Online visual fatigue detection system and method based on deep learning

Abstract

The invention discloses an online visual fatigue detection system based on deep learning, which mainly solves the problems of single operator information acquisition, poor system operation real-time performance and low fatigue detection accuracy in the prior art. The system comprises a data acquisition module, an image data processing module and a fatigue detection module; the data acquisition module is arranged under a computer display and is used for acquiring eye movement data, RGB images and depth information; the image data processing module is used for detecting face positions and face feature points in the image data and extracting depth information of the feature points; and the fatigue detection module is used for performing feature extraction, feature fusion and classification on the eye movement data, the face feature point data and the depth data, and outputting the fatigue degree of the operator. According to the invention, a non-contact method is used, the influence on the working state of an operator is reduced, the design of manual features is avoided, and the accuracy of visual fatigue detection is improved. The invention can be used for detecting the visual fatigue level of an operator online in real time.

Description

technical field [0001] The invention belongs to the technical field of computer vision and video analysis, and further relates to an online visual fatigue detection system and method, which can be used for online real-time detection of visual fatigue levels of operators. Background technique [0002] With the continuous progress of social development, the use of computers has involved all walks of life, and more and more jobs require practitioners to be proficient in computer-related skills and require operators to use computers for a long time. This type of work requires less physical labor, and the work content is relatively monotonous and repetitive, which can easily cause visual fatigue of the operator, resulting in a decline in the operator's working ability and greatly reducing its work efficiency. Moreover, when the human body continues to experience visual fatigue, it is easy to cause the operator to have symptoms such as inattention, dry eyes, astringent eyes, and d...

AI Technical Summary

Problems solved by technology

The disadvantage of this method is: due to the manual design of related features and thresholds, the quality of the features and the size of the threshold will directly affect the final fatigue detection results

There are two deficiencies in this system: first, because the device only has video data input, the data type is single, and other effective information is lacking, so the result of judging the fatigue state is inaccurate and is easily affected by light factors; second, the The device only inputs image data in 2D space and lacks depth information, so it cannot represent face pose information

The disadvantage of this system in the detection process is that it cannot fully detect the fatigue state of the operator because only the video stream information is collected and the information is of a single type.

Because this method directly operates on sequence images, it will result in a large amount of network parameters, a lot of redundant information, and poor real-time performance. If real-time performance is to be satisfied, the requirements for hardware equipment are high.

Images