A Video Saliency Detection Model in Compressed Domain
A Video Saliency Detection Model in Compressed Domain
复制标题
DOI：
10.1109/tcsvt.2013.2273613
复制
发表时间：
2014
影响因子：
8.4
通讯作者：
Yuming Fang;Weisi Lin;Zhenzhong Chen;Chia-Ming Tsai;Chia-Wen Lin
中科院分区：
文献类型：
--
作者：
Yuming Fang;Weisi Lin;Zhenzhong Chen;Chia-Ming Tsai;Chia-Wen Lin
显著性检测被广泛用于提取图像中的感兴趣区域以用于各种图像处理应用。近年来，针对未压缩（像素）域的视频提出了许多显著性检测模型。然而，互联网上的视频通常存储在压缩域中，例如MPEG2、H.264和MPEG4 Visual。本文提出了一种新的基于特征对比度的压缩域视频显著性检测模型。从视频码流的离散余弦变换系数和运动矢量中提取亮度、颜色、纹理和运动四种特征。基于亮度、颜色和纹理特征计算未预测帧（I帧）的静态显著性图，而通过运动特征计算预测帧（P和B帧）的运动显著性图。设计了一种新的联合收割机，将静态显著图和运动显著图结合起来，得到每帧视频的最终显著图。由于直接在压缩域中导出的特征，该模型可以有效地预测视频帧的显著区域。在公共数据库上的实验结果表明，该模型在压缩域具有上级性能。
Saliency detection is widely used to extract regions of interest in images for various image processing applications. Recently, many saliency detection models have been proposed for video in uncompressed (pixel) domain. However, video over Internet is always stored in compressed domains, such as MPEG2, H.264, and MPEG4 Visual. In this paper, we propose a novel video saliency detection model based on feature contrast in compressed domain. Four types of features including luminance, color, texture, and motion are extracted from the discrete cosine transform coefficients and motion vectors in video bitstream. The static saliency map of unpredicted frames (I frames) is calculated on the basis of luminance, color, and texture features, while the motion saliency map of predicted frames (P and B frames) is computed by motion feature. A new fusion method is designed to combine the static saliency and motion saliency maps to get the final saliency map for each video frame. Due to the directly derived features in compressed domain, the proposed model can predict the salient regions efficiently for video frames. Experimental results on a public database show superior performance of the proposed video saliency detection model in compressed domain.