2022
DOI: 10.1109/tgrs.2022.3173610
|View full text |Cite
|
Sign up to set email alerts
|

Ship Detection in High-Resolution Optical Remote Sensing Images Aided by Saliency Information

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
13
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
4
3

Relationship

0
7

Authors

Journals

citations
Cited by 27 publications
(13 citation statements)
references
References 53 publications
0
13
0
Order By: Relevance
“…It can narrow down the detection range and enhance detection efficiency. Ren et al [70] added a saliency prediction branch to introduce saliency information with stronger foreground expression ability in SDORSIs. It improves the ship detection capability in complex environments.…”
Section: Saliency-constraint-based Methodsmentioning
confidence: 99%
“…It can narrow down the detection range and enhance detection efficiency. Ren et al [70] added a saliency prediction branch to introduce saliency information with stronger foreground expression ability in SDORSIs. It improves the ship detection capability in complex environments.…”
Section: Saliency-constraint-based Methodsmentioning
confidence: 99%
“…For remote sensing, LEO satellite observes and gathers earth resource data on low-earth orbit. Such data presents the features and changes of ground objects, and is often used for geographical applications [31][32] [33]. For example, farmland monitoring promotes agricultural harvesting production.…”
Section: Leo Satellites For Remote Sensing and On-orbit Computingmentioning
confidence: 99%
“…Song et al proposed an improved parallel ISSD ship detection algorithm based on the SSD target detection network [54]. By introducing a new feature extraction layer generated by a saliency dataset and the extraction layer of the original network for feature fusion [55], the ship recognition rate under the occlusion of thin-cloud and fog is effectively improved. This method effectively improves the ship recognition rate in the environment of thin-cloud and fog occlusion.…”
Section: B Ship Detection Strategy In Foggy Environmentmentioning
confidence: 99%
“…Unlike the images in computer vision (CV), such as Microsoft Common Objects in Context (COCO) [42] and Pascal Visual Object Classes (VOC) [43], targets in satellite remote sensing images are usually very small because remote sensing images are taken from a distance, usually hundreds or even thousands of kilometers from the ground. For example, in a remote sensing image of 1000×1000 pixels, a ship target only occupy 50×50 pixels [44][45]. In terms of algorithms, the mainstream target detection algorithms based on deep learning come from the field of CV.…”
Section: Introductionmentioning
confidence: 99%