CN108354611B - Blink action detection method and device, readable storage medium and electronic equipment - Google Patents
Blink action detection method and device, readable storage medium and electronic equipment Download PDFInfo
- Publication number
- CN108354611B CN108354611B CN201711375988.XA CN201711375988A CN108354611B CN 108354611 B CN108354611 B CN 108354611B CN 201711375988 A CN201711375988 A CN 201711375988A CN 108354611 B CN108354611 B CN 108354611B
- Authority
- CN
- China
- Prior art keywords
- detection chip
- body motion
- motion detection
- blink
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1103—Detecting eye twinkling
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Public Health (AREA)
- Molecular Biology (AREA)
- Veterinary Medicine (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Animal Behavior & Ethology (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Physiology (AREA)
- Surgery (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Psychiatry (AREA)
- Ophthalmology & Optometry (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The disclosure relates to a blink action detection method, a blink action detection device, a readable storage medium and an electronic device, wherein the method comprises the following steps: simultaneously sampling signals output by a plurality of body movement detection chips for detecting blinking movement; when the voltage value of a sampling point of any body motion detection chip is larger than a first threshold value, determining actual values of various blink characteristic parameters corresponding to each body motion detection chip according to sampling point data of each body motion detection chip within a preset time length from the corresponding moment of the sampling point; aiming at each body motion detection chip, matching the actual value of the target blink characteristic parameter group corresponding to the body motion detection chip with the ideal value of the group of target blink characteristic parameters corresponding to the body motion detection chip; and when the ratio of the number of the successfully matched body motion detection chips to the total number of the body motion detection chips is larger than or equal to a second threshold value, determining that the blinking motion of the examinee occurs. Therefore, the real-time performance and the accuracy of the detection process can be ensured, and the applicability is wider.
Description
Technical Field
The disclosure relates to the field of eye blink detection, in particular to a blink motion detection method and device, a readable storage medium and electronic equipment.
Background
The body movement detecting chip integrates a whole set of circuits with electromagnetic wave transmitting and receiving functions into one chip for detecting the movement of a human body, and has the advantages of small volume, low power consumption and convenient use. The basic principle is to emit electromagnetic waves to the outside, detect the reflected electromagnetic waves and output the detection result in a voltage mode. When the body movement detection chip works, the electromagnetic wave transmitting and receiving are a continuous process, and the output voltage is a continuously changing process. When the human body action is not detected, the output voltage is stabilized in a numerical range with extremely tiny change; when human body action is detected, the output voltage fluctuates, the amplitude of the fluctuation corresponds to the amplitude of the detected human body action, and the frequency of the fluctuation corresponds to the frequency of the human body action. The detection result output by the body movement detection chip is a path of analog signal with continuously changed voltage, and the analog signal is output to the outside in a chip pin mode.
The blinking motion is closely related to the physical state of the user, so that the blinking motion of the user can be monitored in real time, and the physical state of the user can be monitored. For example, it may be determined whether the user is in a tired state according to the result of the blink action detection. In the prior art, the method for identifying and detecting eye blinking according to the voltage signal output by the single body movement detection chip can determine that the eye blinking movement of the examinee occurs after the examinee blinks, so that the blinking judgment is delayed, and the accuracy is low. Meanwhile, when the method is executed, the voltage signal output by the body motion detection chip needs to be processed ceaselessly and the large amount of sampling point data needs to be stored. Therefore, the requirements on the memory and the performance of the hardware are higher in the implementation process of the method, so that the overall cost of the product is increased. In addition, the processing operation of long-term heavy-load calculation and storage has large loss on hardware, so that the failure rate of the product is increased, and the service life of the product is greatly reduced.
Disclosure of Invention
An object of the present disclosure is to provide a blink action detection method, apparatus, readable storage medium, and electronic device that can quickly and accurately determine whether a subject has a blink action.
In order to achieve the above object, according to a first aspect of the present disclosure, there is provided a blink action detection method including:
simultaneously sampling signals output by a plurality of body movement detection chips for detecting blinking movement;
when the voltage value of a sampling point of any body motion detection chip is larger than a first threshold value, determining actual values of various blink characteristic parameters corresponding to each body motion detection chip according to sampling point data of each body motion detection chip within a preset time length from the corresponding moment of the sampling point;
for each body motion detection chip, matching an actual value of a target blink characteristic parameter set corresponding to the body motion detection chip with an ideal value of the target blink characteristic parameter set corresponding to the body motion detection chip, wherein the target blink characteristic parameter set comprises at least one of the blink characteristic parameters;
and when the ratio of the number of the successfully matched body motion detection chips to the total number of the body motion detection chips is larger than or equal to a second threshold value, determining that the blinking motion of the examinee occurs.
Optionally, before the step of matching, for each body motion detection chip, an actual value of the set of target blink feature parameters corresponding to the body motion detection chip with an ideal value of the set of target blink feature parameters corresponding to the body motion detection chip, the method further includes:
and screening the plurality of blink characteristic parameters according to the actual values of the plurality of blink characteristic parameters corresponding to each body motion detection chip and the ideal values of the plurality of blink characteristic parameters corresponding to each body motion detection chip to obtain the target blink characteristic parameter group corresponding to each body motion detection chip.
Optionally, the screening the plurality of blink feature parameters according to the actual values of the plurality of blink feature parameters corresponding to each body movement detection chip and the ideal values of the plurality of blink feature parameters corresponding to each body movement detection chip includes:
aiming at each blink characteristic parameter, calculating a first average value of the blink characteristic parameter according to the actual value of the blink characteristic parameter corresponding to the plurality of body motion detection chips, and calculating a second average value of the blink characteristic parameter according to the ideal value of the blink characteristic parameter corresponding to the plurality of body motion detection chips;
and if the absolute value of the difference value between the first average value and the second average value is less than or equal to a third threshold value corresponding to the blink characteristic parameter, determining the blink characteristic parameter as a target blink characteristic parameter.
