Method utilizing multi-scale multi-task convolutional neural network for population counting of stationary images

Abstract

The invention discloses a method utilizing the multi-scale multi-task convolutional neural network for population counting of stationary images. According to the method, firstly, an inverse Gaussian density map is combined with an original Gaussian density map to form a combined density map; secondly, non-overlapping sampling of an input image is carried out to acquire several image sub-blocks, and the network is trained based on the image sub-blocks and corresponding true combined density maps thereof; overlapping sampling of the input image is carried out in the same pace, combined density maps of each image sub-block predicted by the MMCNN are superposed to reconstruct the combined density map of a complete crowd image, and population counting is realized. For the problem of populationscale difference, learning characteristics of different scale networks are measured through a fractional loss function, moreover, the population combined density map, the density level and foreground / background classification are simultaneously predicted in a multi-task mode, estimation accuracy of the combined density map is improved, and thereby an uneven population density problem is ameliorated.

Description

technical field [0001] The invention belongs to the field of intelligent monitoring, in particular to a method for counting crowds of static images by using a multi-scale and multi-task convolutional neural network. Background technique [0002] As an important part of intelligent video surveillance, crowd counting in public places has many applications, including crowd control, abnormal behavior detection, and pedestrian behavior analysis. Crowd counting can be used to detect potential risks and prevent overcrowding at religious or sporting events. Meanwhile, crowd counting can be extended to other fields, such as counting cells or bacteria from microscopic images. [0003] Existing crowd counting methods are generally divided into three categories, namely, counting by detection, counting by clustering, and counting by regression. Through the detection and counting method, crowd counting is realized according to the number of people in the detection scene. However, the d...

AI Technical Summary

Problems solved by technology

However, crowd counting based on deep learning still has challenges such as uneven crowd distribution and different scales

Images