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

Identification crowdsourcing system of optical remote sensing ship models based on fine granularity features

An optical remote sensing, fine-grained technology, applied in scene recognition, character and pattern recognition, instruments, etc., can solve the problems of lack of feasibility and lack of scalability

Active Publication Date: 2018-07-27
SHANGHAI OCEAN UNIV +1
View PDF6 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0016] (2) The existing artificial selection to extract the underlying features lacks scalability
[0018] (3) It is not feasible to construct a large-scale training sample set
However, there is no report on the method for identifying the type of this optical remote sensing ship.

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
  • Identification crowdsourcing system of optical remote sensing ship models based on fine granularity features
  • Identification crowdsourcing system of optical remote sensing ship models based on fine granularity features
  • Identification crowdsourcing system of optical remote sensing ship models based on fine granularity features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0143] The specific embodiments provided by the present invention will be described in detail below in conjunction with the accompanying drawings.

[0144] Please refer to Image 6 , Image 6 It is a block flow diagram of an optical remote sensing ship model identification crowdsourcing system based on fine-grained features of the present invention. A kind of optical remote sensing ship type identification crowdsourcing system based on fine-grained features, the optical remote sensing ship type identification crowdsourcing system includes the following steps:

[0145] Step S1, design the fine-grained features of the ship and its formal expression, design the ship feature labeling task and release it in the crowdsourcing mode;

[0146] Step S2. Obtain the standard label and confidence level of the ship through multi-level quality control;

[0147] Step S3, using the decision tree algorithm to automatically classify the fine-grained feature standard annotations and hand over ...

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 relates to an identification crowdsourcing system of optical remote sensing ship models based on fine granularity features. The identification crowdsourcing system of the optical remotesensing ship models comprise the following steps: a step S1, designing the fine granularity features and formalization representation of ships, and designing ship feature annotation tasks and issuingby adopting a crowdsourcing mode; a step S2, performing multi-stage quality control to obtain standard annotation and a confidence level; and a step S3, automatically classifying the standard annotation of the fine granularity features by adopting a decision tree algorithm and handling over the ship targets with low confidence level to experts to audit and judge and determine, and finally, realizing automatic identification of the ship models. The identification crowdsourcing system disclosed by the invention has the advantages that through crowdsourcing decomposition tasks and cooperative processing, difference advantages of manual judgement and determination and computer identification are combined, and the reliable and high-effective automatic identification of the ship models is realized.

Description

technical field [0001] The present invention relates to the technical fields of image feature design, ship recognition, machine learning, and image annotation crowdsourcing, and specifically designs fine-grained features for ship targets in optical remote sensing images and uses crowdsourcing systems to Methods for labeling and identifying ships. Background technique [0002] Ship target recognition is an important issue of computer vision and pattern recognition, and it is of great significance in military and civilian fields such as precision guidance, maritime traffic management, anti-terrorism, and search and rescue. In the prior art, ship target recognition mainly includes: remote sensing technology, optical remote sensing ship recognition technology, crowdsourcing system, etc. The specific contents are as follows: [0003] 1. Remote sensing technology [0004] Remote sensing technology is a space observation technology that emerged in the 1970s. Large-scale, long-se...

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
CPCG06V20/13G06F18/24323
Inventor 唐非凡杜艳玲陈德利李舰宋洪波汪卫宋巍
Owner SHANGHAI OCEAN UNIV