Automatic trajectory measurement of large numbers of crowded objects
This work addresses a domain-specific problem for researchers studying collective behaviors in biology, such as fish schools or cell groups, by providing an automated solution for high-throughput trajectory measurement.
The paper tackles the problem of automatically measuring trajectories of large numbers of crowded, similar-looking objects like fish or cells, which is challenging due to occlusions and detection issues, and presents a framework that achieves effective results as evaluated on multiple datasets.
Complex motion patterns of natural systems, such as fish schools, bird flocks, and cell groups, have attracted great attention from scientists for years. Trajectory measurement of individuals is vital for quantitative and high-throughput study of their collective behaviors. However, such data are rare mainly due to the challenges of detection and tracking of large numbers of objects with similar visual features and frequent occlusions. We present an automatic and effective framework to measure trajectories of large numbers of crowded oval-shaped objects, such as fish and cells. We first use a novel dual ellipse locator to detect the coarse position of each individual and then propose a variance minimization active contour method to obtain the optimal segmentation results. For tracking, cost matrix of assignment between consecutive frames is trainable via a random forest classifier with many spatial, texture, and shape features. The optimal trajectories are found for the whole image sequence by solving two linear assignment problems. We evaluate the proposed method on many challenging data sets.