Due to its rising importance in science and technology in recent years, particle tracking in videos presents itself as a tool for successfully acquiring new knowledge in the field of life sciences and physics. Accordingly, different particle tracking methods for various scenarios have been developed. In this article, we present a particle tracking application implemented in Python for, in particular, spherical magnetic particles, including superparamagnetic beads and Janus particles. In the following, we distinguish between two sub-steps in particle tracking, namely the localization of particles in single images and the linking of the extracted particle positions of the subsequent frames into trajectories. We provide an intensity-based localization technique to detect particles and two linking algorithms, which apply either frame-by-frame linking or linear assignment problem solving. Beyond that, we offer helpful tools to preprocess images automatically as well as estimate parameters required for the localization algorithm by utilizing machine learning. As an extra, we have implemented a technique to estimate the current spatial orientation of Janus particles within the $x$–$y$-plane. Our framework is readily extendable and easy-to-use as we offer a graphical user interface and a command-line tool. Various output options, such as data frames and videos, ensure further analysis that can be automated.

Program summary

Program Title: AdaPT

CPC Library link to program files: http://dx.doi.org/10.17632/xxpnsbv3cs.1

Developer’s repository link: https://git.ies.uni-kassel.de/adapt/adapt

Licensing provisions: MPL-2.0

Programming language: Python 3.6

Supplementary material: We provide supplementary material to increase the traceability of the provided example. It consists of an exemplary input video, the corresponding annotated video with tracked particles, a data frame including the tracking information, and a plot displaying the trajectories.

Nature of problem: Particle tracking in videos is an important tool for acquiring new knowledge in diverse fields. Several particle tracking methods have been developed for these diverse applications. The presented particle tracking software has been developed for the motion analysis of spherical or close to spherical magnetic particles. Up until now, no easily extensible automated particle tracking software for close to spherical microparticles and their current positioning status is available.

Solution method: AdaPT is an extensible, easy-to-use microparticle tracking application developed explicitly for lab on chip applications but easily extensible to other applications and further functionalities. Currently implemented linking algorithms are a frame-by-frame linking approach as well as an approach solving linear assignment problems. In addition to many assistance possibilities for the user in the form of estimates of parameter values through machine learning, we offer the particular option to determine the orientation and rotation of spherical polymer particles with hemispherical metallic caps (Janus particles). The application can be used via console and graphical user interface.

Additional comments including restrictions and unusual features: This software requires video data with spherical or close to spherical magnetic particles. It was tested on videos containing spherical superparamagnetic and magnetic Janus particles. Only mobile particles are detected; immobile particles are ignored by the software, reducing the amount of output data considerably. As a unique feature, the spatial orientation within the $x$–$y$-plane of Janus particles can be determined. The application has been tested on a variety of two-dimensional particle motion patterns. The latest version of AdaPT can be found here: https://git.ies.uni-kassel.de/adapt/adapt.

中文翻译：

---

AdaPT：适用于芯片实验室系统的球形微粒的自适应粒子跟踪

由于近年来在科学和技术中的重要性日益提高，视频中的粒子跟踪将自己展示为成功获取生命科学和物理学领域新知识的工具。因此，已经开发出用于各种场景的不同粒子跟踪方法。在本文中，我们介绍了一个用Python实现的粒子跟踪应用程序，特别是针对球形磁性粒子，包括超顺磁珠和Janus粒子。在下文中，我们区分粒子跟踪中的两个子步骤，即单个图像中粒子的定位以及后续帧中提取的粒子位置到轨迹的链接。我们提供了一种基于强度的定位技术来检测粒子和两种链接算法，适用于逐帧链接或线性分配问题解决。除此之外，我们提供有用的工具来自动预处理图像，并通过利用机器学习来估计定位算法所需的参数。另外，我们实施了一项技术来估算Janus粒子在$X$–$ÿ$-飞机。由于我们提供了图形用户界面和命令行工具，因此我们的框架易于扩展且易于使用。各种输出选项（例如数据帧和视频）确保可以自动进行进一步的分析。

计划摘要

节目名称： AdaPT

CPC库链接到程序文件： http : //dx.doi.org/10.17632/xxpnsbv3cs.1

开发人员的资料库链接： https : //git.ies.uni-kassel.de/adapt/adapt

许可规定： MPL-2.0

编程语言： Python 3.6

补充材料：我们提供补充材料以增加所提供示例的可追溯性。它由示例性输入视频，具有跟踪粒子的相应带注释视频，包含跟踪信息的数据帧以及显示轨迹的图组成。

问题的性质：视频中的粒子跟踪是获取各个领域新知识的重要工具。针对这些不同的应用，已经开发了几种粒子跟踪方法。提出的粒子跟踪软件已开发用于球形或接近球形磁性粒子的运动分析。到目前为止，还没有适用于接近球形微粒及其当前定位状态的易于扩展的自动微粒跟踪软件。

解决方法： AdaPT是可扩展的，易于使用的微粒跟踪应用程序，专门为芯片实验室应用而开发，但易于扩展至其他应用程序和其他功能。当前实现的链接算法是逐帧链接方法以及解决线性分配问题的方法。除了通过机器学习来估计参数值的形式为用户提供许多帮助以外，我们还提供了特殊的选项来确定带有半球形金属盖（球形颗粒）的球形聚合物颗粒的方向和旋转。可以通过控制台和图形用户界面使用该应用程序。

其他注释包括限制和异常功能：该软件需要具有球形或接近球形磁性颗粒的视频数据。它在包含球形超顺磁性和磁性Janus粒子的视频上进行了测试。仅检测到可移动的粒子。软件会忽略不动的粒子，从而大大减少了输出数据量。作为一项独特功能，$X$–$ÿ$可以确定Janus粒子的平面。该应用程序已在各种二维粒子运动模式上进行了测试。可以在以下位置找到最新版本的AdaPT：https：//git.ies.uni-kassel.de/adapt/adapt。