结合边缘纹理和抽样推断的自适应阴影检测算法

姜柯; 李艾华; 苏延召

doi:10.7652/xjtuxb201302007

您当前的位置：

首页 >

文章列表页 >

结合边缘纹理和抽样推断的自适应阴影检测算法

更新时间：2025-07-09

- 结合边缘纹理和抽样推断的自适应阴影检测算法
- An Adaptive Shadow Detection Algorithm Using Edge Texture and Sampling Deduction
- 西安交通大学学报 2013年47卷第2期页码：39-46
- 作者机构：
  
  第二炮兵工程大学502教研室,西安,710025
- 作者简介：
- 基金信息：
  
  : 2012-05-22。作者简介: 姜柯(1985—),男,博士生;李艾华(通信作者),男,教授,博士生导师。基金项目: 国家自然科学基金资助项目(61132008)
- DOI：10.7652/xjtuxb201302007
  中图分类号： TP391
- 网络首发：2013-02-10，
  
  纸质出版：2013
- 稿件说明：
移动端阅览
姜柯, 李艾华, 苏延召. 结合边缘纹理和抽样推断的自适应阴影检测算法[J]. 西安交通大学学报, 2013,47(2):39-46.

An Adaptive Shadow Detection Algorithm Using Edge Texture and Sampling Deduction[J]. 2013, 47(2): 39-46.
姜柯, 李艾华, 苏延召. 结合边缘纹理和抽样推断的自适应阴影检测算法[J]. 西安交通大学学报, 2013,47(2):39-46. DOI： 10.7652/xjtuxb201302007.

An Adaptive Shadow Detection Algorithm Using Edge Texture and Sampling Deduction[J]. 2013, 47(2): 39-46. DOI： 10.7652/xjtuxb201302007.

摘要

为改进阴影检测的准确度和场景自适应能力

提高运动目标检测精度

设计了一种自适应的阴影检测算法。该算法利用候选前景与原始背景的Y、U、V分量变化比率来检测阴影像素

并结合全局边缘纹理特征及抽样推断方法来估计检测阈值。算法能自动完成阈值估计及阴影判别过程而无需人工干预

并可自动适应各种光线条件

具有较强的鲁棒性。对不同光线环境的标准视频检测实验表明

该算法在精度和实时性上均有所提升

阴影检测综合性能指标达到了94%以上。

Abstract

An adaptive shadow detection algorithm is proposed to improve the accuracy and scene adaptive capacity of the shadow detection and to raise the effect of moving object detection. The change ratios of YUV components between candidate foreground and original background are used to detect shadow pixels

and the global edge texture and sampling deduction methods are employed to estimate the detection threshold values. The algorithm automatically complete the processes of both thresholds estimation and shadow discriminant without any manual intervention

so the algorithm is adaptive to different light conditions and has a strong robustness. Experiment results on standard videos with different lighting conditions show that both the accuracy and stability are raised by the proposed algorithm and the average comprehensive index of the proposed algorithm can reach more than 94%.

关键词

Keywords

references

CANDAMO J, SHREVE M, GOLDGOF D B, et al. Understanding transit scenes: a survey on human behavior-recognition algorithms [J]. IEEE Transactions on Intelligent Transportation Systems, 2010, 11(1): 206-224.

SANIN A, SANDERSON C, LOVELL B C. Shadow detection: a survey and comparative evaluation of recent methods [J]. Pattern Recognition, 2012, 45(4): 1684-1695.

HSIEH J W, HU W F, CHANG C J, et al. Shadow elimination for effective moving object detection by Gaussian shadow modeling [J]. Image and Vision Computing, 2003, 21(6): 505-516.

CUCCHIARA R, GRANA C, PICCARDI M, et al. Detecting moving objects, ghosts, and shadows in video streams [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(10):1337-1342.

HUANG J B, CHEN C S. Moving cast shadow detection using physics-based features [C]∥Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2009: 2310-2317.

LEONE A, DISTANTE C. Shadow detection for moving objects based on texture analysis [J]. Pattern Recognition, 2007, 40(4): 1222-1233.

SANIN A, SANDERSON C, LOVELL B C. Improved shadow removal for robust person tracking in surveillance scenarios [C]∥Proc of the 20th International Conference on Pattern Recognition. Piscataway, NJ, USA: IEEE, 2010: 141-144.

LEONE A, DISTANTE C. Shadow detection for moving objects based on texture analysis [J]. Pattern Recognition, 2007, 40(4): 1222-1233.

JOSHI A J, PAPANIKOLOPOULOS N P. Learning to detect moving shadows in dynamic environments [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(11): 2055-2063.

MARTEL-BRISSON N, ZACCARIN A. Kernel-based learning of cast shadows from a physical model of light sources and surfaces for low-level segmentation [C]∥Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2008: 1-8.

CELIK H, ORTIGOSA A M, HANJALIC A, et al. Autonomous and adaptive learning of shadows for surveillance [C]∥Proc of the 9th International Workshop on Image Analysis for Multimedia Interactive Services. Piscataway, NJ, USA: IEEE, 2008: 59-62.

CHOI J, YOO Y J, CHOI J Y. Adaptive shadow estimator for removing shadow of moving object [J]. Computer Vision and Image Understanding, 2010, 114(9): 1017-1029.

KIM K, CHALIDABHONGSE T H, HARWOOD D, et al. Real-time foreground-background segmentation using codebook model [J]. Real-Time Imaging, 2005, 11(3): 172-185.

刘宏, 李锦涛, 刘群, 等. 融合颜色和梯度特征的运动阴影消除方法 [J]. 计算机辅助设计与图形学学报, 2007, 19(10): 1279-1285.

LIU Hong, LI Jintao, LIU Qun, et al. Moving cast shadow elimination based on color and gradient features [J]. Journal of Compute-Aided Design and Graphics, 2007, 19(10): 1279-1285.

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

自然场景下运动目标检测与阴影剔除方法

超临界二氧化碳向心透平轮背间隙内风阻损失及流动特性研究

离子液体改性燃料的电流体动力学效应研究

采用试验设计方法的第三代CO2气体箔轴承箔片几何参数敏感性分析

EBSILON软件在热电联产系统优化中的应用综述