Robust Object Tracking Against Template Drift

Pan, Jiyan; Hu, Bo

doi:10.1109/icip.2007.4379319

Cited by 13 publications

(13 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Akf: Covariance Matchingmentioning

confidence: 99%

“…Many recent works [11,13,14] employ this method to update the filter noise covariances. In [13], the authors attribute the observation noise to the precision of the template transformation parameters and obtain an expression to explicitly evaluate it. In [11] and [14], the observation noise σ 2 v is initialized in the first frame and then held constant for the rest of the tracking process.…”

Section: Akf: Covariance Matchingmentioning

confidence: 99%

See 1 more Smart Citation

Appearance learning by adaptive Kalman filters for FLIR tracking

Venkataraman

Fan

et al. 2009

2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

View full text Add to dashboard Cite

show abstract

Section: Akf: Covariance Matchingmentioning

confidence: 99%

Section: Akf: Covariance Matchingmentioning

confidence: 99%

Appearance learning by adaptive Kalman filters for FLIR tracking

Venkataraman

Fan

et al. 2009

2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

View full text Add to dashboard Cite

show abstract

“…Particularly for a highly maneuverable target, this implies that the target and background signatures observed at the sensor focal plane array (FPA) may exhibit profound nonstationary variations over relatively short time scales, making it difficult to maintain both a reliable detection process and a robust track lock over longer time scales -phenomena that have been referred to variously as the "drifting problem" in [1], [2], the "template update problem" in [3]- [6], and a "stale template condition" in [7]. These challenges are exemplified by the well-known AMCOM closure sequences 1 [8]- [15] as well as the newly released SENSIAC ATR dataset.…”

mentioning

confidence: 99%

Adaptive Kalman Filtering for Histogram-Based Appearance Learning in Infrared Imagery

Venkataraman

Fan

Havlicek

et al. 2012

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Targets of interest in video acquired from imaging infrared sensors often exhibit profound appearance variations due to a variety of factors, including complex target maneuvers, ego-motion of the sensor platform, background clutter, etc., making it difficult to maintain a reliable detection process and track lock over extended time periods. Two key issues in overcoming this problem are how to represent the target and how to learn its appearance online. In this paper, we adopt a recent appearance model that estimates the pixel intensity histograms as well as the distribution of local standard deviations in both the foreground and background regions for robust target representation. Appearance learning is then cast as an adaptive Kalman filtering problem where the process and measurement noise variances are both unknown. We formulate this problem using both covariance matching and, for the first time in a visual tracking application, the recent autocovariance least-squares (ALS) method. Although convergence of the ALS algorithm is guaranteed only for the case of globally wide sense stationary process and measurement noises, we demonstrate for the first time that the technique can often be applied with great effectiveness under the much weaker assumption of piecewise stationarity. The performance advantages of the ALS method relative to the classical covariance matching are illustrated by means of simulated stationary and nonstationary systems. Against real data, our results show that the ALS-based algorithm outperforms the covariance matching as well as the traditional histogram similarity-based methods, achieving sub-pixel tracking accuracy against the well-known AMCOM closure sequences and the recent SENSIAC automatic target recognition dataset.

show abstract

Section: Akf: Covariance Matchingmentioning

confidence: 99%