激光与光电子学进展, 2020, 57 (2): 021002, 网络出版: 2020-01-03
基于背景抑制和前景更新的显著性检测 下载: 870次
Saliency Detection Based on Background Suppressing and Foreground Updating
图像处理 显著性检测 背景抑制 前景更新 贝叶斯框架 image processing saliency detection background suppressing foreground updating Bayesian framework
摘要
针对现有显著性检测方法存在背景抑制效果差和前景分辨率低的问题,提出一种基于背景抑制和前景更新的显著性检测方法。首先利用MR(manifold ranking)算法计算背景先验图,通过超像素分割算法提取的边缘超像素来构建背景模板,计算出稀疏重构图,点乘运算获得高质量的背景抑制图;同时利用高斯混合模型计算颜色先验图,通过CA(Cellular Automata)模型计算多尺度下的颜色优化图,点乘运算获得高精度的前景更新图;最后在贝叶斯框架下融合背景抑制图和前景更新图获得满足人眼要求的最终显著图。在2个公开数据集上的实验结果表明,本文算法能够获得背景抑制效果明显、前景分辨率高的显著图,并且其准确率、F-measure、平均绝对误差(MAE)等指标均优于其他8种对比算法。
Abstract
To address the poor background suppression and low foreground resolution in existing saliency detection methods, we propose a saliency detection algorithm based on background suppressing and foreground updating. First, the manifold ranking (MR) algorithm is used to calculate the background prior map, and the super-pixel segmentation algorithm for extracting edge super-pixels is used to construct a background template and calculate a sparse reconstruction map. Next, we obtain the high-quality suppressed background map through point multiplication. Subsequently, we use a Gaussian mixture model to calculate the color prior map, a CA (Cellular Automata) model to calculate the multiscale color optimization map, and point multiplication to obtain the high-precision updated foreground map. Finally, under the Bayesian framework, the suppressed background map and updated foreground map are fused to obtain the final saliency map that meets the requirements of the human eye. Experimental results on two public datasets show that the proposed algorithm can obtain a saliency map with good background suppression and high foreground resolution. Moreover, it provides improved precision, F-measure, mean absolute error, and other indicators relative to eight other algorithms used for comparison.
崔丽群, 陈晶晶, 齐博华, 叶晋. 基于背景抑制和前景更新的显著性检测[J]. 激光与光电子学进展, 2020, 57(2): 021002. Cui Liqun, Chen jingjing, Qi Bohua, Ye Jin. Saliency Detection Based on Background Suppressing and Foreground Updating[J]. Laser & Optoelectronics Progress, 2020, 57(2): 021002.