Simple Two-Dimensional Object Tracking based on a Graph Algorithm
This work addresses the automation of biomedical tasks like cell tracking, but it is incremental as it builds on existing basic algorithms.
The authors tackled the problem of tracking fast-moving micrometer-sized objects in microscopic videos by combining blob recognition, feature-based shape recognition, and a graph algorithm in a novel way, achieving high accuracy in object and trajectory recognition and superior performance compared to a similar algorithm.
The visual observation and tracking of cells and other micrometer-sized objects has many different biomedical applications. The automation of those tasks based on computer methods helps in the evaluation of such measurements. In this work, we present a general purpose algorithm that excels at evaluating deterministic behavior of micrometer-sized objects. Our concrete application is the tracking of fast moving objects over large distances along deterministic trajectories in a microscopic video. Thereby, we are able to determine characteristic properties of the objects. For this purpose, we use a set of basic algorithms, including blob recognition, feature-based shape recognition and a graph algorithm, and combined them in a novel way. An evaluation of the algorithms performance shows a high accuracy in the recognition of objects as well as of complete trajectories. Moreover, a direct comparison to a similar algorithm shows superior recognition rates.