Attention detection method and system for personnel work images based on deep learning

Abstract

The present invention is based on the attention detection method of the personnel working image of deep learning, comprises the following steps: obtain the working image of the staff; Euler angle; 2) Utilize the key points of the human eyes in the key points of the human face obtained to obtain the rectangular frame where the eyes are located, and obtain the open and closed state of the eyes; 3) use the rectangular frame where the human face is located and the rectangular frame where the eyes are located Box, to obtain the gaze direction of both eyes; based on the above-acquired head posture angle, the gaze direction of both eyes, and the state of eye opening and closing, the staff's attention is monitored, recorded and triggered to be reminded. The invention also discloses its system. The invention has the advantages of being able to monitor the working state of personnel in real time and has high reliability, and is especially suitable for monitoring the working state of X-ray machine security inspectors and monitoring the working state of security guards in monitoring rooms.

Description

technical field [0001] The invention relates to the technical field of staff attention monitoring, in particular to a deep learning-based attention detection method and system technology for staff work images. Background technique [0002] The working status of staff, such as X-ray machine security inspectors and monitoring room security guards, directly affects the work results, especially their attention at work. Now due to the popularity of mobile phones, I often play with mobile phones at work. Although some offices are equipped with surveillance cameras, the images captured by the surveillance cameras cannot convey the attention of the staff. Therefore, the monitoring of the working status of the staff has become a kind of management. tool. The images obtained by the existing surveillance cameras are not analyzed, but are often analyzed manually and then reminded, which is often difficult to meet the needs, and it makes the management staff tired, and also causes incoo...

AI Technical Summary

Problems solved by technology

Now due to the popularity of mobile phones, I often play with mobile phones at work. Although some offices are equipped with surveillance cameras, the images captured by the surveillance cameras cannot convey the attention of the staff. Therefore, the monitoring of the working status of the staff has become a kind of management. tool

The images obtained by the existing surveillance cameras are not analyzed, but are often analyzed manually and then reminded, which is often difficult to meet the needs, and it makes the management staff tired, and also causes incoordination of interpersonal relationships, making it difficult to achieve management effects

Images