Remote sensing image rotating ship target detection method based on local straight line matching

A target detection and remote sensing image technology, applied in the field of deep learning, can solve the problem of high false alarm rate, reduce the false alarm rate and improve the effectiveness.

Pending Publication Date: 2021-03-12
HANGZHOU DIANZI UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is accurate enough when the target object to be located is a small target such as a person or a small animal, but it is not suitable for a special rotating target such as a ship, a vehicle, or a road with an angle or radian. This kind of rotating target can be detected by using the method based on dense sub-region cutting, but due to the shape characteristics of the ship with a large aspect ratio, using the conventional sub-region merging method after the detection will lead to a high false alarm rate

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
  • Remote sensing image rotating ship target detection method based on local straight line matching
  • Remote sensing image rotating ship target detection method based on local straight line matching
  • Remote sensing image rotating ship target detection method based on local straight line matching

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The present invention is further analyzed below in conjunction with specific examples.

[0043] In this embodiment, a group of collected ship target images is divided into a training set and a test set. Such as figure 1 As shown, the specific steps to complete the target detection task using a remote sensing image rotating ship target detection method based on local line matching are as follows:

[0044] Step (1), training set data preprocessing

[0045] Use the image annotation tool to annotate the target to be detected in the training set image. Firstly, the coordinates (x, y) of the center point of the target in the image, the width w, the height h of the target, and the angle information angle of the target are obtained. Then according to the set cutting step step and the height h of the target, determine the number n of sub-targets for target cutting:

[0046] n=h / step+1

[0047] Calculate the length h_vec and width w_vec of the subobject:

[0048] h_vec=[h*c...

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 remote sensing image rotating ship target detection method based on local straight line matching. According to the invention, when sub-region dense segmentation is carried out on the target, annotation of the head, the tail and the body of the ship is added, local sub-region division is carried out on the center point of the body sub-target obtained on the test picture byusing hierarchical agglomeration clustering, interference is reduced, and then straight line detection is carried out on the divided local region by using Hough transform; and finally, the points after straight line detection are fit into line segments, thus matching the line segments with the headtail sub-target data, and removing false alarms to complete detection of special targets with anglesand the like. The invention can be used for rotating ship targets and effectively reducing the false alarm rate of detection results.

Description

technical field [0001] The invention belongs to the field of deep learning, and in particular relates to a method for detecting a rotating ship target in a remote sensing image based on local straight line matching. Background technique [0002] At present, target detection has been widely used in military and civilian fields. The deep convolutional neural network can use the target data set to autonomously learn the target to be detected and improve its own model. YOLO V5 is a single-step target detection algorithm. This algorithm does not need to use the region candidate network RPN to extract candidate target information, but directly integrates the two tasks of extracting candidate areas and classifying them into one network, and generates them through the network. The location and category information of the target is an end-to-end target detection algorithm. Therefore, the single-step object detection algorithm has a faster detection speed. [0003] The YOLO V5 mode...

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): G06K9/34G06K9/46G06K9/62G06N3/04G06T7/11G06T7/73
CPCG06T7/11G06T7/73G06T2207/20081G06T2207/20084G06T2207/30204G06V10/443G06V10/267G06V2201/07G06N3/045G06F18/2321G06F18/214
Inventor 陈华杰吕丹妮白浩然
Owner HANGZHOU DIANZI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap