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

Method and device for detecting objects from pictures

A technology of objects in pictures, applied in the field of computer vision, can solve problems such as inability to adjust and low object detection accuracy, and achieve the effect of improving accuracy

Active Publication Date: 2020-11-10
BEIJING SENSETIME TECH DEV CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, because the features considered in each stage of the existing cascaded classifiers are different from each other, the multiple sets of features used in each stage can only be learned separately, and cannot be adjusted based on the existing features, resulting in the accuracy of object detection. lower

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
  • Method and device for detecting objects from pictures
  • Method and device for detecting objects from pictures
  • Method and device for detecting objects from pictures

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific implementation manners described herein are only used to explain the present application, rather than to limit the present application. In addition, it should be noted that, for ease of description, only parts relevant to the present application are shown in the drawings. Hereinafter, the present application will be described in detail with reference to the accompanying drawings and in combination with embodiments.

[0032] figure 1 A flowchart of a method 10 for detecting an object from a picture according to an exemplary embodiment of the present application is shown.

[0033] Such as figure 1 As shown, first, in step S11, map the picture features of the object area frame in the picture to a plurality of first features, wherein the combination of the feature value and the surrounding padding value...

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 application discloses methods and devices for detecting objects from pictures. According to one embodiment, the method for detecting an object from a picture includes: mapping the picture features of the object area frame in the picture to a plurality of first features, wherein the combination of the feature value and the surrounding filling value of each first feature Combinations of feature values ​​and surrounding fill values ​​are different from other first features; multiple second features are generated based on multiple first features based on feature links; and samples of image features of the object area frame are determined according to multiple second features State, the sample state includes positive samples and negative samples.

Description

technical field [0001] The present application relates to the field of computer vision, in particular, to methods and devices for detecting objects from pictures. Background technique [0002] Object detection is an important problem in the field of computer vision. However, there is a sample imbalance problem in object detection. The number of negative samples as background is much larger than the number of positive samples as foreground objects. [0003] One of the existing methods is to use cascaded classifiers, in which classifiers of multiple stages are cascaded, and the classifiers of each stage only consider the characteristics of the current stage, and the negative samples are sequentially removed through the cascaded multiple classifiers. However, because the features considered in each stage of the existing cascaded classifiers are different from each other, the multiple sets of features used in each stage can only be learned separately, and cannot be adjusted ba...

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): G06K9/62
CPCG06F18/2148
Inventor 欧阳万里王晓刚朱欣王坤
Owner BEIJING SENSETIME TECH DEV CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com