This paper proposes a saliency detection method via two-stage absorbing Markov chain based on background and foreground for detecting salient objects in images. Firstly, image preprocessing is performed, followed by convex hull construction and superpixel segmentation, to prepare for subsequent processing. Secondly, according to the boundary connectivity, the superpixels with lower background probability value in the candidate boundary background set $B_0$ are deleted, and the boundary background set $B_1$ is obtained. With the saliency values of the nodes in the boundary-prior saliency map $S_{bg1}$, the background seeds are added appropriately in the region outside the candidate boundary background set $B_0$ and the convex hull $H$, and the background seed set $B$ is obtained after update. Then, the background-absorbing Markov chain is constructed to generate background-absorbing saliency map $S_{bg2}$. By fusing the saliency maps $S_{bg1}$ and $S_{bg2}$, the first-stage background-based saliency map $S_{\mathit{bg}}$ is obtained. Thirdly, in the range of the convex hull $H$, the foreground seed set $F$ is determined according to the saliency map $S_{\mathit{bg}}$. Then, the foreground-absorbing Markov chain is constructed, to obtain the second-stage foreground-absorbing saliency map $S_{\mathit{fg}}$. Finally, the saliency maps $S_{\mathit{bg}}$ and $S_{\mathit{fg}}$ of the two stages are combined to obtain a fused saliency map $S$, and the final saliency map $S^{\ast }$ is obtained after optimization through smoothing mechanism. Compared with the traditional methods, the performance of the proposed method is significantly improved. The proposed method is tested on three public image datasets, and it shows great accuracy in detecting salient objects.

提出了一种基于背景和前景的两级吸收马尔可夫链显着性检测方法，用于检测图像中的显着物体。首先，执行图像预处理，然后进行凸包构造和超像素分割，以准备进行后续处理。其次，根据边界连通性，候选边界背景集中背景概率值较低的超像素${乙}_0$ 删除，并设置边界背景 ${乙}_{\mathrm{1个}}$获得。具有边界优先级显着图中的节点的显着性值${\mathrm{小号}}_{bG\mathrm{1个}}$，将背景种子适当添加到候选边界背景集之外的区域中 ${乙}_0$ 和凸包 $H$，以及背景种子集 $乙$是在更新后获得的。然后，构造背景吸收马尔可夫链以生成背景吸收显着图${\mathrm{小号}}_{bG2}$。通过融合显着图${\mathrm{小号}}_{bG\mathrm{1个}}$ 和 ${\mathrm{小号}}_{bG2}$，第一阶段基于背景的显着性图 ${\mathrm{小号}}_{\mathit{bg}}$获得。第三，在凸包的范围内$H$，前景种子集 $F$ 根据显着图确定 ${\mathrm{小号}}_{\mathit{bg}}$。然后，构建前景吸收马尔可夫链，以获得第二阶段前景吸收显着图${\mathrm{小号}}_{\mathit{fg}}$。最后，显着性图${\mathrm{小号}}_{\mathit{bg}}$ 和 ${\mathrm{小号}}_{\mathit{fg}}$ 合并两个阶段中的一个以获得融合显着图 $\mathrm{小号}$，以及最终显着性地图 ${\mathrm{小号}}^{\ast }$通过平滑机制优化后获得。与传统方法相比，该方法的性能有了很大的提高。该方法在三个公共图像数据集上进行了测试，在检测显着物体方面显示出很高的准确性。