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

Pedestrian detection model training method based on AdaBoost classifier

A pedestrian detection and model training technology, applied in the field of pedestrian detection, can solve the problems of not fully mining the effect, only focusing on feature design and classifier selection, ignoring the reasonable use of training sample information, etc.

Active Publication Date: 2014-07-02
NAT UNIV OF DEFENSE TECH
View PDF3 Cites 30 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In recent years, in the research in the field of pedestrian detection, most researchers only focus on feature design and classifier selection, but ignore the reasonable use of training sample information, and cannot fully exploit the effects of the methods used.

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
  • Pedestrian detection model training method based on AdaBoost classifier
  • Pedestrian detection model training method based on AdaBoost classifier
  • Pedestrian detection model training method based on AdaBoost classifier

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] Such as figure 1 As shown, the present embodiment provides a pedestrian detection model training method based on AdaBoost classifier:

[0039] 1. Determination of the initial training set of positive and negative samples:

[0040] First, select an appropriate standard dataset for pedestrian detection, such as the INRIA dataset, which includes positive images containing pedestrians and negative images that do not contain pedestrians. According to the annotation file of the data set, the 64*128 pedestrian image is obtained from the block diagram of the positive sample image and copied after mirror symmetry processing, and the extracted image integral channel feature [2] proposed in literature 3 (described in detail in point 4 later) ), that is, after reverse symmetric replication of all positive sample pedestrian images, they are added to the positive sample training set. The positive sample training set is formed in the above way Among them, N=2416, in the negative s...

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 pedestrian detection model training method based on an AdaBoost classifier. The pedestrian detection model training method comprises the steps of firstly, conducting real-time statistics on the sum of sample weight values in the AdaBoost training process, when degeneration is carried out to a certain extent, using a currently-trained weak classifier set for scanning a non-pedestrian image for a false detection window, using the false detection window as a difficult sample to be added in negative sample training sets, and decreasing a degeneration degree threshold value so as to reduce sample update efficiency; finally, removing a part of negative samples through random sampling, and reducing the number of the negative sample training sets so as to reduce the calculated amount of the training process. According to the pedestrian detection model training method based on the AdaBoost classifier, on the premise that a feature extraction method is not changed, the training effect of the classifier can be improved to the maximum extent, and the final detection precision is improved.

Description

Technical field: [0001] The invention mainly relates to the field of pedestrian detection based on static images, in particular to a pedestrian detection model training method based on an AdaBoost classifier. Background technique: [0002] Traffic accidents are an important cause of casualties and property losses in peacetime. Among them, traffic accidents involving pedestrians account for about 14% of the total traffic accidents. The safety of pedestrians in road traffic has attracted widespread attention from the whole society. Researchers Began to work on vehicle assisted driving technology to reduce the accident rate of pedestrians in road traffic, among which pedestrian detection technology is particularly important. Due to the characteristics of both rigid and flexible objects, the appearance of pedestrians is easily affected by clothing, scale, occlusion, posture and viewing angle [4], making pedestrian detection a difficult and hot topic in computer vision research. ...

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): G06K9/00G06K9/66
Inventor 熊志辉张茂军王炜徐玮赖世铭高晨旭
Owner NAT UNIV OF DEFENSE TECH
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