计算机科学 ›› 2021, Vol. 48 ›› Issue (7): 233-237.doi: 10.11896/jsjkx.200600131

• 计算机图形学&多媒体 • 上一篇    下一篇

基于区域提取与改进 LBP 特征的运动目标检测

辛元雪, 史朋飞, 薛瑞阳   

  1. 河海大学物联网工程学院 江苏 常州213022
  • 收稿日期:2020-06-22 修回日期:2020-08-30 出版日期:2021-07-15 发布日期:2021-07-02
  • 通讯作者: 辛元雪(xinyx@hhu.edu.cn)
  • 基金资助:
    国家自然科学基金(61801168,61801169);江苏省自然科学基金(BK20170305)

Moving Object Detection Based on Region Extraction and Improved LBP Features

XIN Yuan-xue, SHI Peng-fei, XUE Rui-yang   

  1. College of Internet of Things Engineering,Hohai University,Changzhou,Jiangsu 213022,China
  • Received:2020-06-22 Revised:2020-08-30 Online:2021-07-15 Published:2021-07-02
  • About author:XIN Yuan-xue,born in 1987,Ph.D,lecturer.Her main research interests include communication system, information acquisition and processing.
  • Supported by:
    National Natural Science Foundation of China(61801168, 61801169) and Jiangsu Province Natural Science Foundation(BK20170305).

摘要: 树叶晃动、光照变化等自然场景下的动态背景会影响运动目标检测的准确性,区分动态背景和前景目标的变化是复杂场景下运动目标检测的首要任务。针对现有的前景提取算法逐点提取前景从而导致计算资源浪费的问题,提出了一种区域提取与改进LBP(Local Binary Patterns)纹理特征相结合的运动目标检测算法。首先,将图像分为大小相等的图像块,利用各图像块的统计特性建立核密度估计(Kernel Density Estimation,KDE)模型,并用KDE模型估计出前景区域。然后,计算前景块中所有像素点的改进 LBP 纹理特征直方图。最后,通过直方图匹配提取所有的前景像素实现目标的精确提取,并用概率模型更新背景。实验结果表明,该方法在快速提取运动目标前景区域的同时能够消除大部分动态背景产生的干扰,相比传统算法更适用于自然场景下的运动目标检测。

关键词: KDE, LBP纹理特征, 动态背景, 区域提取, 运动目标检测

Abstract: Detection accuracy of moving object is dramatically affected by the dynamic natural background,for instance,the shaking leaves and varying illumination.Therefore,it is essential to distinguish between the dynamic background and the foreground moving object.The existing foreground extraction algorithm extracts the foreground point by point,which leads to a waste of computing resources.This paper proposed a novel moving object detection algorithm based on region extraction and improved Local Binary Patterns (LBP).First,the image is divided into several image blocks of same size,and the Kernel Density Estimation (KDE) model is established according to the statistical characteristics of these image blocks.The foreground region is estimated by the KDE model.Then,the improved LBP texture feature histogram of all pixels in the foreground block is obtained.By ma-tching the histogram,all the foreground pixels are extracted,and the background is updated with a probabilistic model.The experimental results show that the proposed method can quickly extract the foreground region of moving target and eliminate most of the interference caused by dynamic background.Compared with the traditional algorithm,the proposed method is more suitable for moving object detection in natural scenes.

Key words: Dynamic background, Kernel density estimation, Local binary patterns texture features, Moving object detection, Region extraction

中图分类号: 

