Pedestrian detection method based on directional chamfering distance characteristics

A distance feature, pedestrian detection technology, applied in the fields of machine learning, computer vision, pattern recognition, pedestrian detection, can solve the problems of few applications, high computational complexity of 3D models, difficult parameter tuning, etc. Effects of Interference Ability

Inactive Publication Date: 2016-06-29
SOUTHEAST UNIV
View PDF2 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the high computational complexity and the difficulty of parameter tuning, 3D models are rarely used in the case of a single camera or lack of image depth information
[0018] Although there have ...

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 directional chamfering distance characteristics
  • Pedestrian detection method based on directional chamfering distance characteristics
  • Pedestrian detection method based on directional chamfering distance characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The technical scheme of the present invention is described in detail below in conjunction with accompanying drawing:

[0048] According to the traditional pattern recognition theory, the problem of pedestrian detection can be solved according to figure 1 It is transformed into a two-category problem, that is, to determine whether the input image is a pedestrian. In this way, the focus of pedestrian detection lies in two parts: feature extraction and classifier design.

[0049] The classic features in the field of pedestrian detection include Haar-like features, HOG (Histogram of Oriented Gradient) features, contour features, etc. As a common target classification problem, there are SIFT (ScaleInvariantFeatureTransform) features, SURF (Speeded-UpRobustFeatures) features and other feature descriptors. Classifiers also have relatively mature Bayesian classifiers, nearest neighbor classifiers, neural network classifiers, support vector machines, etc. Uncertain factors su...

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 provides a pedestrian detection method based on directional chamfering distance characteristics. The method comprises following steps of (1) inputting a to-be-detected image and preprocessing the to-be-detected image so as to obtain a to-be-detected edge image; (2) extracting the directional chamfering distance characteristics; (3) by taking a directional chamfering distance as a distance metric, comparing similarity of a profile of the to-be-detected edge image obtained in the step (1) with a profile of a template image and judging whether the to-be-detected edge image is a pedestrian image; and if the template image has been judged, judging that the template image is an image of a pedestrian profile. According to the invention, by expanding the original directional chamfering distance characteristics, adding characteristics in the profile direction, and further carrying out codebook and multi-scale describing on the characteristics, strong directional chamfering distance characteristics with scale invariance are formed; the anti-interference ability of the directional chamfering distance characteristics to noise is improved; and accuracy of the pedestrian detection system is sufficiently increased.

Description

technical field [0001] The invention relates to the fields of pattern recognition, machine learning, and computer vision, and is directly applied to the fields of pedestrian detection and the like. Background technique [0002] As an important part of most computer vision problems, people's individual actions, interactions between humans, and interactions between humans and machines have attracted more and more attention. Detecting, recognizing and tracking human body has become one of the most challenging topics in recent years. In the United States alone, about 5,000 of the nearly 35,000 accidental traffic accidents each year are directly related to pedestrians, so it is urgent to design and implement an automatic pedestrian detection system. [0003] Pedestrian detection, as a basic step in recognition and tracking, is widely used in many fields: [0004] 1) Video surveillance [0005] With the popularization of surveillance cameras, the monitoring of public places has...

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): G06T7/00G06K9/62
CPCG06T7/0002G06T2207/20016G06T2207/30196G06F18/2411
Inventor 陈单啇夏思宇
Owner SOUTHEAST 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