Multi-scene crowd density estimation method based on convolution network and multi-task learning

Abstract

The invention discloses a multi-scene crowd density estimation system and method based on convolution network and multi-task learning. Including crowd density map generation module, cross-camera multi-scene learning module, each scene density map calibration module. The first part of the framework is a robust density map generation module based on convolution neural network, The convolution neuralnetwork is composed of three deep fusion subnetworks, Each deep fusion sub-network has three convolution cores with different size and number, so it can effectively grasp the commonness of density estimation problem, and estimate the density map of multi-scene surveillance video frames with different background, illumination and crowd density in practical application. The second part of the framework is the data distribution learning based on multi-task learning, and learns the different characteristics of the crowd distribution in each scene. In the third part of the framework, the results of general crowd density estimation in the first part are calibrated and fine-tuned by using the characteristics of crowd distribution in each scene learned by multi-task learning. This system can estimate the crowd density of multi-scene and multi-camera with high efficiency and accuracy under the real surveillance scene.

Description

technical field [0001] The invention relates to a computer vision and intelligent monitoring technology, in particular to a multi-scene crowd density estimation system based on convolutional network and multi-task learning. Background technique [0002] In recent years, the phenomenon of high-density crowd gathering in cities has become more and more frequent, and stampede incidents have occurred from time to time, which seriously threatens urban public safety. Therefore, the technology of crowd control and early warning in public places has increasingly become the focus of research in the field of intelligent monitoring and urban security. Crowd density estimation technology refers to the estimation of crowd density through computer vision technology, so as to provide early warning and evacuation of high-density crowds, and has become an important technology in crowd control. [0003] There are currently solutions based on unsupervised learning methods for people counting t...

AI Technical Summary

Problems solved by technology

This method is more accurate, but the disadvantage is that it is necessary to ensure that the data of the training set and the test set are in the same distribution

However, in actual application scenarios, due to the different backgrounds of the cameras at each location, the concentrated distribution area of ​​the crowd and the density of the crowd will be quite different. Therefore, whenever a camera needs to be deployed in a scene corresponding to it, it is often necessary to collect and mark a large number of this camera. Retraining the density map regression network on the crowd images corresponding to the scene, or using the model fine-tuning method to migrate, these two mechanisms need to pay additional data collection labeling and model training costs for the deployment scene, in the actual deployment and application of a large number of cameras The cost of data labeling and model training in the process is extremely high

Images