CN-121996484-A - Test method, test device, test equipment and storage medium

CN121996484ACN 121996484 ACN121996484 ACN 121996484ACN-121996484-A

Abstract

The application relates to the technical field of virtual reality and discloses a testing method, a testing device, testing equipment and a storage medium, wherein the testing method comprises the steps of controlling a human-simulated eye part to rotate towards a first test point through a motor, and obtaining a first rotating angle of the motor and a first tracking angle obtained by tracking the human-simulated eye part through an eye movement tracking system; the method comprises the steps of controlling the rotation of a human-simulated eye part to face a second test point through a motor, obtaining a second rotation angle of the motor and a second tracking angle obtained by tracking the human-simulated eye part through an eye tracking system, obtaining an eye movement relative angle difference according to a first tracking angle and the second tracking angle, obtaining a motor theoretical relative angle difference according to the first rotation angle and the second rotation angle, testing the eye movement tracking system based on the eye movement relative angle difference and the motor theoretical relative angle difference, and generating a test result. The application can eliminate the accumulated influence of the absolute position error of the motor, thereby improving the accuracy of the test result.

Inventors

Shao Qihang
Matsugawa Takeo
ZHANG SHAOQIAN

Assignees

歌尔科技有限公司

Dates

Publication Date: 20260508
Application Date: 20251229

Claims (10)

1. A test method, characterized in that the method is applied to a test device with a motor and a human eye-like member, the motor being used for driving the human eye-like member to rotate, the test device being connected to a smart glasses provided with an eye movement tracking system, the method comprising: The motor is used for controlling the rotation of the human-simulated eye part to face a first test point, and a first rotation angle of the motor and a first tracking angle obtained by tracking the human-simulated eye part through the eye movement tracking system are obtained; The motor is used for controlling the rotation of the human-simulated eye part to face a second test point, a second rotation angle of the motor and a second tracking angle obtained by tracking the human-simulated eye part through the eye movement tracking system are obtained, and the positions of the first test point and the second test point are different; Obtaining an eye movement relative angle difference according to the first tracking angle and the second tracking angle, and obtaining a motor theoretical relative angle difference according to the first rotation angle and the second rotation angle; And testing the eye movement tracking system based on the eye movement relative angle difference and the motor theoretical relative angle difference, and generating a test result of the eye movement tracking system.
2. The method of claim 1, wherein the first tracking angle comprises a first left eye tracking angle and a first right eye tracking angle, the second tracking angle comprises a second left eye tracking angle and a second right eye tracking angle, and the step of obtaining the eye movement relative angle difference based on the first tracking angle and the second tracking angle comprises: Generating a first fusion tracking angle based on the first left eye tracking angle and the first right eye tracking angle; generating a second fusion tracking angle based on the second left eye tracking angle and the second right eye tracking angle; and obtaining the eye movement relative angle difference according to the first fusion tracking angle and the second fusion tracking angle.
3. The method of claim 2, wherein the step of generating a first fused tracking angle based on the first left eye tracking angle and the first right eye tracking angle comprises: determining a first confidence coefficient corresponding to the first left eye tracking angle and a second confidence coefficient corresponding to the first right eye tracking angle; And fusing the first left eye tracking angle and the first right eye tracking angle based on the first confidence coefficient and the second confidence coefficient to generate a first fused tracking angle.
4. The method of claim 2, wherein the step of generating a second fused tracking angle based on the second left eye tracking angle and the second right eye tracking angle comprises: determining a third confidence coefficient corresponding to the second left eye tracking angle and a fourth confidence coefficient corresponding to the second right eye tracking angle; And fusing the second left eye tracking angle and the second right eye tracking angle based on the third confidence coefficient and the fourth confidence coefficient to generate a second fused tracking angle.
5. The method of any one of claims 1 to 4, wherein the step of testing the eye-tracking system based on the eye-movement relative angle difference and the motor theoretical relative angle difference, generates a test result of the eye-tracking system, comprises: Determining a relative angular error between the first test point and the second test point based on the eye movement relative angular difference and the motor theoretical relative angular difference; And testing the eye tracking system based on the relative angle error and a preset dynamic error threshold value, and generating a test result of the eye tracking system.
6. The method of claim 5, wherein the step of testing the eye-tracking system based on the relative angular error and a preset dynamic error threshold, prior to generating the test result for the eye-tracking system, further comprises: determining an angular velocity between the first test point and the second test point; and determining a preset dynamic error threshold value based on the angular velocity, the basic static threshold value and the velocity sensitivity coefficient.
7. The method of claim 6, wherein the step of determining an angular velocity between the first test point and the second test point comprises: acquiring a first acquisition time of the first test point and a second acquisition time of the second test point; Determining a test time interval between the first test point and the second test point according to the first acquisition time and the second acquisition time; and determining the angular speed between the first test point and the second test point based on the motor theoretical relative angular difference and the test time interval.
8. A test apparatus, the apparatus comprising: the data acquisition module is used for controlling the rotation of the human-simulated eye part to face the first test point through the motor, and acquiring a first rotation angle of the rotation of the motor and a first tracking angle obtained by tracking the human-simulated eye part through the eye movement tracking system; The data acquisition module is used for controlling the rotation of the human-simulated eye part to face a second test point through the motor, acquiring a second rotation angle of the rotation of the motor and a second tracking angle obtained by tracking the human-simulated eye part through the eye movement tracking system, and the positions of the first test point and the second test point are different; The angle difference determining module is used for obtaining an eye movement relative angle difference according to the first tracking angle and the second tracking angle and obtaining a motor theoretical relative angle difference according to the first rotating angle and the second rotating angle; And the testing module is used for testing the eye movement tracking system based on the eye movement relative angle difference and the motor theoretical relative angle difference and generating a testing result of the eye movement tracking system.
9. The test equipment is characterized by comprising a motor and a human-simulated eye part, wherein the motor is used for driving the human-simulated eye part to rotate; The apparatus further comprises a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the test method according to any one of claims 1 to 7.
10. A storage medium, characterized in that the storage medium is a computer-readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the test method according to any one of claims 1 to 7.

