Method and system for training road anomaly recognition model and road abnormity recognition method and system

A technology of abnormal identification and road, applied in the field of pattern recognition, can solve the problem of low efficiency of abnormal identification of roads, and achieve the effect of overcoming low efficiency

Inactive Publication Date: 2019-08-16
BEIJING E HUALU INFORMATION TECH
View PDF5 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Therefore, a kind of training road anomaly identification model provided by the present invention, the method and system o

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
  • Method and system for training road anomaly recognition model and road abnormity recognition method and system
  • Method and system for training road anomaly recognition model and road abnormity recognition method and system
  • Method and system for training road anomaly recognition model and road abnormity recognition method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] An embodiment of the present invention provides a method for training a road anomaly recognition model, such as figure 1 As shown, the method for training the road anomaly recognition model includes the following steps:

[0033] Step S11: Obtain images of road abnormalities and road normal conditions.

[0034] In the embodiment of the present invention, the road abnormalities include: road water, road fires and traffic accidents, and the crawler program can be used to crawl Internet pages and / or extract frames from videos to obtain road water, road fires, traffic accidents and traffic accidents. The images of ordinary roads are only used as examples and not limited thereto.

[0035] Step S12: Input the images of abnormal road conditions and normal road conditions into the neural network model.

[0036] In the embodiment of the present invention, the neural network structure adopted is a convolutional neural network, and ResNet or MobileNet can be selected. The embodim...

Embodiment 2

[0045] The embodiment of the present invention provides a road anomaly identification method, which can be applied to real-time monitoring of roads, such as Figure 6 shown, including:

[0046] Step S21: Obtain the road image to be recognized.

[0047] In the embodiment of the present invention, frame extraction can be performed on the monitoring video of the road to obtain real-time road images.

[0048] Step S22: Input the road image to be recognized into the neural network model for road abnormality recognition to obtain a recognition result, which is used to indicate whether the road is abnormal.

[0049] In the embodiment of the present invention, the road image to be recognized obtained by the road image monitoring device is input into the neural network model for road abnormality recognition obtained according to the method of training the road abnormality recognition model described in Embodiment 1 of the present invention, and the recognition As a result, the road i...

Embodiment 3

[0052] An embodiment of the present invention provides a system for training a road anomaly recognition model, such as Figure 7 As shown, the system for training road anomaly recognition models includes:

[0053] The road image acquisition module 1 is used to acquire images of abnormal road conditions and normal road conditions; this module executes the method described in step S11 in Embodiment 1, which will not be repeated here.

[0054] The image input module 2 is used for inputting the images of the abnormal condition of the road and the normal condition of the road into the neural network model; this module executes the method described in step S12 in Embodiment 1, which will not be repeated here.

[0055] The recognition model acquisition module 3 is used to perform transfer learning on the preset trainable layers in the neural network model according to the images of abnormal road conditions and normal road conditions, so as to obtain a neural network model for road ab...

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 method and system for training a road anomaly recognition model and a road anomaly recognition method and system. The method for training the road anomaly recognition model comprises the steps: acquiring images of road anomaly conditions and road normal conditions; inputting the images of the road abnormal condition and the road normal condition into a neural network model; and carrying out transfer learning on the preset trainable layer number in the neural network model according to the images of the road abnormal condition and the road normal condition to obtain aneural network model for road abnormal recognition. According to the recognition model, the input full-frame road original image does not need to be positioned and the like, only one operation needs to be carried out on the image, the real-time performance is high, the model training convergence speed is increased by applying the transfer learning technology, and various road abnormal conditions including road ponding, road fire and traffic accidents can be recognized.

Description

technical field [0001] The invention relates to the technical field of pattern recognition, in particular to a method and system for training a road anomaly recognition model and road anomaly recognition. Background technique [0002] At present, based on traditional non-deep learning machine learning algorithms, road image features are extracted and classified and recognized. The advantage is that the amount of training data required is small and easy to implement, but the disadvantage is that the accuracy rate is not as good as deep learning when the amount of training data is sufficient. Algorithm, and it is necessary to locate the abnormal position of the road, and it needs to perform multiple calculations on the image, which cannot meet the needs of real-time video image processing. Contents of the invention [0003] Therefore, a training road anomaly recognition model, a method and a system for road anomaly recognition provided by the present invention overcome the d...

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): G06K9/00G06K9/62G06N3/04
CPCG06V20/588G06N3/045G06F18/214
Inventor 李高杨林拥军宋征张星郝燕茹
Owner BEIJING E HUALU INFORMATION 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