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

A method for the semantic segmentation of an image

A semantic segmentation, image technology, applied in image analysis, image enhancement, image communication and other directions, can solve problems such as the inapplicability of convolutional networks

Inactive Publication Date: 2018-11-02
DELPHI TECH INC
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Specifically, deep and complex convolutional networks are not suitable for embedded devices in autonomous vehicles

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
  • A method for the semantic segmentation of an image
  • A method for the semantic segmentation of an image
  • A method for the semantic segmentation of an image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] exist figure 1 In , a raw image 20 captured by a digital camera mounted to a motor vehicle is shown. Image 20 included in figure 1 A two-dimensional arrangement of individual pixels that are not visible in . In the original image 20 , various objects of interest such as a road 10 , a vehicle 11 , and a traffic sign 13 can be recognized. For autonomous driving applications and advanced driver assistance systems, computer-based understanding of the captured scene is required. One means for achieving this automatic scene understanding is semantic segmentation of images, where each pixel is labeled according to a semantic category such as "road", "non-road", "pedestrian", "traffic sign", etc. exist figure 2 , as the original image 20 ( figure 1 ) results of semantic segmentation, which exemplarily shows the processed image 21. Semantic segments 15 of the processed image 21 correspond to different categories and are displayed in different colors or gray scales.

[00...

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 a method for the semantic segmentation of an image. The method for the semantic segmentation of an image having a two-dimensional arrangement of pixels comprises the steps of: segmenting at least a part of the image into superpixels, determining image descriptors for the superpixels, wherein each image descriptor comprises a plurality of image features, feeding the image descriptors of the superpixels to a convolutional network and labeling the pixels of the image according to semantic categories by means of the convolutional network, wherein the superpixels areassigned to corresponding positions of a regular grid structure extending across the image and the image descriptors are fed to the convolutional network based on the assignment.

Description

technical field [0001] The invention relates to a method for semantically segmenting an image with a two-dimensional pixel arrangement. Background technique [0002] Automated scene understanding is an important goal in the modern field of computer vision. One way to achieve automatic scene understanding is semantic segmentation of images, where individual pixels of an image are labeled according to their semantic categories. This semantic segmentation of images is especially useful in the context of object detection in advanced driver assistance systems (ADAS). For example, semantic segmentation of an image may involve dividing pixels into regions that belong to roads and regions that do not. In this case, the semantic categories are "road" and "non-road". According to the present application, there may be more than two semantic categories, such as "pedestrian", "car", "traffic sign", etc. Correctly labeling pixels is a challenging task because the appearance of predefi...

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 Applications(China)
IPC IPC(8): G06T7/10G06K9/46G06K9/00G06N3/04G06V10/50G06V10/764
CPCG06T7/10G06V20/588G06V10/44G06N3/045G06T7/11G06T7/187G06T2207/20084G06V20/58G06V10/467G06V10/50G06V10/267G06V10/82G06V10/764G06T2207/20081G06V20/41G06V20/584G06F18/241H04N23/80
Inventor F·佐霍里安B·安蒂克J·西格蒙德M·莫伊特
Owner DELPHI TECH INC
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