Visibility discrimination method and device combining semantic segmentation and frequency domain analysis, and medium

A technology of frequency domain analysis and semantic segmentation, applied in the field of meteorological detection, can solve the problems of expensive erection intervals, difficulty in meeting large-area rain and fog weather detection, poor timeliness, etc.

Pending Publication Date: 2022-06-03
深研人工智能技术(深圳)有限公司
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the timeliness of personnel visual inspection is poor, and the coverage of expressway sections is limited, which consumes high labor costs
The detection of instruments and equipment mainly uses infrared light and laser equipment, which have defects such as high price and generally sparse installation intervals (for example, the interval is about 20km), which is difficult to meet the detection of large-scale rain and fog weather.

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
  • Visibility discrimination method and device combining semantic segmentation and frequency domain analysis, and medium
  • Visibility discrimination method and device combining semantic segmentation and frequency domain analysis, and medium
  • Visibility discrimination method and device combining semantic segmentation and frequency domain analysis, and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0028] It should be understood that when used in this specification and the appended claims, the terms "comprising" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude one or Presence or addition of multiple other features, integers, steps, operations, elements, components and / or collections thereof.

[0029] It should also be understood that the terminology 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
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a visibility discrimination method and device combining semantic segmentation and frequency domain analysis and a medium, and the method comprises the steps: respectively obtaining a first road segment image with clear visibility and a second road segment image with current visibility for the same road segment; edge information in the first road section image and the second road section image is segmented through a semantic segmentation network, and first feature parts and second feature parts are obtained; based on frequency domain analysis, respectively filtering the first feature part and the second feature part to obtain a first high-frequency information image and a second high-frequency information image; respectively extracting a first edge pixel in the first high-frequency information image and a second edge pixel in the second high-frequency information image by using an edge detector; calculating the proportion of the edge pixel in the total pixel of the feature part; and calculating a difference value between the first proportion and the second proportion, and taking the difference value as a current visibility value of the road section. According to the invention, the accuracy of road visibility recognition can be improved.

Description

technical field [0001] The invention relates to the technical field of meteorological detection, in particular to a visibility judgment method, device and medium combining semantic segmentation and frequency domain analysis. Background technique [0002] Low visibility due to weather such as fog, rain, snow, or dust is an important cause of traffic accidents, especially on high-speed roads where the speed of the vehicle is fast and the traffic flow is large, and the visibility caused by weather such as fog and haze is low. Unable to see the situation in front and around, resulting in inaccurate estimation of vehicle distance and speed, difficulty in identifying other vehicles, traffic signs or road facilities, and easy to cause important traffic accidents such as rear-end collisions. Therefore, it is necessary to develop a method for accurately judging the visibility of road sections, which is of great significance to traffic control and safety. [0003] Common methods for ...

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): G06V20/58G06V10/26G06V10/44G06V10/774G06V10/80G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/04G06N3/08G06F18/253G06F18/214Y02A90/10
Inventor施岚峰杨元弢林丕成宋开银
Owner深研人工智能技术(深圳)有限公司