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

Data reorganization method capable of reserving time sequence and video structuring system

A data reorganization and data technology, applied in the field of data processing, can solve the problems that objects cannot be synthesized into the same video summary, the original data timing is not preserved, and the difficulty of real-time system is increased, so as to avoid the problem of parameter adjustment and achieve good time compression effect. , the effect of short video duration

Active Publication Date: 2013-01-02
深圳市华尊科技股份有限公司
View PDF4 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are three main disadvantages in such a method: firstly, the amount of calculation or calculation time will increase exponentially with the increase of the number of objects, resulting in a large difference in the processing time of videos with different contents. Not suitable for real-world applications
However, such a processing method will cause objects in different time periods to be unable to be synthesized into the same video summary, so it is not suitable for real-time systems
The third is that there is no time correlation between the reorganization results obtained by using energy minimization and the original data. There is no time series correlation between them, which increases the difficulty of application in real-time systems; for example, in the application of video summarization, the method of energy minimization will cause the objects in the daytime to be synthesized into the night background, while the objects in the nighttime will be synthesized into the daytime background situation emerges

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
  • Data reorganization method capable of reserving time sequence and video structuring system
  • Data reorganization method capable of reserving time sequence and video structuring system
  • Data reorganization method capable of reserving time sequence and video structuring system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] Please combine figure 1 , figure 2 As shown, this example takes video stream reassembly as an example to illustrate the reassembly method.

[0031] Realize object connection: For each object appearing in a certain video stream, classify each object into different groups according to the principle of temporal and spatial connectivity and correlation. The specific inductive methods of groups can vary according to different emphases, different objects of concern, or different needs for data reorganization. Since the specific inductive method of groups is only calculated for the relevance of time and space, it can be guaranteed that two associated objects appearing in video A and video B at the same time are classified into the same group.

[0032] For example, the first object A character and the second object B vehicle in a certain video appear at the adjacent position of the video scene at the same time, then it is determined that the first object A character and the ...

Embodiment 2

[0039] In this example, on the basis of Embodiment 1, if the user wishes to receive more things at the same time and pay attention to more groups or objects, the density parameter of reorganization can be preset to limit the reorganization at the same time The minimum number of objects allowed. The purpose of setting the density parameter is to provide users with a flexible choice. If the user can receive more items at the same time, the density parameter can be set larger. If the user can receive less items at the same time, it should be set to The Density parameter is set a little smaller.

[0040] Please refer to image 3 with Figure 4 As shown, let the density parameter be 2,

[0041] The first moment: select the first group at this moment, because B appears two moments later than A, so A appears, but B does not appear; since the density parameter is 2, select the object of the second group with the closest appearance time, Since the original time series of objects C ...

Embodiment 3

[0047] Please refer to Figure 5 As shown, assuming that the density parameter is 3,

[0048] The first moment: select the first group at this moment, because B appears two moments later than A, so A appears, B does not appear; since the density parameter is 3, select the nearest second group, C and D The original sequence appears at the same time. In order to ensure the relevance of C and D, both C and D appear, and the number of objects is greater than or equal to the density parameter 3, so EF does not sort at this moment.

[0049] The sixth moment: Since the CD is completed, only AB is left to sort, and the number of objects is 2, which is less than the density parameter 3, so the group C is selected, so the sorting result at the sixth moment is ABF.

[0050] The recombination method in this example can be widely used in video structured (abstract) systems, video surveillance systems, data compression systems (including audio, video, pictures and text, etc.), from the reo...

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 data reorganization method capable of reserving time sequence and a video structuring system. The data reorganization method comprises a data extraction process and a data merging process, wherein the data extraction process comprises the step of respectively extracting data related to objects in the same group from original data; and the data merging process comprises the steps of ordering and merging the data related to the objects in the same group according to the time sequence to form reorganized data with the original time sequence being reserved. Since the complexity of the algorithm provided by the invention is low, the consumed computation resources are fewer and the processing time is linearly and positively correlated to the number of input data, the algorithm is very easy to realize on software or hardware. Since the input and output results of group data have FIFO (first in first out) characteristics, the reorganized data maintains the input time sequence to a certain extent and the data reorganization method is suitable for a real-time system.

Description

【Technical field】 [0001] The invention relates to data processing, in particular to a data reorganization method. 【Background technique】 [0002] In the field of traditional video surveillance, if you want to find a certain event, object or person, you generally need to manually backtrack the video and watch a large amount of video content to find the target event, object or person. The search time is often equal to the length of the video. For example, to find a certain object from a 3-hour video, the surveillance personnel must spend the same 3 hours watching this video to find the target object, even through fast forwarding. To watch the video, the time that can be compressed is also limited (usually 4 times is the limit), and it is easy to cause missed viewing, especially for faster or smaller objects. [0003] In the field of data processing, in many cases, reorganizing the original data first can better store and express the data content, and can also save the amount ...

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): G06F17/30
Inventor 施欣欣余倬王蒙
Owner 深圳市华尊科技股份有限公司
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