CNN-based multi-sensor building elevator user identity verification system

Abstract

The invention discloses a CNN-based multi-sensor building elevator user identity verification system, which comprises a real-time acquisition unit for acquiring multi-angle real-time image data of passengers in an elevator car, a data processing center which is used for carrying out technical analysis according to the passenger information transmitted by the real-time acquisition unit, respectively obtaining images and infrared information of multi-angle passengers containing passenger face information, forming a training set and a test set by the data information, and carrying out network training to obtain a proper weight of the CNN network, a real-time processing unit which is used for receiving and processing elevator passenger information in real time according to the trained CNN network and giving out a user identity recognition result so as to accurately verify the current passenger identity, and a real-time analysis unit which is used for judging the identity of the passenger according to the image information of the passenger, recording the information of the registered user if the passenger belongs to the registered user, and suggesting to pay attention to the external non-registered user if the user is judged to be the non-registered user.

Description

technical field [0001] The invention belongs to the technical field of deep learning, and in particular relates to a multi-sensor building elevator user identity verification system based on CNN. Background technique [0002] Elevators are currently an important means of building transportation. For safety reasons, it is very important to quickly verify the identity of elevator passengers. Most of the existing identification methods for elevator personnel only use a single camera to collect a single facial data for identification. If 3D printing is performed for Face ID or silicone headgear is used for unusual situations, effective identification cannot be carried out. Contents of the invention [0003] In view of the technical problems above, the present invention provides a multi-sensor building elevator user identity verification system based on CNN. [0004] In order to solve the problems of the technologies described above, the present invention adopts the following ...

AI Technical Summary

Problems solved by technology

Most of the existing elevator personnel identification methods only use a single camera to collect a single face data for identification. If Face ID is 3D printed or used in unusual situations such as silicone headgear, effective identification cannot be carried out

Images