Deep learning ship target detection method based on edge candidate region extraction

A candidate area, target detection technology, applied in the field of deep learning ship target detection, can solve problems such as sea conditions, cloud conditions, lighting differences, target influence, etc., and achieve the effect of accurate target detection and positioning results

Active Publication Date: 2018-06-05
BEIHANG UNIV
View PDF4 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] (1) Under the influence of different seasons, different shooting times, and different weather conditions, there are large differences in sea conditions, cloud conditions, and illumination, which have a great impact on the target;

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
  • Deep learning ship target detection method based on edge candidate region extraction
  • Deep learning ship target detection method based on edge candidate region extraction
  • Deep learning ship target detection method based on edge candidate region extraction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0057] Due to the large width of the optical remote sensing image, it occupies a large space in the computer storage. However, due to the capacity limitation of the computer's internal storage devices such as video memory and internal memory, it is difficult to directly use a complete optical remote sensing image as training data for training. Model optimization or direct model testing. The traditional method mostly adopts the strategy of sliding window to sol...

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 provides a deep learning ship target detection method based on edge candidate region extraction. The deep learning ship target detection method provided by the invention has the following advantages that a remote sensing image under different conditions is subjected to edge detection by utilizing a structured random forest model to obtain purposeful edge detection results, and the influence of sea states, illumination and other situations on the edge detection results is inhibited; candidate regions where targets possibly exist are extracted from the remote sensing image with large width by utilizing a candidate region extraction algorithm based on the edge detection results; the selection results are inputted into a deep learning network, so that the network processing efficiency is improved, and the detection speed is increased.

Description

technical field [0001] The present invention relates to the technical field of digital image processing, and more specifically relates to a deep learning ship target detection method based on edge candidate region extraction. Background technique [0002] Object detection technology is one of the core issues in the field of computer vision. my country has a vast territorial sea, long coastline, and rich marine resources. In order to effectively manage my country's marine resources, protect maritime rights and interests, and maintain territorial waters, it is of great significance to the management and monitoring of ships on the sea surface. That is, the research on ship target detection in remote sensing images is of great importance. Value. In recent years, with the rapid development of graphics processing unit (GPU) and other hardware, the computing performance of computers has been greatly improved, which provides an important foundation for the training of large-scale de...

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): G06K9/46G06K9/62G06T7/13G06N3/04
CPCG06T7/13G06V10/462G06V10/44G06N3/045G06F18/214
Inventor 姜志国张浩鹏黄洁谢凤英赵丹培罗晓燕史振威尹继豪
Owner BEIHANG 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