Cao Xiaochun, Tao Zhiqiang, Zhang Bao, Fu Huazhu, Feng Wei
IEEE Trans Image Process. 2014 Sep;23(9):4175-4186. doi: 10.1109/TIP.2014.2332399. Epub 2014 Jun 23.
Co-saliency detection aims at discovering the common salient objects existing in multiple images. Most existing methods combine multiple saliency cues based on fixed weights, and ignore the intrinsic relationship of these cues. In this paper, we provide a general saliency map fusion framework, which exploits the relationship of multiple saliency cues and obtains the self-adaptive weight to generate the final saliency/cosaliency map. Given a group of images with similar objects, our method firstly utilizes several saliency detection algorithms to generate a group of saliency maps for all the images. The feature representation of the co-salient regions should be both similar and consistent. Therefore, the matrix jointing these feature histograms appears low rank. We formalize this general consistency criterion as the rank constraint, and propose two consistency energy to describe it, which are based on low rank matrix approximation and low rank matrix recovery, respectively. By calculating the self-adaptive weight based on the consistency energy, we highlight the common salient regions. Our method is valid for more than two input images and also works well for single image saliency detection. Experimental results on a variety of benchmark datasets demonstrate that the proposed method outperforms the state-of-the-art methods.
协同显著性检测旨在发现多个图像中存在的共同显著物体。大多数现有方法基于固定权重组合多个显著性线索，而忽略了这些线索之间的内在关系。在本文中，我们提供了一个通用的显著性图融合框架，该框架利用多个显著性线索之间的关系并获得自适应权重，以生成最终的显著性/协同显著性图。给定一组具有相似物体的图像，我们的方法首先利用几种显著性检测算法为所有图像生成一组显著性图。共同显著区域的特征表示应该既相似又一致。因此，连接这些特征直方图的矩阵呈现低秩。我们将这种通用的一致性准则形式化为秩约束，并分别基于低秩矩阵逼近和低秩矩阵恢复提出两种一致性能量来描述它。通过基于一致性能量计算自适应权重，我们突出了共同显著区域。我们的方法对两个以上的输入图像有效，并且在单图像显著性检测中也表现良好。在各种基准数据集上的实验结果表明，所提出的方法优于现有方法。
