡的关键观察的启发并进行了探索。我们提出了一个研究议程，其中包含增强移动视觉堆栈的两个原则，通过利用其多样化的资源/精度配置文件来补充 3D 视觉及其 2D 视觉，并使用 2D 视觉线索处理 3D 数据（例如点云）以减轻高计算和存储成本。
While mobile applications have greatly benefited from 2D computer vision algorithms such as object detection and classification, there is limited research on exploring 3D vision that is enabled by the increasing availability of depth cameras and LiDAR scanners on mobile devices. In this paper, we propose a hybrid mobile vision system that intelligently combines 2D and 3D vision for improving the performance of emerging applications such as augmented and mixed reality and volumetric content analytics. Our research is motivated by and explores the key observation of the crucial latency-accuracy tradeoff between 2D and 3D vision. We present a research agenda with two principles for enhancing mobile vision stack, complementing 3D vision with its 2D counterpart by leveraging their diverse resource/accuracy profiles and processing 3D data (e.g., point clouds) with 2D vision cues for mitigating the high computation and storage costs.