Method and device for associating large and small images in intelligent capture device
An intelligent, image-cutting technology, applied in image communication, closed-circuit television system, selective content distribution, etc., can solve problems such as difficult traceability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0080] On the basis of the above scheme, the target object information of each analysis frame extracted in the step S2 is stored in the text of the json format;
[0081] Before the step S3, it includes parsing the text in json format to obtain the timestamp of the analysis frame where the target object is located in the target object information, the target object ID, the target object coordinates and the target object quality score.
[0082] In this embodiment, the text of the json format is used to record the target object information. The Json format is a text format, which is more convenient to read and has a corresponding third-party library for analysis.
Embodiment 2
[0084] In the above, after the step S5 is stored as a small image, compression coding is performed on the small image.
[0085] In this embodiment, the thumbnail image can be compressed by various types of commonly used graphics such as JPEG, so as to reduce the size of the thumbnail image and reduce the storage pressure.
Embodiment 3
[0087] In the above, the step of setting up the first linked list / array or cache for storing the small images is also included. It also includes the step of setting up a second linked list / array or cache for storing large images.
[0088] It can be seen that in this solution, the MJPG stream obtained by the front end is essentially a JPG image. As for the original video stream and video analysis stream used as reference frames for matting, both are data in yuv format, and the video analysis stream is also sent to the smart phone for analysis in the form of image frames. The cutout reference frame is mainly used to cut out the small picture. According to the object coordinates output by the analysis, the corresponding face or vehicle small picture is dug out in the cutout reference frame, which is also in yuv format, and then encoded into a JPG picture. So the final association, as well as the size of the transmission, are all JPG images. Therefore, two linked lists / arrays or...
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