Optionally, the matching, for each body motion detection chip, an actual value of the set of target blink feature parameters corresponding to the body motion detection chip with an ideal value of the set of target blink feature parameters corresponding to the body motion detection chip includes:
matching the actual value of the target blink characteristic parameter group corresponding to the body motion detection chip with the ideal value of the set of target blink characteristic parameters corresponding to the body motion detection chip by the following formula:
wherein G isiThe matching degree of the actual value of the target blink characteristic parameter group corresponding to the ith individual movement detection chip and the ideal value of the group of target blink characteristic parameters corresponding to the individual movement detection chip is represented;
fi(t) a vector formed by ideal values of various target blink characteristic parameters in a target blink characteristic parameter group corresponding to the ith individual movement detection chip is represented;
Fi(t) a vector formed by actual values of various target blink characteristic parameters in a target blink characteristic parameter group corresponding to the ith individual movement detection chip is represented;
Cov(fi(t),Fi(t)) represents fi(t) and Fi(t) covariance;
at the matching degree GiWhen greater than the fourth threshold, determining theThe ith motion detection chip is successfully matched.
Optionally, the fourth threshold is obtained by:
sampling signals output by a plurality of body movement detection chips for detecting blinking movement in advance simultaneously;
determining experimental values of various blink characteristic parameters corresponding to each body motion detection chip according to sampling point data of each body motion detection chip in a period of time;
for each body motion detection chip, calculating a third average value corresponding to each body motion detection chip according to the experimental values of the plurality of blink characteristic parameters corresponding to the body motion detection chip and the ideal values of the plurality of blink characteristic parameters through the following formula:
wherein M isiRepresenting a third average value corresponding to the ith individual dynamic detection chip;
p represents the number of types of the blink characteristic parameter;
fi(tj) Representing an ideal value of the jth blink characteristic parameter corresponding to the ith individual movement detection chip;
gi(tj) The experimental value of the jth blink characteristic parameter corresponding to the ith individual movement detection chip is represented;
H＝max[Mi]and H denotes the fourth threshold value.
Optionally, the method further comprises:
when the blinking motion of the examinee is determined, determining the blinking ending time corresponding to each body motion detection chip; and under the condition that the blink ending time corresponding to each body motion detection chip is obtained, returning to the step of determining the actual values of the various blink characteristic parameters corresponding to each body motion detection chip according to the sampling point data of each body motion detection chip in the preset time length from the time corresponding to the sampling point when the voltage value of the sampling point of any body motion detection chip is larger than the first threshold value.
According to a second aspect of the present disclosure, there is provided a blink action detection device, the device comprising:
the sampling module is used for simultaneously sampling signals output by a plurality of body motion detection chips for detecting blinking motions;
the first determination module is used for determining actual values of various blink characteristic parameters corresponding to each body movement detection chip according to sampling point data of each body movement detection chip within a preset time length from the corresponding time of the sampling point when the voltage value of the sampling point of any body movement detection chip is larger than a first threshold value;
a matching module, configured to match, for each body motion detection chip, an actual value of a set of target blink feature parameters corresponding to the body motion detection chip with an ideal value of the set of target blink feature parameters corresponding to the body motion detection chip, where the set of target blink feature parameters includes at least one of the plurality of blink feature parameters;
and the second determination module is used for determining that the eye blinking action of the examinee occurs when the ratio of the number of the successfully matched body movement detection chips to the total number of the body movement detection chips is larger than or equal to a second threshold value.
Optionally, the apparatus further comprises:
and the screening module is used for screening the plurality of blink characteristic parameters according to the actual values of the plurality of blink characteristic parameters corresponding to each body motion detection chip and the ideal values of the plurality of blink characteristic parameters corresponding to each body motion detection chip before the matching module matches the actual values of the target blink characteristic parameter set corresponding to the body motion detection chip with the ideal values of the target blink characteristic parameters corresponding to the body motion detection chip, so as to obtain the target blink characteristic parameter set corresponding to each body motion detection chip.
Optionally, the screening module comprises:
the calculating submodule is used for calculating a first average value of each blink characteristic parameter according to the actual value of the blink characteristic parameter corresponding to the plurality of body motion detection chips and calculating a second average value of the blink characteristic parameter according to the ideal value of the blink characteristic parameter corresponding to the plurality of body motion detection chips;
and the first determining submodule is used for determining the blink characteristic parameter as the target blink characteristic parameter if the absolute value of the difference value of the first average value and the second average value is less than or equal to a third threshold value corresponding to the blink characteristic parameter.
Optionally, the matching module comprises:
the matching submodule is used for matching the actual value of the target blink characteristic parameter group corresponding to the body motion detection chip with the ideal value of the group of target blink characteristic parameters corresponding to the body motion detection chip through the following formula:
wherein G isiThe matching degree of the actual value of the target blink characteristic parameter group corresponding to the ith individual movement detection chip and the ideal value of the group of target blink characteristic parameters corresponding to the individual movement detection chip is represented;
fi(t) a vector formed by ideal values of various target blink characteristic parameters in a target blink characteristic parameter group corresponding to the ith individual movement detection chip is represented;
Fi(t) a vector formed by actual values of various target blink characteristic parameters in a target blink characteristic parameter group corresponding to the ith individual movement detection chip is represented;
Cov(fi(t),Fi(t)) represents fi(t) and Fi(t) covariance;
a second determining submodule for determining the degree of matching GiAnd when the current value is larger than the fourth threshold value, determining that the ith motion detection chip is successfully matched.
Optionally, the fourth threshold is obtained by:
sampling signals output by a plurality of body movement detection chips for detecting blinking movement in advance simultaneously;
determining experimental values of various blink characteristic parameters corresponding to each body motion detection chip according to sampling point data of each body motion detection chip in a period of time;
for each body motion detection chip, calculating a third average value corresponding to each body motion detection chip according to the experimental values of the plurality of blink characteristic parameters corresponding to the body motion detection chip and the ideal values of the plurality of blink characteristic parameters through the following formula:
wherein M isiRepresenting a third average value corresponding to the ith individual dynamic detection chip;
p represents the number of types of the blink characteristic parameter;
fi(tj) Representing an ideal value of the jth blink characteristic parameter corresponding to the ith individual movement detection chip;
gi(tj) The experimental value of the jth blink characteristic parameter corresponding to the ith individual movement detection chip is represented;
H＝max[Mi]and H denotes the fourth threshold value.
