A multi-scale dense crowd counting method

Abstract

The invention discloses a multi-scale dense crowd counting method, and belongs to the field of aviation monitoring. Firstly, collecting data of a dense scene, marking and preprocessing crowd images toserve as training pictures, and then sequentially subjecting the training pictures to convolution operation and a multi-level pooling module to obtain feature maps corresponding to the pictures and fusing with multi-scale information, and using a convolutional layer with a convolution kernel of 1 * 1 step length of 1 to respectively perform positioning information enhancement on each feature mapto obtain the corresponding feature map with enhanced positioning information, and repeatedly using the convolution operation and the multi-level pooling module to fuse each positioning information enhanced feature map, re-positioning the information enhancement to obtain a final feature map, decoding, and gradually recovering the spatial resolution by using a bilinear interpolation method to obtain respective final crowd density map, and carrying out integral summation by using the pixel value in each crowd density map to obtain the final number of people. According to the invention, the counting precision is improved, and a better cognitive ability is provided for a monitoring scene.

Description

technical field [0001] The invention belongs to the field of aerial surveillance, in particular to a multi-scale dense crowd counting method. Background technique [0002] With the exponential growth of the world's population and the resulting urbanization, crowds have gathered more frequently in recent years. In this case, in order to better manage the population and ensure the safety of the population, it is necessary to analyze crowd behavior. Dense crowd counting refers to the calculation of the number of people in crowded scenes, which is to map an input crowd image to the corresponding density map, which is crucial for building higher-level cognitive abilities in crowded scenes. [0003] However, due to the high crowd density in dense crowd scenes, it causes severe occlusion and inconsistent target scales. Manual dense crowd counting methods are time-consuming and labor-intensive. Therefore, it has been proposed to realize space-based autonomous surveillance through ...

AI Technical Summary

Problems solved by technology

[0005] Due to the different shooting angles and flight heights of drones, the collected picture data of dense crowds has multi-scale and multi-view problems, making it difficult to count

Images