Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Pavement pit and pond detection method based on machine vision in complex environment

A machine vision, complex environment technology, applied in neural learning methods, instruments, computer parts and other directions, can solve the problems of small target scale, texture feature degradation, complex background, etc., to reduce interference, improve robustness, and improve detection. The effect of precision

Inactive Publication Date: 2020-01-21
NANJING UNIV OF SCI & TECH
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for complex road scene images from the monitoring perspective, it has the characteristics of complex background, small target scale, and degraded texture features. The method performs target detection on this type of image, and the effect obtained is relatively limited.

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
  • Pavement pit and pond detection method based on machine vision in complex environment
  • Pavement pit and pond detection method based on machine vision in complex environment
  • Pavement pit and pond detection method based on machine vision in complex environment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] Such as figure 1 As shown, a machine vision-based road surface pothole detection method in a complex environment, the specific steps are:

[0030] Step 1, using the traffic monitoring images with pixel-level annotations as training samples to train the semantic segmentation model;

[0031] In a further embodiment, the semantic segmentation model may use, but is not limited to, a convolutional neural network with an encoding-decoding structure or a convolutional neural network adopting a dilated convolution strategy.

[0032] Such as figure 2 , 4 As shown, in a further embodiment, the base layer of the semantic segmentation model is a ResNet network pre-trained using a dilated convolution strategy; the output of the base layer is connected to a pyramid pooling module, wherein the pyramid pooling module passes four expansion rates Different dilated convolutions extract feature maps at four different scales, and upsample these four feature maps to make the scales the s...

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 a pavement pit and pond detection method based on machine vision in a complex environment. The method comprises the following steps: firstly, training a semantic segmentation model by utilizing a traffic monitoring image subjected to pixel-level labeling; secondly, carrying out background modeling on the traffic monitoring video to obtain a traffic monitoring background image, utilizing a semantic segmentation model to segment the background image, and extracting a road in the image; then, carrying out binarization on the extracted road, segmenting areas with deep colorsand large areas on the road surface out, adopting a support vector machine to classify the areas, and obtaining candidate areas of the road surface pit pond; and finally, outputting candidate regionswhich are divided into the pavement pit and pond sub-regions by the semantic segmentation model. According to the invention, the interference of a complex background on a detection task is effectively reduced, the robustness of the algorithm is improved, and the detection precision is improved.

Description

technical field [0001] The invention belongs to the technical field of machine vision, and specifically relates to a machine vision-based detection method for road surface pits and ponds in a complex environment. Background technique [0002] Relying on the new generation of information technologies such as artificial intelligence, cloud computing, and the Internet of Things, and with the help of sensing devices such as video surveillance, GPS, and mobile terminals, more and more automatic detection technologies for road potholes have been proposed by researchers. The traditional method is usually to conduct targeted feature analysis on different road potholes, and then rely on these features for target detection; at the same time, some researchers use existing data sets to train neural networks in order to identify various road potholes . However, for complex road scene images from the monitoring perspective, it has the characteristics of complex background, small target s...

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): G06T7/00G06T7/11G06N3/04G06N3/08G06K9/62
CPCG06T7/0002G06T7/11G06N3/084G06T2207/10016G06T2207/30232G06N3/045G06F18/2411
Inventor 丁俊杰郭唐仪练智超刘悦邓洁仪朱永璇周钰汀郭玉洁孙豪郝浪吕亦江伊特格勒朱云霞
Owner NANJING UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap 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