Pedestrian detection method based on multi-feature fusion

A multi-feature fusion and pedestrian detection technology, which is applied in the field of pedestrian tracking, can solve the problems of low detection rate, poor real-time performance, and poor real-time performance, and achieve good practicability, improved pedestrian detection accuracy, and strong pedestrian representation capabilities Effect

Active Publication Date: 2015-06-17
NANJING UNIV OF POSTS & TELECOMM
View PDF2 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The advantage of this method is that it is not susceptible to appearance changes, such as lighting conditions, clothing colors, etc.; its disadvantage is that it requires a series of continuous pictures and moving targets, and the real-time performance is not good and stationary pedestrians canno

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 multi-feature fusion
  • Pedestrian detection method based on multi-feature fusion
  • Pedestrian detection method based on multi-feature fusion

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0032] The invention will be further described in detail below in conjunction with the accompanying drawings of the specification.

[0033] The present invention provides a pedestrian detection method based on multi-feature fusion. The method first uses Kinnect to obtain a depth image, and performs noise reduction processing on the depth image; then a depth threshold-based method realizes the detection of a region of interest; and finally extracts HOG- LBP combines features and uses SVM classifier to achieve target detection.

[0034] A preferred embodiment of the pedestrian detection method based on multi-feature fusion of the present invention specifically includes the following steps:

[0035] Step 1. Use Kinnect to obtain the depth image and perform noise reduction processing on the depth image.

[0036] (1) The acquisition process of depth imaging is as follows figure 1 As shown, the specific process is described as follows:

[0037] Calibration; first, collect speckle patterns w...

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 multi-feature fusion. The method includes the following steps that noise suppression is conducted on an obtained depth image; area-of-interest detection is achieved through a depth threshold; on the basis of obtaining the HOG-LBP union features, target detection is achieved through a classifier. According to the pedestrian detection method based on multi-feature fusion, the fused features of the HOG and the LBP are classified through a support vector machine. The method has higher pedestrian representation capacity, and the pedestrian detection accuracy is obvious improved under a complex background.

Description

technical field [0001] The invention relates to a pedestrian tracking method, in particular to a pedestrian tracking method based on multi-feature fusion. Background technique [0002] Pedestrian detection has a wide range of applications in video surveillance, robotics, virtual reality and other fields, and it is also an important research direction in the fields of computer vision and pattern recognition. Different figures, postures, clothing, lighting, complex background scenes, and the movement and shaking of the camera itself are all difficulties in pedestrian detection. How to quickly and accurately detect pedestrians from the video or image background is still a research hotspot. [0003] The current pedestrian detection methods can be divided into the following three categories: pedestrian detection based on motion characteristics, pedestrian detection based on multi-part template matching, and pedestrian detection based on machine learning. [0004] Pedestrian det...

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): G06K9/00G06K9/62
Inventor 朱松豪陈玲玲李向向
Owner NANJING UNIV OF POSTS & TELECOMM
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