Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Target recognition model training and target recognition method and device, computing equipment

A technology for target recognition and model training, which is applied in the field of computer vision and can solve time-consuming problems

Active Publication Date: 2019-09-13
BEIJING SENSETIME TECH DEV CO LTD
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The target recognition problem is usually very time-consuming because it is necessary to label the positions of all objects in the image
According to the practical experience of common methods, it usually takes 5-8 minutes to obtain an accurate target recognition label with a size of 400*600 pixels

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
  • Target recognition model training and target recognition method and device, computing equipment
  • Target recognition model training and target recognition method and device, computing equipment
  • Target recognition model training and target recognition method and device, computing equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0046] In the field of computer vision technology, in order to achieve accurate recognition of objects in images, images are often disassembled into multiple local candidate regions for understanding and learning. The principle of dismantling is to be able to cover as many objects of different sizes in the image as possible; each local candidate area can cover a part of the object, and does not have to completely contain the object,...

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 invention discloses a target recognition model training and target recognition method, device, and computing equipment, which belong to the technical field of computer vision, wherein the method includes: inputting a plurality of local candidate regions selected for the training image into the target recognition model, obtaining the preliminary results of the classification of multiple local candidate regions output by the target recognition model; performing local candidate region fusion according to the weak supervision information and the preliminary results of the classification of the multiple local candidate regions; according to the multiple The preliminary results of local candidate region classification and local candidate region fusion results correct the parameters of the target recognition model; iteratively execute the above training steps until the training results of the target recognition model meet a predetermined convergence condition. The solution of the present invention not only has direct supervision at the pixel level, but also can optimize the semantic segmentation model end-to-end, and can improve the result of target recognition based on the judgment of local candidate regions.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a target recognition model training and target recognition method and device, and computing equipment. Background technique [0002] Object recognition is a classic problem in the field of computer vision, where the purpose is to predict the location of a given object in an input image. A good object recognition scheme relies on the object category of each pixel to achieve accurate and dense image pixel-level understanding. The object recognition problem is usually very time-consuming because of the need to label the positions of all objects in the image. According to the practical experience of common methods, it usually takes 5-8 minutes to obtain an accurate target recognition label with a size of 400*600 pixels. Therefore, the speed and quality of data annotation has become an important issue that restricts the problem from obtaining big data support and further dev...

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
CPCG06F18/2321G06F18/2134G06F18/213G06F18/23G06F18/214
Inventor 石建萍
Owner BEIJING SENSETIME TECH DEV CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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