Small-scale pedestrian target rapid super-resolution method for intelligent roadside equipment

A pedestrian target and super-resolution technology, applied in the field of rapid super-resolution of small-scale pedestrian targets, can solve the problem of long algorithm execution time, and achieve the effects of avoiding gradient dispersion, ensuring real-time performance, and reducing dimensions

Active Publication Date: 2020-12-25
SOUTHEAST UNIV
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, due to the complexity of the network structure, the existing deep learning super-resolution methods all have a serious problem that

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
  • Small-scale pedestrian target rapid super-resolution method for intelligent roadside equipment
  • Small-scale pedestrian target rapid super-resolution method for intelligent roadside equipment
  • Small-scale pedestrian target rapid super-resolution method for intelligent roadside equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The technical solutions provided by the present invention will be described in detail below in conjunction with specific examples. It should be understood that the following specific embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention.

[0045] The present invention provides a fast super-resolution method for small-scale pedestrian targets for intelligent roadside equipment. By constructing a small-scale pedestrian multi-resolution training data set for intelligent roadside scenes, a network model data support is formed, combined with a generated confrontation network. In view of the specific problems of traditional super-resolution network model algorithms such as long execution time and serious training time, a lightweight super-resolution generation network and discriminant network suitable for roadside real-time scenes are designed, and finally combined with the feature map loss function The g...

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 small-scale pedestrian target rapid super-resolution method for intelligent roadside equipment. The method comprises the steps of collecting and constructing a small-scale pedestrian high-low resolution data training set; based on a generative adversarial idea, building a lightweight generative network for a low-resolution small-scale pedestrian image. The network firstlyuses separable convolution to extract image preliminary features, then combines a residual module to fit high-frequency information, and finally uses a pixel recombination module to perform high-resolution reconstruction on the low-resolution pedestrian image. A discrimination network is built, and discrimination training is performed on the parameters of the generation network to obtain an optimal generation network; and super-resolution on the low-resolution small-scale pedestrian picture is performed by using the optimal generation network to obtain a high-resolution pedestrian target. Thelightweight super-resolution generation network designed by the invention has the remarkable advantages of short training time and low reasoning delay, and fills the technical gap of small-scale pedestrian real-time super-resolution in the field of intelligent roadsides.

Description

technical field [0001] The invention belongs to the field of computer vision and intelligent transportation, and relates to a super-resolution method for small-scale pedestrian targets in intelligent traffic roadside scene images, in particular to a fast super-resolution method for small-scale pedestrian targets for intelligent roadside equipment. Background technique [0002] With the rapid growth of my country's road traffic scale, frequent traffic accidents between pedestrians and vehicles, the safety performance of vehicles has been continuously improved, but the safety equipment for pedestrians has been in a lack of state. In order to ensure the basic safety of pedestrians, the intelligent roadside system, which uses electronic information technology to assist pedestrians to provide safety warnings to surrounding drivers or smart cars, has become the focus of research at home and abroad. Among them, the accurate recognition of small-scale pedestrians is a prerequisite f...

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): G06T3/40G06T5/50
CPCG06T3/4053G06T5/50G06T2207/10004G06T2207/20081G06T2207/20084
Inventor 李旭朱建潇赵琬婷徐启敏
Owner SOUTHEAST 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
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