EDGE ARTIFICIAL INTELLIGENCE: A MULTI-CAMERA VIDEO SURVEILLANCE APPLICATION

被引:0
作者
Berardini, Daniele [1 ]
Mancini, Adriano [1 ]
Zingaretti, Primo [1 ]
Moccia, Sara [2 ,3 ]
机构
[1] Univ Politecn Marche, Dept Informat Engn, Ancona, Italy
[2] Scuola Super Sant Anna, BioRobot Inst, Pisa, Italy
[3] Scuola Super Sant Anna, Dept Excellence Robot & AI, Pisa, Italy
来源
PROCEEDINGS OF ASME 2021 INTERNATIONAL DESIGN ENGINEERING TECHNICAL CONFERENCES AND COMPUTERS AND INFORMATION IN ENGINEERING CONFERENCE, IDETC-CIE2021, VOL 7 | 2021年
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Nowadays, video surveillance has a crucial role. Analyzing surveillance videos is, however, a time consuming and tiresome procedure. In the last years, artificial intelligence paved the way for automatic and accurate surveillance-video analysis. In parallel to the development of artificial-intelligence methodologies, edge computing is becoming an active field of research with the final goal to provide cost-effective and real time deployment of the developed methodologies. In this work, we present an edge artificial intelligence application to video surveillance. Our approach relies on a set of four IP cameras, which acquire video frames that are processed on the edge using the NVIDIA (R) Jetson Nano. A state-of-the-art deep-learning model, called Single Shot multibox Detector (SSD) MobileNetV2 network, is used to perform object and people detection in realtime. The proposed infrastructure obtained an inference speed of similar to 10.0 Frames per Second (FPS) for each parallel video stream. These results prompt the possibility of translating our work into a real word scenario. The integration of the presented application into a wider monitoring system with a central unit could bring benefits to the overall infrastructure. Indeed our application could send only video-related high-level information to the central unit, allowing it to combine information with data coming from other sensing devices without unuseful data overload. This would ensure a fast response in case of emergency or detected anomalies. We hope this work will contribute to stimulate the research in the field of edge artificial intelligence for video surveillance.
引用
收藏
页数:6
相关论文
共 12 条
[1]  
[陈珺娴 Chen Junxian], 2020, [高分子通报, Polymer Bulletin], P1
[2]   Latency and Throughput Characterization of Convolutional Neural Networks for Mobile Computer Vision [J].
Hanhirova, Jussi ;
Kamarainen, Teemu ;
Seppala, Sipi ;
Siekkinen, Matti ;
Hirvisalo, Vesa ;
Yla-Jaaski, Antti .
PROCEEDINGS OF THE 9TH ACM MULTIMEDIA SYSTEMS CONFERENCE (MMSYS'18), 2018, :204-215
[3]   Deep Residual Learning for Image Recognition [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778
[4]   Deep learning architectures in emerging cloud computing architectures: Recent development, challenges and next research trend [J].
Jauro, Fatsuma ;
Chiroma, Haruna ;
Gital, Abdulsalam Y. ;
Almutairi, Mubarak ;
Abdulhamid, Shafi'i M. ;
Abawajy, Jemal H. .
APPLIED SOFT COMPUTING, 2020, 96
[5]  
Jiang J., 2020, IEEE Transactions on Intelligent Transportation Systems
[6]  
Liciotti Daniele, 2017, Video Analytics. Face and Facial Expression Recognition and Audience Measurement. Third International Workshop, VAAM 2016, and Second International Workshop, FFER 2016. Revised Selected Papers: LNCS 10165, P1, DOI 10.1007/978-3-319-56687-0_1
[7]   SSD: Single Shot MultiBox Detector [J].
Liu, Wei ;
Anguelov, Dragomir ;
Erhan, Dumitru ;
Szegedy, Christian ;
Reed, Scott ;
Fu, Cheng-Yang ;
Berg, Alexander C. .
COMPUTER VISION - ECCV 2016, PT I, 2016, 9905 :21-37
[8]  
Mancini A., 2013, INT DES ENG TECHN C, V55911
[9]  
Ren SQ, 2016, Arxiv, DOI arXiv:1506.01497
[10]   MobileNetV2: Inverted Residuals and Linear Bottlenecks [J].
Sandler, Mark ;
Howard, Andrew ;
Zhu, Menglong ;
Zhmoginov, Andrey ;
Chen, Liang-Chieh .
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :4510-4520