Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Passenger detecting method based on Haar-PCA characteristic and probability neural network

A probabilistic neural network and pedestrian detection technology, applied in the field of image processing, can solve the problems of reducing the detection rate and lengthy BPANN training time, and achieve the effects of reducing dimensionality, improving classification performance, and reducing training time

Inactive Publication Date: 2016-08-31
JIANGSU UNIV
View PDF3 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, BPANN has two disadvantages: 1. The training is easy to fall into the local minimum point and reduce the detection rate; 2. BPANN needs to determine the network weight through training.
When the number of samples is large and the dimensionality is large, the BPANN training time is lengthy, requiring dozens of hours or even days

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
  • Passenger detecting method based on Haar-PCA characteristic and probability neural network
  • Passenger detecting method based on Haar-PCA characteristic and probability neural network
  • Passenger detecting method based on Haar-PCA characteristic and probability neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention.

[0036] Step 1: Manually select a large number of pictures of pedestrians and non-pedestrians, and mark them as positive and negative samples respectively. All positive and negative samples are normalized to a dimension of 32 pixels in length and width. Let the total number of positive and negative samples be n.

[0037] Step 2: Take any positive and negative sample S i Characterize with Haar features to generate Haar feature vector H i , (i=1, 2, . . . , n).

[0038] Step 2-1: There are various types of Haar rectangle features. Considering that pedestrians present more horizontal and vertical line features in the image, select such as figure 2 The 10 classes of Haar features shown. There are white and black rectangles in the Haar feature template, and the size of a certa...

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 passenger detecting method based on a Haar-PCA characteristic and a probability neural network. The passenger detecting method comprises the steps of manually selecting a large number of passenger pictures and non-passenger pictures, and respectively marking the passenger pictures and the non-passenger pictures as positive samples and negative samples; representing a random positive sample or negative sample Si by means of an Haar characteristic, generating an Haar characteristic vector Hi, wherein i=1, 2, ..., n; selecting a main element subset vector Hi<PCA> which comprises majority part information on the Haar characteristic vector Hi of all samples through main component analysis; determining a classifier CPNN structure and determining to-be-classified samples, similarly with the step 2 and step 3, representing a to-be-determined sample according to the Harr-PCA characteristic vector Hi<PCA>, and inputting the vector into the CPNN which is obtained in the step 4, wherein the to-be-determined sample belongs to a class of which the output neuron is 1. The passenger detecting method has advantages of greatly reducing number of dimensions of a training characteristic vector through the Haar-PCA characteristic, reducing training load of the classifier, and greatly improving detection accuracy through replacing traditional BPANN by means of the probability neural network (PNN).

Description

technical field [0001] The invention belongs to the technical field of image processing and relates to image information perception, in particular to a pedestrian detection method based on Haar-PCA features and a probability neural network. Background technique [0002] Traffic safety has become a major worldwide issue, and the impact of automobile safety on human life and property is self-evident. With the development of highways and the improvement of automobile performance, the speed of automobiles has also increased accordingly. In addition to the increase in the number of automobiles and the increasingly busy traffic, the casualties and property losses caused by the increase in automobile accidents have become a social problem that cannot be ignored. The driving safety of automobiles is even more important. Traditional passive safety is far from being able to avoid traffic accidents, but active safety technology has attracted much attention because it can prevent accid...

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): G06K9/00G06T3/40G06K9/48G06K9/62G06N3/04
CPCG06T3/40G06T2207/30252G06V40/103G06V10/46G06N3/047G06F18/241
Inventor 蔡英凤王海陈龙江浩斌袁朝春徐兴李诚郑正扬
Owner JIANGSU 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
Eureka Blog
Learn More
PatSnap group products