Target recognition training system and method based on EEG-NIRS

A training system and target recognition technology, applied in character and pattern recognition, input/output process of data processing, input/output of user/computer interaction, etc. Recognition ability, low efficiency of manual recognition, etc.

Pending Publication Date: 2020-12-25
SHANGHAI UNIV
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

On the basis of big data, machine vision can achieve high-speed and accurate recognition of some target objects with simple background environments and obvious contour features, but for tiny target objects with complex background environments and indistinct contour features, due to the limitation of generalization ability, Machine vision is difficult to accurately identify
Human vision is far superior to machine vision in the perception of tiny target images in complex backgrounds, but the efficiency of manual recognition is relatively low, and the brain is prone to fatigue and cannot work for a long time. While maintaining a high recognition rate, it ensures a high recognition accuracy
At present, the human-computer hybrid target recognition technology based on EEG can provide trainers with a multi-stage progressive training system, but there is a shortcoming: due to the lack of quantitative fatigue indicators, the system cannot be humanized according to The fatigue level of the trainers automatically adjusts the presentation frequency of the target image in time, which will easily lead to poor training effect and low efficiency, and cannot effectively improve the target recognition ability of the trainers; in the actual target recognition process, the system cannot The fatigue level of personnel is adjusted in time, and the staff need to be forced to work fatigued, resulting in a decrease in the accuracy of target recognition

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
  • Target recognition training system and method based on EEG-NIRS
  • Target recognition training system and method based on EEG-NIRS
  • Target recognition training system and method based on EEG-NIRS

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0075] see figure 1, a target recognition training system based on EEG-NIRS, comprising a signal acquisition cap 1, an EEG signal amplifier 2, a near-infrared brain function imager 3 and a computer 4, characterized in that: the signal acquisition cap 1 is connected to the EEG signal The input end of the amplifier 2 and the input end of the near-infrared brain function imager 3; the signal of the host computer 5 of the computer 4 is connected to the output end of the EEG signal amplifier 2 and the output end of the near-infrared brain function imager 3; the computer 4 It consists of a host computer 5, a display 6, a keyboard 7, a P300 decoding unit 8, and a NIRS analysis unit 9. The display 6 displays the training system interface, and the user wears a signal collection cap 1 on his head and watches the information interface through the display 6. The EEG-based - The target recognition training system of NIRS calculates the target recognition rate of the user as an evaluation i...

Embodiment 2

[0078] This embodiment is basically the same as Embodiment 1, and the special features are as follows:

[0079] see figure 1 with figure 2 , the trainer wears the signal collection cap 1, opens the training system interface in the computer 4, and selects different training stages according to needs; after the training starts, based on the RSVP paradigm, the display interface randomly displays target pictures and non-target pictures at a set frequency , the trainers stare at the display interface, the EEG electrodes on the signal collection cap 1 collect the EEG signals of the trainers, and transmit them to the P300 decoding unit 8 in the computer 4 after being amplified by the EEG signal amplifier 2. 300 milliseconds after the target picture, the P300 EEG signal is induced, and the induced EEG signal is decoded through filtering processing, feature extraction and classification recognition algorithm. The decoding result is combined with the label information corresponding to...

Embodiment 3

[0083] This embodiment is basically the same as the above-mentioned embodiment, and the special features are as follows:

[0084] see figure 1 , the signal acquisition cap 1 is composed of EEG acquisition electrode part and near-infrared emitter and receiver part; EEG acquisition electrode part is wet electrode of 32 leads, through special parallel communication cable and EEG signal amplifier 2 connection, to transmit the collected EEG signals; the near-infrared transmitter and receiver are composed of 8 transmitters and 8 receivers, which form the collection area of ​​24 near-infrared optical channels, and connect with the near-infrared optical channel through a dedicated parallel communication cable. The brain function imager 3 is connected to transmit the collected near-infrared light signal.

[0085] see figure 1 , described computer 4, hardware part comprises: main frame 5, monitor 6 and keyboard 7; 3. The light signal data transmitted and the operating instructions tr...

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 target recognition training system and method based on an EEGNIRS. The target recognition training system comprises a signal acquisition cap, an electroencephalogram signal amplifier, a near-infrared brain function imager, a computer, a training system interface, a P300 decoding unit and an NIRS analysis unit. A trainee wears a signal acquisition cap and opens a trainingsystem interface; after training is started, the display interface randomly displays a target picture and a non-target picture, a trainee watches the display interface, and the signal acquisition capacquires an electroencephalogram signal of the trainee, amplifies the electroencephalogram signal and transmits the amplified electroencephalogram signal to the P300 decoding unit for decoding, so that a target recognition rate is calculated, and the recognition capability is further evaluated; and an NIRS analysis unit in the computer is used for quantifying the brain fatigue degree of the trainee and adjusting the frequency of picture presentation in the display interface. According to the invention, multi-stage progressive training can be realized, the image presentation frequency can be adaptively adjusted according to the brain fatigue degree of a trainee, the target recognition rate can be analyzed according to P300 electroencephalogram, and the ability of the trainee can be evaluated.

Description

technical field [0001] The present invention relates to the field of human-machine mixed target image recognition, in particular to a target recognition training system and method based on EEG-NIRS, which is a kind of target recognition training system and method based on electroencephalography (electroencephalography, EEG)-near-infrared spectroscopy (NIRS) A target recognition training system and method that can realize multi-stage progressive training, adaptively adjust the frequency of image presentation according to the degree of brain fatigue of trainers, analyze the target recognition rate based on P300 EEG and evaluate the ability of trainers. Background technique [0002] With the further development of artificial intelligence, machine vision target recognition technology based on deep learning theory is widely used, such as obstacle recognition in the field of automatic driving, face recognition in access control systems, environmental monitoring based on synthetic a...

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): G06F3/01G06Q10/06G06K9/62G06K9/80
CPCG06F3/015G06Q10/06393G06V10/20G06F18/2414
Inventor 杨帮华周雨松夏新星汪小帆高守玮
Owner SHANGHAI 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