视频质量波动影响下的视频异常检测算法有效性分析
Effectivity analysis of video anomaly detection algorithm with video quality fluctuation
刘存 1杨曦晨 1陈天海 1吉根林1
作者信息
- 1. 南京师范大学计算机与电子信息学院,江苏南京 210023
- 折叠
摘要
大部分异常检测算法并没有考虑实际场景中视频质量波动对算法性能的影响.文章首先选用视频异常检测领域的公开数据集,并采用仿真方式在其中加入监控视频中的常见失真,构建出面向异常检测的失真数据集.然后系统地分析了视频质量波动对4个经典的视频异常检测算法性能的影响.实验结果表明,监控数据质量下降会对视频异常检测算法的有效性产生负面效果,并且不同失真类型、不同失真程度对算法的影响存在差异,其中高斯噪声失真和过亮失真对算法的影响较大.
Abstract
As most anomaly detection methods generally ignore the impact of video quality fluctuations in actual scenarios on their performance.Firstly,public datasets from the field of video anomaly detec-tion were selected,and a distortion dataset for anomaly detection by artificially introducing common distortions found in surveillance videos through simulation methods was constructed.This paper sys-tematically analyzes the impact of video quality fluctuations on the performance of four classic video a-nomaly detection algorithms.And the experimental results show that the degradation of surveillance data quality have a negative effect on the effectiveness of the video anomaly detection algorithm.Mo-reover,the impact of different distortion types and different degrees of distortion on the algorithm is different,as well as,Gaussian noise distortion and over brightness distortion have a greater impact on the algorithm.
关键词
异常检测/质量波动/仿真/失真/有效性Key words
anomaly detection/quality fluctuation/simulation/distortion/effectiveness引用本文复制引用
基金项目
国家自然科学基金(41971343)
国家自然科学基金青年基金(62101268)
出版年
2024
国家科技期刊平台
NSTL
万方数据