Monitor scene type identification method for intelligent video monitor

A technology of intelligent video monitoring and identification method, which is applied in the field of scene image recognition, can solve the problem of low accuracy of monitoring scene image recognition, achieve the effect of increasing intelligence, accurate judgment, and overcoming scale changes

Active Publication Date: 2015-05-13
泰山信息科技有限公司
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the technical problem that the existing monitoring scene type identification method has a low accuracy rate for monitoring scene image identification with scale changes, viewing angle changes or object occlusions, and to provide a monitoring scen

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
  • Monitor scene type identification method for intelligent video monitor
  • Monitor scene type identification method for intelligent video monitor
  • Monitor scene type identification method for intelligent video monitor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0074] Embodiment: A kind of monitoring scene type identification method oriented to intelligent video monitoring in this embodiment, such as figure 1 shown, including the following steps:

[0075] S1: Create a monitoring scene image sample set {I 1 , I 2 ,..., I N}, N is a natural number, including the following steps:

[0076] S11: Select 10 common monitoring scene types, and give each type a different type label: the 10 monitoring scene types and their corresponding type labels are as follows: channel [1], living room [2], store [3] ], office [4], square [5], fence [6], community [7], expressway [8], outdoor parking lot [9], city street [10].

[0077] S12: For each surveillance scene type, collect several surveillance scene images belonging to this type as samples (all images are single-frame static images intercepted from video data of visible light video surveillance cameras).

[0078] S13: assign corresponding type labels to the pictures under each monitoring scene ...

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

Provided is a monitor scene type identification method for intelligent video monitor. The method comprises the following steps: creating a monitor scene image sample set; pre-processing the monitor scene image sample set; establishing a corresponding multi-scale image pyramid set based on the pre-processed monitor scene image sample set; using the multi-scale image pyramid set to generate a visual vocabulary library; using the visual vocabulary library to extract characteristic values of all images in the monitor scene image sample set; constructing three monitor scene type identifiers; identifying the monitor scene type of any monitor scene image with an unknown scene type besides the monitor scene image sample set. The monitor scene type identification method for intelligent video monitor is able to effectively overcome the problems of scale change, visual angle change, object blockage, and the like, which are commonly existed in the video monitor scene images, thereby increasing the accuracy of the identification.

Description

technical field [0001] The invention relates to the technical field of scene image recognition, in particular to a monitoring scene type recognition method for intelligent video monitoring. Background technique [0002] Target detection and recognition in surveillance scenes is one of the important research contents in the field of intelligent video surveillance. Currently, it has a wide range of application space and market demand in both civilian and military fields. However, due to the limitations of existing video surveillance imaging technology and the constraints of construction costs, usually the video surveillance scene images we can obtain often have images such as "low resolution", "high noise", "fuzzy" and "image distortion". At the same time, bottleneck problems such as "illumination change", "object occlusion", "view angle change" and "scale change" are common in video images. All the above problems have brought great difficulties to the target detection and re...

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): G06K9/64H04N7/18
Inventor 张睿童玉娟周兆忠张元祥
Owner 泰山信息科技有限公司
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