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

Method and device for attention-driven image segmentation

An image segmentation and equipment technology, applied in image analysis, image enhancement, image data processing and other directions, can solve the problem of not being able to learn important areas correctly

Active Publication Date: 2020-07-28
STRADVISION
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the errors corresponding to said important regions are less reflected in the loss, so that the important regions cannot be learned correctly

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 attention-driven image segmentation
  • Method and device for attention-driven image segmentation
  • Method and device for attention-driven image segmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0039] In order for those skilled in the art of the present application to easily implement it, exemplary embodiments of the present application will be described in detail by referring to the accompanying drawings, as shown below.

[0040] figure 1 It is a schematic diagram of the structure of the learning device for this application.

[0041] refer to figure 1 , the learning device 100 may include a CNN200. Various input and output data functions and calculation processes of the CNN200 are respectively executed by the communication part 110 and the processor 120 therein. But when figure 1 In , the detailed description about how the communication part 110 and the processor 120 are connected is omitted. In addition, the learning device 100 may further include a memory 115 capable of storing computer readable instructions (Computer Readable Instructions) for performing the following processes. As an example, the processor, the memory, the medium (Medium), etc. may be integ...

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

A method for an attention-driven image segmentation by using at least one adaptive loss weight map is provided to be used for updating HD maps required to satisfy level 4 of autonomous vehicles. By the method, vague objects such as lanes and road markers at distance may be detected more accurately. Also, the method can be usefully performed in military, where identification of friend or foe is important, by distinguishing aircraft marks or military uniforms at distance. The method includes steps of: a learning device instructing a softmax layer to generate softmax scores; instructing a loss weight layer to generate loss weight values by applying loss weight operations to predicted error values generated therefrom; and instructing a softmax loss layer to generate adjusted softmax loss values by referring to initial softmax loss values, generated by referring to the softmax scores and their corresponding GTs, and the loss weight values.

Description

technical field [0001] This application relates to a method for Attention-Driven image segmentation by using at least one Adaptive loss weighted map to update the High Definition (HD) map to meet the level of self-driving cars 4 requirements. More specifically, a method for image segmentation by using at least one adaptive loss weighted map, a learning device, a testing method and a testing device using the method and the learning device (LEARNING METHOD ANDLEARNING DEVICE FOR ATTENTION-DRIVEN IMAGE SEGMENTATION BY USING AT LEAST ONE ADAPTIVE LOSS WEIGHT MAP TO BE USED FOR UPDATING HD MAPS REQUIRED TO SATISFYLEVEL 4 OF AUTONOMOUS VEHICLES AND TESTING METHOD AND TESTING DEVICE USING THE SAME). Wherein, described method comprises the following steps: [0002] Step (a), when at least one input image is obtained, (i) instruct the encoding (Encoding) layer of CNN to generate at least one feature map by performing more than one convolution operation on the input image, and (ii) in...

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): G06T7/11G06N3/04G06N3/08G06V10/26
CPCG06T7/11G06N3/084G06T2207/20081G06T2207/30256G06N3/045G06T2207/20084G06V20/56G06V10/26G06V10/454G06V10/82G06F18/2413G06N3/04G05D1/0088B60W60/0015G06F18/217G06F18/2148G06N7/01
Inventor 金桂贤金镕重金寅洙金鹤京南云铉夫硕焄成明哲吕东勋柳宇宙张泰雄郑景中诸泓模赵浩辰
Owner STRADVISION
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