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

Pedestrian monitoring method and device based on distance image head and shoulder features

A technology of distance image and head and shoulder features, which is applied in the field of pedestrian monitoring based on distance image and color image processing, can solve the problem of less information in the laser method, improve passenger flow management service and safety assurance level, wide application range, and equipment low cost effect

Active Publication Date: 2014-03-19
黄卫 +2
View PDF3 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the above-mentioned defects, the object of the present invention is to provide a pedestrian monitoring algorithm and device based on distance image processing, which can overcome the disadvantages of the simple video method that is susceptible to external interference and the laser method with less information, and realize detection in various environments including night. Accurate pedestrian detection and tracking in the environment can meet the needs of pedestrian monitoring and statistics in complex environments and areas with dense passenger flow

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 monitoring method and device based on distance image head and shoulder features
  • Pedestrian monitoring method and device based on distance image head and shoulder features
  • Pedestrian monitoring method and device based on distance image head and shoulder features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] A pedestrian detection method based on the head-and-shoulder feature of the range image, the steps comprising:

[0043] 1) Color image acquisition and distance image acquisition in the monitoring area:

[0044] The acquired color image is used for the processing of step 4);

[0045] The distance image is obtained, and the distance image is converted into a height image according to the erection height and inclination angle of the distance image acquisition device;

[0046] 2) For height images, filter out the background by a set height threshold:

[0047] The image in the height image is compared with the height threshold, and the image area below the threshold is filtered out as the background image area, and the image area above the threshold is used as the foreground area;

[0048] 3) For the foreground area after the background is filtered out, the position of the peak area in the foreground area is first determined by the mean shift method, which is the head posi...

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 monitoring method and device based on distance image head and shoulder features. According to the method, a distance image is acquired, calculation is performed to obtain a height image, the background is filtered out by adopting a height threshold value, a pedestrian detection result is obtained through the head and shoulder height feature template matching and the color image textural feature template matching, and the passenger flow parameter extraction and event discrimination are performed through the pedestrian tracking and trajectory analysis. The device for performing pedestrian detection by adopting the algorithm comprises an integrated probe which is used to acquire the distance image and the color image at the same time and perform synchronous correction, a video image processing and central control unit, a cache module, a memory module, an encryption chip, a network transport module, a USB interface and a power module.

Description

technical field [0001] The invention belongs to the field of intelligent detection, in particular to an algorithm and device for pedestrian monitoring based on distance image and color image processing. Background technique [0002] Pedestrian detection technology is widely used in passenger flow statistics, intrusion detection, security and other fields. It can be widely used in subways, stations, museums, plazas, shopping malls, parks and other important places and densely populated areas. It can realize real-time detection of pedestrians, Functions such as extraction of individual characteristics and group characteristics and parameters can provide data acquisition means for systems such as pedestrian detection-based data collection, abnormal information extraction, passenger flow statistics and early warning, and business analysis. The status quo of storage is an intelligent upgrade of monitoring methods, and it is also an important manifestation of smart cities. [000...

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): G06K9/60G06K9/62
Inventor 魏运田青
Owner 黄卫
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