Remote traffic sign detection and recognition method based on F-RCNN

A traffic sign and recognition method technology, applied in the field of intelligent transportation, can solve the problem of low precision

Active Publication Date: 2019-08-23
NORTHEAST GASOLINEEUM UNIV
View PDF6 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to provide a long-distance traffic sign detection and recognition method based on F-RCNN, which is used to sol...

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
  • Remote traffic sign detection and recognition method based on F-RCNN
  • Remote traffic sign detection and recognition method based on F-RCNN
  • Remote traffic sign detection and recognition method based on F-RCNN

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0164] The present invention adopts Tsinghua-Tencent 100K as the data set of model training study, to 44 kinds of common traffic signs (refer to image 3 ) were detected and identified. In this data set, the resolution of each traffic scene is 2048×2048, and the size of traffic signs is between 0-32 pixels and 32-96 pixels, accounting for 41.6% and 49.1% of the data set, or 90.7% of the traffic signs The proportion of the size of the traffic scene is less than 1%, which belongs to the long-distance traffic sign detection and recognition situation.

[0165] F-RCNN model training and on-the-spot test situation description (test is in order to grasp the feasibility of the present invention's 1st step~8th step)

[0166] In the process of training the F-RCNN model, in order to eliminate the imbalance of the sample set, for categories with less than 100 pictures, the method of resampling is used in each training iteration to make the number of pictures exceed 1000. The ratio of tr...

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 relates to a remote traffic sign detection and recognition method based on F-RCNN, which comprises: 1, preprocessing the traffic sign image sample set; 2, pre-training VGG-16 in F-RCNN;3, inputting the traffic sign training data set to the VGG-16 to complete feature extraction; 4, constructing a fusion feature map; enabling the region generation network RPN in the F-RCNN to performregion generation according to the fusion feature map to obtain a candidate region of the traffic sign; 6, inputting all candidate regions to the RoI-Pooling layer in the F-RCNN to generate a fixed-size feature vector; 7, sending the feature vector to the extreme learning machine network to output the category and location of the traffic sign; 8, training the F-RCNN model by the contribution adaptive loss function; 9, completing the traffic sign detection and identification of the actual scene. The invention realizes the detection and identification of the long-distance traffic sign, and the recognition precision is high.

Description

[0001] 1. Technical field: [0002] The invention relates to the field of intelligent transportation oriented to unmanned driving and assisted driving, and solves the long-distance detection and recognition method of road traffic signs, and specifically relates to the long-distance traffic sign detection and recognition method based on F-RCNN. [0003] 2. Background technology: [0004] In the field of intelligent transportation, traffic sign detection and recognition is an important research issue for systems such as unmanned driving and assisted driving. A lot of research work has been done on this at home and abroad, but there are still great deficiencies, which cannot be practically applied to practice. The reasons are as follows: (1) Some detection and recognition methods use the public German traffic sign datasets GTSRB and GTSDB. Traffic signs occupy a large proportion of the image, and the detection distance of traffic signs is short, which is difficult to adapt to the ...

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): G06K9/00G06K9/46G06K9/62G06N3/04
CPCG06V20/582G06V10/40G06N3/045G06F18/253
Inventor 杜娟刘志刚刘贤梅王辉刘苗苗王梅
Owner NORTHEAST GASOLINEEUM 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