Optionally, the apparatus further comprises:
a third determining module, configured to determine a blink end time corresponding to each body movement detecting chip when the second determining module determines that the subject blinks; and under the condition that the blink ending time corresponding to each body motion detection chip is obtained, triggering the first determining module to determine the actual values of various blink characteristic parameters corresponding to each body motion detection chip according to the sampling point data of each body motion detection chip in the preset time length from the corresponding time of the sampling point when the voltage value of the sampling point of any body motion detection chip is larger than a first threshold value.
According to a third aspect of the present disclosure, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method of the first aspect.
According to a fourth aspect of the present disclosure, there is provided an electronic device comprising:
the computer-readable storage medium of the third aspect; and
one or more processors to execute the program in the computer-readable storage medium.
In the above technical solution, when the voltage value of the sampling point of any body motion detection chip is greater than the first threshold, it indicates that there is a possibility of blink action occurring at this time, and therefore, according to the data of the sampling point within the preset time duration from this time, the actual values of the plurality of blink characteristic parameters corresponding to each body motion detection chip are respectively determined, so as to match the determined actual values of the blink characteristic parameters with the corresponding ideal values, and determine the matching result of each body motion detection chip. And finally, comprehensively judging whether the blinking motion of the examinee occurs according to the matching results of the plurality of body motion detection chips, so that the accuracy of the blinking motion detection can be effectively improved. In addition, whether the subject blinks or not is detected based on the plurality of body movement detection chips, and only partial processes in the blinking process can be matched, so that the detection result is determined, namely the blinking action can be determined in the blinking process, the time delay phenomenon that the blinking action is detected after the blinking action is finished in the prior art is avoided, and the real-time performance and the accuracy of the detection process are ensured. In addition, compared with a complex algorithm performed when a single body movement detection chip is used for detecting blinking movement in the prior art, the method and the device can avoid a large number of calculation processes, so that the complexity of a signal data processing process is simplified, and the time complexity of signal data processing is reduced. In addition, the method can reduce the high requirements on the memory and performance of hardware when being implemented, and has wider applicability.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure without limiting the disclosure. In the drawings:
fig. 1 is a flow chart of a blink action detection method provided according to an embodiment of the disclosure;
fig. 2 is a flow chart of a blink action detection method provided according to another embodiment of the disclosure;
FIGS. 3A and 3B are a side view and a top view, respectively, of a plurality of body motion detecting chips in positional relationship with a subject;
fig. 4 is a block diagram of a blink action detection device provided according to an embodiment of the disclosure;
fig. 5 is a block diagram of a blink action detection device provided in accordance with another embodiment of the disclosure;
fig. 6 is a block diagram of a screening module in a blink action detection device provided according to an embodiment of the disclosure;
fig. 7 is a block diagram of a matching module in a blink motion detection device provided according to an embodiment of the disclosure;
FIG. 8 is a block diagram illustrating an electronic device in accordance with an exemplary embodiment;
FIG. 9 is a block diagram illustrating an electronic device in accordance with an example embodiment.
Detailed Description
The following detailed description of specific embodiments of the present disclosure is provided in connection with the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the present disclosure, are given by way of illustration and explanation only, not limitation.
Fig. 1 is a flowchart of a blink detection method according to an embodiment of the disclosure, and the method includes:
in S11, signals output from a plurality of body motion detection chips for detecting a blinking motion are simultaneously sampled.
The signals output by the body motion detection chips for detecting the blinking motion are sampled simultaneously, so that the time consistency of sampling point data of the body motion detection chips can be ensured, and accurate data support is provided for subsequent detection. For example, the sampling manner may be to sample the signals output by the plurality of body motion detection chips at a certain predetermined time interval.
In S12, when the voltage value of the sampling point of any body motion detection chip is greater than the first threshold, the actual values of the blinking feature parameters corresponding to each body motion detection chip are determined according to the sampling point data of each body motion detection chip within the preset time period from the time corresponding to the sampling point.
Wherein the first threshold is derived from a large amount of experimental data. Specifically, the signals output from the plurality of body motion detection chips are sampled simultaneously in advance. In the following, taking any body motion detection chip as an example, the instantaneous sampling point data Temp (v, t) of the body motion detection chip is recorded, t is the corresponding time of the sampling point, and v is the voltage value of the sampling point of the body motion detection chip at the time of t. Illustratively, when v (temp) continuously increases with T, the time corresponding to the sampling point at which v (temp) starts to increase is recorded as T _ begin, and the voltage value corresponding to the time T _ begin is recorded as v (T _ begin). Thereafter, after v (T _ begin) of each body movement detection chip is obtained separately, the minimum value thereof is determined as the first threshold value. The first threshold value may represent a minimum value of voltage values output by the body motion detection chips when the blinking motion occurs, and when the voltage value of a sampling point of any one body motion detection chip is greater than the first threshold value, it represents that the blinking motion is likely to occur at this time, so that whether the blinking motion occurs to the examinee may be determined according to sampling point data of each body motion detection chip within a preset time period from a time corresponding to the sampling point. Wherein the preset time duration is less than an average single blink time, and the average single blink time can be determined by a large amount of sampling point data obtained by pre-sampling. Illustratively, the preset duration may be 1/2 of the average single blink time.
For example, the blink feature parameters obtained from the sampling point data within the preset time length for each body movement detection chip may include the following parameters:
v (T _ begin): and the voltage value of the sampling point is increased by the minimum value of the voltage value in the process.
v (peak): maximum value of voltage value of sampling point.
Vm: acceleration at which the voltage value of the sampling point increases.
Tr: the time required for the voltage value of the sampling point to increase from v (T _ begin) to v (peak).
V _ minus: and the difference between the voltage values of two adjacent sampling points, wherein when a plurality of differences exist in the process of determining the difference, the maximum value of the differences is taken as the parameter value.
N _ times: the number of sampling points.
In S13, for each body movement detection chip, matching an actual value of a set of target blink feature parameters corresponding to the body movement detection chip with an ideal value of the set of target blink feature parameters corresponding to the body movement detection chip, wherein the set of target blink feature parameters includes at least one of the plurality of blink feature parameters.
