Intelligent video analysis method

An intelligent video analysis and video image technology, applied in the field of video analysis, can solve problems such as inability to link, inability to quickly locate, and no image resources to be converted into information materials, etc., to achieve the effect of improving efficiency

Inactive Publication Date: 2016-11-16
BEIJING SHUZHIYUAN TECH CO LTD
View PDF3 Cites 31 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] 1. There are many real-time monitoring screens, all relying on manual identification
[0005] 2. Massive video recordings, unable to quickly locate
[0006] 3. The integration efficiency of video surveillance resources is low, and a unified resource pool cannot be formed
[0007] 4. Video surveillance and business systems are relatively independent and cannot be linked
[0008] 5. Video surveillance is only used for time-based evidence collection, and early warning is difficult
[0009] 6. The image resources are not converted into information materials, and the actual combat assistance is not enough

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
  • Intelligent video analysis method
  • Intelligent video analysis method
  • Intelligent video analysis method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals designate the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.

[0040] The present invention provides an intelligent video analysis method, refer to the attached Figure 1-2 , including the following steps:

[0041] Step S1, create training samples according to the acquired video images.

[0042] The training samples include positive samples and negative samples, where positive samples refer to target samples for a certain category of detection (such as face samples in face recognition, pedestrian samples in pedestrian detection, car samples in vehicle detection, etc.). Negative samples ref...

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 proposes an intelligent video analysis method. The method comprises the following steps of S1, creating a training sample according to an obtained video image; S2, extracting a characteristic according to the training sample; S3, establishing a training classification model according to the extracted characteristic; and S4, detecting a target according to the training classification model. The method has a capability of intelligently analyzing, acquiring, storing and transmitting large-scale diversified basic videos, an image big data management capability, and integrative capabilities of interconnection with other business systems and the like. Characteristic description information can be stored to form an index, and a video of a concerned event can be quickly located and played from massive video files by effectively utilizing and managing stored video file resources, so that the video record reverse query efficiency is improved and intelligent management of video data is realized.

Description

technical field [0001] The invention relates to the technical field of video analysis, in particular to an intelligent video analysis method. Background technique [0002] With the advancement of my country's informatization process, it is undeniable that the construction of a large number of front-end high-definition video equipment has greatly improved the quality of the entire video surveillance. Meet the viewing needs of front-end video for personnel at all levels. A large number of regulatory work often faces various emergencies. In actual operation, due to the relatively backward technology of the video surveillance application system and its independence from the business system, the implementation effect of the crisis management mechanism is greatly restricted. [0003] The current video surveillance system mainly has the following problems: [0004] 1. There are many real-time monitoring screens, all rely on manual identification. [0005] 2. Massive video recordi...

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 Applications(China)
IPC IPC(8): G06K9/00
CPCG06V20/42
Inventor 戴元永苏蓉蓉
Owner BEIJING SHUZHIYUAN TECH CO LTD
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