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

Ship detection method based on a sea surface infrared remote sensing image

A technology for remote sensing images and ship detection, which is applied to instruments, character and pattern recognition, scene recognition, etc., and can solve the problems of poor adaptability and adaptability to sea scenes

Inactive Publication Date: 2019-04-05
北京市遥感信息研究所
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among them, the methods based on visual perception mechanism mainly include methods based on selective attention mechanism, visual saliency model and visual asymmetry mechanism, which are easily disturbed by light, weather and sea conditions, and have poor adaptability; The method mainly detects ships from grayscale information such as contrast, gradient, edge, variance, etc., and has poor adaptability to different types of sea scenes.

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
  • Ship detection method based on a sea surface infrared remote sensing image
  • Ship detection method based on a sea surface infrared remote sensing image
  • Ship detection method based on a sea surface infrared remote sensing image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The preferred embodiments of the present invention will be described below in conjunction with the accompanying drawings of the specification. It should be understood that the preferred embodiments described here are only used to illustrate and explain the present invention, not to limit the present invention, and in the case of no conflict, the present invention The embodiments in and the features in the embodiments can be combined with each other.

[0031] The specific implementation steps of the method for detecting maritime targets in infrared remote sensing images based on sea scene classification provided by the present invention will be described in detail below with reference to the accompanying drawings. Such as figure 1 As shown, for infrared remote sensing images, the following steps can be used to accurately extract maritime targets in different scenes:

[0032] (1) Divide the infrared remote sensing image according to the size of M×M pixels to obtain sub-blocks...

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 ship detection method based on a sea surface infrared remote sensing image. The ship detection method comprises the following steps: dividing and quantifying the infrared remote sensing image to obtain infrared remote sensing image quantification subblocks; Carrying out statistics on each infrared remote sensing image quantization sub-block to obtain temperature distribution of the infrared remote sensing image quantization sub-blocks; Dividing the infrared remote sensing image quantization sub-blocks into three types of scenes according to the temperature frequency distribution concentration of the infrared remote sensing image quantization sub-blocks; Quantifying the sub-blocks of the infrared remote sensing image in the scene without obvious shielding and thincloud shielding, and determining an offshore target by counting the cumulative distribution of the temperature frequency; And quantifying the sub-blocks of the infrared remote sensing image in the thick cloud shielding scene, performing circumferential filtering on all pixel points in the sub-blocks, and determining an offshore target. According to the invention, the detection accuracy of the infrared remote sensing image ship under different marine scenes is greatly improved.

Description

Technical field [0001] The invention relates to a remote sensing image marine detection method, in particular to an infrared remote sensing image marine detection method based on sea scene classification, and belongs to the technical field of digital image processing. Background technique [0002] Remote sensing image ship detection can effectively monitor ships in the "two oceans and four seas" area, and play a pivotal role in maintaining channel safety, supervising the marine exclusive economic zone, and reducing disputes; in civil use, remote sensing image ship detection is at sea Traffic control, marine environment monitoring, and fighting against illegal fishing, smuggling and smuggling play an important role. [0003] The infrared sensor uses the thermal radiation difference between the target and the environment to image, with high temperature sensitivity, large dynamic range, high spatial resolution, strong fog penetration, and can work day and night. With the implementati...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/13G06F18/24
Inventor 赵鹏徐其志李伟王红钢
Owner 北京市遥感信息研究所