The ideal value of the target blinking feature parameter is obtained by sampling and processing a signal output by the body movement detection chip when the subject blinks under experimental conditions and without external interference and under the condition that the subject guarantees normal physiological conditions, so that when the actual value of the target blinking feature parameter set corresponding to the body movement detection chip is successfully matched with the ideal value of the set of target blinking feature parameters corresponding to the body movement detection chip, it indicates that the subject may blink within the preset time period.
In one embodiment, the set of target blink characteristic parameters includes all blink characteristic parameters of the plurality of blink characteristic parameters determined in S12.
In another embodiment, as shown in fig. 2, before matching, at S12, for each body motion detecting chip, an actual value of the set of target blink feature parameters corresponding to the body motion detecting chip with an ideal value of the set of target blink feature parameters corresponding to the body motion detecting chip, the method further includes:
in S21, the multiple blink feature parameters are screened according to the actual values of the multiple blink feature parameters corresponding to each body motion detector chip and the ideal values of the multiple blink feature parameters corresponding to each body motion detector chip, so as to obtain the target blink feature parameter set corresponding to each body motion detector chip.
For example, the plurality of blink characteristic parameters may be filtered as follows:
for each blink characteristic parameter, calculating a first average value of the blink characteristic parameter according to the actual values of the blink characteristic parameter corresponding to the plurality of body motion detection chips, for example, calculating the first average value of the blink characteristic parameter by the following formula:
wherein, EFjA first average value representing a jth blink characteristic parameter;
n represents the total number of the body motion detection chips;
Fi(tj) Representing the actual value of the jth blink characteristic parameter corresponding to the ith individual movement detection chip;
and calculating a second average value of the blink characteristic parameter according to the ideal values of the blink characteristic parameter corresponding to the plurality of body motion detection chips, for example, calculating the second average value of the blink characteristic parameter by the following formula:
wherein, EfjA second average value representing a jth blink characteristic parameter;
n represents the total number of the body motion detection chips;
fi(tj) Representing an ideal value of the jth blink characteristic parameter corresponding to the ith individual movement detection chip;
and if the absolute value of the difference value between the first average value and the second average value is less than or equal to a third threshold value corresponding to the blink characteristic parameter, determining the blink characteristic parameter as a target blink characteristic parameter.
Illustratively, there are 7 body motion detection chips, each of which is disposed in a range directly in front of the line of sight of the subject, for example, 7 body motion detection chips are disposed in a range of 100 ° in front of the line of sight of the subject, as shown in fig. 3A and 3B, that is, the angle a in fig. 3B is 100 °. Fig. 3A and 3B are a side view and a top view, respectively, of the positional relationship between the plurality of body motion detecting chips and the subject. Illustratively, the plurality of blink characteristic parameters determined in S12 for each body movement detection chip include V (T _ begin), V (peak), Vm, Tr, V _ minus, and N _ times as described above. Each blink characteristic parameter has a corresponding third threshold value, the third threshold value is used for judging whether the blink characteristic parameter is valid data or invalid data, and when the blink characteristic parameter is determined to be invalid data, the blink characteristic parameter is ignored.
Taking the blink feature parameter v (peak) as an example, the average value of the actual values of v (peak) corresponding to the 7 motion detection chips determined in S12, that is, the first average value of v (peak), is calculated; and calculating the average value of the ideal values of v (peak) corresponding to 7 motion detection chips, namely, the second average value of v (peak). When the absolute value of the difference value between the first average value and the second average value of v (peak) is less than or equal to the third threshold value corresponding to v (peak), the actual value of the blink characteristic parameter v (peak) is effective data, and therefore v (peak) is determined as the target blink characteristic parameter. For example, when the absolute value of the difference between the first average value and the second average value of Vm is greater than the third threshold corresponding to Vm, it may be determined that the blink feature parameter Vm is invalid data, and at this time, the blink feature parameter Vm is not used as the target blink feature parameter, that is, in the subsequent matching process, the actual value of the blink feature parameter Vm is not required to be used as the data for blink motion detection.
The third threshold corresponding to each blink characteristic parameter is obtained according to a large amount of sampling point data of the body motion detection chip which is obtained in advance. For example, the absolute value of the difference between the average of the actual values of each blink characteristic parameter and the average of the ideal values of the blink characteristic parameter, which are obtained through the plurality of sample point data, may be used as the third threshold corresponding to the blink characteristic parameter.
In the above technical solution, before the step of matching the actual value of the target blink feature parameter set corresponding to each body motion detection chip with the ideal value of the set of target blink feature parameters corresponding to the body motion detection chip, a plurality of blink feature parameters are screened to obtain the target blink feature parameter set corresponding to each body motion detection chip. Through the technical scheme, various blink characteristic parameters are screened, the accuracy of data in the subsequent matching process can be ensured, the influence of invalid data on the final result is avoided, and data support is provided for improving the accuracy of blink action detection.
Optionally, turning back to fig. 1, in S13, for each body motion detection chip, an example implementation manner of matching an actual value of the set of target blink feature parameters corresponding to the body motion detection chip with an ideal value of the set of target blink feature parameters corresponding to the body motion detection chip is as follows, including:
matching the actual value of the target blink characteristic parameter group corresponding to the body motion detection chip with the ideal value of the set of target blink characteristic parameters corresponding to the body motion detection chip by the following formula:
wherein G isiThe matching degree of the actual value of the target blink characteristic parameter group corresponding to the ith individual movement detection chip and the ideal value of the group of target blink characteristic parameters corresponding to the individual movement detection chip is represented;
fi(t) a vector formed by ideal values of various target blink characteristic parameters in a target blink characteristic parameter group corresponding to the ith individual movement detection chip is represented;
Fi(t) a vector formed by actual values of various target blink characteristic parameters in a target blink characteristic parameter group corresponding to the ith individual movement detection chip is represented;
for example, the ideal values of the plurality of target blink feature parameters corresponding to the ith motion detection chip may be formed into one row vector (or column vector), and the ideal value of each target blink feature parameter is one element value in the row vector (or column vector). The method for forming the vector by the actual values of the plurality of target blink characteristic parameters is the same as that described above, and when the ideal value and the actual value of the target blink characteristic parameter form the vector, the sequence of the target blink characteristic parameters corresponding to the elements of the vector is the same.
