Hierarchical Image Saliency Detection on Extended CSSD
Hierarchical Image Saliency Detection on Extended CSSD
复制标题
DOI：
10.1109/tpami.2015.2465960
复制
发表时间：
2016-04-01
影响因子：
23.6
通讯作者：
Jia, Jiaya
中科院分区：
文献类型：
--
作者：
Shi, Jianping;Yan, Qiong;Jia, Jiaya
复杂的结构通常存在于自然图像中。当图像在背景或前景中包含小规模高对比度图案时，显着性检测可能会受到不利影响，从而导致错误和不均匀的显着性分配。这个问题对现有方法构成了根本性挑战。我们从规模的角度来解决这个问题，并提出了一种多层方法来分析显着性线索。与改变补丁大小或缩小图像不同，我们测量基于区域的尺度。使用分层推理以最佳方式组合不同尺度的所有显着性线索，推断出最终的显着性值。通过我们的推理模型，选择单尺度信息来获得显着图。我们的方法提高了许多传统方法无法很好处理的图像的检测质量。我们还构建了一个扩展的复杂场景显着性数据集（ECSSD）以包含复杂但一般的自然图像。
Complex structures commonly exist in natural images. When an image contains small-scale high-contrast patterns either in the background or foreground, saliency detection could be adversely affected, resulting erroneous and non-uniform saliency assignment. The issue forms a fundamental challenge for prior methods. We tackle it from a scale point of view and propose a multi-layer approach to analyze saliency cues. Different from varying patch sizes or downsizing images, we measure region-based scales. The final saliency values are inferred optimally combining all the saliency cues in different scales using hierarchical inference. Through our inference model, single-scale information is selected to obtain a saliency map. Our method improves detection quality on many images that cannot be handled well traditionally. We also construct an extended Complex Scene Saliency Dataset (ECSSD) to include complex but general natural images.