Xi Tao, Zhao Wei, Wang Han, Lin Weisi
IEEE Trans Image Process. 2017 Jul;26(7):3425-3436. doi: 10.1109/TIP.2016.2631900. Epub 2016 Nov 22.
Saliency detection for images has been studied for many years, for which a lot of methods have been designed. In saliency detection, background priors which are often regarded as pseudo-background are effective clues to find salient objects in images. Although image boundary is commonly used background priors, it doesn't work well for images of complex scenes and videos. In this paper, we explore how to identify the background priors for a video and propose a saliency based method to detect the visual objects by using background priors. For a video, we integrate multiple pairs of SIFT flows from long-range frames and a bidirectional consistency propagation is conducted to obtain the accurate and sufficient temporal background priors, which are combined with spatial background priors to generate spatiotemporal background priors. Next, a novel dual-graph based structure using spatiotemporal background priors is put forward in computation of saliency maps, fully taking advantage of appearance and motion information in videos. Experimental results on different challenging datasets show that the proposed method robustly and accurately detect the video objects in both simple and complex scenes and achieve better performance compared with other state-of-the-art video saliency models.
图像显著度检测已经研究多年，为此设计了许多方法。在显著度检测中，背景先验通常被视为伪背景，是在图像中找到显著物体的有效线索。虽然图像边界是常用的背景先验，但对于复杂场景和视频的图像效果不佳。在本文中，我们探索如何识别视频的背景先验，并提出一种基于显著度的方法，利用背景先验来检测视觉对象。对于视频，我们整合来自远距离帧的多对SIFT流，并进行双向一致性传播以获得准确且充分的时间背景先验，将其与空间背景先验相结合以生成时空背景先验。接下来，在显著度图的计算中提出了一种基于新颖双图结构的时空背景先验，充分利用视频中的外观和运动信息。在不同具有挑战性的数据集上的实验结果表明，所提出的方法能够在简单和复杂场景中稳健且准确地检测视频对象，并且与其他最新的视频显著度模型相比具有更好的性能。
