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

A method for detecting ship targets at sea

A target detection and ship technology, applied in the field of target detection, can solve the problems of reliability and real-time performance of the interference detection system, and achieve the effects of reducing computational complexity, improving accuracy, and improving detail

Active Publication Date: 2021-08-27
SHANGHAI MARITIME UNIVERSITY
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The influence of complex sea clutter on ship target detection will seriously interfere with the reliability and real-time performance of the detection system, so the research topic of using saliency to detect sea ship images has great practical significance

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 method for detecting ship targets at sea
  • A method for detecting ship targets at sea
  • A method for detecting ship targets at sea

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] The present invention will be further elaborated below by describing a preferred specific embodiment in detail with reference to the accompanying drawings.

[0053] like figure 1 As shown, the present invention proposes a saliency color abstract network structure integrating local stability, the main frame of the network structure is based on color saliency detection, and a simple structure of the stability detection algorithm is introduced to selectively eliminate clutter regions, Maintain effective information on ship targets to improve detection accuracy. This network structure is mainly divided into two parts. The first part is the stability detection, which extracts the ship target by screening the local stable area, and eliminates the sea clutter area where the pixel gray value changes frequently in the image. In the second part, after RG filtering and superpixel segmentation preprocessing, the color feature and spatial distance information of each pixel are comb...

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 discloses a method for detecting a ship target at sea, which comprises: processing a visible light ship image to obtain a region stable map; processing the visible light ship image to obtain a color abstract saliency map; fusing the region stable map and the color abstract saliency map to form The final saliency ship target map. The present invention is aimed at images containing sea clutter, and is different from the top-down algorithm that simply uses low-level feature detection. Different from the low-rank processing of the image, the present invention is based on the original image of visible light, and pays more attention to the combination of stable regions and color salience, which helps to filter out sea clutter.

Description

technical field [0001] The invention relates to a target detection technology, in particular to an efficient detection method for visible light targets in a complex background and a screening process for sea clutter. Background technique [0002] Object detection is the premise of various advanced vision tasks and is widely used in various image processing tasks. In recent years, the salient target detection technology has been proposed to play an important role in detecting a variety of natural images, but relatively speaking, there is no mature application in the detection of ship targets under the light. Therefore, in the past decades, many methods have been adopted to improve the accuracy and stability of detection. However, in scenarios with extremely low signal-to-noise ratios such as coastal defense monitoring, due to the complex background and ocean clutter interference, the detection accuracy and stability problems are still not well resolved, and its performance i...

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): G06K9/32G06K9/46G06T7/66
CPCG06T7/66G06V10/25G06V10/56
Inventor 童子琛周薇娜
Owner SHANGHAI MARITIME UNIVERSITY