Cov(fi(t),Fi(t)) represents fi(t) and Fi(t) covariance;
The calculation methods of the covariance and the mean square error are common knowledge, and are not described herein again.
At the matching degree GiAnd when the current value is larger than the fourth threshold value, determining that the ith motion detection chip is successfully matched. When the matching degree is greater than the fourth threshold, the matching degree between the actual value and the corresponding ideal value of each target characteristic parameter in the target characteristic parameter group of the body motion detection chip is large, namely, the matching degree between the actual value and the ideal value is largeThe similarity of the body motion detection chip is higher, the probability of the occurrence of the blinking motion is higher at the moment, and the body motion detection chip is determined to be successfully matched.
Optionally, the fourth threshold is obtained by:
sampling signals output by a plurality of body movement detection chips for detecting blinking movement in advance simultaneously;
determining experimental values of a plurality of blink characteristic parameters corresponding to each body movement detection chip according to sampling point data of each body movement detection chip in a time period, wherein the time period of the time period can be 30-60 s, so that a large amount of sampling point data can be acquired in the time period, and the accuracy of a fourth threshold value is ensured;
for each body motion detection chip, calculating a third average value corresponding to each body motion detection chip according to the experimental values of the plurality of blink characteristic parameters corresponding to the body motion detection chip and the ideal values of the plurality of blink characteristic parameters through the following formula:
wherein M isiRepresenting a third average value corresponding to the ith individual dynamic detection chip;
p represents the number of types of the blink characteristic parameter;
fi(tj) Representing an ideal value of the jth blink characteristic parameter corresponding to the ith individual movement detection chip;
gi(tj) The experimental value of the jth blink characteristic parameter corresponding to the ith individual movement detection chip is represented;
H＝max[Mi]and H denotes the fourth threshold value.
In the technical scheme, the actual values of various target blinking characteristic parameters in the target blinking characteristic parameter group of each body movement detection chip are matched with the corresponding ideal values, and through the matching algorithm, the data of each sampling point of each body movement detection chip in the preset time length can be prevented from being calculated, the calculated amount of the data is effectively reduced, the performance loss in the calculation process is reduced, and the efficiency of blinking movement detection is improved.
Turning back to fig. 1, in S14, when the ratio of the number of successfully matched body motion detecting chips to the total number of body motion detecting chips is greater than or equal to a second threshold, it is determined that a blinking motion of the subject has occurred.
For example, the second threshold may be 50%, that is, when more than half of the body motion detection chips are successfully matched, it is determined that the subject has a blinking motion.
In the above technical solution, when the voltage value of the sampling point of any body motion detection chip is greater than the first threshold, it indicates that there is a possibility of blink action occurring at this time, and therefore, according to the data of the sampling point within the preset time duration from this time, the actual values of the plurality of blink characteristic parameters corresponding to each body motion detection chip are respectively determined, so as to match the determined actual values of the blink characteristic parameters with the corresponding ideal values, and determine the matching result of each body motion detection chip. And finally, comprehensively judging whether the blinking motion of the examinee occurs according to the matching results of the plurality of body motion detection chips, so that the accuracy of the blinking motion detection can be effectively improved. In addition, whether the subject blinks or not is detected based on the plurality of body movement detection chips, and only partial processes in the blinking process can be matched, so that the detection result is determined, namely the blinking action can be determined in the blinking process, the time delay phenomenon that the blinking action is detected after the blinking action is finished in the prior art is avoided, and the real-time performance and the accuracy of the detection process are ensured. In addition, compared with a complex algorithm performed when a single body movement detection chip is used for blink movement detection in the prior art, the method and the device can avoid a large number of calculation processes, so that the complexity of a signal data processing process is simplified, and the time complexity of signal data processing is reduced. In addition, the method can reduce the high requirements on the memory and performance of hardware when being implemented, and has wider applicability.
Optionally, the method further comprises:
when the blinking motion of the examinee is determined, determining the blinking ending time corresponding to each body motion detection chip; and under the condition that the blink ending time corresponding to each body motion detection chip is obtained, returning to the step of determining the actual values of the various blink characteristic parameters corresponding to each body motion detection chip according to the sampling point data of each body motion detection chip in the preset time length from the time corresponding to the sampling point when the voltage value of the sampling point of any body motion detection chip is larger than the first threshold value.
For example, for each body movement detection chip, the sampling time of the sampling point that is before the first sampling point at which the first voltage value starts to increase is determined as the blink end time corresponding to the body movement detection chip from the time when it is determined that the subject has a blink motion.
In the above technical solution, since the setting positions of each body motion detection chip are different, the blinking end times determined by the body motion detection chips at different positions may also be different, and thus when the blinking end time corresponding to each body motion detection chip is obtained, it is determined that the current blinking motion is completed, and then, the signal output by the body motion detection chip is detected again. By the technical scheme, when the blinking motion of the examinee is determined, the matching process is not performed before the blinking motion is completed, so that an unnecessary calculation process can be avoided, and the performance overhead during calculation is reduced. Meanwhile, the storage capacity of data can be reduced, so that the requirement on a memory can be reduced. In addition, the detection time of the blinking motion can be shortened.
The present disclosure also provides a blink action detection device, as shown in fig. 4, the device 10 including:
a sampling module 100, configured to sample signals output by a plurality of body motion detection chips for detecting a blinking motion at the same time;
the first determining module 200 is configured to, when a voltage value of a sampling point of any one of the body motion detection chips is greater than a first threshold, determine actual values of a plurality of blink characteristic parameters corresponding to each of the body motion detection chips according to sampling point data of each of the body motion detection chips within a preset time period from a time corresponding to the sampling point;
a matching module 300, configured to match, for each body motion detection chip, an actual value of a set of target blink feature parameters corresponding to the body motion detection chip with an ideal value of the set of target blink feature parameters corresponding to the body motion detection chip, where the set of target blink feature parameters includes at least one of the plurality of blink feature parameters;
the second determination module 400 is configured to determine that the subject blinks when the ratio of the number of successfully matched body motion detection chips to the total number of body motion detection chips is greater than or equal to a second threshold.
