Crowd counting and future pedestrian volume prediction method based on video images

Abstract

The invention discloses a crowd counting and future pedestrian volume prediction method based on video images. The method comprises the steps: 1, selecting a video image data set with annotation information, conducting Gaussian function processing according to annotation of a head position, and generating a true value density map; 2, inputting a video frame into a built MPDC model to extract a feature map, and mapping the feature map into a crowd estimation density map (DE); and 3, inputting obtained DE stacking frames into a constructed Bi-ConvLSTM network, predicting a crowd prediction density map at a T+1 moment, and estimating the number of pedestrians at the T+1 moment. According to the method, a convolutional network based on a multi-scale pyramid cavity and a Bi-ConvLSTM network based on residual connection are adopted, a crowd estimation density map is generated by using continuous video frames, a crowd prediction density map of a future frame is further predicted, and the number of crowds is counted. The method aims at the prediction of continuous video images, is a brand-new method, can obtain a real-time crowd density map and the number of people, and also can predict the crowd density map and the pedestrian volume of a future frame.

Description

technical field [0001] The invention belongs to the field of crowd image processing in computer vision, and more specifically relates to a method for counting crowds and predicting future flow of people based on video images. Background technique [0002] Crowd counting is to count the number of people in pictures or video sequences. Crowd counting and prediction are of great significance to public security management, regional spatial planning, and information resource acquisition. It can better monitor and guide the crowd in public places, and provide a basis for reasonable scheduling of personnel, reasonable planning of routes, reasonable guidance of people flow, and site selection of buildings. [0003] Existing crowd counting methods can be divided into three categories: detection, regression, and density map estimation based crowd counting methods. Detection-based methods are suitable for larger and sparser object scenes. However, the method of regressing the number...

AI Technical Summary

Problems solved by technology

[0005] However, in complex backgrounds and scenes where high-density crowds gather, due to the influence of interference factors such as target occlusion caused by high overlap between people, perspective perspective, scale change, and uneven density distribution, the counting of crowds and the impact of density information There is great resistance to obtaining

However, the existing methods for generating density maps based on deep learning usually use multi-column convolution layers and large convolution kernels for feature extraction of multi-scale images, thus generating a large number of parameters and increasing the difficulty of network training.

In addition, there is no research on crowd flow prediction algorithm based on crowd video images.

Images