Live Video Analytics with FPGA-based Smart Cameras

被引：15
作者：
Wang, Shang [1 ,2 ]
Zhang, Chen [1 ]
Shu, Yuanchao [1 ]
Liu, Yunxin [1 ]
机构：
[1] Microsoft Res, Beijing, Peoples R China
[2] Univ Elect Sci & Technol China, Chengdu, Peoples R China
来源：
PROCEEDINGS OF THE 2019 WORKSHOP ON HOT TOPICS IN VIDEO ANALYTICS AND INTELLIGENT EDGES (HOTEDGEVIDEO '19) | 2019年
关键词：
Edge computing; Cameras; Video analytics; FPGA; DNN;
D O I：
10.1145/3349614.3356027
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Analyzing video feeds from large camera networks requires enormous compute and bandwidth. Edge computing has been proposed to ease the burden by bringing resources to the proximity of data. However, the number of cameras keeps growing and the associated computing resources on edge will again fall in short. To fundamentally solve the resource scarcity problem and make edge-based live video analytics scalable, we present an FPGA-based smart camera design that enables efficient in-situ streaming processing to meet the stringent low-power, energy-efficient, low-latency requirements of edge vision applications. By leveraging FPGA's intrinsic properties of architecture efficiency and exploiting its hardware support for parallelism, we demonstrate a 49x speedup over CPU and 6.4x more energy-efficiency than GPU, verified using a background subtraction algorithm.
引用
收藏
页码：9 / 14
页数：6
相关论文
共 28 条
[1]  
[Anonymous], ACM SIGDA FPGA
[2]  
[Anonymous], 2016, ACM MOBISYS
[3]  
Chen TiffanyYu-Han., 2015, ACM SENSYS
[4]  
Chu PongP., 2011, FPGA prototyping by VHDL examples: Xilinx Spartan-3 version
[5]  
Crown Alex, 2019, ACM MobiSys
[6]  
Dobai R, 2013, 2013 NASA/ESA CONFERENCE ON ADAPTIVE HARDWARE AND SYSTEMS (AHS), P164, DOI 10.1109/AHS.2013.6604241
[7]  
Fang B., 2018, ACM MOBICOM
[8]  
Han TL, 2014, 2014 11TH INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS AND KNOWLEDGE DISCOVERY (FSKD), P835, DOI 10.1109/FSKD.2014.6980946
[9]  
Hung Chien-Chun, 2018, IEEE ACM SEC
[10]  
J. Jiang, 2018, ACM SIGCOMM
123