Abstract | ||
---|---|---|
The paper proposes contributions for mean-shift (MS) and covariance tracking (CT), and makes these two complementary methods cooperate. While MS runs fast and can handle non-rigid objects represented by their color distribution, CT is more time-consuming but achieves a generic tracking by mixing color and texture information. Each method is modified in order to alleviate their intrinsic limitations, and make the tracking adaptive to a changing context. Concerning MS, the colorspace is changed automatically when necessary to enhance the distinction between the object and the background. Regarding CT, the number of features is reduced without loss of accuracy, by using Local Binary Patterns. Finally, their complementary advantages are exploited in a cooperation process, which runs faster than CT alone, and is more robust than MS alone. A comprehensive study is made for their acceleration and their efficient execution on different multi-core CPUs. A speedup of ×2.8 is reached for MS and ×2.6 for CT. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1007/s11554-013-0358-x | J. Real-Time Image Processing |
Keywords | Field | DocType |
Color tracking, Covariance matching, Mean-shift tracking, Real-time processing, SSE SIMD optimization | Computer vision,Color space,Covariance matching,Computer science,Local binary patterns,Real-time computing,Artificial intelligence,Acceleration,Covariance,Speedup | Journal |
Volume | Issue | ISSN |
10 | 2 | 1861-8219 |
Citations | PageRank | References |
1 | 0.35 | 27 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Florence Laguzet | 1 | 5 | 1.46 |
Andrés Romero Mier y Terán | 2 | 1 | 0.35 |
Michèle Gouiffès | 3 | 69 | 16.37 |
Lionel Lacassagne | 4 | 127 | 23.17 |
Daniel Etiemble | 5 | 300 | 42.43 |