Invention Grant
- Patent Title: Method for training object detection model and target object detection method
-
Application No.: US17194186Application Date: 2021-03-05
-
Publication No.: US11640678B2Publication Date: 2023-05-02
- Inventor: Xinggang Wang , Wenyu Liu , Chao Li , Junzhou Huang , Juhong Wang , Dongyuan Ma
- Applicant: Tencent Technology (Shenzhen) Company Limited
- Applicant Address: CN Shenzhen
- Assignee: Tencent Technology (Shenzhen) Company Limited
- Current Assignee: Tencent Technology (Shenzhen) Company Limited
- Current Assignee Address: CN Shenzhen
- Agency: Morgan, Lewis & Bockius LLP
- Priority: CN201811479732.8 20181205
- Main IPC: G06K9/00
- IPC: G06K9/00 ; G06T7/77 ; G06T7/194 ; G06V20/69 ; G06V10/25 ; G06F18/214 ; G06F18/21 ; G06V10/764 ; G06V10/82

Abstract:
This application relates to a target object detection method and apparatus, a non-transitory computer-readable storage medium, and a computer device. The method includes: obtaining a to-be-detected image; inputting the to-be-detected image into a target object detection model; generating, by the target object detection model, a prediction diagram corresponding to the to-be-detected image, the prediction diagram describing a relation degree to which pixels of the to-be-detected image belong to a target detection object; and performing region segmentation on the prediction diagram to obtain a target detection object region. In addition, a method and an apparatus for training an object detection model into the target object detection model, a non-transitory computer-readable storage medium, and a computer device are also provided.
Public/Granted literature
- US20210192180A1 METHOD FOR TRAINING OBJECT DETECTION MODEL AND TARGET OBJECT DETECTION METHOD Public/Granted day:2021-06-24
Information query