Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Brain-computer combined target detection method and system based on RSVP normal form

A target detection and paradigm technology, applied in the field of target detection, can solve the problems of low recognition efficiency and low discrimination accuracy, and achieve the effects of enhanced robustness, good real-time performance, and good portability

Active Publication Date: 2020-08-28
BEIJING UNIV OF POSTS & TELECOMM
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among the existing target image screening methods, artificial methods can make full use of the cognitive ability and visual information processing ability of the human brain, and the target image recognition accuracy is high, but its recognition efficiency is low
The computer artificial intelligence method has huge information storage capacity and high-speed processing speed, but its discrimination accuracy is low, and currently it can only identify some low-level feature information.
[0004] At present, there is no human-machine fusion system and method based on the RSVP paradigm for target detection in UAV aerial images

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
  • Brain-computer combined target detection method and system based on RSVP normal form
  • Brain-computer combined target detection method and system based on RSVP normal form
  • Brain-computer combined target detection method and system based on RSVP normal form

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] This embodiment is used to provide a brain-computer combination target detection method based on the RSVP paradigm, such as figure 1 method flow chart and Figure 5 As shown in the control flow chart, it includes the following steps:

[0044] Step 1: Receive the aerial image returned by the UAV;

[0045] The target appears in multiple sub-pictures from multiple angles, which is more conducive to target recognition. Therefore, for the aerial pictures taken continuously by the UAV, some overlaps should be satisfied to ensure that the target is photographed from multiple angles. Therefore, for the aerial pictures taken continuously by the UAV, the heading overlap rate is set. That is, for two aerial images taken continuously, there are repeated sub-images between the sub-images obtained by cutting them.

[0046] Step 2: using the image cutting algorithm to cut the aerial image to obtain the stimulus image and store it;

[0047] For the whole aerial image of the drone, ...

Embodiment 2

[0105] This embodiment is used to provide a brain-computer combination target detection system based on the RSVP paradigm, including:

[0106] An aerial image receiving unit is used to receive the aerial image returned by the UAV;

[0107] Stimulus picture generating unit, used to adopt picture cutting algorithm to cut the aerial image, obtain the stimulus picture, and store it;

[0108] Stimulus picture sequence generating unit, used to select a piece of said stimulus picture in order of storage to form a stimulus picture sequence; wherein, a is a constant;

[0109] An EEG signal acquisition unit, configured to continuously present the sequence of stimulating pictures to the subject to obtain the subject's EEG signal;

[0110] An EEG signal recognition unit is used to use the trained HDCA algorithm model to score the EEG signals corresponding to each of the stimulating pictures to obtain a recognition result; the recognition result is a target picture and a non-target pictur...

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 a brain-computer combined target detection method and system based on an RSVP normal form, being characterized by cutting an aerial image of an unmanned aerial vehicle to obtain a stimulation picture; continuously presenting a stimulation picture sequence to a testee to obtain an electroencephalogram signal of the testee; providing a novel target online identification algorithm by combining an FTRL online algorithm and an HDCA offline algorithm, and performing real-time scoring on the electroencephalogram signal of the testee, thereby realizing target identification. According to the brain-computer combined target detection method and system, the recognition precision of the algorithm is improved, and the training time is shortened, and the robustness of the systemis enhanced.

Description

technical field [0001] The invention relates to the technical field of target detection, in particular to a brain-computer combination target detection method and system based on the RSVP paradigm. Background technique [0002] There are two main types of existing UAV target detection and search and rescue systems: target positioning with beacons and target positioning based on images. Some personnel wear a specially developed individual beacon machine to transmit data with the drone during the mission. In contrast, image-based target positioning has a wider range of applications. However, the machine vision-related algorithms used in the existing image-based target positioning technology often require a large amount of training data and a large number of parameter adjustments for target detection in order to enhance the system's ability to recognize targets, and can only detect specified targets. , if a new recognition target is added, the model needs to be retrained. ...

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
IPC IPC(8): G06K9/00G06K9/62G06F3/01
CPCG06F3/015G06V20/00G06V2201/07G06F18/214Y02T10/40
Inventor 张洪欣张舒玲杨晨叶晓晨袁超赵玉雪
Owner BEIJING UNIV OF POSTS & TELECOMM
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
Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com