Chinese Journal on Internet of Things ›› 2019, Vol. 3 ›› Issue (4): 63-71.doi: 10.11959/j.issn.2096-3750.2019.00133

• Theory and Technology • Previous Articles     Next Articles

Research on neuromorphic vision sensor and its applications

Yongsheng SANG1,Renhao LI1,Yaoqian LI1,Qiangwei WANG2,Yao MAO3()   

  1. 1 College of Computer Science,Sichuan University,Chengdu 610065,China
    2 Sichuan Tourism University,Chengdu 610100,China
    3 Institute of Optics and Electronics,Chinese Academy of Sciences,Chengdu 610209,China
  • Revised:2019-10-31 Online:2019-12-30 Published:2020-02-05
  • Supported by:
    The National Natural Science Foundation of China(U1831121);The Key S&T Special Projects of Sichuan(2019ZDZX0006);The Key S&T Special Projects of Sichuan(2018GZDZX0028)

Abstract:

Neuromorphic vision sensor is a biologically inspired artificial neural system that mimics algorithmic behavior of biological vision systems,which has numerous advantages over standard vision sensors,such as high temporal resolution,low latency,low power,high dynamic range,etc.At first,a brief introduction to neuromorphic engineering,neuromorphic chips,and vision sensors was given.Then the main computing methods for neuromorphic vision were reviewed,including probability and statistics,spiking neural network and deep neural network.Finally,several kinds of applications based on neuromorphic vision sensors were given,such as simultaneous localization and mapping (SLAM),image reconstruction (IR),etc.A review of hardware,computing methods and applications for neuromorphic vision sensors was given,which provided a comprehensive reference for researchers.

Key words: neuromorphic vision sensor, event-based camera, frame-based camera, neural network, simultaneous localization and mapping, image reconstruction

CLC Number: 

No Suggested Reading articles found!