Pedestrian detection method based on combined features

A technology of pedestrian detection and combination features, which is applied in the direction of instruments, character and pattern recognition, computer components, etc.

Active Publication Date: 2012-12-26
HUAQIAO UNIVERSITY
View PDF2 Cites 35 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In order to overcome the shortcomings of the existing pedestrian detection technology in complex scenes, the present invention proposes a pedes

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 method based on combined features
  • Pedestrian detection method based on combined features
  • Pedestrian detection method based on combined features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] A pedestrian detection method based on combined features of the present invention is mainly divided into a training process and a detection process. First, a cascade classifier for distinguishing pedestrians is trained offline, and then the cascade classifier is used to detect whether there are pedestrians in the image. Some pedestrians marked it out:

[0057] Such as Figure 5 As shown, the training process specifically includes the following steps:

[0058] Step 11, intercepting a window with a size of AxB (width x height) containing pedestrians from the image containing pedestrians as a positive sample, and the n positive samples form a positive training sample set. In this embodiment, A=52, B=114; random The interception size is AxB The window that does not contain pedestrians is used as a negative sample, the m negative samples form an initial negative training sample set, and h pictures with complex scenes but no pedestrians are selected as the initial content of...

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 method based on combined features. A certain number of training samples which are the same in size comprise positive samples which comprise pedestrians and randomly intercepted negative samples which do not comprise the background of the pedestrians. Statistical structure gradient features of the training samples are extracted and then delivered to a support vector machine to train, and a classifier is obtained, and then a cascade structure is used to train an n-layer cascade classifier, an offline cascade classifier is obtained to be as a final classifier which distinguishes the pedestrians, the pedestrians in a photo or a video are detected by the final classifier and marked out. The pedestrian detection method based on the combined features can accurately describe the pedestrians and calculate simply, and can balance detection accuracy and detection speed well.

Description

technical field [0001] The invention relates to a pedestrian detection method based on combined features. Background technique [0002] In recent years, in the field of computer video surveillance, back-end intelligent video analysis is a hot research field. Pedestrian detection technology is a prerequisite for some intelligent video analysis technology. At present, there are two ways of pedestrian detection: one is pedestrian detection based on local features, and the other is pedestrian detection based on global features. The advantage of pedestrian detection based on local features is that the calculation speed is fast and the real-time performance is good. However, since pedestrians are a macroscopic representation in the image, unlike human faces, which are small enough to describe with local features (micro), use local features (micro) It is difficult to characterize pedestrians; the advantage of pedestrian detection based on global features is high accuracy. Due to ...

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): G06K9/62
Inventor 戴声奎定志锋
Owner HUAQIAO UNIVERSITY
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