2017
DOI: 10.1016/j.neucom.2017.06.031
|View full text |Cite
|
Sign up to set email alerts
|

Two-level superpixel and feedback based visual object tracking

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
7
0

Year Published

2018
2018
2019
2019

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 8 publications
(7 citation statements)
references
References 26 publications
0
7
0
Order By: Relevance
“…To solve the model drift problem, another paper [18] proposed an optimized tracking framework. There are also some papers [19]- [20] combined traditional algorithms with algorithms based on Correlation Filter. They have achieved good tracking results obviously.…”
Section: Related Workmentioning
confidence: 99%
“…To solve the model drift problem, another paper [18] proposed an optimized tracking framework. There are also some papers [19]- [20] combined traditional algorithms with algorithms based on Correlation Filter. They have achieved good tracking results obviously.…”
Section: Related Workmentioning
confidence: 99%
“…A superpixel based representation got much a ention by computer vision community for object recognition [17], human detection [120], activity recognition [163], and image segmentation [2]. Numerous tracking algorithms have been developed using superpixels [75,95,154,155,167].…”
Section: Superpixel Basedmentioning
confidence: 99%
“…Optical ow is used for the temporal smoothness to impose short-term target appearance, while appearance tness servers as long-term appearance model to enforce objectness. Wang et al [154] presented a Bayesian tracking method at coarse-level and ne-level superpixel appearance model. e coarse-level appearance model computes few superpixels such that there is only one superpixel in the target bounding box, and a con dence measure de nes whether that superpixel corresponds to background/target.…”
Section: Superpixel Basedmentioning
confidence: 99%
“…As the term "superpixel" suggests, it meets the goal of representing an image by perceptually meaningful entitieswhich heavily reduces the number of pixels. This is why superpixels can significantly improve the efficiency of segmentation in practice and become a key preprocessing step for advanced tasks such as video segmentation [2], target tracking [3], object recognition [4], super-resolution [5] and depth estimation [6].…”
Section: Introductionmentioning
confidence: 99%