Data processing system, object detection method, and apparatus thereof

ChangeBridge: Patent Grants - AI & Computing (G06N)

Published March 24th, 2026

Detected March 25th, 2026

Summary

The USPTO has granted patent US12585944B2 to Huawei Technologies Co., Ltd. for a data processing system and object detection method applied to the artificial intelligence field. The patent introduces shallow texture detail information into deep feature maps for improved target detection.

View original document View source feed page

What changed

The United States Patent and Trademark Office (USPTO) has granted patent US12585944B2 to Huawei Technologies Co., Ltd. The patent covers a data processing system, object detection method, and apparatus thereof, specifically designed for applications within the artificial intelligence field. The core innovation involves a method for generating feature maps by incorporating shallow texture detail information into deep feature maps, which are then used for target detection.

This patent grant signifies the USPTO's recognition of novel technology in AI-driven object detection. While this is a patent grant and not a regulatory rule imposing obligations, it highlights advancements in AI processing that may influence future industry standards or inspire further research and development. Companies operating in the AI and computing sectors, particularly those involved in image recognition and data processing, should be aware of this granted patent and its potential implications for intellectual property landscapes.

Source document (simplified)

← USPTO Patent Grants

Data processing system, object detection method, and apparatus thereof

Grant US12585944B2 Kind: B2 Mar 24, 2026

Assignee

HUAWEI TECHNOLOGIES CO., LTD.

Inventors

Jiangyong Ying, Xiongwei Zhu, Jing Gao, Lei Chen

Abstract

This application discloses a data processing system, an object detection method, and an apparatus thereof, and is applied to the artificial intelligence field. In this application, a second feature map generation unit introduces shallow texture detail information of an original feature map (a plurality of first feature maps generated by a convolutional processing unit) into a deep feature map (a plurality of second feature maps generated by a first feature map generation unit), to generate a plurality of third feature maps, and the third feature map including the shallow rich texture detail information is used as entered data on which a detection unit is to perform target detection.