Mean-shift blob tracking through scale space

By Robert T. Collins. 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings., 2003

955 citations recorded by the source corpus.

Subfields: Biophysics, Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/eeb76fa577520b5c99c46eae4acc23b1ea43061b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biophysics

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Semi-Supervised Kernel Mean Shift Clustering (2014, background): “, image smoothing and segmentation [11], [41], visual tracking [9], [19] and information fusion [7], [10].”
Fast Visual Tracking via Dense Spatio-temporal Context Learning (2014, methodology): “The 18 trackers we compare with are: scale mean-shift (SMS) tracker [7], fragment tracker (Frag) [1], semi-supervised Boosting tracker (SSB) [12], local orderless tracker (LOT) [21], incremental visual tracking (IVT) method [22], online AdaBoost tracker (OAB) [11], multiple instance learning…”
Robust Superpixel Tracking (2014, methodology): “Comparison with color-based trackers: We compare the proposed SPT algorithm with two color-based trackers, the mean shift tracker with adaptive scale (MS) [34] and the adaptive color-based particle filter (PF) tracker [35].”
Segmentation and Tracking of Multiple Humans in Crowded Environments (2008, methodology): “The last term of LðuÞ is the density estimate computed with kernel profile kðÞ at u. The mean-shift algorithm with negative weight [ 4 ] applies.”
Efficient mean-shift tracking via a new similarity measure (2005, methodology): “In contrast, the scaling updating rule proposed by Collins [8] employs the scale-space theory which could be confused by the multiple scales within the targets.”
Human Tracking Using Convolutional Neural Networks (2010, background): “In [ 30 ] a solution to scale integrated in mean-shift framework is presented.”
Nuclei Segmentation Using Marker-Controlled Watershed, Tracking Using Mean-Shift, and Kalman Filter in Time-Lapse Microscopy (2006, methodology): “Collins [21] used scale space theory to automatically select the kernel size.”
Distribution fields for tracking (2012, methodology): “An alternative to building a template is using a histogram to describe the object [8, 6].”
Spatiograms versus histograms for region-based tracking (2005, methodology): “Mean shift has recently gained signiﬁcant attention as an efﬁcient and robust method for visual tracking [3, 2, 11].”
Tracking of migrating cells under phase-contrast video microscopy with combined mean-shift processes (2005, methodology): “, vehicle tracking, closed loop video) [19], [20], but usually do not give object contours.”
Robust Fragments-based Tracking using the Integral Histogram (2006, methodology): “A second issue is the partial versus full explanation dilemma described earlier and in [7] when choosing scale.”
Clustering via Mode Seeking by Direct Estimation of the Gradient of a Log-Density (2014, methodology): “Thanks to this extremely useful property, the mean shift has been successfully employed in various applications such as image segmentation [8,24,26] and object tracking [7,9].”
Unsupervised Detection and Tracking of Arbitrary Objects with Dependent Dirichlet Process Mixtures (2012, methodology): “To improve the accuracy of these methods, techniques have been developed for performing extraction and segmentation in a joint manner, incorporating statistical methods for maintaining hypotheses of different numbers of detected objects, and introducing some of the multi-object tracking methods desc”
Online Object Tracking: A Benchmark (2013, neutral): “2 KMS [16] H, IH LOS N C 3,159 SMS [14] H, IH LOS N C 19.”
Object Tracking Benchmark (2015, neutral): “2 KMS [16] H, IH LOS N C 3,159 SMS [13] H, IH LOS N C 19.”
Multiple kernel tracking with SSD (2004, methodology): “The kernel used in the single kernelbased and the mean shift approach is the Epanechnikov kernel used by [3] for mean shift tracking.”