Abstract | ||
---|---|---|
Successful multi-object tracking requires consistently maintaining object identities and real-time performance. This task becomes more challenging when objects are indistinguishable from one another. This paper presents a Bayesian framework for maintaining the identities of multiple objects. Our semi-independent joint motion model (SIMM) solves the coalescence and identity switching problem in real time. This joint motion model is a non-parametric mixture model that simultaneously captures linear motion and repulsive motion. Linear motion is a constant velocity model, while repulsive motion is described by a repulsive potential in MRF. By maintaining multimodality from multiple motion models, we can infer the appropriate motion model using image evidence and consequently avoid many identity switching errors. Moreover, we develop a new sampling method that does not suffer from the curse of dimensionality because of the availability of high-quality samples. Experimental results show that our approach can track numerous objects in real time and maintain identities under difficult situations. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1007/978-3-319-16817-3_24 | COMPUTER VISION - ACCV 2014, PT IV |
Field | DocType | Volume |
Computer vision,Linear motion,Markov random field,Computer science,Curse of dimensionality,Sampling (statistics),Artificial intelligence,Motion estimation,Coalescence (physics),Mixture model,Bayesian probability | Conference | 9006 |
ISSN | Citations | PageRank |
0302-9743 | 0 | 0.34 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
LeJun Shen | 1 | 15 | 1.15 |
Zhisheng You | 2 | 417 | 52.22 |
Qing Liu | 3 | 0 | 0.34 |