Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Image semantic segmentation model based on reinforcement learning and transfer learning and modeling method

A technology of reinforcement learning and transfer learning, applied in the field of image semantic segmentation model and modeling based on reinforcement learning and transfer learning, can solve the problems of not fully considering the relationship between pixels and pixels, lack of spatial consistency, and insensitive to details. , to avoid too long training time, reduce training time, and achieve the effect of accurate details

Active Publication Date: 2020-03-06
SUN YAT SEN UNIV
View PDF3 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these networks based on or partially using the FCN idea, due to upsampling, the model is not sensitive enough to the details of the image, the semantic segmentation is relatively vague, and the relationship between pixels is not fully considered, that is, when a certain pixel is judged to be a certain category. Judging the influence of surrounding pixels, lacking spatial consistency

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
  • Image semantic segmentation model based on reinforcement learning and transfer learning and modeling method
  • Image semantic segmentation model based on reinforcement learning and transfer learning and modeling method
  • Image semantic segmentation model based on reinforcement learning and transfer learning and modeling method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] like figure 1 Shown is an embodiment of an image semantic segmentation model based on reinforcement learning and transfer learning in the present invention, including: a preprocessing module for preprocessing the original image; a perception module for the environment part in reinforcement learning; pixel The category decision module is used for the agent part in reinforcement learning; the preprocessing module, the perception module, and the pixel category decision module are sequentially connected by communication.

[0053] In addition, the perception module includes: a state generation sub-module for generating different states according to fine or rough levels; a reward generation sub-module for generating rewards; the state generation sub-module communicates with the reward generation sub-module and the preprocessing module.

[0054] Wherein, the rewards generated by the reward generation sub-module include split effect rewards and split ratio rewards.

[0055] Am...

Embodiment 2

[0058] like Figure 2 to Figure 3 Shown is a kind of modeling method of the image semantic segmentation model based on reinforcement learning and transfer learning of the present invention, comprises the following steps:

[0059] S1. Preprocessing the image data set through the preprocessing module, including adjusting the size of the entire image to a fixed size, cutting the original image to a fixed size, L×L×3, where L is the image side length, 3 is the number of pixel channels, And randomly rotate for image enhancement; then get the data set , and use 80% of the entire data set as a training set and 20% as a test set;

[0060] S2. Utilize migration learning to initialize the convolutional neural network parameter θ of the image feature extraction submodule; first find a large-scale image data set in a similar field as a source data set, such as the ImageNet data set, and use the model of the present invention to perform image processing The split data set is used as the t...

Embodiment 3

[0089] This embodiment is similar to Embodiment 2, the difference is that, as Figure 4 As shown, the specific steps of step S4 in this embodiment are as follows:

[0090] S41. For each image x_test of the test set i , the state generation sub-module splices the original image with the initial pixel category decision matrix to obtain the initial state s_test 1 ;

[0091] S42. Use the classification strategy to determine the block size m of this round;

[0092] S43. When entering the first round, directly execute step S44; when entering the nth (n ≥ 2 and n is a natural number) round, that is, starting from the second round, judge whether each block is in the boundary or image If so, execute step S44, otherwise keep the category decision of the current block in the previous round, directly move the state to the next block, and repeat step S43;

[0093] S44. The pixel category selection submodule selects the action a_test according to the Q value output by the image feature ...

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 relates to the technical field of semantic segmentation of images, and specifically relates to an image semantic segmentation model based on reinforcement learning and transfer learningand a modeling method. The model comprises a preprocessing module used for preprocessing an original image, a sensing module used for an environment part in reinforcement learning and a pixel categorydecision module used for an intelligent agent part in reinforcement learning, which are in communication connection in sequence. According to the method, image semantic segmentation is regarded as asequence decision process, the category of each pixel is sequentially determined instead of generating the segmentation result of the whole image at one time, the relationship between the pixels can be effectively utilized, the training time is shortened, and the accuracy of the image segmentation effect is improved.

Description

technical field [0001] The present invention relates to the technical field of semantic segmentation of images, and more specifically, to an image semantic segmentation model and modeling method based on reinforcement learning and transfer learning. Background technique [0002] Image segmentation is a fundamental and challenging work in the field of computer vision and has become an important part of image understanding. The goal of image segmentation is to extract meaningful target objects from the input image, completely separate the target object from the background, that is, perform pixel-level classification, and find the contour boundary of the target object. The traditional image segmentation method is to use the basic characteristics of the image such as grayscale, texture, shape, etc., and use the principles of digital image processing, topology, mathematics, etc. to segment. With the development of machine learning and deep learning, the effect of image segmentat...

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): G06T7/10
CPCG06T7/10G06T2207/20081G06T2207/20084G06T2207/20021Y02T10/40
Inventor 韩佳琪卓汉逵
Owner SUN YAT SEN UNIV
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
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