  • TP391.41
[1]JAVED S,MAHMOOD A,ALMAADEED S,et al.Moving Object Detection in Complex Scene Using Spatiotemporal Structured-Sparse RPCA[J].IEEE Transactions on Image Proces-sing,2019,28(2):1007-1022.
[2]REZAEI B,OSTADABBAS S.Moving Object DetectionThrough Robust Matrix Completion Augmented With Objectness[J].IEEE Journal of Selected Topics in Signal Processing,2018,12(6):1313-1323.
[3]ELTANTAWY A,SHEHATA M S.An Accelerated Sequential PCP-Based Method for Ground-Moving Objects Detection From Aerial Videos[J].IEEE Transactions on Image Processing,2019,28(12):5991-6006.
[4]ZHENG P,BAI H Y,LI Z M,et al.Design of accurate detection and tracking algorithm for moving target under jitterinterfe-rence[J].Chinese Journal of Scientific Instrument,2019,40(11):90-98.
[5]HAO X L,LIU W,NIU B N,et al.High-Efficiency Detection Algorithm for Moving Targets Based on Adaptive Learning Rate[J].Journal of University of Electronic Science and Technology of China,2020,49(1):123-130.
[6]SENGAR S S,MUKHOPADHYAY S. Moving object area detection using normalized self-adaptive optical flow[J].Journal for Light and Electronoptic,2016,127(16):6258-6267.
[7]XI Y,JIA K,SUN Z,et al.A Moving Object Detection Algorithm Based on a Combination Optical Flow and Edge Detection[C]//Intelligent Data Analysis.2016:130-137.
[8]GUO C,ZHANG L.A Novel Multiresolution SpatiotemporalSaliency Detection Model and Its Applications in Image and Vi-deo Compression[J].IEEE Transactions on Image Proces-sing,2010,19(1):185-198.
[9]GUO Y,LI Z,LIU Y,et al.Video Object Extraction Based on Spatiotemporal Consistency Saliency Detection[J].IEEE Access,2018,6:35171-35181.
[10]ABBASIFARD M R,NADERI H,ALAMDARI O I,et al.Efficient Indexing For Past and Current Position of Moving Objects on Road Networks[J].IEEE Transactions on Intelligent Transportation Systems,2018,19(9):2789-2800.
[11]LU J,WANG Z,ZHU J.Space-time multiscale based moving object detection method[J].Journal of Northwestern Polytechnical University,2017,35(1):98-102.
[12]PANDO A G,MURGUIA M I.Analysis and Trends on Moving Object Detection Algorithm Techniques[J].IEEE Latin America Transactions,2019,17(11):1771-1783.
[13]ELHARROUSS O,MOUJAHID D,TAIRI H.Moving objectdetection with an adaptive background model[C]//Intelligent Systems and Computer Vision.2017.
[14]ROMERO J D,LADO M J,MENDEZ A J,et al.A Background Modeling and Foreground Detection Algorithm Using Scaling Coefficients Defined With a Color Model Called Lightness-Red-Green-Blue[J].IEEE Transactions on Image Processing,2018,27(3):1243-1258.
[15]STAUFFER C,GRIMSON W E.Adaptive background mixture models for real-time tracking[C]//Computer Vision and Pattern Recognition.1999:246-252.
[16]BARNICH O,VAN DROOGENBROECK M.ViBe:A Universal Background Subtraction Algorithm for Video Sequences[J].IEEE Transactions on Image Processing,2011,20(6):1709-1724.
[17]KRYJAK T,KOMORKIEWICZ M,GORGON M,et al.Real-time implementation of foreground object detection from a mo-ving camera using the ViBe algorithm[J].Computer Science and Information Systems,2014,11(4):1617-1637.
[18]TAO H,LU X.Automatic smoky vehicle detection from traffic surveillance video based on vehicle rear detection and multi-feature fusion[J].IET Intelligent Transport Systems,2019,13(2):252-259.
[19]NIRANJIL K A,SURESHKUMAR C.Background Subtraction in Dynamic Environment based on Modified Adaptive GMM with TTD for Moving Object Detection[J].Journal of Electrical Engineering & Technology,2015,10(1):372-378.
[20]EVANGELIO R H,PATZOLD M,KELLER I,et al.Adaptively Splitted GMM With Feedback Improvement for the Task of Background Subtraction[J].IEEE Transactions on Information Forensics and Security,2014,9(5):863-874.
[21]ELGAMMAL A,HARWOOD D,DAVIS L S,et al.Non-parametric Model for Background Subtraction[C]//European Conference on Computer Vision.2000:751-767.
