Crowd density analysis method and system based on two-path cooperation
By employing a dual-path collaborative crowd density analysis method and optimizing the loss function of generative adversarial networks, the problems of lighting and dense scenes in crowd density estimation are solved, achieving efficient and accurate crowd density estimation.
CN114581839BActive Publication Date: 2026-05-01ABD SMART EYE ELECTRONICS CO LTD
1 Cites 0 Cited by
Patent Information
- Application Number
- CN202111632022.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-12-29
- Publication Date
- 2026-05-01
- Estimated Expiration
- 2041-12-29
AI Technical Summary
Technical Problem
Existing technologies for crowd density estimation are greatly affected by lighting, occlusion, and dense crowd scenes, and cannot effectively utilize spatial and density information, resulting in high computational resource consumption and long computation time.
Method used
A crowd density analysis method based on dual-path collaboration is constructed. By optimizing the loss function of the first and second generative adversarial networks, multi-scale feature representation and consistency constraints are introduced to optimize the crowd density estimation model.
Benefits of technology
It improves the accuracy of population density estimation, reduces computation time and resource consumption, and achieves rapid analysis speed.
✦ Generated by Eureka AI based on patent content.
Abstract
This invention provides a crowd density analysis method based on dual-path collaboration, comprising: constructing an analysis model, the analysis model including a first generative model, the first generative model taking an image as input and outputting a crowd density map of the image; training the analysis model, comprising: constructing a training set; constructing a first generative adversarial network (GAN) using the first generative model and a first discriminant model, and inputting the training images from the training set into the first GAN; constructing a second GAN using a second generative model and a second discriminant model, randomly segmenting the training image into multiple sub-training images, and inputting these sub-images into the second GAN; optimizing the first generative model using the loss functions of the first and second GANs; and inputting the original image into the trained analysis model to obtain the crowd density map of the original image. This invention also provides a system. This invention uses only the first generative model when analyzing the original image, reducing model overhead and complexity.
Need to check novelty before this filing date? Find Prior Art