Minimum error bounded efficient ℓ1 tracker with occlusion detection

By Xue Mei, Haibin Ling, Yi Wu, Erik Blasch, Li Bai. Computer Vision and Pattern Recognition, 2011

371 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/070375a20acf9252f903164586c75110472cd84f

How researchers see this paper

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

In Computational Mechanics

In Computer Vision and Pattern Recognition

In Electrical and Electronic Engineering

Citations in the corpus

Object Tracking Benchmark (2015, background): “Furthermore, Mei and Ling [40] proposed a tracking approach based on sparse representation to handle the corrupted appearance and recently it has been further improved [41, 57, 64, 10, 55, 42].”
Online Object Tracking: A Benchmark (2013, background): “tion to handle the corrupted appearance and recently it has been further improved [41, 57, 64, 10, 55, 42].”
Visual tracking via adaptive structural local sparse appearance model (2012, methodology): “Sparse representation has been successfully applied in numerous vision applications [21, 16, 12, 17, 11].”
Struck: Structured Output Tracking with Kernels (2016, neutral): “Even when the object is known, having a flexible tracker that can adapt its model at runtime is attractive and, in real-world scenarios, often essential for successful tracking.”
A survey of appearance models in visual object tracking (2013, positive): “Another way of improving the efficiency of the 1 tracker [Mei and Ling 2009] is to reduce the number of 1 minimizations in the process of evaluating test samples [Mei et al. 2011].”
MEEM: Robust Tracking via Multiple Experts Using Entropy Minimization (2014, background): “Other trackers [22,32,14] use a “censorship mechanism” where an update is prevented when certain criteria are met (or not met).”
Sparse coding based visual tracking: Review and experimental comparison (2013, methodology): “[46], the number of ‘1-norm minimization is reduced by exploiting the fast computational lower bound of the reconstruction error to exclude the unimportant particles.”
Real time robust L1 tracker using accelerated proximal gradient approach (2012, methodology): “Even though the minimal error bound [16] was proposed to reduce the computation load for L1 tracker, there are still many 1-norm related minimizations for solving during the tracking process, For example, in the sequence car with 620 frames, around 80,000 1-norm related minimizations (5) needs to be”
Visual Tracking: an Experimental Survey (2013, neutral): “L1O [60] Multiple boxes Array, intensities Gaussian Constraint optimization L1, robust Update bounding boxes”
Robust Visual Tracking via Structured Multi-Task Sparse Learning (2012, methodology): “2006) has been successfully applied to visual tracking (Mei and Ling 2011; Mei et al. 2011; Liu et al. 2010, 2011).”
A Protocol for Evaluating Video Trackers Under Real-World Conditions (2013, methodology): “The discrepancy is computed based on a distance-based criterion [9]–[11] or an”
Transfer Learning Based Visual Tracking with Gaussian Processes Regression (2014, background): “iii) Some work [9,14], based on the part-based model, focuses on selectively updating the parts of the object to handle the tracking drift caused by heavy occlusion; other work [26,3,45] use occlusion detection strategy to determine whether the template should be updated with the new observation.”