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

Subway bus abnormal retention identification method based on deep learning

A technology of deep learning and recognition methods, applied in character and pattern recognition, instruments, computer components, etc., can solve problems such as low work efficiency

Pending Publication Date: 2021-09-14
GUANGZHOU DIQING ELECTRONICS TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, there is no specific identification method for abnormally stranded passengers. It can only rely on patrol personnel to conduct patrols and video surveillance personnel to conduct patrols, and the work efficiency is low.

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] Below in conjunction with the specific implementation mode for further description:

[0028] A method for identifying the abnormal detention of subway buses based on deep learning, characterized in that it comprises the following steps:

[0029] 1) passenger identification;

[0030] 2) Passenger mark;

[0031] 3) Passenger behavior feature extraction;

[0032] 4) Feature classification and recognition;

[0033] 5) Determine whether to issue an early warning.

[0034] In step 1, the video image is obtained through the camera, all the human body information is obtained through the human body recognition algorithm, and the human body information of the staff member that is pre-set and stored in the database is used for comparison. If the result is non-staff, proceed to the next step.

[0035] In step 2, each passenger is marked by a pedestrian re-identification method, wherein the pedestrian re-identification method includes the following steps:

[0036] S11 uses the...

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 the technical field of subway bus management, in particular to a subway bus abnormal retention identification method based on deep learning. The method comprises the following steps: 1) passenger identification; 2) passenger marking; 3) passenger behavior feature extraction; 4) feature classification and recognition; 5) determination of whether to give out early warning or not. According to the method, all passengers are marked through simple human body recognition, then behavior recognition and further marking of behavior abnormity are carried out, and emotion recognition and re-marking of abnormity are carried out; therefore, early warning is carried out accurately, and recognition and early warning can be carried out on detained persons.

Description

technical field [0001] The invention relates to the technical field of subway bus management, in particular to a deep learning-based identification method for abnormal detention of subway buses. Background technique [0002] On public transportation such as subways and buses, there may sometimes be abnormal stranded passengers, such as children forgotten by their parents in the carriage, disabled or elderly people who move slowly, people with mental disorders, and even trouble-seekers. At present, there is no specific identification method for abnormally stranded passengers, and it can only rely on inspectors to conduct patrols and video surveillance personnel to conduct inspections, and the work efficiency is low. Contents of the invention [0003] Aiming at the deficiencies of the prior art, the present invention provides a method for identifying abnormal retention by using big data and deep learning. [0004] Technical scheme of the present invention is: [0005] A me...

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): G06K9/00G06K9/62G08B21/00
CPCG08B21/00G06F18/2411
Inventor 常伟余捷全
Owner GUANGZHOU DIQING ELECTRONICS TECH