Image encoding process, image decoding process method, electronic device, and program product

CN122457777APending Publication Date: 2026-07-24CHINA MOBILE COMM GRP SHAANXI CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
CHINA MOBILE COMM GRP SHAANXI CO LTD
Filing Date
2026-04-20
Publication Date
2026-07-24

AI Technical Summary

Technical Problem

Existing technologies do not fully consider the differences in importance between regions of interest (ROIs) and non-ROIs in video content, resulting in poor video compression performance, making it difficult to meet the requirements of real-time performance and low storage costs. Furthermore, existing methods are easily affected by background interference and target diversity when identifying ROIs, leading to inaccurate identification results.

Method used

By extracting partitioned feature maps of key image data through a recurrent memory network, and combining adaptive dynamic offset to correct the position parameters of the region of interest, global and local attention weights are determined, and weighted calculation and encoding are performed to form an end-to-end image coding processing method.

Benefits of technology

It improves the accuracy of region of interest identification and coding efficiency, reduces the feature weights of non-regions of interest, lowers computational complexity and time latency, meets the requirements of real-time performance and low storage cost, and improves the quality and efficiency of video compression.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122457777A_ABST
    Figure CN122457777A_ABST
Patent Text Reader

Abstract

Embodiments of the present application provide an image encoding processing method, an image decoding processing method, an electronic device and a program product. The key image data is extracted from the video data, each key image data is processed according to the time sequence of the key image data by the recurrent memory network, and the partition feature map of each key image data is obtained, the partition feature map includes the region of interest and the non-region of interest; the position parameter of the region of interest is corrected based on the adaptive dynamic offset, and the focus feature map is obtained; the global attention weight corresponding to the region of interest and the local attention weight corresponding to the non-region of interest in the focus feature map are determined; the focus feature map is weighted calculated based on the global attention weight and the local attention weight, and the weighted feature map is obtained; the region of interest and the non-region of interest are encoded based on the weighted feature map, and the code stream of the key image data is obtained. According to the method provided by the embodiments of the present application, the efficiency and quality of video compression are improved.
Need to check novelty before this filing date? Find Prior Art