CNS Core: Small: UbiVision: Ubiquitous Machine Vision with Adaptive Wireless Networking and Edge Computing

CNS 核心：小型：UbiVision：具有自适应无线网络和边缘计算的无处不在的机器视觉

• 批准号: 1910844
• 负责人: Tao Han
• 金额: $ 40.38万
• 依托单位: University of North Carolina at Charlotte
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-10-01 至 2021-10-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1910844&HistoricalAwards=false
• 关键词: CNS; Core; Small; UbiVision; Ubiquitous

Penetration of technologies such as wireless broadband and artificial intelligence (AI) is propelling a rapid adoption of network cameras across the household, industrial, and commercial sectors. These cameras such as surveillance cameras, dash cameras, and wearable cameras can capture voluminous amounts of visual data that can be turned into valuable information for public safety, autonomous driving, service robots, augmented/mixed reality, assisted living, etc. To reach the potential, new methods are needed for efficiently and effectively extracting, transferring, and sharing useful information from ubiquitous cameras while preserving user privacy. This project uses techniques and perspectives from wireless networking, computer vision, and edge computing to analyze and solve the problems in ubiquitous camera systems, fosters interdisciplinary research, provides a unique training program for undergraduate and graduate students, and has a high potential to introduce transformative technologies that enable new real-life products and services. This project aims to realize ubiquitous machine vision (UbiVision) and enable efficient utilization of networked cameras for information extraction and sharing. Toward this end, three fundamental research problems are investigated: 1) how to dynamically manage highly coupled resources and functions across multiple technology domains: camera functions, network resources, and computation resources on edge servers; 2) how to design adaptive and efficient machine vision algorithms for resource-constrained smart cameras; and 3) how to engineer reliable machine learning frameworks for robust vision analysis on edge servers. First, a new model-free end-to-end resource orchestration method is designed to improve the efficiency of wireless networking and computing by combining the merits of conventional optimization and emerging machine learning techniques. Second, a novel universal convolution neural network (CNN) and corresponding CNN optimization methods are developed for efficient multi-task feature learning on smart cameras. Third, a teacher-student network learning paradigm is innovated to develop memory and computation efficient machine vision algorithms that are able to achieve robust performance under various adverse conditions caused by varying network conditions and limited server computation budgets.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

无线宽带和人工智能（AI）等技术的渗透正在推动在家庭，工业和商业领域迅速采用网络摄像机。这些相机，例如监视摄像机，仪表板和可穿戴摄像机，可以捕获大量的视觉数据，这些视觉数据可以将其转变为有价值的信息，以进行公共安全，自主驾驶，服务机器人，增强/混合现实，辅助生活等，以达到潜在的方法，以便有效地提取有效的信息，从而供您提供有效的信息，从而提供有效的信息，并提供了ublys usement和ubers usern和ubiit camer和ubiit。该项目使用无线网络，计算机视觉和边缘计算的技术和观点来分析和解决无处不在的摄像机系统中的问题，促进了跨学科研究，为本科生和研究生提供了独特的培训计划，并且具有较高的潜力，可以引入转型技术，以启用新的现实生活中的现实生活中的产品和服务。该项目旨在实现无处不在的机器视觉（Ubivision），并有效利用网络相机进行信息提取和共享。为此，研究了三个基本研究问题：1）如何在多个技术领域动态管理高度耦合的资源和功能：Edge服务器上的相机功能，网络资源和计算资源； 2）如何为资源受限的智能摄像机设计自适应和高效的机器视觉算法； 3）如何设计可靠的机器学习框架，以在边缘服务器上进行强大的视觉分析。首先，一种新的无模型端到端资源编排方法旨在通过结合常规优化和新兴机器学习技术的优点来提高无线网络和计算的效率。其次，开发了一种新型的通用卷积神经网络（CNN）和相应的CNN优化方法，以在智能相机上有效地进行多任务特征学习。第三，创新的教师学习网络学习范例是为了开发记忆和计算有效的机器视觉算法，能够在各种不良条件下通过不同的网络条件和有限的服务器计算预算实现稳健的绩效。这奖反映了NSF的法定任务，并被认为是通过基金会的知识优点和广泛的crietia criperia criperia criperia criperia criperia criperia criperia criperia criperia criperia criperia criperia criperia criperia criperia criperia criperia criperia criperia criperia criperia均值得通过评估。

项目成果

TrustServing: A Quality Inspection Sampling Approach for Remote DNN Services

• DOI: 10.1109/secon48991.2020.9158444
• 发表时间: 2020-06
• 期刊: 2020 17th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON)
• 作者: Xueyu Hou;T. Han

FedVision: Federated Video Analytics With Edge Computing

• DOI: 10.1109/ojcs.2020.2996184
• 发表时间: 2020-01-01
• 期刊: IEEE OPEN JOURNAL OF THE COMPUTER SOCIETY
• 影响因子: 5.9
• 作者: Deng, Yang;Han, Tao;Ansari, Nirwan
• 通讯作者: Ansari, Nirwan

DIRECT: Distributed Cross-Domain Resource Orchestration in Cellular Edge Computing

• DOI: 10.1145/3323679.3326516
• 发表时间: 2019-07
• 期刊: Proceedings of the Twentieth ACM International Symposium on Mobile Ad Hoc Networking and Computing
• 作者: Qiang Liu;Tao Han

Atlas: automate online service configuration in network slicing

• DOI: 10.1145/3555050.3569115
• 发表时间: 2022-10
• 期刊: Proceedings of the 18th International Conference on emerging Networking EXperiments and Technologies
• 作者: Qiang Liu;Nakjung Choi;Tao Han

Density Map Guided Object Detection in Aerial Images

• DOI: 10.1109/cvprw50498.2020.00103
• 发表时间: 2020-01-01
• 期刊: 2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2020)
• 作者: Li, Changlin;Yang, Taojiannan;Guan, Shanyue
• 通讯作者: Guan, Shanyue