改进的基于码本模型目标检测算法

刘翔; 杨鑫; 王蕾

doi:10.3788/YJYXS20142906.0997

您当前的位置：

首页 >

文章列表页 >

改进的基于码本模型目标检测算法

成像技术与图像处理 | 更新时间：2020-08-12

- 改进的基于码本模型目标检测算法
- Object detection algorithm based on improved codebook model
- 液晶与显示 2014年29卷第6期页码：997-1002
- 作者机构：
  
  1. 武汉科技大学工程训练中心,湖北武汉,430065
  2. 中国电力工程顾问集团中南电力设计院, 湖北武汉 430071
- 作者简介：
- 基金信息：
- DOI：10.3788/YJYXS20142906.0997
  中图分类号： TP391.4
- 收稿日期：2013-12-18，
  
  修回日期：2014-03-27，
  
  纸质出版日期：2014-12-05
- 稿件说明：
移动端阅览
刘翔, 杨鑫, 王蕾. 改进的基于码本模型目标检测算法[J]. 液晶与显示, 2014,29(6): 997-1002

LIU Xiang, YANG Xin, WANG Lei. Object detection algorithm based on improved codebook model[J]. , 2014,29(6): 997-1002
刘翔, 杨鑫, 王蕾. 改进的基于码本模型目标检测算法[J]. 液晶与显示, 2014,29(6): 997-1002 DOI： 10.3788/YJYXS20142906.0997.

LIU Xiang, YANG Xin, WANG Lei. Object detection algorithm based on improved codebook model[J]. , 2014,29(6): 997-1002 DOI： 10.3788/YJYXS20142906.0997.

摘要

为克服基于码本模型的目标检测算法在光照变化条件下对检测结果产生的影响，提出了一种融合卡尔曼滤波思想的改进码本算法。该方法在计算图像像素亮度变化时选用了YUV颜色空间，使空间坐标轴与亮度变化方向一致，使亮度变化的计算量平均下降了44.9%。同时在建立码本模型时为每个像素初始化一个卡尔曼滤波器，该滤波器利用前后两帧图像亮度信息预测与修正当前像素值，对光照变化有较好的适应性。仿真实验结果表明，该算法与YUV码本模型、RGB码本模型以及GMM算法相比在亮度变化的条件下对噪声的抑制作用更强，体现出更好的自适应性。

Abstract

In order to overcome the influence of illumination changes on detecting results by using codebook-based object detection algorithm

an improved codebook algorithm that fuses Kalman filtering is proposed in this paper. The algorithm calculates the pixel brightness change in YUV colour space

which corresponds brightness changes with spatial coordinates and makes the calculation of brightness process fallen by an average of 44.9%. Meanwhile

it initializes a Kalman filter for each pixel at the time when the codebook model is established and the filter uses two successive image's brightness information to predict and correct current pixel value. This method has good adaptability on brightness changes. The experimental results show that this algorithm reflects a better adaptability under the condition of brightness changes

compared with ordinary YVU codebook model

RGB codebook model and GMM method.

关键词

Keywords

references

Barron J,Fleet D.Performance of optical flow techniques[J].International Journal of Computer Vision,1994,12(1):42-77.[2] 张水发,丁欢,张文生. 双模型背景建模与目标检测研究[J]. 计算机研究与发展, 2011,48(11):1983-1990. Zhang S F, Ding H, Zhang W S. Background modeling and object detection based on two-model[J].Journal of Computer Research and Development, 2011,48(11):1983-1990.(in Chinese)[3] Lipton A,Fujiyoshi H,Ptail R S. Moving target classification and tracking from real-time video[C].Proc. IEEE Workshop on Application of Computer Vision,1998,17(9):8-14.[4] 吴君钦,刘昊,罗勇. 静态背景下的运动目标检测算法[J]. 液晶与显示, 2012,27(5):682-686. Wu J Q, Liu H, Luo Y. Algorithm of moving object detection in static background[J].Chinese Journal of Liquid Crystals and Displays, 2012,27(5):682-686.(in Chinese)[5] 丁雪梅,王维雅,黄向东. 基于差分和特征不变量的运动目标检测与跟踪[J]. 光学精密工程, 2007,15(4):570-576. Ding X M, Wang W Y, Huang X D. New method for detecting and tracking of moving target based on difference and invariant[J].Optics and Precision Engineering, 2007,15(4):570-576.(in Chinese)[6] 代科学,李国辉,涂丹,等. 监控视频运动目标检测减背景技术的研究现状和展望[J]. 中国图象图形学报, 2006,11(7):919-927. Dai K X, Li G H, Tu D, et al.Prospects and current studies on background subtraction techniques for moving objects detection from surveillance video[J].Journal of Image and Graphics, 2006,11(7):919-927.(in Chinese)[7] 张红颖,胡正. CenSurE特征和时空信息相结合的运动目标检测[J]. 光学精密工程, 2013,21(9):2452-2463. Zhang H Y, Hu Z. Moving object detection in combination of CenSurE and spatial-temporal information[J].Optics and Precision Engineering,2013,21(9):2452-2463.(in Chinese)[8] 袁宝红,张德祥,张玲君. 基于OpenCV的视频运动目标检测与跟踪[J]. 计算机系统应用, 2013,22(5):90-93. Yuan B H, Zhang D X, Zhang L J.Detecting and tracking of moving target in video sequence based on OpenCV[J].Computer Systems and Applications, 2013,22(5):90-93.(in Chinese)[9] 康晓晶,吴谨. 基于高斯背景建模的目标检测技术[J]. 液晶与显示, 2010,25(3):454-459. Kang X J, Wu J. Object detecting technology based on Gauss background modeling[J].Chinese Journal of Liquid Crystals and Displays, 2010,25(3):454-459.(in Chinese)[10] Stauffer C,Grimson W. Adaptive background mixture models for real-time tracking[C] //Int. Conf. Computer Vision and Pattern Recongnition,1999,2:246-252.[11] Kim K,Chalidabhongse T H,Hardwood D,et al.Background modeling and subtraction by codebook construction[C]//Proc. IEEE Int. Conf. on Image Processing,Singapore,2004:3061-3064.[12] 黄进,金炜东,秦娜. 基于三维高斯混合码本模型的运动目标检测算法[J]. 西南交通大学学报, 2012,47(4):662-668. Huang J, Jin W D, Qin N. Moving objects detection algorithm based on three-dimensional gaussian mixture codebook model[J].Journal of Southwest Jiaotong University,2012,47(4):662-668.(in Chinese)[13] 杨冰,张为,王猛. 基于Kalman滤波器运动目标跟踪的火灾监测方法[J]. 信息技术, 2013(7):101-105. Yang B, Zhang W, Wang M. Fire detection method based on moving target tracking with Kalman filter[J].Information technology,2013(7):101-105.(in Chinese)[14] 赵其杰,屠大维,高健,等. 基于Kalman滤波的视觉预测目标跟踪及其应用[J]. 光学精密工程, 2008,16(5):937-942. Zhao Q J, Tu D W, Gao J et al.Kalman filter based vision predicting and object tracking method and its application[J].Optics and Precision Engineering,2008,16(5):937-942.(in Chinese)[15] 杨金显,袁赣南. 基于MIMU／GPS的组合导航设计及实验[J]. 光学精密工程, 2008,16(2):285-294. Yang J X, Yuan G N. Design and experiment for INS based on MIMU/GPS[J].Optics and Precision Engineering,2008,16(2):285-294.(in Chinese)

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于压缩感知的变尺度目标跟踪技术