Cell tracking via Structured Prediction and Learning
Cell tracking via Structured Prediction and Learning
复制标题
DOI：
10.1007/s00138-017-0872-0
复制
发表时间：
2017-11
影响因子：
3.3
通讯作者：
Jiuqing Wan;Chen Xu;Zeng Xianhang
中科院分区：
文献类型：
--
作者：
Jiuqing Wan;Chen Xu;Zeng Xianhang
在这项工作中，我们提出了一种新的联合检测和跟踪方法用于细胞跟踪。首先，我们开发了一种新的程序，通过椭圆拟合生成一组过完备的检测假设，然后，我们定义了几个局部事件及其相应的标记变量，以解释细胞的生物行为和分割错误。将细胞跟踪任务表述为一个带约束的整数线性规划问题，并利用商业软件有效地求解。此外，我们不是独立学习局部分类器，而是利用块坐标Frank-Wolfe算法在结构化支持向量机框架下学习模型的最优参数。我们还提出了学习算法的核化版本，可以进一步提高跟踪性能。在公共数据集上的实验结果表明，我们的方法与最先进的方法相比具有竞争力。
In this work, we propose a new joint detection and tracking method for cell tracking. First, we develop a new procedure for generating an over-complete set of detection hypotheses via ellipse fitting, and then, we define several local events and their corresponding labeling variables to account for both biological behavior of cells and segmentation errors. The task of cell tracking is formulated as an integer linear programming problem with constraints and solved efficiently using commercial software. In addition, instead of learning local classifiers independently, we exploit block-coordinate Frank–Wolfe algorithm to learn the optimal parameters of our model under the framework of structured SVM. We also present the kernelized version of the learning algorithm which can boost the tracking performance further. Experimental results on public datasets show that our method is competitive with the state-of-the-art ones.