arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1302.6557cs.CVcs.AI
收藏

基于测地线的显著目标检测

Geodesic-based Salient Object Detection

Richard M Jiang

摘要:

显著性检测是一种直观的方式,为目标检测和分割提供有用的线索,如许多视觉和图形应用所需。本文提出了一种鲁棒的显著目标检测和分割方法。除了使用各种像素级的对比度定义,我们利用全局图像结构,并提出了一种新的测地线方法专用于显着目标检测。在该方法中,提出了一种新的测地线方案,即测地线隧道处理纹理和局部混沌结构。我们的新的测地线的方法,测地线显着图估计对应的图像中的空间结构。显着对象基准数据集上的实验评估验证了我们的算法始终优于一些最先进的显着性方法,产生更高的精度和更好的召回率。与强大的显着性估计,我们还提出了一个无监督的层次显着对象切割方案,简单地使用自适应显着性阈值,在我们的F-测量测试中获得最高分。我们还将我们的测地线切割方案应用于一些图像编辑任务,如在其他实验中所示。

英文摘要:

Saliency detection has been an intuitive way to provide useful cues for object detection and segmentation, as desired for many vision and graphics applications. In this paper, we provided a robust method for salient object detection and segmentation. Other than using various pixel-level contrast definitions, we exploited global image structures and proposed a new geodesic method dedicated for salient object detection. In the proposed approach, a new geodesic scheme, namely geodesic tunneling is proposed to tackle with textures and local chaotic structures. With our new geodesic approach, a geodesic saliency map is estimated in correspondence to spatial structures in an image. Experimental evaluation on a salient object benchmark dataset validated that our algorithm consistently outperformed a number of the state-of-art saliency methods, yielding higher precision and better recall rates. With the robust saliency estimation, we also present an unsupervised hierarchical salient object cut scheme simply using adaptive saliency thresholding, which attained the highest score in our F-measure test. We also applied our geodesic cut scheme to a number of image editing tasks as demonstrated in additional experiments.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