Predicting accuracy in Multiple Object Tracking tasks from trajectory statistics

• Thesis title in Czech: Predikce výkonu v úloze Sledování více objektů pomocí statistiky trajektorií
• Thesis title in English: Predicting accuracy in Multiple Object Tracking tasks from trajectory statistics
• Key words: Multiple Object Tracking|prediction|modelling
• English key words: Multiple Object Tracking|prediction|modelling
• Academic year of topic announcement: 2019/2020
• Thesis type: diploma thesis
• Thesis language: angličtina
• Department: Department of Software and Computer Science Education (32-KSVI)
• Supervisor: Mgr. et Mgr. Filip Děchtěrenko, Ph.D.
• Author: hidden - assigned and confirmed by the Study Dept.
• Date of registration: 24.01.2020
• Date of assignment: 24.01.2020
• Confirmed by Study dept. on: 24.01.2020
• Date and time of defence: 01.02.2023 09:00
• Date of electronic submission: 06.01.2023
• Date of submission of printed version: 09.01.2023
• Date of proceeded defence: 01.02.2023
• Opponents: Mgr. Ján Antolík, Ph.D.

Guidelines

In Multiple Object Tracking (MOT) experiments, participant's task is to track several moving objects at once. Although the task was primarily used by cognitive scientists to study visual attention, recent years brought in computer scientist to find patterns in the data that could explain human performance by data driven approach. In particular, it is an open question, whether the tracking performance could be explained by parameters of movement trajectories.
In this project, student will create a model that would explain tracking accuracy in MOT task based on individual descriptors of MOT trajectories. After creating individual metrics how to quantify difficulty of trajectories, student will create one model that would explain performance in the trials and verify this model in an experiment.

References

Dobson, A. J., & Barnett, A. G. (2008). An introduction to generalized linear models. Chapman and Hall/CRC.
Lukavský, J. (2013). Eye movements in repeated multiple object tracking. Journal of Vision, 13(7), 9-9.
Meyerhoff, H. S., Papenmeier, F., & Huff, M. (2017). Studying visual attention using the multiple object tracking paradigm: A tutorial review. Attention, Perception, & Psychophysics, 79(5), 1255-1274.
Pylyshyn, Z. W., & Storm, R. W. (1988). Tracking multiple independent targets: Evidence for a parallel tracking mechanism. Spatial vision, 3(3), 179-197.
Scimeca, J. M., & Franconeri, S. L. (2015). Selecting and tracking multiple objects. Wiley Interdisciplinary Reviews: Cognitive Science, 6(2), 109-118.