Video structurization system and target search method thereof

A target and video data technology, applied in the field of computer vision, can solve the problems of wide-angle cameras not being able to see clearly, reducing the performance of video structuring, and limiting the amount of information in video structuring, etc.

Inactive Publication Date: 2016-08-24
BEIJING DEEPGLINT INFORMATION TECH
View PDF8 Cites 39 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The embodiment of this application proposes a video structuring system and its target search method to solve the shortcomings of the existing technology that the wide-angle camera can not see clearly, which reduce

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
  • Video structurization system and target search method thereof
  • Video structurization system and target search method thereof
  • Video structurization system and target search method thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] figure 1 Shows a schematic structural diagram of a video structured system in Embodiment 1 of the present application. As shown in the figure, the video structured system may include: a linked camera group 101, a video analysis processor 102, and a background database 103. The linked camera The group 101 includes a wide-angle camera 1011, a telephoto camera 1012, and a pan-tilt 1013. The video analysis processor 102 includes an acquisition module 1021, a storage module 1022, and an index module 1023.

[0036] The wide-angle camera 1011 is used to obtain video data of a surveillance scene;

[0037] The pan / tilt head 1013 is configured to detect a foreground target in the surveillance scene according to the video data, and send a scheduling instruction to the telephoto camera, the scheduling instruction includes the information of the foreground target;

[0038] The telephoto camera 1012 is configured to obtain video data of the foreground target according to the information of ...

Embodiment 2

[0075] Based on the same inventive concept, an embodiment of the present application also provides a method for target search using the above-mentioned system, which is described below.

[0076] figure 2 It shows a schematic flowchart of the implementation of the target search method in the second embodiment of the present application. As shown in the figure, the target search method may include the following steps:

[0077] Step 201: Determine the image of the target to be searched;

[0078] Step 202: Search the image of the target to be searched in the background database, and determine the image that is closest to or coincides with the image of the target to be searched;

[0079] Step 203: Determine the temporal and spatial position of the target to be searched in the video of the wide-angle camera according to the index of the image.

[0080] During specific implementation, since the video structuring system has already established an index, the embodiment of the present applicatio...

Embodiment 3

[0105] image 3 A schematic diagram of a monitoring scene at the bank entrance in Embodiment 3 of the present application is shown. As shown in the figure, in this embodiment of the application, a set of linked camera groups can be set up at the entrance of the bank, and managers can adjust the monitoring scene of the wide-angle camera, for example: The lens of the wide-angle camera faces a preset area of ​​the bank entrance, and the correspondence between the position and orientation of the wide-angle camera and the telephoto camera can be accurately determined through mechanical and visual calibration.

[0106] The wide-angle camera shoots real-time surveillance video of the bank entrance. Assuming that at 00:20, there is a passerby A and a user B who wants to enter the bank at the bank entrance. The pan / tilt head detects the passerby based on the video data captured by the wide-angle camera. A and user B who wants to enter the bank send a dispatching instruction to the telephot...

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 provides a video structurization system and a target search method thereof. The video structurization system comprises a linkage camera set, a video analysis processor and a background database. The linkage camera set comprises a wide-angle camera, a long-focus camera and a cradle head. The wide-angle camera is used for acquiring video data of a monitored scene. The cradle head is used for detecting a foreground target in the monitored scene according to the video data and sending a scheduling instruction to the long-focus camera. The long-focus camera is used for acquiring video data of the foreground target according to information of the foreground target; the video analysis processor is used for acquiring feature images of the foreground target according to the video data of the foreground target, storing the feature images in the background database and establishing indexes for the foreground target; the indexes point to the feature images of the foreground target and the space-time position of the foreground target in the video data acquired by the wide-angle camera. By means of the video structurization system and the target search method thereof, remote high-definition shooting of targets within a large range can be achieved, and the targets within the remote large range can be rapidly recognized and positioned.

Description

Technical field [0001] This application relates to the field of computer vision technology, and in particular to a video structuring system and a target search method thereof. Background technique [0002] Video structuring refers to the extraction of the semantic content of the video. It uses computer vision methods such as detection, recognition, and tracking to organize the video into text information that can be understood by computers and people according to semantic relationships. From the perspective of the data processing flow, video structuring can transform video into information that can be understood by humans and machines, and further into practical information, realizing the transformation of unstructured video data into structured information. [0003] The clarity of objects in the video is very important for video structuring. Generally speaking, the clearer the object, the easier and more accurate it is to detect, identify, and track objects of interest (such as pe...

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): G06F17/30H04N7/18
CPCG06F16/683G06F16/686H04N7/181
Inventor 潘争
Owner BEIJING DEEPGLINT INFORMATION TECH
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