吉林大学学报(工学版) ›› 2021, Vol. 51 ›› Issue (4): 1370-1374.doi: 10.13229/j.cnki.jdxbgxb20200252

• 计算机科学与技术 • 上一篇    

基于运动矢量空间编码的视频监控动态目标检测方法

潘德伦1(),冀隽2,张跃进3   

  1. 1.北京体育大学 信息网络中心,北京 100084
    2.北京体育大学 图书馆,北京 100084
    3.华东交通大学 信息工程学院,南昌 330013
  • 收稿日期:2020-04-17 出版日期:2021-07-01 发布日期:2021-07-14
  • 作者简介:潘德伦(1982-),男,高级工程师.研究方向:视频自动识别.E-mail:pandelun45@sina.com
  • 基金资助:
    国家自然科学基金项目(11862006);江西省交通运输厅项目(2018X0016)

Dynamic object detection method of video surveillance based on motion vector space coding

De-lun PAN1(),Jun JI2,Yue-jin ZHANG3   

  1. 1.Information Network Center,Beijing Sport University,Beijing 100084,China
    2.Library,Beijing Sport University,Beijing 100084,China
    3.School of Information Engineering,East China Jiaotong University,Nanchang 330013,China
  • Received:2020-04-17 Online:2021-07-01 Published:2021-07-14

摘要:

针对当前视频监控动态目标检测过程中因忽略了目标位置的预估计而导致检测耗时较长、检测误差较大的问题,提出了基于运动矢量空间编码的视频监控动态目标检测方法。通过运动矢量空间编码方法进行背景建模,采用基于卡尔曼滤波器的CamShift目标跟踪算法检测目标,并对下一时刻目标的搜索范围和出现位置进行估计,通过CamShift结合估计结果搜索目标的真实位置,并对目标搜索范围、加速度和速度进行修正,完成视频监控动态目标的检测。实验结果表明,本文方法的视频监控动态目标检测效率高、检测结果准确率高,验证了本文方法具有较强应用性。

关键词: 运动矢量空间编码, 视频监控, 背景建模, 动态目标检测

Abstract:

In the current video monitoring dynamic target detection process, the pre-estimation of the target position is ignored, which leads to a long detection time and a large detection error. To solve this problem, a dynamic target detection method for video surveillance based on motion vector space coding is proposed. Motion vector space coding method is applied for background modeling, CamShift target tracking algorithm based on kalman filter is used to detect the target, and estimate the search scope and the location of the target at the next appearing moment. CamShift is combined with estimation results to search the true location, correct the target search scope, acceleration and speed, thus, completing the video monitoring dynamic target detection. The experimental results show that the proposed method has high efficiency in detecting dynamic targets and high accuracy in detecting results.

Key words: motion vector space coding, video surveillance, background modeling, dynamic target detection

中图分类号: 

  • TP391

图1

不同方法的测试结果"

图2

不同方法的检测准确率"

