Method and device for detecting objects from images

A technology for detecting objects and images, applied in character and pattern recognition, instruments, calculations, etc., can solve problems such as omissions and inaccurate detection results, and achieve the effects of reducing detection results, clear characteristics and advantages, and reducing omissions

Active Publication Date: 2021-08-03
CANON KK
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, person detection (such as by figure 2 (b) The detection results marked with dotted lines) are missed, and the final detection results are more inaccurate, such as, become larger rectangles, or deviate from the actual ground truth, etc., like figure 2 The detection results of the solid line marks in (b) are the same

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] A preferred embodiment of the present invention will be described in detail below with reference to the drawings.

[0022] Please note that similar reference numbers and letters refer to similar items in the figure, and once a project is defined in a picture, it is not necessary to discuss in the drawing.

[0023] In the present disclosure, the terms "first", "second", etc. are only used to distinguish between components or steps, and is not intended to represent time order, priority or importance.

[0024] First, the meaning of some of the terms in the context disclosed will be explained.

[0025] Hereinafter, the embodiments of the present invention will be described in the context of the present invention as an example and the rectangular region as an example of the object as an example of the present invention as an example of the present invention as an example of the present invention as an example of the present invention as an example and the rectangular area as an ...

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 invention provides methods and apparatus for detecting objects from images. The method for detecting an object from an image includes: scanning the image with a detection window and outputting a plurality of candidate object regions; reducing the candidate object regions to generate a reduced candidate object region; The regions are grouped into at least one subset; and the reduced candidate object regions in each subset are merged to obtain a merged object region. With the present invention, the person in the image can be located more precisely, and the missed detection results can be reduced.

Description

Technical field [0001] The present invention relates to a method and apparatus for detecting an object from an image. Background technique [0002] Recently, techniques from detecting objects, especially characters are widely used. Typically, a single final character detection result is obtained for each person based on the multiple overlapping object area. The character detector uses the detection window to scan the image in all positions and scale, and generate a plurality of overlapping object areas as the detection result. Then the overlapping object area is combined to obtain the final character detection result. According to P. Viola and Mjjones.Robust, Real-Time Face Detection, International Journal of Computer Vision, 57 (2): 137-154, 2004, ISSN 0920-5691) describes the following steps Methods of completing multiple overlapping object areas into a single test result: the object area is divided into a subset that does not intersect, where the two object areas are integrate...

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): G06K9/00
CPCG06V40/161
Inventor 王世婷胥立丰
Owner CANON KK
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap