Multidirectional moving population flow estimation method on basis of generalized regression neural network

Abstract

The invention relates to a multidirectional moving population flow estimation method on the basis of a generalized regression neural network. A method on the basis of linear regression is difficult to respond to the complex conditions of serious shielding between pedestrians and poor population dividing quality. The multidirectional moving population flow estimation method comprises the following steps of: firstly, extracting dynamic textural features of a moving population by an optical flow field; then implementing division of the population according to the moving directions by the dynamic textural features and a level set algorithm to obtain ROIs (Region of Interest) representing different moving directions; and implementing regression analysis between ROI features and the population flow by utilizing the GRNN (Generalized Regression Neural Network) so as to acquire an accurate and real-time flow statistical result of the population with different moving directions in a scene. According to the multidirectional moving population flow estimation method provided by the invention, not only can the complex process of extracting and tracking personal features of the pedestrians be avoided and the capability of resisting the shielding between the pedestrians of the algorithm is greatly promoted, but also the integrity and difference of the pedestrian movement can be considered, so that the division of the population according to the moving directions is implemented.

Description

technical field [0001] The invention belongs to the technical field of image processing and pattern recognition, and in particular relates to a method for estimating the flow of multi-directional sports crowds based on a generalized regression neural network. Background technique [0002] With the rapid development of the economy and the continuous increase of people's social activities, the importance of crowd flow information is increasingly reflected. It is not only closely related to the economic interests of public consumption places such as large shopping malls and supermarkets, but also is an important factor for exhibition halls, stadiums, subways, It is an important basis for rational planning and layout of public places such as buses, prevention of emergencies, and elimination of major safety hazards. Traditional crowd flow counting methods include manual method, infrared method, and pressure pedal method, etc., which have high order requirements for crowd movement...

AI Technical Summary

Problems solved by technology

The main defect of this type of method is that the statistical model used (such as Gaussian background model) usually only focuses on the statistical difference between the moving crowd and the background, without considering the differences in motion characteristics between pedestrians within the crowd, so it is impossible to realize the Segmentation according to the direction of movement. At the same time, the regression model between the ROI (Region of Interest) feature established by the linear regression method and the crowd flow is too simple, making it difficult for the linear regression-based method to deal with severe occlusion between pedestrians and the quality of crowd segmentation. Complications when poor

Images