Optionally, as shown in fig. 5, on the basis of fig. 4, the apparatus 10 further includes:
a screening module 500, configured to, before the matching module 300 matches, for each of the body movement detection chips, an actual value of a target blink feature parameter set corresponding to the body movement detection chip with an ideal value of the set of target blink feature parameters corresponding to the body movement detection chip, screen the plurality of blink feature parameters according to the actual values of the plurality of blink feature parameters corresponding to each of the body movement detection chips and the ideal values of the plurality of blink feature parameters corresponding to each of the body movement detection chips, so as to obtain the target blink feature parameter set corresponding to each of the body movement detection chips.
Optionally, as shown in fig. 6, the screening module 500 includes:
a calculating submodule 501, configured to calculate, for each blink feature parameter, a first average value of the blink feature parameter according to the actual value of the blink feature parameter corresponding to the plurality of body motion detection chips, and calculate a second average value of the blink feature parameter according to the ideal value of the blink feature parameter corresponding to the plurality of body motion detection chips;
a first determining sub-module 502, configured to determine the blink characteristic parameter as the target blink characteristic parameter if an absolute value of a difference between the first average value and the second average value is smaller than or equal to a third threshold corresponding to the blink characteristic parameter.
Optionally, as shown in fig. 7, the matching module 300 includes:
a matching sub-module 301, configured to match an actual value of the set of target blink feature parameters corresponding to the physical movement detection chip with an ideal value of the set of target blink feature parameters corresponding to the physical movement detection chip by using the following formula:
wherein G isiThe matching degree of the actual value of the target blink characteristic parameter group corresponding to the ith individual movement detection chip and the ideal value of the group of target blink characteristic parameters corresponding to the individual movement detection chip is represented;
fi(t) a vector formed by ideal values of various target blink characteristic parameters in a target blink characteristic parameter group corresponding to the ith individual movement detection chip is represented;
Fi(t) a vector formed by actual values of various target blink characteristic parameters in a target blink characteristic parameter group corresponding to the ith individual movement detection chip is represented;
Cov(fi(t),Fi(t)) represents fi(t) and Fi(t) covariance;
a second determining submodule 302 for determining the degree of matching GiAnd when the current value is larger than the fourth threshold value, determining that the ith motion detection chip is successfully matched.
Optionally, the fourth threshold is obtained by:
sampling signals output by a plurality of body movement detection chips for detecting blinking movement in advance simultaneously;
determining experimental values of various blink characteristic parameters corresponding to each body motion detection chip according to sampling point data of each body motion detection chip in a period of time;
aiming at each body motion detection chip, calculating a third average value corresponding to each body motion detection chip according to the experimental values of the plurality of blink characteristic parameters corresponding to the body motion detection chip and the ideal values of the plurality of blink characteristic parameters through the following formula;
wherein M isiRepresenting a third average value corresponding to the ith individual dynamic detection chip;
p represents the number of types of the blink characteristic parameter;
fi(tj) Representing an ideal value of the jth blink characteristic parameter corresponding to the ith individual movement detection chip;
gi(tj) The experimental value of the jth blink characteristic parameter corresponding to the ith individual movement detection chip is represented;
H＝max[Mi]and H denotes the fourth threshold value.
Optionally, the apparatus 10 further comprises:
a third determining module, configured to determine a blink end time corresponding to each body movement detecting chip when the second determining module 400 determines that the subject has a blink action; and under the condition that the blink ending time corresponding to each body motion detection chip is obtained, triggering the first determining module 200 to determine the actual values of various blink characteristic parameters corresponding to each body motion detection chip according to the sampling point data of each body motion detection chip within the preset time length from the time corresponding to the sampling point when the voltage value of the sampling point of any body motion detection chip is greater than the first threshold value.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Fig. 8 is a block diagram illustrating an electronic device 800 in accordance with an example embodiment. As shown in fig. 8, the electronic device 800 may include: a processor 801, a memory 802, a multimedia component 803, an input/output (I/O) interface 804, and a communications component 805.
The processor 801 is configured to control the overall operation of the electronic device 800 to complete all or part of the steps of the blink detection method. The memory 802 is used to store various types of data to support operation at the electronic device 800, such as instructions for any application or method operating on the electronic device 800 and application-related data, such as contact data, transmitted and received messages, pictures, audio, video, and so forth. The Memory 802 may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk or optical disk. The multimedia components 803 may include screen and audio components. Wherein the screen may be, for example, a touch screen and the audio component is used for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may further be stored in the memory 802 or transmitted through the communication component 805. The audio assembly also includes at least one speaker for outputting audio signals. The I/O interface 804 provides an interface between the processor 801 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the electronic device 800 and other devices. Wireless Communication, such as Wi-Fi, bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination of one or more of them, so that the corresponding Communication component 805 may include: Wi-Fi module, bluetooth module, NFC module.
In an exemplary embodiment, the electronic Device 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for performing the blink detection method described above.
In another exemplary embodiment, a computer readable storage medium, such as the memory 802, is also provided that includes program instructions executable by the processor 801 of the electronic device 800 to perform the blink motion detection method described above.
Fig. 9 is a block diagram illustrating an electronic device 900 in accordance with an example embodiment. For example, the electronic device 900 may be provided as a server. Referring to fig. 9, the electronic device 900 includes a processor 922, which may be one or more in number, and a memory 932 for storing computer programs executable by the processor 922. The computer programs stored in memory 932 may include one or more modules that each correspond to a set of instructions. Further, the processor 922 may be configured to execute the computer program to perform the blink motion detection method described above.
Additionally, the electronic device 900 may also include a power component 926 and a communication component 950, the power component 926 may be configured to perform power management of the electronic device 900, and the communication component 950 may be configured to enable communication, e.g., wired or wireless communication, of the electronic device 900. The electronic device 900 may also include input/output (I/O) interfaces 958. The electronic device 900 may operate based on an operating system stored in the memory 932, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, and the like.
In another exemplary embodiment, a computer readable storage medium, such as the memory 932, is also provided that includes program instructions executable by the processor 922 of the electronic device 900 to perform the blink motion detection method described above.
The preferred embodiments of the present disclosure are described in detail with reference to the accompanying drawings, however, the present disclosure is not limited to the specific details of the above embodiments, and various simple modifications may be made to the technical solution of the present disclosure within the technical idea of the present disclosure, and these simple modifications all belong to the protection scope of the present disclosure.
