计算机科学 ›› 2020, Vol. 47 ›› Issue (6A): 609-611.doi: 10.11896/JsJkx.190700118

• 交叉&应用 • 上一篇    下一篇

基于FPGA的智能视频加速检索系统

赵博1, 2, 杨明2, 汤志伟2, 蔡玉鑫2   

  1. 1 上海大学通信与信息工程学院 上海 200444;
    2 公安部第三研究所 上海 201204
  • 发布日期:2020-07-07
  • 通讯作者: 杨明(ympoine@163.com)
  • 作者简介:95130880@qq.com
  • 基金资助:
    国家重点研发计划(2017YFC0806500)

Intelligent Video Surveillance Systems Based on FPGA

ZHAO Bo1, 2, YANG Ming2, TANG Zhi-wei2 and CAI Yu-xin2   

  1. 1 School of Communication and Information Engineering,Shanghai University,Shanghai 200444,China
    2 The Third Research Institute of the Ministry of Public Security,Shanghai 201204,China
  • Published:2020-07-07
  • About author:ZHAO Bo, Ph.D.Her main research interests include signal and information processing and artificial intelligence, IoT technology.
    YANG Ming, associate professor.His main research interests include IoT security and artificial intelligence, IoT technology.
  • Supported by:
    This work was supported by the National Key R&D Program of China (2017YFC0806500).

摘要: 根据视频监控对处理、检索视频的准确性、速度以及功耗等新的需求,文中研究设计一套基于FPGA的智能视频检索系统,可同时实现视频预处理、人脸检测、智能背景去除、视频结构化描述等功能,并实现硬件加速的智能视频加速检索,以达到快速分析、处理监控视频,并迅速得到理想的处理结果的目的。该系统通过FPGA集成CPU(ARM9)、DDR、视频采集模块、各种外设(UART,GPIO等)可实现对实时视频的检测分析。对于1280*720分辨率的视频,所有时钟都采用的280MHz同步时钟,系统帧率大约为6.6fps,和FPGA上结论一致,将该系统IP集成到SOC芯片中时,处理速度可达到30fps。

关键词: FPGA, 背景去除, 结构化描述, 人脸检测, 视频检索

Abstract: According to the video monitoring new requirements,this paper designed a set of intelligent video surveillance and retrieval system based on FPGA.The system can perform video preprocessing,face detection,intelligent background removal and video structural description simultaneously,and realize intelligent video acceleration retrieval relies on hardware acceleration,so that to achieve rapid analysis and processing of surveillance video,and quickly get the ideal processing results.By FPGA integration (ARM9) CPU,DDR,video acquisition module,a variety of peripherals (UART,GPIO,etc.),the system can realize the detection and analysis of real-time video.For videos with a resolution of 1280*720,280MHz synchronous clock is adopted,and the system frame rate is about 6.6fps.When these Intellectual Property cores are integrated into the SOC chip,the processing speed can reach 30fps.

Key words: Background removal, Face detection, FPGA, Structured description, Video retrieval

中图分类号: 

