Crowd counting method based on generative adversarial network

Abstract

The invention provides a crowd counting method based on a generative adversarial network. The method comprises the steps of constructing the generative adversarial network, wherein the generative adversarial network comprises a generator and a discriminator, the generator is used for generating a corresponding crowd density image according to an input crowd image, and the discriminator is used fordiscriminating the authenticity of the crowd density image generated by the generator in a training stage of the generative adversarial network; performing cross-scale consistency training on the generative adversarial network to obtain a trained generative adversarial network; and taking a to-be-counted crowd image as an input of the trained generative adversarial network, obtaining the target crowd density image, and counting the number of people in the target crowd density image. The method is effective for counting the number of people in a monitored scene, and has good robustness for complex and changeable backgrounds and high-density crowds.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a crowd counting method based on a generative confrontation network. Background technique [0002] With the development of science and technology, finance and culture, the content and scope of human activities are also constantly expanding, showing a trend of a large number of people and a high degree of density. As the main body of human activities, crowds exist in a form different from individuals, and the interaction between people creates more unknowns. Therefore, there have been a large number of safety accidents related to crowd activities. Traditional accidents Prevention methods have been unable to meet human needs. With the development of technology and the improvement of hardware level, video surveillance has gradually entered the human line of sight in the field of security. People hope to use video surveillance to improve the ability to prevent accidents in ...

AI Technical Summary

Problems solved by technology

The network of this algorithm is relatively shallow, which makes it difficult to distinguish the background and foreground (crowd), and the pooling layer in the network makes the size of the final crowd density image smaller and blurred than the original image.

Images