Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A detection method for abnormal personnel in rail transit based on motion recognition

A motion recognition and personnel detection technology, applied in the field of aviation surveillance, can solve the problem of indistinguishable abnormal personnel and staff, achieve high practicability and robustness, and solve the effect of huge cost

Active Publication Date: 2020-04-14
BEIHANG UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the above problems, the present invention proposes a detection method for abnormal personnel in rail transit based on motion recognition, which solves the problem of robustness of space-based monitoring of abnormal personnel and the difficulty of distinguishing abnormal personnel from staff, and also provides solutions for people in other fields. Anomaly detection problem provides a reference

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
  • A detection method for abnormal personnel in rail transit based on motion recognition
  • A detection method for abnormal personnel in rail transit based on motion recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] In order to make the technical principles of the present invention more clearly understood, the embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0035] The present invention is a method for detecting abnormal personnel in rail transit based on action recognition, which conducts inspections on the daily operation and maintenance of railways, reduces operation and maintenance costs, and distinguishes between staff and abnormal personnel, and timely checks out risky personnel on the railway, and detects abnormal situations. Alarm to improve the safety of railway operation.

[0036] Such as figure 2 As shown, the present invention trains the SSD (Single Shot Detection) detection model based on convolutional neural network, key point detection model, LSTM action recognition model, Resnet-18 clothing classification model and DNN personnel type classification model, and it is tested, After achieving the c...

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 an action recognition-based detection method for abnormal personnel in rail transit, which belongs to the field of aviation surveillance. UAVs are used to inspect railways, and frames are drawn from the video. By training and using the SSD detection model, the position information of each person in each video frame image is obtained, and the local area containing the person is intercepted. Point detection model and Resnet-18 clothing classification model for training; use the key point detection model to predict the joint coordinates of each person, form the joint coordinates within a certain period of time into a human skeleton sequence, input the LSTM action recognition model, and identify the action category of each person . Clothing classification of people by Resnet‑18 clothing classification model. According to each person's action category and corresponding appearance and clothing, determine whether the person is a staff member. The invention solves the problem of huge cost of traditional manpower inspection or roadbed inspection, and has high practicability and robustness.

Description

technical field [0001] The invention belongs to the field of aviation monitoring, in particular to an action recognition-based detection method for abnormal persons in rail transit, which is used for monitoring abnormal persons in railways. Background technique [0002] During the daily operation and maintenance of the railway, there will be a certain flow of people, for example, the normal maintenance of railway workers, pedestrians crossing the railway, or criminals attempting to cause damage to the railway and so on. The abnormal appearance of these personnel seriously affected the normal operation of the railway, causing unnecessary casualties and property losses. In order to avoid the occurrence of such dangers, railways usually adopt measures such as patrolling the railways or using protective nets to prevent losses caused by abnormal intrusion of personnel. [0003] The traditional inspection methods are as follows, all of which have certain defects: such as 1), regu...

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 Patents(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/20G06V40/10G06F18/24G06F18/214
Inventor 曹先彬罗晓燕王昊臣王帅
Owner BEIHANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products