A reference frame synthesis method and device for vehicle object coding in surveillance video
A monitoring video and object coding technology, which is applied in the field of reference frame synthesis of vehicle object coding, can solve the problems of low coding efficiency, achieve the effects of robust environmental factors, improve coding efficiency, and reduce prediction residuals
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0058] This embodiment provides a reference frame synthesis method for vehicle object coding in surveillance video, please refer to figure 1 , the method includes:
[0059] First, step S1 is performed: based on the 3D model of the vehicle object in the historical surveillance video, a global reference frame is generated.
[0060] Specifically, due to the single-source object coding method or multi-source object coding method commonly used in the prior art, the single-source object coding method uses local information for prediction, and it is difficult to eliminate the redundancy existing between different videos, while the multi-source object coding method The encoding method utilizes global information for prediction, which is easily affected by environmental factors such as illumination. Therefore, it is difficult to achieve ideal coding efficiency by using local or global information prediction alone. Therefore, based on the idea of image fusion, the present invention ...
Embodiment 2
[0126] This embodiment provides a reference frame synthesis device for vehicle object coding in surveillance video, please refer to figure 2 , the device consists of:
[0127] The global reference frame generation module is used to generate a global reference frame based on the three-dimensional model of the vehicle object in the historical surveillance video;
[0128] The local reference frame generation module is used to perform three-dimensional pose transformation on the vehicle object in the encoded video frame according to the vehicle object in the video to be encoded to generate a local reference frame;
[0129] The synthesis module is configured to set a corresponding fusion method according to the image attributes of different regions of the vehicle, and fuse the global reference frame and the local reference frame based on the corresponding fusion method to generate a synthetic reference frame.
[0130] In one embodiment, the global reference frame generation modul...
Embodiment 3
[0157] See image 3 , based on the same inventive concept, the present application also provides a computer-readable storage medium 300, on which a computer program 311 is stored. When the program is executed, the method as described in the first embodiment is implemented.
[0158]Since the computer-readable storage medium introduced in the third embodiment of the present invention is the computer equipment used to implement the reference frame synthesis method for vehicle object coding in the surveillance video in the first embodiment of the present invention, it is based on the introduction in the first embodiment of the present invention method, those skilled in the art can understand the specific structure and deformation of the computer-readable storage medium, so details are not repeated here. All computer-readable storage media used in the method in Embodiment 1 of the present invention fall within the scope of protection intended by the present invention.
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