  • TP391
[1] 骆云志,刘治红.视频监控技术发展综述.兵工自动化,2009(1):1-3,11.
[2] 徐晓夏,陈泉林.智能交通监控系统中的自适应背景更新算法研究.上海大学学报(自然科学版),2003(5):35-36.
[3] 王少斌,苏淑靖,袁财源.基于FPGA的高清视频采集系统设计.电子技术应用,2019,45(7):63-66,71.
[4] 王鹏,王慧,孔凡宁,等.基于FPGA的视频监控摔倒检测报警系统.电机与控制学报,2019(8):122-128.
[5] 杨家成,刘杰.智能视频监控技术存在的问题及应对措施浅议.中国新通信,2019,21(7):60-61.
[6] WINDYG A,PIOTR S.Fast impulsive noise removal.IEEE Transactions on Image Processing,2001,10(1):173-179.
[7] YOU Y,BADAL S P,SHELLEY J T.Automatic Analyte-Ion Recognition and Background Removal for Ambient Mass-Spectrometric Data Based on Cross-Correlation.Journal of the American Society for Mass Spectrometry,2019,30:1720-1732.
[8] HONG S,FENG S.A Real-Time Algorithm for Moving ObJects Detection in Video Images//Fifth World Congress on Intelligent Control and Automation.2004.
[9] 闫河,王鹏,杨晓龙,等.一种新的Ada Boost人脸检测方法.重庆理工大学学报(自然科学),2019,33(2):106-110,161.
[10] LONG X Z,LU H T,PENG Y,et al.Graph regularized discriminative non-negative matrix factorization for face recognition.Multimedia Tools and Applications,2014,72(3):2679-2699.
[11] 李天煌.基于级联结构的人脸检测若干方法研究.南京:东南大学,2018.
[12] SUNG M K,SOO J P,CHEE S W.Image Retrieval via Query-by-Layout Using MPEG-7 Visual Descriptors.ETRI Journal,2007.
[13] 徐检.浅议MPEG-7标准及应用.有线电视技术,2005(3):39-43.
[14] SARNO R,RIDOEAN J A,KOM S,et al.Classification of Music Mood Using MPEG-7 Audio Features and SVM with Confidence Interval.International Journal of Artificial Intelligence Tools,2018,27.
[15] 卢成浪,吴宗大,李桂玲.基于MPEG-7视频检索系统的设计与实现.西北大学学报(自然科学版),2018,48(3):369-375.
[16] DING S T,QU S R,XI Y L,et al.A long video caption generation algorithm for big video data retrieval.Future Generation Computer Systems,2019,93:583-595.
[17] 王治,韩祥.视频结构化解析技术在公安警务实战中的建设与应用.警察技术,2018(5):63-66.
[18] SURYONO S,PUTRO S P,WIDOWATI,et al.System on chip (SOC) wi-fi microcontroller for multistation measurement of water surface level using ultrasonic sensor.Journal of Phy-sics:Conference Series,2018,27(5).
[1] 景慧昀, 周川, 贺欣.
针对人脸检测对抗攻击风险的安全测评方法
Security Evaluation Method for Risk of Adversarial Attack on Face Detection
计算机科学, 2021, 48(7): 17-24. https://doi.org/10.11896/jsjkx.210300305
[2] 王登天, 周华, 钱荷玥.
LDPC自适应最小和译码算法及其FPGA实现
LDPC Adaptive Minimum Sum Decoding Algorithm and Its FPGA Implementation
计算机科学, 2021, 48(6A): 608-612. https://doi.org/10.11896/jsjkx.200800134
[3] 张开强, 蒋从锋, 程小兰, 贾刚勇, 张纪林, 万健.
多分辨率下资源感知的图像目标自适应缩放检测
Resource-aware Based Adaptive-scaling Image Target Detection Under Multi-resolution Scenario
计算机科学, 2021, 48(4): 180-186. https://doi.org/10.11896/jsjkx.201200116
[4] 齐延荣, 周夏冰, 李斌, 周清雷.
基于FPGA的CNN图像识别加速与优化
FPGA-based CNN Image Recognition Acceleration and Optimization
计算机科学, 2021, 48(4): 205-212. https://doi.org/10.11896/jsjkx.200600089
[5] 邓良, 许庚林, 李梦杰, 陈章进.
基于深度学习与多哈希相似度加权实现快速人脸识别
Fast Face Recognition Based on Deep Learning and Multiple Hash Similarity Weighting
计算机科学, 2020, 47(9): 163-168. https://doi.org/10.11896/jsjkx.190900118
[6] 王喆, 唐麒, 王玲, 魏急波.
一种基于模拟退火的动态部分可重构系统划分-调度联合优化算法
Joint Optimization Algorithm for Partition-Scheduling of Dynamic Partial Reconfigurable Systems Based on Simulated Annealing
计算机科学, 2020, 47(8): 26-31. https://doi.org/10.11896/jsjkx.200500110
[7] 陈利锋, 朱路平.
一种基于云端加密的FPGA自适应动态配置方法
Encrypted Dynamic Configuration Method of FPGA Based on Cloud
计算机科学, 2020, 47(7): 278-281. https://doi.org/10.11896/jsjkx.190700110
[8] 朱丽花, 王玲, 唐麒, 魏急波.
一种针对动态部分可重构SoC软硬件划分的高效MILP模型
Efficient MILP Model for HW/SW Partitioning of Dynamic Partial Reconfigurable SoC
计算机科学, 2020, 47(4): 18-24. https://doi.org/10.11896/jsjkx.190300001
[9] 钟马驰, 张俊朗, 蓝扬波, 何月铧.
基于人脸检测和模糊综合评判的在线教育专注度研究
Study on Online Education Focus Degree Based on Face Detection and Fuzzy Comprehensive Evaluation
计算机科学, 2020, 47(11A): 196-203. https://doi.org/10.11896/jsjkx.191100203
[10] 林增敏, 洪朝群, 庄蔚蔚.
融合人脸跟踪和聚类的人脸图像去重方法
Face Image Deduplication Based on Fusion of Face Tracking and Clustering
计算机科学, 2020, 47(11A): 615-619. https://doi.org/10.11896/jsjkx.200400142
[11] 李斌, 周清雷, 斯雪明, 陈晓杰.
基于FPGA集群的Office口令恢复优化实现
Optimized Implementation of Office Password Recovery Based on FPGA Cluster
计算机科学, 2020, 47(11): 32-41. https://doi.org/10.11896/jsjkx.200500040
[12] 周惠婷, 周杰.
基于改进NC-OFDM算法的仿真设计与分析
Simulation and Analysis on Improved NC-OFDM Algorithm
计算机科学, 2020, 47(10): 263-268. https://doi.org/10.11896/jsjkx.190800043
[13] 胡志军,徐勇.
基于内容的视频检索综述
Overview of Content-based Video Retrieval
计算机科学, 2020, 47(1): 117-123. https://doi.org/10.11896/jsjkx.190100231
[14] 贾迅, 钱磊, 邬贵明, 吴东, 谢向辉.
FPGA应用于高性能计算的研究现状和未来挑战
Research Advances and Future Challenges of FPGA-based High Performance Computing
计算机科学, 2019, 46(11): 11-19. https://doi.org/10.11896/jsjkx.191100500C
[15] 李浪,刘波涛.
Surge:一种新型、低资源、高效的轻量级分组密码算法
Surge:A New Low-resource and Efficient Lightweight Block Cipher
计算机科学, 2018, 45(2): 236-240. https://doi.org/10.11896/j.issn.1002-137X.2018.02.041
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!