Target tracking method and device
A target tracking and target technology, applied in the field of computer vision, can solve problems such as poor robustness, inability to distinguish which face, target tracking failure, etc., to achieve the effect of preventing target loss and accurate target tracking ability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
example 1
[0082] Example 1: When this method is applied to educational robots and home robots, since their interactive objects are usually their owners, the target face should be the owner's face. In this case, face recognition can be achieved by Some general / commonly used face recognition algorithms are implemented, such as: local binary pattern algorithm (local binary pattern, LBP), such as FaceNet and other algorithms based on deep neural networks or convolutional neural networks, etc. These face recognition algorithms can feature-match the image with the specified face information, so that only the face of the specified person can be used as the target face. The embodiment of the present application does not limit the implementation method of using the face recognition algorithm to identify the target face. As an example, the face recognition algorithm can be as follows: Image 6 It includes four stages of face detection, face alignment, feature description and feature matching, amo...
example 2
[0087] Example 2: When this method is applied to a service robot in a public place, the first person who appears in the field of view of the camera device within a period of time can be used as the tracking target, and its face can be used as the target face; A microphone is installed on the device to detect the position of the human voice, so that the face of the user who is talking to the service robot is used as the target face.
[0088] Region of interest (ROI) refers to the area to be processed that is outlined in the form of a box, circle, ellipse, irregular polygon, etc. from the processed image in the field of machine vision and image processing. Therefore, the first region of interest is the region to be processed of the target face outlined from the T-th frame of image. For example, as Figure 7 As shown, the first ROI is a box-shaped area 141 , which may include part or all of the target face 142 , for example, the area including the eyes, nose, mouth and other parts...
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