Document Detail

What are We Tracking: A Unified Approach of Tracking and Recognition.
MedLine Citation:
PMID:  22997269     Owner:  NLM     Status:  Publisher    
Tracking is essentially a matching problem. While traditional tracking methods mostly focus on low-level image correspondences between frames, we argue that highlevel semantic correspondences are indispensable to make tracking more reliable. Based on that, a unified approach of low-level object tracking and high-level recognition is proposed for single object tracking, in which the target category is actively recognized during tracking. High-level offline models corresponding to the recognized category are then adaptively selected and combined with low-level online tracking models so as to achieve better tracking performance. Extensive experimental results show that our approach outperforms state-of-the-art online models in many challenging tracking scenarios such as drastic view change, scale change, background clutter, and morphable objects.
J Fan; X Shen; Y Wu
Related Documents :
22482909 - Structure unifies the viral universe.
24262569 - Experimental design approach to evaluate the impact of oak chips and micro-oxygenation ...
24431999 - Nengo: a python tool for building large-scale functional brain models.
22997269 - What are we tracking: a unified approach of tracking and recognition.
23436609 - Sampling stored product insect pests: a comparison of four statistical sampling models ...
23872969 - Statistical modeling of coverage in high-throughput data.
20119329 - Aerosol extinction contribution to atmospheric attenuation in infrared wavelengths.
11003489 - Quantification of gamma-ray compton-scatter nondestructive testing
9339309 - Health impacts of large releases of radionuclides. transport and processes in freshwate...
Publication Detail:
Type:  JOURNAL ARTICLE     Date:  2012-9-13
Journal Detail:
Title:  IEEE transactions on image processing : a publication of the IEEE Signal Processing Society     Volume:  -     ISSN:  1941-0042     ISO Abbreviation:  IEEE Trans Image Process     Publication Date:  2012 Sep 
Date Detail:
Created Date:  2012-9-21     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  9886191     Medline TA:  IEEE Trans Image Process     Country:  -    
Other Details:
Languages:  ENG     Pagination:  -     Citation Subset:  -    
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

Previous Document:  Linear Distance Coding for Image Classification.
Next Document:  Exemplar-based Image Inpainting using Multiscale Graph Cuts.