2016
DOI: 10.1007/s11042-016-4025-7
|View full text |Cite
|
Sign up to set email alerts
|

Small target detection combining regional stability and saliency in a color image

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
19
0

Year Published

2018
2018
2024
2024

Publication Types

Select...
6
3

Relationship

0
9

Authors

Journals

citations
Cited by 40 publications
(19 citation statements)
references
References 24 publications
0
19
0
Order By: Relevance
“…(2) RSS [27]: By considering both the stability and the saliency of small targets, this algorithm presents a novel model, called "RSS". RSS combines the regional stability and saliency to help with figure-ground segregation.…”
Section: Comparison With State-of-the-art Methodsmentioning
confidence: 99%
“…(2) RSS [27]: By considering both the stability and the saliency of small targets, this algorithm presents a novel model, called "RSS". RSS combines the regional stability and saliency to help with figure-ground segregation.…”
Section: Comparison With State-of-the-art Methodsmentioning
confidence: 99%
“…The visual attention operator was used to fuse various features, effectively overcoming the background disturbances such as waves, wakes, and onshore buildings. Lou et al [16] solved the small target detection problem in color images from two aspects of stability and saliency. By multiplying the stability and saliency maps by pixels, the noise interference in the background was eliminated.…”
Section: Related Workmentioning
confidence: 99%
“…The traditional resampling algorithm only resamples the particles according to certain particle weight rules, without considering the particles distributed in the high likelihood region, and the small weight samples fail [11] , leading to particle degradation and new large estimation errors. In response to the negative effects created by resampling techniques, an improved resampling algorithm is proposed to replace the traditional particle resampling algorithm, improve the particle filtering algorithm performance, adaptively adjust the particles distributed in the high likelihood region according to the accuracy factor value reflecting the measurement noise [12] , increase existing knowledge and the same region of likelihood, and improve the algorithm robustness.…”
Section: Particle Filtering Algorithmmentioning
confidence: 99%
“…Therefore, a second-order regression process is used to describe the motion law. The AR(2) model is (12) where is the time series, and are the drift coefficient matrices [13] , is the white noise series, and , where . Let the linear transfer function be .…”
Section: Power Modelmentioning
confidence: 99%