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

Detection method of abnormal behavior of monitoring target under laser night vision

A technology of monitoring targets and laser night vision, which is applied in the directions of instruments, calculations, character and pattern recognition, etc., can solve the problems such as the difficulty of accurate detection of moving objects, and achieve the effect of less manual adjustment parameters, low computational complexity and good precision

Inactive Publication Date: 2018-12-07
江苏精湛光电仪器股份有限公司 +1
View PDF7 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the lack of light at night, it brings great difficulties to the accurate detection of moving objects

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
  • Detection method of abnormal behavior of monitoring target under laser night vision
  • Detection method of abnormal behavior of monitoring target under laser night vision
  • Detection method of abnormal behavior of monitoring target under laser night vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The present invention will be further described below in conjunction with specific embodiments.

[0044] The flow chart of abnormal behavior detection of monitoring targets under laser night vision is as follows: figure 1 , the specific implementation is divided into 3 steps:

[0045] Step 1: Pre-train the CNN (Convolution Neural Network convolutional neural network) model on the cifar10 database:

[0046] This step needs to design the structure of CNN. The structure of CNN is shown in Table 1. There are 3 convolutional layers, 1 fully connected layer, and 1 output layer. The training results are: the training loss is about 0.04, the classification accuracy rate is above 98%, the test loss is 0.7, and the classification accuracy rate is 81.44%;

[0047] Table 1 CNN structure

[0048]

[0049] Step 2: Video expression; video expression is divided into three steps: first, laser night vision image preprocessing; second, single frame image feature extraction; third, vid...

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 method for detecting abnormal behavior of a monitoring target under laser night vision in the field of video monitoring, comprising the following steps: 1) establishing a model: pre-training a CNN model on a cifar10 database, the CNN model includes three convolution layers, one Full connection layer and 1 output layer; 2) Video expression: express video images as dimensional features; 3) Event reconstruction: distinguish normal events and abnormal events, the invention improves the detection accuracy and improves the abnormal event recognition rate, Can be used in video surveillance.

Description

technical field [0001] The invention relates to a video monitoring and detection method, in particular to a laser night vision monitoring and detection method. Background technique [0002] Most of the existing video surveillance systems only detect or track moving objects in the scene, and do little further processing. The purpose of monitoring in life is to detect and analyze abnormal events or abnormal behaviors of people in the scene. Smart video The detection of abnormal behavior by monitoring can not only detect improper behavior in time, inform the staff to deal with it in time, prevent the occurrence of illegal behavior, but also save a lot of storage space, and avoid massive search and evidence collection by staff after illegal behavior occurs. [0003] Many scholars at home and abroad have done a lot of work on anomaly detection based on video sequences, which can be roughly divided into two categories: one is the method based on the model, and the other is the met...

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): G06K9/00
CPCG06V20/46G06V20/41
Inventor 黄凯奇康运锋张旭李大一瞿世鲲
Owner 江苏精湛光电仪器股份有限公司
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

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