Unlock instant, AI-driven research and patent intelligence for your innovation.

Crowd counting method based on spatial information fusion and convolutional neural network

A convolutional neural network and spatial information technology, applied in the field of image-based crowd counting, can solve problems such as poor robustness, and achieve the effect of improving robustness and solving fusion problems.

Active Publication Date: 2020-07-17
HARBIN INSTITUTE OF TECHNOLOGY SHENZHEN (INSTITUTE OF SCIENCE AND TECHNOLOGY INNOVATION HARBIN INSTITUTE OF TECHNOLOGY SHENZHEN)
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the robustness of the network to scale changes in current methods is poor

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
  • Crowd counting method based on spatial information fusion and convolutional neural network
  • Crowd counting method based on spatial information fusion and convolutional neural network
  • Crowd counting method based on spatial information fusion and convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0046] attached figure 1 It shows a model frame diagram of a crowd counting method based on spatial information fusion and convolutional neural network proposed by the present invention. The method involves a basic module, a multi-scale module and a fusion module. Specifically, low-level semantics is performed through the basic module Feature extraction, multi-scale feature extraction is performed through the multi-scale module, and multi-stage feature fusion is completed through the fusion module. The detailed steps are as follows:

[0047]S1: Extract low-level semantic features through the basic...

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 crowd counting method based on spatial information fusion and a convolutional neural network. Based on a basic module, a multi-scale module and a fusion module, the method comprises the following steps: extracting low-order semantic features through the basic module: preprocessing an obtained picture, and adding the preprocessed picture into a single-column module of a small-size filter to extract low-level semantic features; extracting multi-scale features through the multi-scale module; extracting human head features of corresponding scales by using filters of different sizes; and completing fusion of multi-stage features through the fusion module. According to the crowd counting method based on spatial information fusion and the convolutional neural network provided by the invention, the robustness of the module in the aspect of human head scale transformation is improved, and the fusion problem of two types of multi-scale features is solved.

Description

technical field [0001] The invention belongs to the field of crowd counting based on pictures, in particular to a crowd counting method based on spatial information fusion and convolutional neural network. Background technique [0002] With the influence of population flow and urbanization worldwide, large-scale crowd gathering has become a common phenomenon. Crowd density automatic estimation and counting technology has received more and more attention in crowd safety control, and plays a vital role in crowd monitoring and management. It can be used to measure crowd comfort and detect potential risks to prevent crowding disasters. In visual surveillance systems, crowd size is one of the important primary indicators for detecting threats such as riots, violent protests, fighting, crowd panic and excitement. [0003] Thanks to the powerful feature learning ability of convolutional neural network, the current crowd counting model based on convolutional neural network has ach...

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 Applications(China)
IPC IPC(8): G06K9/62G06K9/46G06K9/42G06K9/00G06N3/04
CPCG06V40/10G06V20/53G06V10/32G06V10/56G06N3/045G06F18/25G06F18/214
Inventor 张海军董丽
Owner HARBIN INSTITUTE OF TECHNOLOGY SHENZHEN (INSTITUTE OF SCIENCE AND TECHNOLOGY INNOVATION HARBIN INSTITUTE OF TECHNOLOGY SHENZHEN)