Kang Xuejing, Zhu Lei, Ming Anlong
IEEE Trans Image Process. 2020 Jan 23. doi: 10.1109/TIP.2020.2967583.
In this paper, we propose a novel random walk model, called Dynamic Random Walk (DRW), which adds a new type of dynamic node to the original RW model and reduces redundant calculation by limiting the walk range. To solve the seed-lacking problem of the proposed DRW, we redefine the energy function of the original RW and use the first arrival probability among each node pair to avoid the interference for each partition. Relaxation of our DRW is performed with the help of a greedy strategy and the Weighted Random Walk Entropy(WRWE) that uses the gradient feature to approximate the stationary distribution. The proposed DRW not only can enhance the boundary adherence but also can run with linear time complexity. To extend our DRW for superpixel segmentation, a seed initialization strategy is proposed. It can evenly distribute seeds in both 2D and 3D space and generate superpixels in only one iteration. The experimental results demonstrate that our DRW is faster than existing RW models and better than the state-of-the-art superpixel segmentation algorithms with respect to both efficiency and segmentation effects.
在本文中，我们提出了一种新颖的随机游走模型，称为动态随机游走（DRW），它在原始随机游走（RW）模型中添加了一种新型动态节点，并通过限制游走范围减少了冗余计算。为了解决所提出的DRW的种子缺乏问题，我们重新定义了原始RW的能量函数，并使用每个节点对之间的首次到达概率来避免对每个分区的干扰。我们的DRW借助贪婪策略和使用梯度特征来近似平稳分布的加权随机游走熵（WRWE）进行松弛。所提出的DRW不仅可以增强边界粘附性，而且可以在线性时间复杂度下运行。为了将我们的DRW扩展用于超像素分割，提出了一种种子初始化策略。它可以在二维和三维空间中均匀分布种子，并且仅在一次迭代中生成超像素。实验结果表明，我们的DRW比现有的RW模型更快，并且在效率和分割效果方面均优于当前最先进的超像素分割算法。
