Rezatofighi Seyed Hamid, Gould Stephen, Hartley Richard, Mele Katarina, Hughes William E
College of Engineering & Computer Sci., Australian National University, ACT.
Med Image Comput Comput Assist Interv. 2012;15(Pt 1):357-64. doi: 10.1007/978-3-642-33415-3_44.
We propose a multi-target tracking method using an Interacting Multiple Model Joint Probabilistic Data Association (IMM-JPDA) filter for tracking vesicles in total internal reflection fluorescence microscopy (TIRFM) sequences. We enhance the accuracy and reliability of the algorithm by tailoring an appropriate framework to this application. Evaluation of our algorithm is performed on both realistic synthetic data and real TIRFM data. Our results are compared against related methods and a commercial tracking software.
我们提出了一种使用交互式多模型联合概率数据关联(IMM-JPDA)滤波器的多目标跟踪方法,用于在全内反射荧光显微镜(TIRFM)序列中跟踪囊泡。我们通过为该应用量身定制一个合适的框架来提高算法的准确性和可靠性。我们的算法在逼真的合成数据和真实的TIRFM数据上都进行了评估。我们将结果与相关方法和一款商业跟踪软件进行了比较。