【摘要】 提出基于纹理特征及统计学模型的背景提取方法来完成背景的稳健提取和实时更新。根据灰度-基元共生矩阵建立图像的纹理特征描述并据此初步判断某一区域是否有运动目标,进一步基于混合高斯分布模型进行背景像素判别和背景提取,最后应用多分辨率计算方法提高算法实现效率。实验结果表明,该方法能够更好地适应光照条件的不同变化,特别适用于交通视频监控时图像亮度变化和路口交通繁忙的实际情况,能够准确地获取背景图像,计算时间仅为原来的1/4,从而满足了背景提取算法在复杂环境下的稳健性和实时自适应更新的要求。更多还原

【Abstract】 A new background image extract method is put forward based on textural and statistical features and the textural description of the image is established with grayscale-primitive cooccurence matrix.The textural feature is used to roughly evaluate the presence of moving targets in a region.Then background pixels are determined according to the mixed Gaussian distribution model,and the background of video sequence is extracted.Finally,the multi-resolution method is introduced to improve the computational efficiency.The experimental results show that the proposed method can allow various changes of lighting conditions,and can extract exact background scenes even in vehicle-packed crossroad.The computation period of the method is 1/4 that of original method.Therefore,the method can better satisfy the requirements of background extraction algorithm for a robust and an adaptive updating in complex environment.更多还原