Crowd counting method, network, system and electronic device

Abstract

The embodiment of the invention provides a crowd counting method, a network, a system and an electronic device. The method comprises the steps of obtaining a to-be-detected image; inputting the to-be-detected image into a neural network, and carrying out feature extraction; and processing the features extracted by the neural network, and counting the number of people. By utilizing the method disclosed by the invention, a high-quality crowd density map can be outputted in the crowd counting problem, and meanwhile, the high-accuracy crowd counting estimation can be obtained.

Description

technical field [0001] The present application relates to the field of image processing, in particular to a crowd counting method, network, system and electronic equipment. Background technique [0002] At present, crowd counting technology has been widely used in many fields such as video surveillance, public safety, traffic flow control, etc., so it has received more and more attention. However, the main difficulty of crowd counting lies in the large difference in the size of the head in the image, the serious occlusion of the human body, the perspective deformation of the camera, the diverse distribution of the crowd, and the environmental background noise. This all makes the task of accurate crowd counting extremely challenging. [0003] Existing crowd counting techniques roughly include two categories, traditional feature-based methods and deep neural network-based methods. The traditional feature method mainly extracts artificially designed description features from ...

AI Technical Summary

Problems solved by technology

However, the problem with this method is that the convolution kernel sizes of different branches need to be manually set, relying on practical experience

At the same time, the

Images