[22]LIU C,YUEN P C,QIU G,et al.Object motion detection using information theoretic spatio-temporal saliency[J].Pattern Re-cognition,2009,42(11):2897-2906.
[23]HEIKKILA M,PIETIKAINEN M.A texture-based method for modeling the background and detecting moving objects[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(4):657-662.
[24]DING Y,LI W H,FAN J T,et al.Robust moving object detection under complex background[J].Computer Science and Information Systems,2010,7(1):201-210.
[25]CHAKRABORTI T,CHATTERJEE A.A novel binary adap-tive weight GSA based feature selection for face recognition using local gradient patterns,modified census transform,and local binary patterns[J].Engineering Applications of Artificial Intelligence,2014,33:80-90.
[26]KIM B,CHOI J,JOO S,et al.Errata:Haar-like compact local binary pattern for illumination-robust feature matching[J].Journal of Electronic Imaging,2012,21(4):49801-49801.
[27]PARCA G,TEIXEIRA P,TEIXEIRA A,et al.All-optical image processing and compression based on Haar wavelet transform[J].Applied Optics,2013,52(12):2932-2939.
[28]XUE G,SUN J,SONG L.Dynamic background subtractionbased on spatial extended center-symmetric local binary pattern[C]//IEEE International Conference on Multimedia & Expo.IEEE,2010.
[29]ZHANG E,LI Y,DUAN J.Moving object detection based on confidence factor and cslbp features[J].The Imaging Science Journal,2016,64(5):253-261.
[30]GOYAL K,SINGHAI J.Texture-based self-adaptive movingobject detection technique for complex scenes[J].Computers & Electrical Engineering,2016,70:275-283.
[1] 金华, 朱靖宇, 王昌达.
视频隐私保护技术综述
Review on Video Privacy Protection
计算机科学, 2022, 49(1): 306-313. https://doi.org/10.11896/jsjkx.201200047
[2] 祝轩, 王磊, 张超, 梅东锋, 薛珈萍, 曹晴雯.
基于连续性约束背景模型减除的运动目标检测
Moving Object Detection Based on Continuous Constraint Background Model Deduction
计算机科学, 2019, 46(6): 311-315. https://doi.org/10.11896/j.issn.1002-137X.2019.06.047
[3] 唐佳林,郑杰锋,李熙莹,苏秉华.
航拍视频中运动目标检测算法研究
Research on Detecting Algorithm of Moving Target in Aerial Video
计算机科学, 2017, 44(Z11): 175-177. https://doi.org/10.11896/j.issn.1002-137X.2017.11A.036
[4] 张文雅,徐华中,罗杰.
基于ViBe的复杂背景下的运动目标检测
Moving Objects Detection under Complex Background Based on ViBe
计算机科学, 2017, 44(9): 304-307. https://doi.org/10.11896/j.issn.1002-137X.2017.09.057
[5] 任典元,王文伟,马强.
基于颜色和局部二值相似模式的背景减除
Background Subtraction Based on Color and Local Binary Similarity Pattern
计算机科学, 2016, 43(3): 296-300. https://doi.org/10.11896/j.issn.1002-137X.2016.03.055
[6] 王思思,任世卿.
一种改进的基于混合高斯模型的运动目标检测算法
Improved Moving Target Detection Algorithm Based on Gaussian Mixture Model
计算机科学, 2015, 42(Z11): 173-174.
[7] 张笙,严云洋,李郁峰.
热红外与可见光视频融合的运动目标检测
Moving Target Detection Using Fusion of Visual and Thermal Video
计算机科学, 2015, 42(8): 86-89.
[8] 范文超,李晓宇,魏 凯,陈兴林.
基于改进的高斯混合模型的运动目标检测
Moving Target Detection Based on Improved Gaussian Mixture Model
计算机科学, 2015, 42(5): 286-288. https://doi.org/10.11896/j.issn.1002-137X.2015.05.058
[9] 杨国亮,周丹,张进辉.
基于SILTP纹理信息的运动目标检测算法
Moving Object Detection Algorithm Using SILTP Texture Information
计算机科学, 2014, 41(4): 302-305.
[10] 胡小冉,孙涵.
一种新的基于ViBe的运动目标检测方法
Novel Moving Object Detection Method Based on ViBe
计算机科学, 2014, 41(2): 149-152.
[11] 田洪金,战荫伟.
基于自适应分块和SSIM的运动目标检测
Moving Object Detection Based on Adaptive Image Blocking and SSIM
计算机科学, 2014, 41(2): 119-122.
[12] 邹月娴,霍佳森,刘吉,李奕,邓文军.
基于特征融合的WCE图像检索
WCE Image Retrieval by Using Fused Feature
计算机科学, 2013, 40(Z11): 320-324.
[13] 瞿中,张亢,乔高元.
MB-LBP特征提取和粒子滤波相结合的运动目标检测与跟踪算法研究
Research on Algorithm of Moving Target Detection and Tracking Based on MB-LBP Feature Extraction and Particle Filter
计算机科学, 2013, 40(12): 304-307.
[14] 张明,孟丽丽,刘丽红,齐妙.
基于分块和改进粒子滤波的运动目标检测方法
Approach of Moving Object Detection Based on Image Blocks and Improved Particle Filter Algorithm
计算机科学, 2012, 39(11): 261-263.
[15] 林庆,徐柱,王士同,詹永照.
HSV自适应混合高斯模型的运动目标检测
Moving Objects Detection of Adaptive Gaussian Mixture Models on HSV
计算机科学, 2010, 37(10): 254-256.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!