Lightweight semantic segmentation method based on multi-scale visual feature extraction

A multi-scale feature and visual feature technology, applied in neural learning methods, image analysis, image data processing, etc., can solve the problems of large semantic segmentation network model and slow reasoning speed

Pending Publication Date: 2021-04-09
XIAN UNIV OF TECH
View PDF3 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a lightweight semantic segmentation method based on multi-scale visual feature extraction,

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
  • Lightweight semantic segmentation method based on multi-scale visual feature extraction
  • Lightweight semantic segmentation method based on multi-scale visual feature extraction
  • Lightweight semantic segmentation method based on multi-scale visual feature extraction

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0054]The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0055]The present invention provides a lightweight semantic segmentation method based on multi-scale visual features, such asfigure 1 As shown, specifically, follow these steps:

[0056]Step 1, build a lightweight convolutional neural network LTNET based on multi-scale feature extraction, extract the image characteristics by feature extractor, extracting the image multi-scale feature of the characteristic incoming fusion hole convolution, and finally sampling by simply sampling The module completes feature integration, restores image resolution;

[0057]Its network structure is divided into three modules: 1) Feature extraction module; 2) Multi-scale fusion module; 3) on the sample module;

[0058]After the image input network, first sample extract characteristics by the feature extraction module, then fuse the context information, and extract the image multi-scal...

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 discloses a lightweight semantic segmentation method based on multi-scale visual feature extraction, and the method comprises the following steps: network building: firstly building a lightweight convolutional neural network LitNet based on multi-scale feature extraction, extracting image features through a feature extractor, transmitting the features to a spatial pyramid module fused with hole convolution to extract multi-scale features of the image, and finally completing the feature integration through a simple up-sampling module to recover the image resolution; network training: employing a Tensorflow framework for building a network structure, employing a cross entropy function as a loss function, employing an Adam algorithm for optimizing training parameters, and adopting an early stop strategy in the training process to prevent network training overfitting so as to achieve the optimal training effect; network testing: inputting the test image into the network to obtain a semantic segmentation result, calculating mIoU and FPS, and evaluating the network performance. Through testing, the model size on the CamVid data set is 10M, the mIoU is 70.24%, the 34FPS can be reached, and the real-time segmentation requirement can be met.

Description

technical field [0001] The invention belongs to the technical field of image segmentation, and relates to a lightweight semantic segmentation method based on multi-scale visual feature extraction. Background technique [0002] In high-mobility autonomous decision-making terminal systems such as drones and unmanned vehicles, how to achieve accurate environmental perception is an important basis for system operation. Knowledge inference can be performed on the pictures collected by the equipment to complete the scene understanding of the equipment. Image semantic segmentation is an important branch in the field of AI and an important part of image understanding in machine vision technology. Semantic segmentation is a process from rough reasoning to fine reasoning, that is, by finding the category of image pixels, identifying the content and position in the picture, and finally completing the overall labeling of each object in the image to form an image mask or output The clas...

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): G06T7/10G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06T7/10G06N3/08G06T2207/10016G06V10/40G06N3/045G06F18/241G06F18/253Y02D10/00
Inventor 宋霄罡付旺梁莉张元培
Owner XIAN UNIV OF TECH
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