Image semantic segmentation method and device

A semantic segmentation and image technology, applied in the field of image processing, can solve the problems of structural redundancy, semantic segmentation performance and efficiency decline, and achieve the effect of improving performance and efficiency and reducing structural redundancy.

Pending Publication Date: 2021-04-20
BEIJING SANKUAI ONLINE TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In order to take into account the real-time and effectiveness requirements of semantic segmentation, a mainstream practice in the design of real-time semantic segmentation is: select an existing lightweight backbone network for encoding, and independently design a lightweight decoding network to achieve improved segmentation. Efficiency,

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 method and device
  • Image semantic segmentation method and device
  • Image semantic segmentation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] refer to figure 1 , shows a flow chart of the steps of an image semantic segmentation method provided by an embodiment of the present disclosure, as figure 1 As shown, the image semantic segmentation method specifically may include the following steps:

[0068] Step 101: Input the image to be processed into the image recognition model; the image recognition model includes: a short-term densely connected network layer and a decoding network layer, and the short-term densely connected network layer includes: a convolution module, a plurality of serially connected Short-time densely connected layers and output modules, each short-time densely connected layer contains multiple short-time densely connected modules.

[0069] The embodiments of the present disclosure can be applied in the scene of performing semantic segmentation on images.

[0070] The image to be processed refers to the image that needs to be subjected to image semantic segmentation. In this example, the ...

Embodiment 2

[0097] refer to figure 2 , shows a flow chart of steps of another image semantic segmentation method provided by an embodiment of the present disclosure, as figure 2 As shown, the image semantic segmentation method specifically may include the following steps:

[0098] Step 201: Input the image to be processed into the image recognition model; the image recognition model includes: a short-term densely connected network layer and a decoding network layer, and the short-term densely connected network layer includes: a convolution module, a plurality of serially connected Short-time densely connected layers and output modules, each short-time densely connected layer contains multiple short-time densely connected modules.

[0099] The embodiments of the present disclosure can be applied in the scene of performing semantic segmentation on images.

[0100] The image to be processed refers to the image that needs to be subjected to image semantic segmentation. In this example, t...

Embodiment 3

[0148] refer to Figure 4 , shows a schematic structural diagram of an image semantic segmentation device provided by an embodiment of the present disclosure, as shown in Figure 4 As shown, the image semantic segmentation device 400 may specifically include the following modules:

[0149] The image to be processed input module 410 is used to input the image to be processed to the image recognition model; the image recognition model includes: a short-term densely connected network layer and a decoding network layer, and the short-term densely connected network layer includes: a convolution module , multiple short-term densely connected layers and output modules connected in series, each short-term densely connected layer includes multiple short-term densely connected modules;

[0150] The first feature map acquisition module 420 is configured to call the convolution module to process the image to be processed, and obtain a first feature map corresponding to the image to be pr...

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 provides an image semantic segmentation method and device. The method comprises the steps of inputting a to-be-processed image into an image recognition model, wherein the image recognition model comprises a short-time dense connection network layer and a decoding network layer, the short-time dense connection network layer comprises a convolution module, a plurality of short-time dense connection layers and an output module, and each short-time dense connection layer comprises a plurality of short-time dense connection modules; calling a convolution module to process the to-be-processed image to obtain a first feature map corresponding to the to-be-processed image; calling a short-time dense connection layer to process the first feature map to obtain a second feature map; calling an output module to process the second feature map to obtain a third feature map; calling a decoding network layer to perform up-sampling on the third feature map and mapping the third feature map to the segmentation category to obtain a fourth feature map of which the channel number is the segmentation category number; and determining a semantic segmentation result corresponding to the to-be-processed image according to the fourth feature map. According to the invention, the network structure redundancy can be reduced, and the image semantic segmentation performance and efficiency are improved.

Description

technical field [0001] Embodiments of the present disclosure relate to the technical field of image processing, and in particular, to a method and device for image semantic segmentation. Background technique [0002] Semantic segmentation is a basic direction in the field of computer vision. With the progress of deep learning methods in recent years, the direction of semantic segmentation has also made great progress, and has been applied in more and more scenarios, such as autonomous driving, human-computer interaction, and medical treatment. Analytics, augmented reality, and more. [0003] In order to take into account the real-time and effectiveness requirements of semantic segmentation, a mainstream practice in the design of real-time semantic segmentation is: select the existing lightweight backbone network for encoding, and independently design a lightweight decoding network to achieve improved segmentation. Efficiency, among which ResNet-18, Xception-39, etc. are oft...

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): G06K9/34G06K9/46G06N3/04G06N3/08
Inventor 范铭源赖申其黄君实罗钧峰魏晓明张珂苏金明郭魏铭
Owner BEIJING SANKUAI ONLINE TECH CO LTD
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