It should be noted that the various features described in the above embodiments may be combined in any suitable manner without departing from the scope of the invention. In order to avoid unnecessary repetition, various possible combinations will not be separately described in this disclosure.
In addition, any combination of various embodiments of the present disclosure may be made, and the same should be considered as the disclosure of the present disclosure, as long as it does not depart from the spirit of the present disclosure.
Claims (9)
1. A blink action detection method, the method comprising:
simultaneously sampling signals output by a plurality of body movement detection chips for detecting blinking movement;
when the voltage value of a sampling point of any body motion detection chip is larger than a first threshold value, determining actual values of various blink characteristic parameters corresponding to each body motion detection chip according to sampling point data of each body motion detection chip within a preset time length from the corresponding moment of the sampling point;
screening the plurality of blink characteristic parameters according to the actual values of the plurality of blink characteristic parameters corresponding to each body motion detection chip and the ideal values of the plurality of blink characteristic parameters corresponding to each body motion detection chip to obtain a target blink characteristic parameter group corresponding to each body motion detection chip;
for each body motion detection chip, matching an actual value of a target blink characteristic parameter set corresponding to the body motion detection chip with an ideal value of the target blink characteristic parameter set corresponding to the body motion detection chip, wherein the target blink characteristic parameter set comprises at least one of the blink characteristic parameters;
and when the ratio of the number of the successfully matched body motion detection chips to the total number of the body motion detection chips is larger than or equal to a second threshold value, determining that the blinking motion of the examinee occurs.
2. The method of claim 1, wherein the screening the plurality of blink characteristic parameters according to the actual values of the plurality of blink characteristic parameters corresponding to each body movement detector chip and the ideal values of the plurality of blink characteristic parameters corresponding to each body movement detector chip comprises:
aiming at each blink characteristic parameter, calculating a first average value of the blink characteristic parameter according to the actual value of the blink characteristic parameter corresponding to the plurality of body motion detection chips, and calculating a second average value of the blink characteristic parameter according to the ideal value of the blink characteristic parameter corresponding to the plurality of body motion detection chips;
and if the absolute value of the difference value between the first average value and the second average value is less than or equal to a third threshold value corresponding to the blink characteristic parameter, determining the blink characteristic parameter as a target blink characteristic parameter.
3. The method of claim 1 or 2, wherein the matching, for each of the body motion detecting chips, the actual values of the set of target blink feature parameters corresponding to the body motion detecting chip with the ideal values of the set of target blink feature parameters corresponding to the body motion detecting chip comprises:
matching the actual value of the target blink characteristic parameter group corresponding to the body motion detection chip with the ideal value of the set of target blink characteristic parameters corresponding to the body motion detection chip by the following formula:
wherein G isiThe matching degree of the actual value of the target blink characteristic parameter group corresponding to the ith individual movement detection chip and the ideal value of the group of target blink characteristic parameters corresponding to the individual movement detection chip is represented;
fi(t) a vector formed by ideal values of various target blink characteristic parameters in a target blink characteristic parameter group corresponding to the ith individual movement detection chip is represented;
Fi(t) a vector formed by actual values of various target blink characteristic parameters in a target blink characteristic parameter group corresponding to the ith individual movement detection chip is represented;
Cov(fi(t),Fi(t)) represents fi(t) and Fi(t) covariance;
at the matching degree GiAnd when the current value is larger than the fourth threshold value, determining that the ith motion detection chip is successfully matched.
4. The method of claim 3, wherein the fourth threshold is obtained by:
sampling signals output by a plurality of body movement detection chips for detecting blinking movement in advance simultaneously;
determining experimental values of various blink characteristic parameters corresponding to each body motion detection chip according to sampling point data of each body motion detection chip in a period of time;
for each body motion detection chip, calculating a third average value corresponding to each body motion detection chip according to the experimental values of the plurality of blink characteristic parameters corresponding to the body motion detection chip and the ideal values of the plurality of blink characteristic parameters through the following formula:
wherein M isiRepresenting a third average value corresponding to the ith individual dynamic detection chip;
p represents the number of types of the blink characteristic parameter;
fi(tj) Representing an ideal value of the jth blink characteristic parameter corresponding to the ith individual movement detection chip;
gi(tj) The experimental value of the jth blink characteristic parameter corresponding to the ith individual movement detection chip is represented;
H＝max[Mi]and H denotes the fourth threshold value.
5. The method of claim 1, further comprising:
when the blinking motion of the examinee is determined, determining the blinking ending time corresponding to each body motion detection chip; and under the condition that the blink ending time corresponding to each body motion detection chip is obtained, returning to the step of determining the actual values of the various blink characteristic parameters corresponding to each body motion detection chip according to the sampling point data of each body motion detection chip in the preset time length from the time corresponding to the sampling point when the voltage value of the sampling point of any body motion detection chip is larger than the first threshold value.
6. A blink behavior detection device, the device comprising:
the sampling module is used for simultaneously sampling signals output by a plurality of body motion detection chips for detecting blinking motions;
the first determination module is used for determining actual values of various blink characteristic parameters corresponding to each body movement detection chip according to sampling point data of each body movement detection chip within a preset time length from the corresponding time of the sampling point when the voltage value of the sampling point of any body movement detection chip is larger than a first threshold value;
the screening module is used for screening the plurality of blink characteristic parameters according to the actual values of the plurality of blink characteristic parameters corresponding to each body motion detection chip and the ideal values of the plurality of blink characteristic parameters corresponding to each body motion detection chip so as to obtain a target blink characteristic parameter group corresponding to each body motion detection chip;
a matching module, configured to match, for each body motion detection chip, an actual value of a set of target blink feature parameters corresponding to the body motion detection chip with an ideal value of the set of target blink feature parameters corresponding to the body motion detection chip, where the set of target blink feature parameters includes at least one of the plurality of blink feature parameters;
and the second determination module is used for determining that the eye blinking action of the examinee occurs when the ratio of the number of the successfully matched body movement detection chips to the total number of the body movement detection chips is larger than or equal to a second threshold value.