Description

Test method, test device, test equipment and storage medium Technical Field The present application relates to the field of virtual reality technologies, and in particular, to a testing method, apparatus, device, and storage medium. Background Eye tracking (EYE TRACKING, ET) technology has been widely used in many fields in recent years, including Virtual Reality (VR), augmented Reality (AR), human-computer interaction, and the like. The eye movement tracking system can provide a natural, efficient and visual interaction mode for a user by monitoring the movement direction and the position change of eyes. In order to ensure the reliability and accuracy of the eye tracking system in practical application, it is important to perform accurate and reliable tests on the eye tracking system. At present, when an eye tracking system is tested, a fixed initial point is usually used as a reference, and external devices such as a motor and the like drive a test target (such as a simulated human eye) to accurately move so as to obtain a theoretical eyeball relative angle, meanwhile, the eye movement relative angle measured by the eye tracking system is recorded, and then the performance of the eye tracking system is evaluated by adopting angle difference calculation. However, the motor inevitably generates minute positional deviations in long-term operation or in complex-track movement, and these deviations are accumulated with the increase in movement distance or with the lapse of time. When the fixed initial point is taken as a reference, the theoretical angle of each subsequent test point actually comprises all accumulated errors generated by moving from the initial point to the point, so that the finally calculated angle difference value is a composite index which is mixed with the measured error of the eye tracking system and the accumulated error of the motor transmission system, the relative angle measuring precision and stability of the eye tracking system cannot be truly reflected, the test result is distorted, and the real performance of the eye tracking system is difficult to accurately evaluate. Disclosure of Invention The application mainly aims to provide a testing method, a testing device, testing equipment and a storage medium, and aims to solve the technical problem that the accuracy of a testing result is low because the conventional testing method of an eye tracking system is easy to introduce the accumulated error of a motor into the testing result of the eye tracking system. To achieve the above object, the present application proposes a testing method applied to a testing apparatus with a motor for driving rotation of a human eye-like member and the human eye-like member, the testing apparatus being connected to smart glasses provided with an eye-movement tracking system, the method comprising: The motor is used for controlling the rotation of the human-simulated eye part to face a first test point, and a first rotation angle of the motor and a first tracking angle obtained by tracking the human-simulated eye part through the eye movement tracking system are obtained; The motor is used for controlling the rotation of the human-simulated eye part to face a second test point, a second rotation angle of the motor and a second tracking angle obtained by tracking the human-simulated eye part through the eye movement tracking system are obtained, and the positions of the first test point and the second test point are different; Obtaining an eye movement relative angle difference according to the first tracking angle and the second tracking angle, and obtaining a motor theoretical relative angle difference according to the first rotation angle and the second rotation angle; And testing the eye movement tracking system based on the eye movement relative angle difference and the motor theoretical relative angle difference, and generating a test result of the eye movement tracking system. In one embodiment, the first tracking angle comprises a first left eye tracking angle and a first right eye tracking angle, the second tracking angle comprises a second left eye tracking angle and a second right eye tracking angle, and the step of obtaining the eye movement relative angle difference according to the first tracking angle and the second tracking angle comprises the following steps: Generating a first fusion tracking angle based on the first left eye tracking angle and the first right eye tracking angle; generating a second fusion tracking angle based on the second left eye tracking angle and the second right eye tracking angle; and obtaining the eye movement relative angle difference according to the first fusion tracking angle and the second fusion tracking angle. In an embodiment, the step of generating a first fusion tracking angle based on the first left eye tracking angle and the first right eye tracking angle comprises: determining a first confidence coefficient corresponding to the first left eye trac