Low-Cost CNN Design for Intelligent Surveillance System

Liang Wei Yang*, Chung Yen Su

*此作品的通信作者

研究成果: 書貢獻/報告類型會議論文篇章

4 引文 斯高帕斯(Scopus)

摘要

In today's world, video surveillance appears everywhere in our life. The challenge for a video surveillance system is to recognize the object of interest for analysis. The convolutional neural network (CNN) models achieve high accuracy on image recognition, but the models require powerful calculations. The models cannot be applied to most smart surveillance systems directly. In this paper, we propose a low-cost CNN design for the application of surveillance systems. Instead of using GPUs, we use a hardware accelerator called Neural Compute Stick (NCS) accompanied with the Rock64 to build the system. The NCS is a low-cost and low-power USB device, which has the advantages in the high-speed calculation of images. As a result, we use the NCS to load the Single Shot MultiBox Detector (SSD) network for human detection. Our system can get each detected image in 0.15 sec. It is six times faster than other single-board surveillance systems. Furthermore, the cost of building the real-time surveillance system is less than 100. Therefore, our system can achieve a low-cost and high-performance intelligent surveillance system.

原文英語
主出版物標題2018 International Conference on System Science and Engineering, ICSSE 2018
發行者Institute of Electrical and Electronics Engineers Inc.
ISBN(電子)9781538662854
DOIs
出版狀態已發佈 - 2018 十一月 1
事件2018 International Conference on System Science and Engineering, ICSSE 2018 - New Taipei City, 臺灣
持續時間: 2018 六月 282018 六月 30

出版系列

名字2018 International Conference on System Science and Engineering, ICSSE 2018

會議

會議2018 International Conference on System Science and Engineering, ICSSE 2018
國家/地區臺灣
城市New Taipei City
期間2018/06/282018/06/30

ASJC Scopus subject areas

  • 控制與系統工程
  • 控制和優化

指紋

深入研究「Low-Cost CNN Design for Intelligent Surveillance System」主題。共同形成了獨特的指紋。

引用此