Comparison of two 3D tracking paradigms for freely flying insects

In this paper, we discuss and compare state-of-the-art 3D tracking paradigms for flying insects such as Drosophila melanogaster. If two cameras are employed to estimate the trajectories of these identical appearing objects, calculating stereo and temporal correspondences leads to an NP-hard assignme...

Authors: Risse, Benjamin
Berh, Dimitri
Tao, Junli
Jiang, Xiaoyi
Klette, Reinhard
Klämbt, Christian
Division/Institute:FB 13: Biologie
Document types:Article
Media types:Text
Publication date:2013
Date of publication on miami:25.02.2014
Modification date:16.04.2019
Edition statement:[Electronic ed.]
Source:EURASIP Journal on Image and Video Processing (2013) 57
Subjects:Drosophila melanogaster; Fruit flies; 3D tracking; Unscented Kalman filter; Global correspondence selection; Gibbs sampling; Greedy optimization
DDC Subject:510: Mathematik
License:CC BY 2.0
Language:English
Notes:Finanziert durch den Open-Access-Publikationsfonds 2013/2014 der Deutschen Forschungsgemeinschaft (DFG) und der Westfälischen Wilhelms-Universität Münster (WWU Münster).
Format:PDF document
URN:urn:nbn:de:hbz:6-84309622905
Permalink:http://nbn-resolving.de/urn:nbn:de:hbz:6-84309622905
Other Identifiers:DOI: 10.1186/1687-5281-2013-57
Digital documents:1687-5281-2013-57.pdf

In this paper, we discuss and compare state-of-the-art 3D tracking paradigms for flying insects such as Drosophila melanogaster. If two cameras are employed to estimate the trajectories of these identical appearing objects, calculating stereo and temporal correspondences leads to an NP-hard assignment problem. Currently, there are two different types of approaches discussed in the literature: probabilistic approaches and global correspondence selection approaches. Both have advantages and limitations in terms of accuracy and complexity. Here, we present algorithms for both paradigms. The probabilistic approach utilizes the Kalman filter for temporal tracking. The correspondence selection approach calculates the trajectories based on an overall cost function. Limitations of both approaches are addressed by integrating a third camera to verify consistency of the stereo pairings and to reduce the complexity of the global selection. Furthermore, a novel greedy optimization scheme is introduced for the correspondence selection approach. We compare both paradigms based on synthetic data with ground truth availability. Results show that the global selection is more accurate, while the previously proposed tracking-by-matching (probabilistic) approach is causal and feasible for longer tracking periods and very high target densities. We further demonstrate that our extended global selection scheme outperforms current correspondence selection approaches in tracking accuracy and tracking time.