We present a focal adhesion (FA) detector and tracker based on an Interacting Multiple Model (IMM) algorithm combined with the double use of the linear assignment problem (LAP) for data association. Performance has been evaluated using a real confocal microscopy image sequence of a migrating cell stained for FAs. The tracker has been compared against several state-of-the-art, commercially available tracking algorithms. With a multiple object tracking accuracy (MOTA) of 31.6, it outperforms each of these other methods.
|Title of host publication||Irish Machine Vision and Image Processing Conference Proceedings 2018: Proceedings|
|Publication status||Published - 2018|
|Event||Irish Machine Vision and Image Processing Conference - Ulster University, Belfast, United Kingdom|
Duration: 29 Aug 2018 → 31 Aug 2018
Conference number: 2018
|Conference||Irish Machine Vision and Image Processing Conference|
|Period||29/08/2018 → 31/08/2018|
FingerprintDive into the research topics of 'LAP-based tracking for focal adhesions'. Together they form a unique fingerprint.
Student thesis: Doctoral Thesis › Doctor of PhilosophyFile