Eyeball recognition degree improving method for driver monitoring system

Abstract

The invention discloses an eyeball recognition degree improving method for a driver monitoring system, and the main design concept of the invention lies in that based on a mature algorithm of visual eyeball tracking, according to the state of a driver wearing sunglasses and preferably in combination with the state of a light source environment, the infrared light intensity for supplementing light to a human face, especially a human eye area is automatically adjusted, and the visual eyeball recognition degree is improved. According to the method and the system, the reliability of the eyeball tracking function in the driver monitoring system is optimized, and the specific problem that the pupil state of a driver cannot be recognized due to wearing of sunglasses is effectively solved.

Description

Technical Field

[0001] The present invention relates to the technical field of driver monitoring systems, and in particular to a method for improving eye recognition for a driver monitoring system. Background Art

[0002] The driver monitoring system can realize functions such as driver fatigue monitoring, driver attention monitoring, dangerous driving behavior monitoring and driver identity recognition, and has different alarm mechanisms designed according to different vehicle models and different levels of autonomous driving. It can improve vehicle driving safety and is an important function of high-level intelligent driving.

[0003] Driver attention monitoring currently has relatively mature recognition algorithms for eyes, mouth, and head posture. The latest research direction is to use human sight for judgment, which has the advantage of being able to effectively recognize and judge the following situations:

[0004] 1. The head turns, but the sight remains on the road ahead;

[0005] 2. The head is in the direction of the driving road, but the line of sight is off track;

[0006] 3. The driver looks at the large screen or other directions to detect and expand the field of vision.

[0007] However, in real application scenarios, the eye tracking algorithm of the driver monitoring system still faces the test of the driver's changing state. For example, the car driver wearing sunglasses will hinder the tracking of the eyes. Such scenarios where eye and line of sight detection cannot be performed will cause this specific function to fail. Summary of the invention

[0008] In view of the above, the present invention aims to provide a method for improving eye recognition of a driver monitoring system to solve the problem of failure of the eye tracking function of the driver monitoring system due to wearing sunglasses.

[0009] The technical solution adopted by the present invention is as follows:

[0010] The present invention provides a method for improving eye recognition of a driver monitoring system, comprising:

[0011] After the eye tracking function takes effect, the driver's face is detected;

[0012] Judging whether the human eye information meeting the established standards is obtained according to the face detection result;

[0013] If the human eye information is not obtained, it is determined whether the driver is wearing sunglasses;

[0014] If it is determined that the person is wearing sunglasses, the infrared fill light is triggered and regulated to the face area;

[0015] During the infrared fill light process, face detection is continued until human eye information that meets the established standards is obtained, and then the existing driver monitoring mode is executed.

[0016] In at least one possible implementation, the method for controlling infrared fill light includes:

[0017] Initially output infrared light of a preset light intensity value;

[0018] Detect whether human eye information that meets established standards can be obtained;

[0019] If it still cannot be obtained, increase the light intensity of the infrared fill light according to the preset gradient and continue to detect human eye information.

[0020] In at least one possible implementation, the method for controlling infrared fill light includes:

[0021] Detecting the wearing state of sunglasses, wherein the wearing state includes: the curvature of the sunglasses;

[0022] If the wearing state of the sunglasses exceeds the limit, the infrared light intensity will be actively adjusted.

[0023] In at least one possible implementation, determining whether the driver is wearing sunglasses includes:

[0024] If the driver's pupils are not recognized, it is determined that the driver is wearing sunglasses.

[0025] In at least one possible implementation manner, determining whether the driver is wearing sunglasses includes: directly identifying whether the driver is wearing sunglasses through a pre-deployed algorithm.

[0026] In at least one possible implementation, the method of triggering infrared fill light to the face area includes:

[0027] Trigger the light sensor inside the camera to obtain the light source environment information around the driver's face;

[0028] According to the light source environment information, the infrared fill light device located in the driver's face area is triggered to output infrared light.

[0029] Compared with the prior art, the main design concept of the present invention is that, based on a mature algorithm of visual eye tracking, the infrared light intensity for fill-in lighting the face, especially the eye area, is automatically adjusted according to the driver's sunglasses-wearing state and preferably in combination with the light source environment state, so as to meet the driver monitoring system's reliable detection of the human eye, thereby improving the feasibility of the eye tracking function. The present invention optimizes the reliability of the eye tracking function in the driver monitoring system, thereby effectively solving the specific problem of being unable to identify the driver's pupil state due to wearing sunglasses. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be further described below with reference to the accompanying drawings, in which:

[0031] Figure 1 A schematic diagram of a method for improving eye recognition in a driver monitoring system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0032] Embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be interpreted as limiting the present invention.

[0033] The present invention proposes an embodiment of a method for improving eye recognition of a driver monitoring system. Specifically, Figure 1 shown, including:

[0034] Step S1: After the eye tracking function takes effect, the driver's face is detected;

[0035] Step S2: judging whether human eye information meeting a predetermined standard is obtained according to the face detection result;

[0036] Step S3: if the human eye information is not obtained, determine whether the driver is wearing sunglasses;

[0037] Step S4: If it is determined that the person is wearing sunglasses, trigger and control the infrared fill light to the face area;

[0038] Step S5: During the infrared fill light process, face detection is continuously performed until eye information that meets the established standards is obtained, and then the existing driver monitoring mode is executed.

