Unlock instant, AI-driven research and patent intelligence for your innovation.

Image processing, neural network training method and device, storage medium

An image processing and static image technology, applied in the field of computer vision, can solve problems such as the inability to apply general objects

Active Publication Date: 2021-07-23
BEIJING SENSETIME TECH DEV CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These tasks usually use predefined human body and face key points, so they can only be applied to objects with unified structural features such as human body and face, and cannot be applied to general objects

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image processing, neural network training method and device, storage medium
  • Image processing, neural network training method and device, storage medium
  • Image processing, neural network training method and device, storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0068] The exemplary embodiment will be described in detail herein, and examples thereof are shown in the drawings. The following description is related to the drawings, unless otherwise indicated, the same numbers in the drawings represent the same or similar elements. The embodiments described in the exemplary embodiments described below do not represent all embodiments consistent with the present disclosure. Instead, they are only examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0069] The term operational in the present disclosure is to describe the purposes of specific embodiments, not intended to limit the disclosure. "One", "one", "one", "one", "" "," and "" "operating in the present disclosure and the appended claims, are also intended to include other forms unless the context clearly represents other meanings. It should also be understood that the terms "and / or" of this article refer to any or m...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The present disclosure provides an image processing, neural network training method and device, and a storage medium, wherein the image processing method includes: according to the first static image containing the target object, the first sparse optical flow, and at least one first random vector , determine at least one first dense optical flow; wherein, the first sparse optical flow is used to make the velocity of the known movable position in the set of known movable positions of the target object in the first dense optical flow is lower than a first value; based on the at least one first dense optical flow, determining a first movable position of the target object, wherein a movable part of the target object includes the first movable position. The present disclosure can locate movable parts of a target object from a static image.

Description

Technical field [0001] The present disclosure relates to the field of computer visual, and more particularly to an image processing, a neural network training method, and a storage medium. Background technique [0002] At present, in the field of image understanding, it is generally tended to understand the semantics of the object, such as image classification, segmentation, and detection, etc., based on the semantics of the object in a given image, is not concerned about the physical structure of the object. [0003] In the relevant technique, the work of understanding the physical structure of the object mainly includes human attitude identification and face key recognition. These tasks typically use a predefined human body and face key point, so it can only be applied to the human body, and the face of the structural feature of the face cannot be applied to a general object. Inventive content [0004] In view of this, the present disclosure provides an image processing scheme...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00G06T7/70G06N3/04G06N3/08
CPCG06T7/0002G06T7/70G06N3/08G06T2207/10004G06N3/045
Inventor 詹晓航潘新钢刘子纬林达华吕健勤
Owner BEIJING SENSETIME TECH DEV CO LTD