7. The apparatus of claim 6, wherein the matching module comprises:
the matching submodule is used for matching the actual value of the target blink characteristic parameter group corresponding to the body motion detection chip with the ideal value of the group of target blink characteristic parameters corresponding to the body motion detection chip through the following formula:
wherein G isiRepresenting ith movementThe matching degree of the actual value of the target blink characteristic parameter group corresponding to the detection chip and the ideal value of the group of target blink characteristic parameters corresponding to the physical movement detection chip is detected;
fi(t) a vector formed by ideal values of various target blink characteristic parameters in a target blink characteristic parameter group corresponding to the ith individual movement detection chip is represented;
Fi(t) a vector formed by actual values of various target blink characteristic parameters in a target blink characteristic parameter group corresponding to the ith individual movement detection chip is represented;
Cov(fi(t),Fi(t)) represents fi(t) and Fi(t) covariance;
a second determination submodule for determining the degree of matching GiAnd when the current value is larger than the fourth threshold value, determining that the ith motion detection chip is successfully matched.
8. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 5.
9. An electronic device, comprising:
the computer-readable storage medium recited in claim 8; and
one or more processors to execute the program in the computer-readable storage medium.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711375988.XA CN108354611B (en) | 2017-12-19 | 2017-12-19 | Blink action detection method and device, readable storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711375988.XA CN108354611B (en) | 2017-12-19 | 2017-12-19 | Blink action detection method and device, readable storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108354611A CN108354611A (en) | 2018-08-03 |
| CN108354611B true CN108354611B (en) | 2020-11-13 |
Family
ID=63010303
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711375988.XA Active CN108354611B (en) | 2017-12-19 | 2017-12-19 | Blink action detection method and device, readable storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108354611B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7659920B2 (en) * | 2005-03-22 | 2010-02-09 | Microsoft Corp. | System and method for very low frame rate teleconferencing employing image morphing and cropping |
| US8610585B1 (en) * | 2009-12-07 | 2013-12-17 | Matthew Kielbasa | Electronic alerting device and associated method |
| CN103870814A (en) * | 2014-03-18 | 2014-06-18 | 上海理工大学 | Non-contact real-time eye movement identification method based on intelligent camera |
| CN104755023A (en) * | 2012-11-02 | 2015-07-01 | 索尼公司 | Image display device and information input device |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7639146B2 (en) * | 2004-09-29 | 2009-12-29 | Baura Gail D | Blink monitor for detecting blink occurrence in a living subject |
| CN104049761B (en) * | 2014-06-27 | 2017-11-07 | 北京智谷睿拓技术服务有限公司 | Eye electro-detection method and eye electric detection means |
| JP6344254B2 (en) * | 2015-02-12 | 2018-06-20 | トヨタ自動車株式会社 | Sleepiness detection device |
| JP6406171B2 (en) * | 2015-08-25 | 2018-10-17 | トヨタ自動車株式会社 | Blink detection device |
| CN106580334B (en) * | 2016-11-24 | 2019-07-19 | 东软集团股份有限公司 | Determine the method and device that eyes blink |
-
2017
- 2017-12-19 CN CN201711375988.XA patent/CN108354611B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7659920B2 (en) * | 2005-03-22 | 2010-02-09 | Microsoft Corp. | System and method for very low frame rate teleconferencing employing image morphing and cropping |
| US8610585B1 (en) * | 2009-12-07 | 2013-12-17 | Matthew Kielbasa | Electronic alerting device and associated method |
| CN104755023A (en) * | 2012-11-02 | 2015-07-01 | 索尼公司 | Image display device and information input device |
| CN103870814A (en) * | 2014-03-18 | 2014-06-18 | 上海理工大学 | Non-contact real-time eye movement identification method based on intelligent camera |
Non-Patent Citations (2)
| Title |
|---|
| Automated Detection and Quantification of Circadian Eye Blinks Using a Contact Lens Sensor;Christophe Gisler, Antonio Ridi, Jean Hennebert，et al;《Transl Vis Sci Technol》;20151231;全文 * |
| 基于眼动特征的疲劳驾驶检测方法;牛清宁，周志强，金立生，等;《哈尔滨工程大学学报》;20150331;第36卷(第3期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108354611A (en) | 2018-08-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3639051B1 (en) | Sound source localization confidence estimation using machine learning | |
| US10613740B2 (en) | Method for controlling screen of user terminal and user terminal | |
| US9702899B2 (en) | Pedometer with lag correction | |
| CN108255343B (en) | Flash lamp adjusting method, user terminal and medium product | |
| EP2457499B1 (en) | Line-of-sight estimation device | |
| CN108665889B (en) | Voice signal endpoint detection method, device, equipment and storage medium | |
| CN109800858B (en) | Application system abnormality detection method and device, readable storage medium and electronic equipment | |
| US20170296081A1 (en) | Frame based spike detection module | |
| US10659680B2 (en) | Method of processing object in image and apparatus for same | |
| CN105959480B (en) | control method and electronic equipment | |
| CN105704609B (en) | Sound equipment mode adjusting method and device | |
| CN107016996B (en) | Audio data processing method and device | |
| CN112784985A (en) | Training method and device of neural network model, and image recognition method and device | |
| CN108245171B (en) | Method for obtaining parameter model, fatigue detection method and device, medium and equipment | |
| US20190159111A1 (en) | Method for Wireless Fidelity Network Scanning and Terminal Device | |
| CN113867142A (en) | Sensor control method, sensor control device, electronic device and storage medium | |
| CN108354611B (en) | Blink action detection method and device, readable storage medium and electronic equipment | |
| CN110739077A (en) | Epileptic seizure early warning method and system | |
| CN110275639B (en) | Touch data processing method and device, terminal and storage medium | |
| EP3125433A1 (en) | Method and device for triggering predetermined operation | |
| CN107220021B (en) | Voice input recognition method and device and head-mounted equipment | |
| CN115798520A (en) | Voice detection method and device, electronic equipment and storage medium | |
| US10761203B2 (en) | Decision based re-processing framework for radar technology | |
| US11088817B2 (en) | Data transmission method, data transmission device, and computer readable storage medium | |
| US11322137B2 (en) | Video camera |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |