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

Traffic scene character recognition system and recognition method on basis of vehicle-mounted videos

A text recognition and traffic scene technology, applied in the field of video-based traffic scene text recognition system, can solve the problems of poor robustness, low positioning and recognition accuracy, etc., achieve high positioning and recognition accuracy, improve recognition efficiency, and be robust sexual effect

Inactive Publication Date: 2018-07-06
CHINA ELECTRONIC TECH GRP CORP NO 38 RES INST
View PDF18 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a vehicle-based video-based traffic scene text recognition system and recognition method in order to solve the defects in the prior art that the positioning and recognition accuracy of traffic scene characters is not high, and the robustness is poor under different lighting environments to solve the above problems

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
  • Traffic scene character recognition system and recognition method on basis of vehicle-mounted videos
  • Traffic scene character recognition system and recognition method on basis of vehicle-mounted videos
  • Traffic scene character recognition system and recognition method on basis of vehicle-mounted videos

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] Such as figure 1 As shown, a traffic scene text recognition system based on video is used to automatically detect and recognize traffic signs and advertisement text in vehicle video, including video acquisition module, image preprocessing module, MSER detection module, candidate area screening module, cascaded The classifier obtains a text area module, a text segmentation module, and a CNN text recognition module;

[0057] The video acquisition module collects video and sends the video information to the image preprocessing module;

[0058] The image preprocessing module converts a single frame image into a grayscale image and performs contrast enhancement preprocessing, searches the most stable extremum area of ​​the preprocessed image as a text candidate area, and sends the text candidate area to the MSER detection module;

[0059] The MSER detection module screens the candidate area to obtain the text candidate area that meets the prior knowledge, and sends the text...

Embodiment 2

[0065] Such as figure 2 As shown, based on the above-mentioned system, the present invention also discloses a video-based traffic scene text recognition method for automatically detecting and identifying traffic signs and advertisement text in vehicle-mounted videos, including the following steps:

[0066] 1) Convert a single frame image into a grayscale image and use the Retinex algorithm for contrast enhancement preprocessing, and search for the most stable extremum area of ​​the preprocessed image as a text candidate area;

[0067] First read the key frames in the car video and convert the image into a grayscale image; then use the Retinex algorithm for contrast enhancement processing, which can restore the image well for foggy and backlit scenes; then search for the most stable image after preprocessing The extreme value area is used as the text candidate area, and the algorithm has strong affine transformation invariance to the image;

[0068] The steps of the Retinex a...

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 traffic scene character recognition system and recognition method on the basis of vehicle videos. According to the system, video single-frame images are pre-processed first, the most stable extreme value regions in the images are searched for and used as candidate areas of characters, and then prior knowledge is used for screening the candidate areas to obtain candidate areas conforming to the prior knowledge. The candidate areas conforming to the prior knowledge are subjected to stroke width change, a stroke width mean variance threshold value is set, some candidate areas which do not conform to stroke width features are filtered out, and finally final character areas are obtained by using a binary classifier. After the character areas are obtained, the whole character areas are divided into single characters by using a projection method and a connected domain method, and finally the single characters are sent into a well trained CNN character classifier for character recognition. In order to improve the recognition efficiency, an interesting area of the next-frame image is matched with the character area of the last-frame image by using a gray histogram for tracking and detection. The system has high positioning presicion and high recognition precision for traffic scene characters and good robustness for different lighting environments.

Description

technical field [0001] The invention belongs to the field of pattern recognition and image processing, and relates to a video-based traffic scene text recognition system and recognition method. Background technique [0002] The driver assistance system is an important part of the intelligent transportation system and plays an important role in improving driving safety. The video images captured by the driving recorder usually contain semantic information, which includes information such as route prompts, speed limit signs, and reminders to avoid fatigue driving, and these information play an important role in the driver's cognition of traffic scenes. By automatically recognizing the text in the video of the driving recorder, it is possible to extract warnings, reminders and guidance signs for the driver, and perform selective automatic text information broadcast or storage, so that the driver can make a route choice in advance, which can save time and improve safety. [00...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/34G06K9/72
CPCG06V20/40G06V30/153G06V10/768G06V30/10
Inventor 金东勇连捷肖文光陆迪胡进忠陈俊霞李艳华
Owner CHINA ELECTRONIC TECH GRP CORP NO 38 RES INST
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