Incremental learning based method for detecting and identifying traffic sign in traveling video

A traffic sign, incremental learning technology, applied in the field of traffic sign detection and recognition, can solve problems such as poor robustness, and achieve the effect of improving robustness and reliability

Active Publication Date: 2015-10-14
NORTHWESTERN POLYTECHNICAL UNIV
View PDF3 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In order to overcome the shortcomings of poor robustness of existing traffic sign detection and recognition methods, the present invention provides a method for detection and recognition of traffic signs in driving videos based on incremental learning

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
  • Incremental learning based method for detecting and identifying traffic sign in traveling video
  • Incremental learning based method for detecting and identifying traffic sign in traveling video
  • Incremental learning based method for detecting and identifying traffic sign in traveling video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] refer to Figure 1-4 . The present invention is based on the detection of the traffic sign in the driving video of incremental learning and the concrete steps of identification method are as follows:

[0027] Step 1. First, normalize the training data set, sample image blocks, calculate the channel feature pool, and use the Adaboost algorithm to train the detector model. The detector is obtained by cascading 4-layer strong detectors. This 4-layer strong detector Include 32, 128, 512, 2048 weak classifiers respectively. The detection target that passes all 4 layers of strong classifiers is the candidate target, and the strong classifier model of the last layer is:

[0028]

[0029] Among them, α t is the weight of each weak classifier obtained from training, h t is the weak classifier, and T is the number of weak classifiers.

[0030] Step 2, use the training data to perform offline training on the online incremental SVM detector to complete the initialization pr...

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 an incremental learning based method for detecting and identifying a traffic sign in a traveling video, and is used for solving the technical problem of poor robustness in an existing traffic sign detection and identification method. The technical scheme is as follows: polymerization channel characteristics are adopted for training an Adaboost classifier, and a detector is improved; then a detection result of the detector serves as an observation value of a Kalman filter to perform motion model based tracing; in the tracing process, a new incremental SVM detector is trained on line; when the detection of an original Adaboost detector is failed due to apparent change of the sign, the online incremental detector is used for carrying out detection, the detection result serves as the observation value of the Kalman filter to be input, and targets incapable of being continuously detected are filtered; and finally, a tracing result of the same physical traffic sign is subjected to weighted voting of scale based Gaussian weight, a final identification result is obtained, and the detection and identification robustness are improved.

Description

technical field [0001] The invention relates to a method for detecting and recognizing traffic signs, in particular to a method for detecting and recognizing traffic signs in a driving video based on incremental learning. Background technique [0002] Literature "Andreas Dongran Liu, Mohan M.Trivedi, Traffic Sign Detection for U.S.Roads: Remaining Challenges and a case for Tracking.IEEE Intelligent Transportation Systems Conference, pp.1394-1399.2014."The Adaboost method of cascaded classifiers is used for detection. This paper chooses Integrate channel features to extract features from input training data, then train a 3-layer Adaboost cascade classifier, and use sliding window method to detect input video data. This traffic sign detection method is too dependent on training data and feature extraction methods. For situations that have not appeared in the training data, false detections are prone to occur, or missed detections are caused by changes in target illumination,...

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): G06K9/00G06K9/62
CPCG06V20/56G06F18/24
Inventor 袁媛王琦熊志同
Owner NORTHWESTERN POLYTECHNICAL 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