Introduction
Bimonthly, started in 1957
Administrator
Shanxi Provincial Education Department
Sponsor
Taiyuan University of Technology
Publisher
Ed. Office of Journal of TYUT
Editor-in-Chief
SUN Hongbin
ISSN: 1007-9432
CN: 14-1220/N
Administrator
Shanxi Provincial Education Department
Sponsor
Taiyuan University of Technology
Publisher
Ed. Office of Journal of TYUT
Editor-in-Chief
SUN Hongbin
ISSN: 1007-9432
CN: 14-1220/N
location: home > paper >

Public Security Video Surveillance Image Restoration Based on Stochastic Gradient Descent Algorithm
DOI:
10.16355/j.cnki.issn1007-9432tyut.2022.06.022
Received:
Accepted:
Corresponding author | Institute | |
ZHOU Xiping | National Security Academy, People’s Public Security University of China |
abstract:
With the advent of the era of intelligent technology, the importance of image detection in public security operations has become more and more prominent. Image intelligence analysis is essential to restore crime scenes. However, in the actual image intelligence collection process, image defects and damage are inevitable. A tensor chain decomposition algorithm based on stochastic gradient descent was introduced to repair damaged image information. Research shows that this method can effectively repair damaged image information, retrieve the lost data, and reduce computational complexity. This work provides good conditions for subsequent analysis work, reduces intelligence errors, and improves the efficiency of police work.
Keywords:
video surveillance; image intelligence; stochastic gradient descent; repair algorithm;