Unlock instant, AI-driven research and patent intelligence for your innovation.

A sea surface obstacle detection method based on fusion of sea antenna and visual saliency

A technology of obstacle detection and sea antenna, which is applied in the field of computer vision, can solve the problems that affect the accuracy of visual obstacle detection, the difficulty of detecting obstacles in the sea, and the complexity and changeability, so as to reduce the amount of calculation, eliminate interference, and improve the calculation speed Effect

Active Publication Date: 2022-07-22
SHANGHAI UNIV
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the changeable climate on the sea, frequent smog, and the shaking of the hull caused by the wind, it has brought certain difficulties to the detection of obstacles on the sea.
At the same time, the environment in the nearshore area is mostly complex and changeable, and a large amount of interference information affects the accuracy of visual obstacle detection

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A sea surface obstacle detection method based on fusion of sea antenna and visual saliency
  • A sea surface obstacle detection method based on fusion of sea antenna and visual saliency
  • A sea surface obstacle detection method based on fusion of sea antenna and visual saliency

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] A sea surface obstacle detection method based on fusion of sea antenna and visual saliency, such as figure 1 shown, including the following steps:

[0065] (1) Acquire a color sea surface image, detect the position of the sea antenna in the sea surface image, and extract the seawater area image in the sea surface image according to the position of the sea antenna.

[0066] The specific operation of detecting the position of the sea line is: use the Hough transform to detect the line of the sea surface image, obtain the selection result, and then use the line with the most "votes" in the selection result as the sea line detection result. According to the detection result of the sea line, the part above the sea line in the sea surface image is discarded as the background information, and the sea water area image is obtained.

[0067] (2) Calculate the spatial saliency of seawater area images.

[0068] The calculation method of spatial saliency is:

[0069] Calculate an...

Embodiment 2

[0109] The content of embodiment 2 is basically the same as that of embodiment 1, and the difference lies in:

[0110] The calculation method of the temporal saliency of the seawater area image in step (3) is:

[0111] The temporal saliency of the seawater region is obtained by linearly weighted fusion of the temporal saliency value of each frame image of the current frame image and its previous i (i=1) frame images.

Embodiment 3

[0113] The content of embodiment 3 is basically the same as that of embodiment 1, and the difference lies in:

[0114] The calculation method of the temporal saliency of the seawater area image in step (3) is:

[0115] The temporal saliency of the seawater region is obtained by linearly weighted fusion of the temporal saliency value of the current frame image and its previous i (i=2) frame images.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention belongs to the technical field of computer vision, and specifically discloses a sea surface obstacle detection method based on the fusion of sea antenna and visual saliency. The specific steps of the method are as follows: (1) Detect the position of the sea antenna in the image, and extract the seawater area image in the image according to the position of the sea antenna; (2) Calculate the spatial saliency of the seawater area image; (3) Calculate the temporal saliency of the seawater area image (4) Integrate the spatial saliency and temporal saliency of the seawater area image to obtain the visual saliency map of the seawater area image; (5) use the fixed threshold segmentation method to segment the visual saliency map to extract the visual saliency map Obstacle target in sex map. The detection method of the invention can eliminate the interference of complex background information, greatly improve the detection accuracy of the obstacle target, is conducive to detecting the sea surface target under the complex background, and has high performance on the static and dynamic obstacle targets in the sea surface image. sensitivity and accuracy.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a sea surface obstacle detection method based on the fusion of sea antennas and visual saliency. Background technique [0002] In recent years, unmanned boats have been more and more widely used in civil and military fields, such as marine environment monitoring, marine surveying and mapping, marine search and rescue, marine patrol, unmanned surface warfare and so on. Among them, the detection of obstacles on the sea surface is the basic task of various sea surface work of unmanned boats, and it is also a key and difficult problem. Due to the changeable climate at sea, frequent occurrence of haze, and hull shaking caused by wind, it is difficult to detect obstacles at sea. At the same time, the environment in the nearshore area is mostly complex and changeable, and a large amount of interference information affects the accuracy of visual obstacle detection. Therefore, a...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06V10/46G06V10/75G06V10/25G06K9/62G06T5/40G06T5/50G06T7/11G06T7/90G06F17/16
CPCG06T7/11G06T7/90G06T5/40G06T5/50G06F17/16G06T2207/20221G06V10/255G06V10/462G06V10/757
Inventor 张铁荟李恒宇杨万辉谢少荣罗均
Owner SHANGHAI UNIV