基于背景模型的AVS-S编码

doi:10.12068/j.issn.1005-3026.2021.01.005

东北大学学报（自然科学版） ›› 2021, Vol. 42 ›› Issue (1): 31-36.DOI: 10.12068/j.issn.1005-3026.2021.01.005

基于背景模型的AVS-S编码

桑爱军¹，于欢^1,2，张汉宇¹

(1.吉林大学通信工程学院，吉林长春130022； 2.上海无线电设备研究所，上海201109 )

出版日期:2021-01-15 发布日期:2021-01-13
通讯作者: 桑爱军
作者简介:桑爱军(1973-)，女，山东莱州人，吉林大学教授.
基金资助:
国家自然科学基金重点资助项目(61631009)；吉林省自然科学基金资助项目(20200201295JC).

AVS-S Coding Based on Background Model

SANG Ai-jun¹， YU Huan^1,2， ZHANG Han-yu¹

1. College of Telecommunication Engineering， Jilin University， Changchun 130022， China; 2. Shanghai Radio Equipment Research Institute， Shanghai 201109， China.

Online:2021-01-15 Published:2021-01-13
Contact: SANG Ai-jun
About author:-
Supported by:
-

摘要/Abstract

摘要： 为提高监控视频的编码效率，在AVS监控伸展档次的编码框架下，提出一种新的背景帧更新方法，即迭代更新均值法.根据某一像素在前景区域和背景区域出现频率不同的原理来确定该像素点在某一帧中的性质.通过在监控视频Crossroad，Overbridge和Classover的测试比较，得到不同性质的像素点对应的背景模型像素值.结果表明，慢速运动物体难以从背景中消除的缺点得到一定程度的改进，同时加强了背景信息的完整性和提高了背景帧的质量.在同等码率和相同峰值信噪比的条件下，相比于AVS基准档次方法平均节省码率为43.283%，平均提高峰值信噪比1.186dB，其监控视频的编码效率也得到了提升.

关键词: 背景帧更新方法；背景模型；监控视频；AVS监控伸展档次；AVS基准档次

Abstract: In order to improve the coding efficiency of surveillance video， a new background frame update method was proposed， namely， iterative update mean value method， under the coding framework of AVS surveillance extension grade. The nature of the pixel in a certain frame was determined according to the principle of different frequencies of occurrence of a certain pixel in the foreground area and in the background area. Through the test comparison of the surveillance video Crossroad， Overbridge and Classover， the pixel values of the background model corresponding to the pixels of different nature were obtained. The results showed that the shortcomings that slow moving objects are difficult to eliminate from the background are improved to a certain extent in this experiment. At the same time， the integrity of the background information is strengthened and the quality of the background frame is improved. Under the conditions of the same bit rate and the same peak signal-to-noise ratio， compared with the AVS benchmark method， the average code saving rate is 43.283% and the peak signal-to-noise ratio is increased by 1.186dB on average. The coding efficiency of its surveillance video is also improved.

Key words: background frame update method; background model; surveillance video; monitoring the AVS stretch grade; AVS benchmark grade

中图分类号:

TN919.81

桑爱军，于欢，张汉宇. 基于背景模型的AVS-S编码[J]. 东北大学学报（自然科学版）, 2021, 42(1): 31-36.

SANG Ai-jun， YU Huan， ZHANG Han-yu. AVS-S Coding Based on Background Model[J]. Journal of Northeastern University(Natural Science), 2021, 42(1): 31-36.