[0039] To elaborate, when the eye tracking function of DMS is turned on, the driver monitoring camera in DMS performs facial recognition to determine whether it can obtain human eye information. When the judgment result is not satisfied, the sunglasses wearing status is identified. This process can be located at two levels. First, the driver's pupil is not identified; second, the driver is directly identified as wearing sunglasses through the preset algorithm. The first point does not require additional deployment of a model for distinguishing whether there are sunglasses or not, but the undetected driver's pupil is defaulted to "wearing sunglasses"; the second point has the advantage of using a pre-trained and deployed special model to directly output the conclusion of whether the driver is wearing sunglasses or not.

[0040] Continuing from the previous text, after determining that the driver is wearing sunglasses, the light sensor inside the camera can be triggered to obtain the light source environment information around the driver's face and send it to the driver monitoring system, and the infrared fill light device located in the driver's face area (preferably an infrared fill light configured at the camera or vehicle-mounted camera) is triggered to output infrared light according to the preset light intensity value, and then the actual light intensity emitted by the infrared light is dynamically adjusted according to the detection of the aforementioned facial features (mainly human eye features) (such as increasing the light intensity value of the infrared light output according to the set gradient) until the infrared light can pass through the sunglasses to make the pupil state recognizable, that is, the human eye information is obtained. After successful recognition, the line of sight deviation status is normally monitored according to the existing mode of the driver monitoring system, and an alarm is issued to remind the driver of distraction.

[0041] Finally, it can be added that in addition to the aforementioned closed-loop dimming mode, the state of wearing sunglasses can also be detected, such as detecting the wearing state of sunglasses with too high curvature (above a certain limit value), and actively adjusting the infrared light intensity.

[0042] To sum up, the main design concept of the present invention is to automatically adjust the intensity of infrared light for filling the face, especially the eye area, based on a mature algorithm of visual eye tracking, according to the driver's sunglasses wearing state and preferably in combination with the light source environment state, so as to meet the driver monitoring system's reliable detection of the human eye, thereby improving the feasibility of the eye tracking function. The present invention optimizes the reliability of the eye tracking function in the driver monitoring system, thereby effectively solving the specific problem of being unable to identify the driver's pupil state due to wearing sunglasses.

[0043] If the expressions expressing orientation are mentioned in the embodiments of the present invention, they are relative concepts based on the embodiments. In addition, "at least one" means one or more, and "plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a and b and c, wherein a, b, c can be single or multiple.

[0044] The above describes in detail the structure, features and effects of the present invention based on the embodiments shown in the drawings, but the above is only a preferred embodiment of the present invention. It should be noted that the technical features involved in the above embodiments and their preferred methods can be reasonably combined and matched into a variety of equivalent schemes by those skilled in the art without departing from or changing the design ideas and technical effects of the present invention; therefore, the present invention is not limited to the scope of implementation shown in the drawings, and all changes made in accordance with the concept of the present invention, or modifications to equivalent embodiments with equivalent changes, which still do not exceed the spirit covered by the specification and drawings, should be within the protection scope of the present invention.

Claims

1. A method for improving eye recognition of a driver monitoring system, characterized in that: include: After the eye tracking function takes effect, the driver's face is detected; Judging whether the human eye information meeting the established standards is obtained according to the face detection result; If the human eye information is not obtained, it is determined whether the driver is wearing sunglasses; If it is determined that the person is wearing sunglasses, the infrared fill light is triggered and regulated to the face area; During the infrared fill light process, face detection is continued until human eye information that meets the established standards is obtained, and then the existing driver monitoring mode is executed.

2. The method for improving eye recognition of a driver monitoring system according to claim 1, characterized in that: Methods for controlling infrared fill light include: Initially output infrared light of a preset light intensity value; Detect whether human eye information that meets established standards can be obtained; If it still cannot be obtained, increase the light intensity of the infrared fill light according to the preset gradient and continue to detect human eye information.

3. The method for improving eye recognition of a driver monitoring system according to claim 1, characterized in that: Methods for controlling infrared fill light include: Detecting the wearing state of sunglasses, wherein the wearing state includes: the curvature of the sunglasses; If the wearing state of the sunglasses exceeds the limit, the infrared light intensity will be actively adjusted.

4. The method for improving eye recognition of a driver monitoring system according to claim 1, characterized in that: The determining whether the driver is in the state of wearing sunglasses comprises: If the driver's pupils are not recognized, it is determined that the driver is wearing sunglasses.

5. The method for improving eye recognition of a driver monitoring system according to claim 1, characterized in that: The determining whether the driver is in the state of wearing sunglasses includes: directly identifying whether the driver is wearing sunglasses through a pre-deployed algorithm.

6. The method for improving eye recognition of a driver monitoring system according to any one of claims 1 to 5, characterized in that: Methods for triggering infrared fill light to the face area include: Trigger the light sensor inside the camera to obtain the light source environment information around the driver's face; According to the light source environment information, the infrared fill light device located in the driver's face area is triggered to output infrared light.

Images