Night vehicle detection method of adaptive feature selection

A feature selection and vehicle detection technology, which is applied in the traffic control system of road vehicles, instruments, characters and pattern recognition, etc., can solve the problems of indistinct gradient information, large changes in illumination brightness, and difficult target extraction, and achieve algorithm complexity Low, high recognition rate, strong robustness effect

Inactive Publication Date: 2018-07-06
NANNING HAOFA TECH
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the particularity of the night traffic scene, such as complex lighting conditions, the amount of distinguishable information of the moving vehicle itself in the night traffic video image is small, the brightness of the light changes greatly, the vehicle lights have obvious halos, the gradient information is not obvious, and the target extraction is difficult. High false detection rate and missed detection rate
Most of the research on traffic video detection algorithms focuses on daytime, and many video detection algorithms suitable for daytime, such as background reduction and inter-frame difference, are not suitable for nighttime environments.

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
  • Night vehicle detection method of adaptive feature selection
  • Night vehicle detection method of adaptive feature selection
  • Night vehicle detection method of adaptive feature selection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The following specific examples further illustrate the present invention, but are not intended to limit the present invention.

[0042] A nighttime vehicle detection method based on adaptive feature selection, including the following steps:

[0043] S1: Collect video images of vehicles at night, and preprocess the images;

[0044] S2: Extract the color feature, texture feature and shape feature of the vehicle, fuse the color, texture and shape features, and obtain the feature vector of the night moving vehicle;

[0045] S3: The Boosting fuzzy classifier designed by Boosting algorithm and genetic algorithm is used to train the input samples, and each round of training obtains the weight corresponding to a fuzzy rule in an iterative manner through the genetic algorithm, and adaptively selects features;

[0046] S4: The Boosting method is used to adaptively select the most favorable features for detection in a weighted voting manner, so as to realize the detection of movi...

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 present invention discloses a night vehicle detection method of adaptive feature selection. The method comprises the following steps of: S1: collecting video images of a night vehicle, and performing preprocessing of the images; S2: extracting color features, texture features and shape features of the vehicle, fusing the color features, the texture features and the shape features, and obtaining feature vectors of the night moving vehicle; S3: performing training of input samples by a Boosting fuzzy classifier designed through adoption of the Boosting algorithm and the genetic algorithm, each training obtaining one weight corresponding to one fuzzy rule in an iteration mode by employing the genetic algorithm, and performing adaptive selection of features; and S4: employing the Boostingmethod to perform adaptive selection of features being the best for detection in a weighted voting mode to achieve detection of the night moving vehicle.

Description

technical field [0001] The invention relates to a nighttime vehicle detection method for adaptive feature selection. Background technique [0002] Vehicle detection is an important part of intelligent traffic management system. With the development of computer vision technology, video-based vehicle detection technology has become a research hotspot in the field of transportation and has been widely used due to its low cost, convenient installation and maintenance. However, due to the particularity of the night traffic scene, such as complex lighting conditions, the amount of distinguishable information of the moving vehicle itself in the night traffic video image is small, the brightness of the light changes greatly, the vehicle lights have obvious halos, the gradient information is not obvious, and the target extraction is difficult. The false detection rate and missed detection rate are high. Most of the research on traffic video detection algorithms focuses on daytime, a...

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): G06K9/00G06K9/46G06K9/62G08G1/017
CPCG08G1/0175G06V20/584G06V10/56G06V10/462G06F18/24
Inventor不公告发明人
OwnerNANNING HAOFA TECH