Supercharge Your Innovation With Domain-Expert AI Agents!

A Method of Searching Objects in Video

A technology for searching targets and videos, which is applied in the field of searching for target objects in videos, and can solve the problems of wasting time, consuming the time of viewers, wasting non-target person identification and screening, etc.

Inactive Publication Date: 2016-10-26
台州市合正信息科技有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But it still consumes a lot of time for viewers, and fast-forward is a way of skipping and playing, fast-forwarding to view the video, there is still the possibility of missing important pictures
On the other hand, the time period in which the target object appears in the video may only be a dozen seconds or even a few seconds. In addition to the above-mentioned waste of a lot of time spent watching static images, there is still a lot of time wasted in the existing methods of manually finding the target. Identification and screening of non-target persons

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 Method of Searching Objects in Video
  • A Method of Searching Objects in Video
  • A Method of Searching Objects in Video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0074] The method according to the present invention will be further explained below in conjunction with the drawings. In the form of examples, specific processes such as background modeling, front background separation, feature extraction and feature comparison are described in detail.

[0075] The search method of the present invention is a video analysis search method that combines multiple video analysis technologies, and its main analysis processing flow is as follows figure 1 Shown. The following describes the specific process of the method described in this example step by step, taking the searcher as an example.

[0076] First, the establishment and learning of character modules.

[0077] Section 1.1, the establishment of character modules: such as figure 2 As shown, in the sample, the outline of the character is manually selected, and each circle can be regarded as a coordinate (for example, two points from the top of the head, from left to right are point(215,70), point(2...

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 belongs to the technical field of video analysis and processing, and discloses a method for searching a target in a video. The method comprises the following steps of: on the basis of a foreground / background separation technology and a feature comparison technology, extracting the feature parameters of a target object; separating a foreground object from a video to be detected; extracting the feature parameters of the foreground object one by one; comparing the feature parameters with the features of the target object one by one; and inputting a searching result according to a comparison result. According to the method, the aim of searching a target in a video is fulfilled. On the aspect of application, the method contributes to the improvement of the conventional video monitoring system, and plays important and practical roles in saving human resources, time cost and the like; and on the aspect of technology, a portrait feature comparison technology is applied to target searching practice for the first time, and meanwhile, the conventional feature technology is improved, so that the accuracy of the feature comparison is further increased. Technology progresses in the fields of monitoring and investigation search are facilitated.

Description

Technical field [0001] The invention belongs to the technical field of video analysis and processing, and relates to the extraction and feature matching of moving objects, and specifically discloses a method for searching for a target object in a video. Background technique [0002] With the continuous development of digital camera technology, video surveillance as a security precaution is widely and widely used in daily and professional criminal investigation fields. While video surveillance has brought irreplaceable guarantees for security and other aspects, the existing video surveillance system is too simple, inconvenient for video viewing and target finding, and other shortcomings have gradually emerged. [0003] With the current common surveillance system, when you need to view the surveillance video and look for a target in the video, you must manually view the entire video completely. However, on the one hand, in the actual application process, in the camera monitoring are...

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): G06F17/30
Inventor 郑连松
Owner 台州市合正信息科技有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More