Multiple particle tracking in time-lapse synchrotron X-ray images using discriminative appearance and neighbouring topology learning

作者：

Highlights：

• Multiple particle tracking is challenging in synchrotron X-ray images.

• Discriminative appearance and neighbouring topology learning are proposed.

• A detection recovery method using multi-frame association is proposed.

• Our method achieves tracking errors of 7.03% and association errors of 7.22%.

摘要

•Multiple particle tracking is challenging in synchrotron X-ray images.•Discriminative appearance and neighbouring topology learning are proposed.•A detection recovery method using multi-frame association is proposed.•Our method achieves tracking errors of 7.03% and association errors of 7.22%.

论文关键词：Convolutional neural network (CNN),LDA,Neighbuoring topology,Multi-frame association,Particle tracking

论文评审过程：Received 10 September 2018, Revised 24 April 2019, Accepted 1 May 2019, Available online 1 May 2019, Version of Record 10 May 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.05.007