Post-leaving detection method and system thereof

A detection method and model technology, applied in instruments, character and pattern recognition, computer parts and other directions, can solve problems such as easy generation of false alarms, undetectable moving targets, etc., to improve accuracy, improve accuracy, and reduce errors. The effect of the probability of detection

Active Publication Date: 2017-08-29
GOSUNCN TECH GRP
View PDF8 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is only suitable for indoor scenes, and when the target does not move f

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
  • Post-leaving detection method and system thereof
  • Post-leaving detection method and system thereof
  • Post-leaving detection method and system thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] Such as figure 1 As shown, it is a flow chart of a specific embodiment of an off-duty detection method of the present invention. see figure 1 , a kind of off-duty detection method of present specific embodiment is carried out in two stages, and the first stage is the model training stage of human head, left and right ears, human body upper body, people's whole body, and the second stage is the off-duty detection stage; Specifically:

[0052] S1. Model training stage: train the training set samples including various types of human head, left and right ears, human upper body, and human body images to obtain human head models, left and right ear models, human upper body models, and human body models;

[0053] S2. Leaving post detection stage: Obtain the video frame sequence of the sentry box, use the human head model, left and right ear model, human upper body model, and human body model to detect the sentry box video frame sequence, and at least detect the human head, le...

Embodiment 2

[0080] On the basis of Embodiment 1, the present invention also provides an off-duty detection system. Such as Figure 4 As shown, it is a structure diagram of an off-duty detection system in this specific embodiment. see Figure 4 A kind of off-duty detection system in this specific embodiment specifically includes:

[0081] The model training module 110 is used to train the training set samples including various types of human heads, left and right ears, human upper body, and human body images to obtain human head models, left and right ear models, human upper body models, and human body models;

[0082] The off-post detection module 120 is used to obtain the sentry box video frame sequence, and uses the human head model, left and right ear models, human upper body model, and human body model to detect the sentry box video frame sequence, and at least detects the human head, left and right ears, human upper body, and human body. One of them, otherwise it is judged as off-...

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 video detection field and especially relates to a post-leaving detection method and a system thereof. The method comprises the following steps of a model training step: training a training set sample including various kinds of human heads, left and right ears, an upper part of a human body and a body image so as to acquire a human head model, a left and right ear model, a model of the upper part of the human body and a human body model; and a post-leaving detection step: acquiring a sentry box video frame sequence, using the human head model, the left and right ear model, the model of the upper part of the human body and the human body model to detect the sentry box video frame sequence, and determining that a person is in a post-leaving state if any one of the human head, left and right ears, the upper part of the human body and the human body can not be detected. In the invention, a probability of false detection is greatly reduced and detection accuracy is greatly increased.

Description

technical field [0001] The present invention relates to the field of video detection, and more specifically, to an off-duty detection method and system. Background technique [0002] In some important places related to the national economy and people's livelihood, such as important public facilities and enterprises (such as nuclear power plants), guard posts will be set up outdoors to protect the safety of important targets. In order to eliminate the unnecessary harm caused by the sentry leaving the sentry post without authorization and realize the intelligent and standardized management of the sentinel standing guard in the sentry box, it is necessary to monitor the situation of the sentry leaving the post in real time. [0003] The existing departure detection technology mainly extracts the foreground moving target and analyzes the trajectory of the foreground moving target to determine whether the target has left the sentry post. This type of method has obvious defects, ...

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): G06K9/00G06K9/32G06K9/46G06K9/62
CPCG06V40/10G06V20/62G06V10/44G06F18/214
Inventor 文莉毛亮朱婷婷黄仝宇汪刚宋一兵侯玉清刘双广
Owner GOSUNCN TECH GRP
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