Superpixel tracking

By Shu Wang, Huchuan Lu, Ming-Hsuan Yang. Vision, 2011

568 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/b762ecb0624005831f2f3d8eb626d53e8eca4b6c

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Superpixels: An evaluation of the state-of-the-art (2016, methodology): “Since the introduction of the first superpixel algorithms around 2009, they have been applied to many important problems in computer vision: tracking [10, 11], stereo and occlusion [12, 13], 3D-reconstruction [14], saliency [15, 16], object detection [17, 18] and object proposal detection [19, 20], ”
Superpixel-Based Fast Fuzzy C-Means Clustering for Color Image Segmentation (2019, background): “A superpixel region is usually defined as perceptually uniform and homogenous regions in the image [35].”
An online learned CRF model for multi-target tracking (2012, methodology): “Most visual tracking methods focus on tracking single object or multiple objects separately [9, 16]; they usually try to find proper appearance models that distinguish one object with all other targets or backgrounds, and adopt meanshift [4] or particle filtering [6] like approach to online adjust t”
SEEDS: Superpixels Extracted Via Energy-Driven Sampling (2012, background): “1 Introduction Many computer vision applications benefit from working with superpixels instead of just pixels [1,2,3].”
Robust Superpixel Tracking (2014, background): “1Preliminary results of this work were presented in [25].”
Video Segmentation via Object Flow (2016, methodology): “The superpixel-based tracking methods [38, 40] do not perform well on these sequences since superpixels may not preserve object boundaries well.”
Saliency-Aware Video Object Segmentation (2018, methodology): “video frames unsupervised supervised Ours [7] [9] [22] [26] [28] [24] [58] [59] [60] [61]”
One-Shot Video Object Segmentation (2016, background): “In the latter to JOTS [52], TMFG [25] KEY [24], HVS [17] HBT [16], ST [51] and OFL [49].”
Visual Tracking via Locality Sensitive Histograms (2013, methodology): “The others are the recent tracking methods, including the real time L1 tracker (L1T) [3], the super-pixel tracker (SPT) [24], the real-time compressive tracker (CT) [27], the multiple instance learning tracker (MIL) [2], the structured output tracker (Struck) [8], the visual tracking decomposition m”
Pixel-Level Hand Detection in Ego-centric Videos (2013, methodology): “The use of small clusters of pixels, better known as superpixels, is a preprocessing step used for tasks such as image segmentation and appearance modeling for tracking [19, 28].”
Visual Tracking: an Experimental Survey (2013, unknown): “Recovery from drift may also prove a useful addition to make tracking robust for general purposes as in SPT [67].”
Deep Affinity Network for Multiple Object Tracking (2018, methodology): “There are also techniques that mitigate the problems with object detectors in tracking by employing an on-line trainable classifier for the target objects [50], [51], [52].”
Locally Orderless Tracking (2012, methodology): “Some attempt to combine rigid and deformable object approaches either by using mid level cues that capture spatial information to some extent [12] or by heuristically combining discriminative and generative components [13].”
Siamese Instance Search for Tracking (2016, methodology): “SPT [50] uses super-pixels for matching, HBT [12] uses HOG-features in a probabilistic approach, and FBT [32] uses color invariants for robustness against illumination variations.”
Superpixel segmentation using Linear Spectral Clustering (2015, methodology): “In spite of its simplicity, SLIC has been proved to be effective in various computer vision applications [22].”
Superpixels and Polygons Using Simple Non-iterative Clustering (2017, background): “After their introduction [27], several applications such as object localization [14], multi-class segmentation [15], optical flow [22], body model estimation [24], object tracking [35], and depth estimation [37] took advantage of superpixels .”
Robust object tracking via sparsity-based collaborative model (2012, background): “First, an object can be represented by different features such as intensity [21], color [20], texture [3], superpixels [25], and Haar-like features [10, 11, 4, 12].”
UvA-DARE (Digital Academic Repository) Siamese Instance Search for Tracking (2016, methodology): “SPT [50] uses super-pixels for matching, HBT [12] uses HOG-features in a probabilistic approach, and FBT [32] uses color invariants for robustness against illumination variations.”