计算机科学 ›› 2016, Vol. 43 ›› Issue (6): 294-297.doi: 10.11896/j.issn.1002-137X.2016.06.058

• 图形图像与模式识别 • 上一篇    下一篇

自适应的SILTP算法在运动车辆检测中的研究

李飞,张小洪,赵晨丘,鄢萌   

  1. 重庆大学软件学院 重庆401331,重庆大学软件学院 重庆401331,重庆大学软件学院 重庆401331,重庆大学软件学院 重庆401331
  • 出版日期:2018-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受形状的语义结构表示及其分类学习研究(61173131)资助

Vehicle Detection Research Based on Adaptive SILTP Algorithm

LI Fei, ZHANG Xiao-hong, ZHAO Chen-qiu and YAN Meng   

  • Online:2018-12-01 Published:2018-12-01

摘要: 为了提高复杂背景下运动车辆的检测效率,结合SILTP算法提出了一种自适应的SILTP算法。首先,对运动车辆图像进行二维离散小波变换,提取出两次低通滤波后的图像。其次 ,通过自适应的SILTP算法获得图像的纹理信息。然后,利用高斯混合模型进行背景建模,进而利用新图像的纹理信息动态更新背景。最后,与背景模型进行比较来获得运动车辆。对公路上运动车辆的测试表明,该检测算法在复杂背景尤其是树叶抖动等情况下能够取得较高的检测率,具有良好的自适应性。

关键词: 局部纹理特征,背景建模,车辆检测,自适应SILTP算法

Abstract: This paper presented an adaptive SILTP algorithm based on the SILTP algorithm to improve the efficiency of vehicle detection in complex background.The vehicle detection starts with a two-dimensional discrete wavelet trans-form for the image.The next steps of vehicle detection include extracting the vehicle images’ information texture with the adaptive SILTP algorithm,using Gauss mixture model for background modeling,and using the texture information of the new image to update background dynamically. Finally,moving vehicle is obtained by comparing with the background model.The results demonstrate that this detection algorithm can achieve high detection efficiency under a complex background ,and has strong adaptability.

Key words: Local texture characteristics,Background modeling,Vehicle detection,Adaptive SILTP algorithm

[1] Liu H,Hou X.Moving Detection Research of Background Frame Difference Based on Gaussian Model[C]∥International Confe-rence on Computer Science and Service System.IEEE,2012:258-261
[2] Yan L,Zhi-jian J,Gao J W,et al.Robot fish detection based on a combination method of three-frame-difference and background subtraction[C]∥Control and Decision Conference,Chinese.IEEE,2014:3905-3909
[3] Hegenbart S,Uhl A.A scale-adaptive extension to methodsbased on LBP using scale-normalized Laplacian of Gaussian extrema in scale-space[C]∥2014 IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP).IEEE,2014:4319-4323
[4] Huang Y,Ou Z,Hsieh H,et al.A rapid texture-based moving object detection method[C]∥2011 8th Asian Control Confe-rence (ASCC).IEEE,2011:1205-1209
[5] Qin Y,Tang Y.Dynamic texture recognition based on multiple statistical features with LBP/WLD[C]∥2011 International Conference on Computer Science and Network Technology (ICCSNT).IEEE,2011:957-960
[6] Nguyen D T,Ogunbona P,Li W.Human detection with contour-based local motion binary patterns[C]∥2011 18th IEEE International Conference on Image Processing (ICIP).IEEE,2011:3609-3612
[7] Liao S,Zhao G,Kellokumpu V,et al.Modeling pixel process with scale invariant local patterns for background subtraction in complex scenes[C]∥IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2010:1301-1306
[8] Oualla M,Sadiq A,Mbarki S.A survey of Haar-Like feature representation[C]∥2014 International Conference on Multimedia Computing and Systems (ICMCS).IEEE,2014:1101-1106
[9] Dos Santos V R,Pilla M,Reiser R,et al.Int-Haar:Improving Precision of the Haar Interval Wavelet Extension[C]∥2013 2nd Workshop-School on Theoretical Computer Science (WEIT).IEEE,2013:92-96
[10] Yin H,Yang H,Su H,et al.Dynamic background subtraction based on appearance and motion pattern[C]∥2013 IEEE International Conference on Multimedia and Expo Workshops (ICMEW).IEEE,2013:1-6
[11] Wang H,Sang N,Yan Y.Real-Time Tracking Combined withObject Segmentation[C]∥2014 22nd International Conference on IEEE Pattern Recognition (ICPR).2014:4098-4103
[12] Deng G,Guo K.Self-adaptive background modeling researchbased on change detection and area training[C]∥2014 IEEE Workshop on Electronics,Computer and Applications.2014:59-62
[13] Yuan G,Gao Y,Xu D,et al.A Moving Objects Detection Me-thod Based on a Combination of Im-proved Local Binary Pattern Texture and Hue[M].Springer Berlin Heidelberg,2011:261-268

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!