Object classification in image data using machine learning models

A machine learning model and image data technology, applied in machine learning, computing models, instruments, etc., can solve problems such as inaccurate positioning and identification

Active Publication Date: 2018-06-05
SAP AG
View PDF3 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, both localization and identification of objects within multidimensional image data remain imprecise

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
  • Object classification in image data using machine learning models
  • Object classification in image data using machine learning models
  • Object classification in image data using machine learning models

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The current subject matter is directed to enhanced techniques for locating (ie, detecting, etc.) objects within multidimensional image data. Such multi-dimensional image data can, for example, be generated by optical sensors specifying both color and depth information. In some cases, the multidimensional image data is RGB-D data, while in other cases other types of multidimensional image data can be utilized, including but not limited to point cloud data. Although described below primarily in connection with RGB-D image data, it should be understood that, unless otherwise stated, the present subject matter is applicable to other types of multidimensional image data (i.e., data that combines color and depth data / information) that Types of multidimensional image data include video streams from depth sensors / cameras (which can be represented as a series of RGB-D images).

[0029] figure 1 is a process flow diagram 100 illustrating the generation of a bounding box (box) u...

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

Combined color and depth data for a field of view is received. Thereafter, using at least one bounding polygon algorithm, at least one proposed bounding polygon is defined for the field of view. It can then be determined, using a binary classifier having at least one machine learning model trained using a plurality of images of known objects, whether each proposed bounding polygon encapsulates anobject. The image data within each bounding polygon that is determined to encapsulate an object can then be provided to a first object classifier having at least one machine learning model trained using a plurality of images of known objects, to classify the object encapsulated within the respective bounding polygon. Further, the image data within each bounding polygon that is determined to encapsulate an object is provided to a second object classifier having at least one machine learning model trained using a plurality of images of known objects, to classify the object encapsulated within the respective bounding polygon. A final classification for each bounding polygon is then determined based on the output of the first classifier machine learning model and the output of the second classifier machine learning model.

Description

technical field [0001] The subject matter described in this article involves the classification of objects within image data using machine learning models. Background technique [0002] Sensors are increasingly employed across multiple computing platforms (including standalone sensors for gaming platforms, mobile phones, etc.) to provide multi-dimensional image data (eg, three-dimensional data, etc.). These image data are computationally analyzed to locate objects and, in some cases, to later identify or otherwise characterize these objects. However, both localization and identification of objects within multidimensional image data remain imprecise. Contents of the invention [0003] In an aspect, combined color and depth data for a field of view is received. Thereafter, using at least one boundary polygon algorithm, at least one proposed boundary polygon is defined for the field of view. A binary classifier with at least one machine learning model trained using multipl...

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
IPC IPC(8): G06K9/62G06K9/46G06N20/00
CPCG06N20/00G06V10/56G06V10/44G06F18/2431G06V20/64G06F18/241
Inventor W.A.法罗奇J.利普斯E.施密特T.弗里克N.弗扎诺
Owner SAP AG
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