Model construction method, crowd density estimation method, device, equipment and medium
A technology of crowd density and construction method, applied in the field of computer vision, can solve the problems of large labor consumption and low accuracy in estimating crowd density, and achieve the effect of saving manpower and material resources and improving accuracy.
Active Publication Date: 2022-08-02
PCI TECH GRP CO LTD
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] This application provides a method for constructing a network model, a method for estimating crowd density, a device, a device, and a storage medium, so as to solve the problems of large manpower and low accuracy in estimating crowd density in the prior art
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0048]In order to make the objectives, technical solutions and advantages of the present application clearer, the specific embodiments of the present application will be further described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application. In addition, it should be noted that, for the convenience of description, the drawings only show some but not all of the contents related to the present application. Before discussing the exemplary embodiments in greater detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart depicts various operations (or steps) as a sequential process, many of the operations may be performed in parallel, concurrently, or concurrently. Additionally, the order of operations can be rearranged. The pr...
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
Login to View More Abstract
The embodiments of the present application disclose a method for constructing a network model, a method for estimating crowd density, an apparatus, a device and a storage medium. The labeled training samples are used for training to obtain a preset number of regressors; the training samples are respectively input into each regressor to obtain the corresponding crowd density map; determine the error between each crowd density map and the true density map corresponding to the training sample, and select the number of the regressor corresponding to the crowd density map with the smallest error as the classification number of the training sample; The classification number of the training samples and the training samples are used to fine-tune the initial classifier to obtain a classifier, and the regressor is fine-tuned by applying the training samples classified by the classifier until the preset training conditions are met, and the latest classifier and regressor are used as the target. Classifier and target regressor. The accuracy of crowd density estimation is improved, and manpower and material resources are saved.
Description
technical field [0001] The embodiments of the present application relate to computer vision technologies, and in particular, to a method for constructing a network model, a method for estimating crowd density, an apparatus, a device, and a storage medium. Background technique [0002] With the advancement of science and technology and the improvement of people's living standards, people's social activities are gradually increasing, traffic hubs, large-scale event sites and large-scale public places are increasingly crowded with people, and the safety hazards caused by people's congestion are becoming more and more serious. Therefore, how to estimate the number of people automatically and in real time has important research value, and it also has in-depth guiding significance for public affairs personnel to provide effective event decision-making. [0003] In the prior art, a series of targeted features are usually designed for images, such as LBP (Local Binary Pattern), Gabo...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06V20/50G06V10/82G06V10/764G06K9/62G06N3/04G06N3/08
CPCG06V20/53G06F18/24G06F18/214
Inventor 李德紘李昆明冯琰一赵刚
Owner PCI TECH GRP CO LTD