期刊文献+

基于低秩矩阵二元分解的快速显著性目标检测算法

Efficient salient object detection via low-rank matrix bi-factorization
下载PDF
导出
摘要 近年来,基于矩阵低秩表示模型的图像显著性目标检测受到了广泛关注。在传统模型中通常对秩最小化问题进行凸松弛,但是这种方法在每次迭代中必须执行矩阵奇异值分解(SVD),计算复杂度较高。为此,提出了一种低秩矩阵双因子分解和结构化稀疏矩阵分解联合优化模型,并应用于显著性目标检测。该模型不仅利用低秩矩阵双因子分解和交替方向法(ADM)来降低时间开销,而且引入分层稀疏正则化刻画稀疏矩阵中元素之间的空间关系;此外,所提算法能够无缝集成高层先验知识指导矩阵分解过程。实验结果表明,提出的算法检测性能优于当前主流无监督显著性目标检测算法,且具有较低的时间复杂度。 In recent years,salient object detection via low-rank recovery models has received a significant amount of attention in the field of object detection.Traditional models generally decompose an original image into a low-rank matrix and a sparse matrix by minimizing the nuclear norm.But these methods suffer from high computation complexity due to singular value decomposition(SVD).To solve this issue,this paper presented an efficient low-rank matrix bi-factorization model for salient object detection,which not only took advantage of low-rank matrix bi-factorization and alternating direction method(ADM)to reduce the computation cost,but utilized structured-sparsity regularization to exploit the spatial relations between the elements in the sparse matrix.Furthermore,this paper introduced high-level priors to jointly guide the matrix decomposition.Experimental results on five challenging datasets validate the proposed method outperforms the state-of-the-art methods in terms of six performance metrics.
作者 刘明明 仇文宁 孙伟 Liu Mingming;Qiu Wenning;Sun Wei(School of Intelligent Manufacturing,Jiangsu Vocational Institute of Architectural Technology,Xuzhou Jiangsu 221008,China;School of Information&Control Engineering,China University of Mining&Technology,Xuzhou Jiangsu 221116,China)
出处 《计算机应用研究》 CSCD 北大核心 2020年第7期2210-2216,共7页 Application Research of Computers
基金 国家自然科学基金资助项目(61801198) 江苏省自然科学基金资助项目(BK20180174) “青蓝工程”资助项目。
关键词 显著性目标检测 低秩矩阵双因子分解 分层稀疏正则化 交替方向法 salient object detection low-rank matrix bi-factorization hierarchical sparse regularization alternating direction method
  • 相关文献

参考文献3

二级参考文献6

共引文献22

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部