Sea surface obstacle detection method based on sea-sky-line and visual saliency fusion

The invention belongs to the technical field of computer vision, and particularly discloses a sea surface obstacle detection method based on sea-sky-line and visual saliency fusion. The method comprises the following specific steps: (1) detecting a sea-sky-line position in an image, and extracting a...

Full description

Saved in:
Bibliographic Details
Main Authors LI HENGYU, ZHANG TIEHUI, LUO JUN, YANG WANHUI, XIE SHAORONG
Format Patent
LanguageChinese
English
Published 17.11.2020
Subjects
CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
HANDLING RECORD CARRIERS
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
PRESENTATION OF DATA
RECOGNITION OF DATA
RECORD CARRIERS
Online AccessGet full text

Cover

More Information
Summary:The invention belongs to the technical field of computer vision, and particularly discloses a sea surface obstacle detection method based on sea-sky-line and visual saliency fusion. The method comprises the following specific steps: (1) detecting a sea-sky-line position in an image, and extracting a seawater region image in the image according to the sea-sky-line position; (2) calculating the spatial significance of the seawater region image; (3) calculating the time domain saliency of the seawater region image; (4) fusing the spatial saliency and the time domain saliency of the seawater region image to obtain a visual saliency map of the seawater region image; and (5) segmenting the visual saliency map by adopting a fixed threshold segmentation method, and extracting an obstacle target inthe visual saliency map. The detection method can eliminate the interference of complex background information, greatly improves the accuracy of obstacle target detection, facilitates the detection of a sea surface target un
Bibliography:Application Number: CN202010809048