参考文献

[1]Eren H，Melike S，Cem D，et al.A novel framework and concept-based semantic search interface for abnormal crowd behaviour analysis in surveillance videos［J］.Multimedia Tools Applications，2020，79(25/26):17579-17617.
[2]Sun H，Shi W，Xu L.VU:edge computing-enabled video usefulness detection and its application in large-scale video surveillance systems［J］.IEEE Internet of Things Journal，2020，7(2):800-817.
[3]张晴.视频监控系统在手术室护理安全管理中的应用［J］.中医药管理杂志，2019，27(22):131-132.(Zhang Qing.Application of video monitoring system in nursing safety management of operating room［J］.Journal of Chinese Medicine Management，2019，27(22):131-132.)
[4]Ma M，Song H B.Effective moving object detection in H.264/AVC compressed domain for video surveillance［J］.Multimedia Tools and Applications，2019，78:35195-35209.
[5]Xiem H V，Le D T H，Giap P V.Adaptive long-term reference selection for efficient scalable surveillance video coding［C］//2018 IEEE 12th International Symposium on Embedded Multicore/Manycore Systems-on-Chip(MCSoC).Hanoi:IEEE，2018:69-73.
[6]Shao Z F，Wang L G，Wang Z Y，et al.Saliency-aware convolution neural network for ship detection in surveillance video［J］.IEEE Transactions on Circuits and Systems for Video Technology，2020，30(3):781-794.
[7]Fayyaz M A，Anjum A，Ziauddin S，et al.An improved surveillance video forgery detection technique using sensor pattern noise and correlation of noise residues［J］.Multimedia Tools and Applications，2020，79:5767–5788.
[8]宋庆昌，赵庆波，王丽华.基于Solr与面向对象的全物资编码的研究应用［J］.现代信息科技，2019，3(6):166-168.(Song Qing-chang，Zhao Qing-bo，Wang Li-hua.Research and application of Solr and object oriented full material coding［J］.Modern Information Technology，2019，3(6):166-168.)
[9]Madhav H，Kumar V.A method for predicting software reliability using object oriented design metrics［C］//2019 International Conference on Intelligent Computing and Control Systems.Madurai，India:IEEE，2019:679-682.
[10]Tan Q，Guo B，Hu J，et al.Object-oriented remote sensing image information extraction method based on multi-classifier combination and deep learning algorithm［EB/OL］.(2020-08-31)［2020-09-02］.https://doi.org/10.1016/j.patrec.2020.08.028.
[11]Gu A，Li l，Li S，et al.Method of coupling metrics for object-oriented software system based on CSBG approach［J］.Mathematical Problems in Engineering，2020(5):1-20.
[12]Sun X，Ma H，Zuo W.Perceptual-based HEVC intra coding optimization using deep convolution networks［J］.IEEE Access，2019(7):56308-56316.
[13]陈方栋.基于背景建模的高性能视频编码方法研究［D］.合肥:中国科学技术大学，2017.(Chen Fang-dong.Research on background modeling based high efficiency video coding method［D］.Hefei:University of Science and Technology of China，2017.)
[14]Li H，Ding W，Shi Y，et al.A double background based coding scheme for surveillance videos［C］//2018 Data Compression Conference.Snowbird:IEEE，2018:420-420.
[15]Han S，Zhang X，Tian Y，et al.An efficient background reconstruction based coding method for surveillance videos captured by moving camera［C］//2012 IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance.Beijing:IEEE，2012:160-165.
[16]于欢.面向监控视频的高效压缩编码算法研究［D］.长春:吉林大学，2018.(Yu Huan.Research on high efficiency compression coding algorithm for surveillance video［D］.Changchun:Jilin University，2018.)
[17]Bjontegaad G.Calculation of average PSNR differences between RD curves［EB/OL］.(2001-04-01)［2020-03-15］.http://ss.zhizhen.com/s?ecode=utf-8&sw=Calculation+of+Average+PSNR+Differences+between+RD-curves&strchannel=.(上接第30页)［32］Kang H，Yoo S J，Han D.Senti-lexicon and improved Nave Bayes algorithms for sentiment analysis of restaurant reviews［J］.Expert Systems with Applications，2012，39(5):6000-6010.［33］Prat-Pérez A，Dominguez-Sal D，Larriba-Pey J L.High quality，scalable and parallel community detection for large real graphs［C］//Proceedings of the 23rd International Conference on World Wide Web.Seoul，2014:225-236.［34］Rozemberczki B，Davies R，Sarkar R，et al.GEMSEC:graph embedding with self clustering［C］//Proceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining.Vancouver，2019:65-72.［35］Li P Z，Huang L，Wang C D，et al.EdMot:an edge enhancement approach for motif-aware community detection［C］//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.Anchorage，2019:479-487.［36］Rozemberczki B，Kiss O，Sarkar R.Karate club:an API oriented open-source Python framework for unsupervised learning on graphs［EB/OL］.(2020-05-10)［2020-08-07］.https://arxiv.org/abs/2003.04819.

基于背景模型的AVS-S编码

AVS-S Coding Based on Background Model

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 6

编辑推荐

Metrics

本文评价

[1]	佘黎煌，郭一蓉，张石. 基于方向分数和Frangi滤波器的视网膜血管分割算法[J]. 东北大学学报:自然科学版, 2020, 41(2): 182-187.
[2]	张石，佘黎煌，王雅凡，苏婷. 基于多重分形去趋势波动分析的视网膜图像分割[J]. 东北大学学报:自然科学版, 2019, 40(2): 158-163.
[3]	桑爱军，崔新宇，王艇，李晓妮. 2M维矢量矩阵DCT整数变换及并行实现[J]. 东北大学学报:自然科学版, 2017, 38(11): 1543-1547.
[4]	刘跃，桑爱军，宋立军，王世刚. 基于双向预测插值的多维矢量鬼成像视频[J]. 东北大学学报（自然科学版）, 2022, 43(7): 937-943.
[5]	李寿涛，魏玉博，李秋媛，于丁力. 考虑车辆侧偏刚度变化的MPC稳定性控制方法[J]. 东北大学学报（自然科学版）, 2023, 44(2): 162-167.
[6]	张顺尧，桑爱军，宋立军，王世刚. 针对鬼成像的聚合型三维目标匹配滤波[J]. 东北大学学报（自然科学版）, 2023, 44(2): 186-191.