Cong Runmin, Lei Jianjun, Fu Huazhu, Porikli Fatih, Huang Qingming, Hou Chunping
IEEE Trans Image Process. 2019 Oct;28(10):4819-4831. doi: 10.1109/TIP.2019.2910377. Epub 2019 May 2.
Video saliency detection aims to continuously discover the motion-related salient objects from the video sequences. Since it needs to consider the spatial and temporal constraints jointly, video saliency detection is more challenging than image saliency detection. In this paper, we propose a new method to detect the salient objects in video based on sparse reconstruction and propagation. With the assistance of novel static and motion priors, a single-frame saliency model is first designed to represent the spatial saliency in each individual frame via the sparsity-based reconstruction. Then, through a progressive sparsity-based propagation, the sequential correspondence in the temporal space is captured to produce the inter-frame saliency map. Finally, these two maps are incorporated into a global optimization model to achieve spatio-temporal smoothness and global consistency of the salient object in the whole video. The experiments on three large-scale video saliency datasets demonstrate that the proposed method outperforms the state-of-the-art algorithms both qualitatively and quantitatively.
视频显著性检测旨在从视频序列中持续发现与运动相关的显著物体。由于需要联合考虑空间和时间约束，视频显著性检测比图像显著性检测更具挑战性。在本文中，我们提出了一种基于稀疏重建和传播的视频显著物体检测新方法。借助新颖的静态和运动先验，首先设计一个单帧显著性模型，通过基于稀疏性的重建来表示每个单独帧中的空间显著性。然后，通过基于稀疏性的渐进传播，捕捉时间空间中的序列对应关系，以生成帧间显著性图。最后，将这两个图纳入全局优化模型，以实现整个视频中显著物体的时空平滑性和全局一致性。在三个大规模视频显著性数据集上的实验表明，所提出的方法在定性和定量方面均优于当前的先进算法。
