A public place safety early warning system and method

Abstract

The invention provides a system and a method for early warning safety in a public place. The system includes a hyperspectral camera, a first set of imaging devices, and a data processor. Using the hyperspectral camera to scan the crowd in public places, the hyperspectral images including the position information and the spectral information can be acquired. By processing the hyperspectral images,we can get more obvious outline and posture information, that is, posture parameters. The first imaging device group extracts the position parameters according to the posture parameters obtained by the hyperspectral camera, and then photographs the crowd. According to the 3D reconstruction algorithm of multi-view scene, the moving parameters of pedestrians and the relative parameters between pedestrians can be obtained. Finally, the data processor is combined with artificial intelligence or machine learning algorithm to evaluate the pose parameters, movement parameters and relative parametersbetween pedestrians. As that embodiment of the present application are implemented, an early war signal can be sent out in time when a dangerous situation occurs, and the safety of people's personal property in a public place can be ensured.

Description

technical field [0001] The application belongs to the security field, and specifically relates to a public place safety early warning system and method. Background technique [0002] With the development of science and technology, public place safety early warning technology integrates cutting-edge artificial intelligence technologies such as machine vision, image processing and deep learning. At present, many companies are developing early warning systems based on videos captured by ordinary cameras. [0003] However, this early warning system can only be applied in a limited environment, because in the real environment, factors such as complex backgrounds, insufficient lighting, and diversity of viewing angles in different scenes affect the imaging effect of the camera, reducing the sensitivity and effectiveness of the early warning system. accuracy. Therefore, the sensitivity and accuracy of the above-mentioned security warning system need to be improved. Contents of t...

AI Technical Summary

Problems solved by technology

[0003] However, this early warning system can only be applied in a limited environment, because in the real environment, factors such as complex backgrounds, insufficient lighting, and diversity of viewing angles in different scenes affect the imaging effect of the camera, reducing the sensitivity and effectiveness of the early warning system. accuracy

Therefore, the sensitivity and accuracy of the above-mentioned security warning system need to be improved

Images