An Adaptive Crowd Counting Method

A crowd counting and adaptive technology, applied in computing, computer parts, instruments, etc., can solve the problems of poor density effect, high complexity and high cost, and achieve the effect of improving accuracy, expanding the scope of use, and robust and accurate detection effect.

Active Publication Date: 2019-11-12
FUZHOU UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But using indirect methods at low densities is unnecessarily complex and costly compared to direct methods
[0007] It can be seen that the direct method and the indirect method are suitable for low density and high density respectively, but are less effective at the other density

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
  • An Adaptive Crowd Counting Method
  • An Adaptive Crowd Counting Method
  • An Adaptive Crowd Counting Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The technical solution of the present invention will be specifically described below in conjunction with the accompanying drawings.

[0054] An adaptive crowd counting method of the present invention comprises the following steps,

[0055] S1. Using a pedestrian detector to perform pedestrian detection on the video frames of the input video frame sequence to obtain a detection candidate frame;

[0056]S2. Preprocessing the obtained detection candidate frames, obtaining feature points, and extracting the space, time and color features of each preprocessed detection candidate frame;

[0057] S3. According to the space, time and color features of the detection candidate frames, the detection candidate frames are clustered to obtain the crowd cluster area;

[0058] S4. Using a crowd counting method based on corner points to perform a preliminary count of crowds in each crowd cluster area;

[0059] S5, performing density estimation through the relationship between the coun...

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 an adaptive crowd counting method. First, use the cumulative integral feature pedestrian detector to detect pedestrians to obtain a large number of detection candidate frames, and then preprocess the obtained candidate frames. Next, this paper extracts the space, time and color features of each preprocessed candidate frame; based on These features, the present invention clusters the candidate frames with the Didicre mixture model and Gibbs sampling theory; in this way, to obtain the area of ​​crowd clusters; next, this paper uses the crowd counting method based on corner points To perform a preliminary count of the crowd in each crowd agglomeration area; through the relationship between the counting result and the feature point, the present invention judges the crowd density. For different densities, this paper selects different data fusion methods to improve the accuracy of the counting result. The method of the invention improves the stability and accuracy of crowd counting detection.

Description

technical field [0001] The invention belongs to the fields of computer vision and digital image processing, and in particular relates to an adaptive crowd counting method. Background technique [0002] With the development of society and the advancement of technology, intelligent video surveillance technology plays a vital role in more and more fields, and crowd counting is a vital part of intelligent video surveillance. The so-called crowd counting is through reading Take a picture or video frame to get how many people there are in the current frame or picture. [0003] The current crowd counting methods are mainly divided into two categories: direct method and indirect method. [0004] The direct method is also called a detection-based method. It mainly uses different detection models to segment individual pedestrian detection to achieve crowd counting. When the density is low, the pedestrian detection model based on the human body is mainly used; when the density is med...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/53G06F18/232
Inventor 黄立勤黄炜
Owner FUZHOU 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