Supercharge Your Innovation With Domain-Expert AI Agents!

Vehicle passenger counting method combining face detection and tracking

A face detection and counting method technology, applied in computing, computer parts, instruments, etc., can solve the problem of limited field of view of the camera, and achieve the effect of improving the robustness and accuracy of the algorithm

Inactive Publication Date: 2017-08-22
SUN YAT SEN UNIV
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] In general, the existing research on video people counting technology is aimed at specific scenes such as entrances and exits, buse

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
  • Vehicle passenger counting method combining face detection and tracking
  • Vehicle passenger counting method combining face detection and tracking
  • Vehicle passenger counting method combining face detection and tracking

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0083] The method provided by the present invention utilizes the characteristic that human faces are visible under the vehicle-mounted camera, and proposes a vehicle occupant counting method that integrates face detection and tracking. This method first uses the AdaBoost face detection algorithm to detect the occupant's face initially, then combines the Kalman filter tracking algorithm to track the detected occupant's face, and finally outputs the counting result every 10 frames. The overall framework of the algorithm is as figure 1 As shown, the key steps of the method will be described in detail below.

[0084] 1. Face detection stage:

[0085]The scene mode of the monitoring camera in the car is horizontal shooting, which can capture the faces of the occupants. Based on this, the occupant detection stage assumes that if a human face is detected, it is regarded as an occupant; the number of occupants is the same as the number of human faces. Therefore, occupant detection ...

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 relates to a vehicle passenger counting method combining face detection and tracking. The method comprises the steps that S1 for an image sequence taken by a vehicle-mounted camera, an AdaBoost face detection algorithm is first used to detect and acquire the position of the face of a passenger in a current frame image; S2 a Kalman filter tracking algorithm is used to predict the position of the face of the passenger in a next frame image; S3 an AdaBoost face detection algorithm is used to detect the face of the passenger at the position predicted by the next frame image; and S4 S2 and S3 are repeated to realize continuous tracking of the face of the passenger; and S5 the number of the face of tracked passengers is counted to acquire the number of passengers in a vehicle.

Description

technical field [0001] The invention relates to the technical field of digital image processing, and more particularly, relates to a method for counting car occupants by integrating face detection and tracking. Background technique [0002] There are countless people counting methods available, each of which has its specific application: [0003] (1) People counting method based on human body shape modeling [1-3], the basic idea is to construct a parameter model based on the knowledge of human body structure to realize the detection and counting of pedestrian targets, such as the description of human body partial shape proposed by WU and Nevati[4] The edgelet feature of AdaBoost is used to learn four part detectors of head, torso, leg and whole human body to form a joint probability model. The results show that the detection accuracy reaches 98% when the false positive rate is 10-4. This type of method relies on scenes where the human body is visible and the torso features ...

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): G06K9/00
CPCG06V40/161G06V40/172
Inventor 李熙莹黄秋筱李国鸣邓院昌
Owner SUN YAT SEN UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com