Method and device of video abstraction generation
A technology of video summary and frequency, applied in the field of image processing, can solve the problems of interference, distract the attention of public security organs, and interfere with video browsing by irrelevant targets, and achieve the effect of improving speed, making it easier to observe, and reducing the amount of calculation.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0053] Embodiment 1 of the present invention provides a video summary generation method, see figure 1 shown, including steps:
[0054] In step S110, the location information of the intended area designated by the user is acquired, and the intended area is determined.
[0055] The area of interest, that is, the area of interest to the user. For a specific video, the user may only care about moving objects that pass through a certain area or cross a certain line, so first set the area of interest, and when doing target detection and tracking , only care about the passing objects in the region of interest.
[0056] The intended area can be any polygon, or a line, or a closed area determined by several straight lines.
[0057] Preferably, in this embodiment, when the user specifies a straight line, the rectangular area with the line as the axis of symmetry is used as the intended area; The area is used as the intended area; when the user specifies a polygon or irregular...
Embodiment 2
[0066] Embodiment 2 of the present invention provides a video abstract generation method, see figure 2 shown, including steps:
[0067] Step S210: Obtain the location information of the intended area and / or excluded area specified by the user, and determine the intended area.
[0068] The user can also set an exclusion area, which is an area that the user does not care about. The exclusion area can be an area where leaves shake, or an area where no moving target can appear in some blind spots.
[0069] When there are still some areas that do not need to be processed in the intended area specified by the user, an exclusion area can be specified again in the specified intended area, thereby further reducing the amount of computation and increasing the computation speed.
[0070] Or, when the user does not know the range of the area where the target will appear, but only specifies where the target will not appear, then the intended area may not be specified, but the exclusion a...
Embodiment 3
[0124] Embodiment 3 of the present invention provides a device for generating a video summary, including a user interaction module, a foreground detection module, a tracking module and a generation module.
[0125] The user interaction module is used to obtain the location information of the intended area specified by the user, and determine the intended area; the foreground detection module is used to perform foreground detection on the image of the intended area; the tracking module is used to detect Track the target and extract the track of the target;
[0126] The generation module is used to superimpose each frame image of the target's motion trajectory on the corresponding background to generate a video summary.
[0127] Wherein, the foreground detection module is used to perform background modeling on the image by using a mixture of Gaussian functions to extract the moving foreground. Preferably, it also includes a lighting processing module and a shadow processing mod...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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