1 田合雷, 丁胜, 于长伟, 等. 基于目标检测及跟踪的视频摘要技术研究[J]. 计算机科学, 2016, 43(11):297-299, 312.
Tian He-lei, Ding Sheng, Yu Chang-wei, et al. Research of video abstraction based on object detection and tracking[J]. Computer Science, 2016, 43(11):297-299, 312.
2 李均利, 尹宽, 储诚曦, 等. 视频目标跟踪技术综述[J]. 燕山大学学报, 2019, 43(3):251-262.
Li Jun-li, Yin Kuan, Chu Cheng-xi, et al. Review of video target tracking technology[J]. Journal of Yanshan University, 2019, 43(3):251-262.
3 刘艳波. 一种用于传感器网络的目标检测方法改进研究[J]. 计算机仿真, 2016, 33(9):317-320.
Liu Yan-bo. A used to improve target detection method of sensor network research[J]. Computer Simulation, 2016, 33(9):317-320.
4 龚畅, 王华君, 李荣,等. 基于状态依赖检测的视频运动目标轨迹跟踪算法[J]. 现代电子技术, 2016, 39(7):51-56.
Gong Chang, Wang Hua-jun, Li Rong, et al. Video moving target trail tracking algorithm based on state dependence detection[J]. Modern Electronics Technique, 2016, 39(7):51-56.
5 张谢华, 赵小虎. 煤矿智能视频监控中的运动目标检测研究[J]. 工矿自动化, 2016, 42(4):31-36.
Zhang Xie-hua, Zhao Xiao-hu. Research on moving target detection in coal mine intelligent video monitoring[J]. Industry and Mine Automation, 2016, 42(4):31-36.
6 杨丹, 戴芳. 运动目标检测的ViBe算法改进[J]. 中国图象图形学报, 2018, 23(12):1813-1828.
Yang Dan, Dai Fang. Improved ViBe algorithm for detection of moving objects[J]. Journal of Image and Graphics, 2018, 23(12):1813-1828.
7 陈欣佳, 刘艳霞, 洪晓斌, 等. 基于SSD-CF的无人艇目标检测跟踪方法[J]. 中国测试, 2019, 45(2):145-150.
Chen Xin-jia, Liu Yan-xia, Hong Xiao-bin, et al. Unmanned boat target detection and tracking method based on SSD-CF[J]. China Measurement and Testing Technology, 2019, 45(2):145-150.
8 杨海林, 蔡启忡, 薛圣利,等. 基于改进的VIBE算法在铁路智能视频监控入侵检测的研究[J]. 科学技术与工程, 2016, 16(21):80-82, 87.
Yang Hai-lin, Cai Qi-zhong, Xue Sheng-li, et al. Research on railway video monitoring and moving target detection based on improved ViBE algorithm[J]. Science Technology and Engineering, 2016, 16(21):80-82, 87.
9 赵振杰, 方勇纯, 张雪波. 一种基于筛选机制的快速概率占据图目标定位算法[J]. 机器人, 2016, 38(1):17-26.
Zhao Zhen-jie, Fang Yong-chun, Zhang Xue-bo. A sifting mechanism based object localization algorithm for fast probabilistic occupancy map[J]. Robot, 2016, 38(1):17-26.
10 何松华, 胡霞, 张军. 弹载宽带相控阵雷达高度目标检测的通道级STAP方法[J]. 信号处理, 2016, 32(5):528-535.
He Song-hua, Hu Xia, Zhang Jun. Channel-level STAP method for lofty target detection of missile-borne wideband phased-array radar[J]. Journal of Signal Processing, 2016, 32(5):528-535.
[1] 李志慧, 夏英集, 曲昭伟, 任景琛. 视频监控的数据驱动背景模型[J]. 吉林大学学报(工学版), 2017, 47(4): 1286-1294.
[2] 陈大伟, 刘海龙, 李金屏. 复杂静态背景下多移动目标实时检测系统的FPGA实现[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 287-290.
[3] 傅博, 李文辉, 陈博, 王聪, 王莹. 基于加权光流能量的异常行为检测[J]. 吉林大学学报(工学版), 2013, 43(06): 1644-1649.
[4] 冯杰,陈耀武. 基于H.264压缩域的背景建模与前景对象分割[J]. 吉林大学学报(工学版), 2011, 41(01): 239-0243.
[5] 王殿海,胡宏宇,李志慧,曲昭伟. 违章停车检测与识别算法[J]. 吉林大学学报(工学版), 2010, 40(01): 42-0046.
[6] 赵宏伟,冯嘉,臧雪柏,宋波涛. 一种实用的运动目标检测和跟踪算法[J]. 吉林大学学报(工学版), 2009, 39(增刊2): 386-0390.
[7] 胡宏宇,李志慧,曲昭伟,王殿海. 基于上下文的交通事件表达与识别[J]. 吉林大学学报(工学版), 2009, 39(增刊2): 158-0162.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!