Intelligence computation based on adaptive tracking design for a class of non-linear discrete-time systems

Liu, Yan Jun; Li, Dong-Juan

doi:10.1007/s00521-012-1080-5

Cited by 2 publications

(1 citation statement)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Visual object tracking is attracting more and more researchers' attention due to its potential applications, which are commonly found in video surveillance [7,8,23,16,27], sports analysis [19,29] and human motion recognition [11,31,34]. Interesting applications reported in these studies include crowd control, traffic monitoring and transportation security.…”

Section: Introductionmentioning

confidence: 99%

Hybrid generative–discriminative hash tracking with spatio-temporal contextual cues

Dai

Cheng

2016

Neural Comput & Applic

View full text Add to dashboard Cite

Visual object tracking is of a great application value in video monitoring systems. Recent work on video tracking has taken into account spatial relationship between the targeted object and its background. In this paper, the spatial relationship is combined with the temporal relationship between features on different video frames so that a real-time tracker is designed based on a Hash algorithm with spatio-temporal cues. Different from most of the existing work on video tracking, which is regarded as a mechanism for image matching or image classification alone, we propose a hierarchical framework and conduct both matching and classification tasks to generate a coarse-to-fine tracking system. We develop a generative model under a modified Particle Filter with Hash fingerprints for the coarse matching by the Maximum a Posteriori (MAP) and a discriminative model for the fine classification by maximizing a confidence map based on a context model. The confidence map reveals the spatio-temporal dynamics of the target. Because Hash fingerprint is merely a binary vector and the modified Particle Filter uses only a small number of particles, our tracker has a low computation cost. By conducting experiments on 8 challenging video sequences from a public benchmark, we demonstrate that our tracker outperforms 8 state-of-the-art trackers in terms of both accuracy and speed.

show abstract