近兩年跟蹤速度較快的演算法小結轉）

近兩年跟蹤速度較快的演算法有cn[1]，kcf[2]，stc[3]，odfs[4]等等，均足以滿足現實場景中實時跟蹤的應用

各演算法的主要思想：

cn***：是csk[5]***的改進演算法。它聯合顏色特徵（color name）和灰度特徵來描述目標，在文獻[1]作者通過大量的實驗證明了color name在視覺跟蹤中的卓越效能，並且對color name

參考文獻

[1] martin danelljan, fahad shahbaz khan, michae felsberg. adaptive color attributes for real-time visual

tracking. in cvpr, 2014.

[2] joão f. henriques, rui caseiro, pedro martins. high-speed tracking with kernelized correlation filters.

pami, 2014.

[3] kaihua zhang, lei zhang, qingshan liu. fast visual tracking via dense spatio-temporal context learning.

in eccv, 2014.

[4] kaihua zhang, lei zhang, and ming-hsuan yang. real-time object tracking via online discriminative

feature selection. tip, 2013.

[5] j. henriques, r. caseiro, p. martins, and j. batista. exploiting the circulant structure of tracking-by-detection

with kernels. in eccv, 2012.

[6] b. babenko, m.-h. yang, and s. belongie. robust object tracking with online multiple instance learning. ieee

trans. pattern anal. mach. intell., vol. 33, no. 8, pp. 1619–1632, 2011.

近兩年跟蹤速度較快的演算法小結 轉）