CN113456058A - Head posture detection method and device, electronic equipment and readable storage medium - Google Patents
Head posture detection method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN113456058A CN113456058A CN202010235978.1A CN202010235978A CN113456058A CN 113456058 A CN113456058 A CN 113456058A CN 202010235978 A CN202010235978 A CN 202010235978A CN 113456058 A CN113456058 A CN 113456058A
- Authority
- CN
- China
- Prior art keywords
- target
- head
- millimeter wave
- wave signal
- target object
- 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.)
- Withdrawn
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 75
- 238000000034 method Methods 0.000 claims abstract description 33
- 230000008859 change Effects 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 12
- 210000003128 head Anatomy 0.000 description 327
- 238000010586 diagram Methods 0.000 description 12
- 206010039203 Road traffic accident Diseases 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 5
- 239000000284 extract Substances 0.000 description 4
- 238000001914 filtration Methods 0.000 description 4
- 238000005286 illumination Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 239000011521 glass Substances 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 210000005069 ears Anatomy 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 210000001061 forehead Anatomy 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- ZRHANBBTXQZFSP-UHFFFAOYSA-M potassium;4-amino-3,5,6-trichloropyridine-2-carboxylate Chemical compound [K+].NC1=C(Cl)C(Cl)=NC(C([O-])=O)=C1Cl ZRHANBBTXQZFSP-UHFFFAOYSA-M 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
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
- A61B5/1118—Determining activity level
-
- 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
- A61B5/1116—Determining posture transitions
-
- 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
- A61B5/1121—Determining geometric values, e.g. centre of rotation or angular range of movement
-
- 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
- A61B5/1126—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb using a particular sensing technique
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6887—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient mounted on external non-worn devices, e.g. non-medical devices
- A61B5/6893—Cars
-
- 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
- A61B5/7225—Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation
-
- 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
- A61B5/7235—Details of waveform analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient ; user input means
- A61B5/746—Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Medical Informatics (AREA)
- Heart & Thoracic Surgery (AREA)
- Pathology (AREA)
- Physiology (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Psychiatry (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Geometry (AREA)
- Power Engineering (AREA)
- Image Analysis (AREA)
Abstract
The application relates to a method and a device for detecting head gestures, an electronic device and a computer readable storage medium. The method comprises the steps of obtaining a head posture detection instruction, and transmitting a first millimeter wave signal to a target object according to the head posture detection instruction; receiving a second millimeter wave signal corresponding to the first millimeter wave signal reflected by the target object; determining a target millimeter wave signal corresponding to the head of the target object from the second millimeter wave signal; determining a target head pose of the target object based on the target millimeter wave signal. The head posture detection method and device, the electronic equipment and the computer readable storage medium can more accurately detect the head posture of the target object.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for detecting a head pose, an electronic device, and a computer-readable storage medium.
Background
With the development of society, in many scenes, it is necessary to detect the head posture of a subject such as a human or an animal. In a conventional method for detecting a head pose, an image of an object is generally acquired by a camera and then analyzed to determine the head pose of the object.
However, the traditional head posture detection method has the problem of inaccurate detection.
Disclosure of Invention
The embodiment of the application provides a method and a device for detecting a head posture, electronic equipment and a computer readable storage medium, which can improve the accuracy of head posture detection.
A method of detecting head pose, comprising:
acquiring a head posture detection instruction, and transmitting a first millimeter wave signal to a target object according to the head posture detection instruction;
receiving a second millimeter wave signal corresponding to the first millimeter wave signal reflected by the target object;
determining a target millimeter wave signal corresponding to the head of the target object from the second millimeter wave signal;
determining a target head pose of the target object based on the target millimeter wave signal.
A head pose detection apparatus comprising:
the first millimeter wave signal transmitting module is used for acquiring a head posture detection instruction and transmitting a first millimeter wave signal to a target object according to the head posture detection instruction;
the second millimeter wave signal receiving module is used for receiving a second millimeter wave signal which is reflected by the target object and corresponds to the first millimeter wave signal;
a target millimeter wave signal determination module, configured to determine a target millimeter wave signal corresponding to the head of the target object from the second millimeter wave signal;
a target head pose determination module to determine a target head pose of the target object based on the target millimeter wave signal.
An electronic device comprising a memory and a processor, the memory having stored therein a computer program, which, when executed by the processor, causes the processor to perform the steps of the method of detecting a head pose as described above.
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 as described above.
The head posture detection method, the head posture detection device, the electronic equipment and the computer readable storage medium acquire a head posture detection instruction, and transmit a first millimeter wave signal to a target object according to the head posture detection instruction; receiving a second millimeter wave signal corresponding to the first millimeter wave signal reflected by the target object; determining a target millimeter wave signal corresponding to the head of the target object from the second millimeter wave signal; the target head posture of the target object is determined based on the target millimeter wave signal, so that the influence of factors such as illumination change, background change and the like caused by shooting by a camera is avoided, and the target head posture of the target object can be determined more accurately.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic diagram of a millimeter wave signal processing circuit in one embodiment;
FIG. 2 is a flow diagram of a method for head pose detection in one embodiment;
FIG. 3 is a schematic diagram of a head pose in one embodiment;
FIG. 4 is a flow diagram that illustrates steps in one embodiment for extracting target feature information for a header of a target object;
FIG. 5 is a flow diagram that illustrates steps in one embodiment for obtaining reference feature information for a reference head pose;
FIG. 6 is a flow diagram for training a head pose detection model in one embodiment;
FIG. 7 is a flowchart of a head pose detection method in another embodiment;
FIG. 8 is a block diagram showing a configuration of a head posture detecting apparatus according to an embodiment;
fig. 9 is a schematic diagram of an internal structure of an electronic device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
It will be understood that, as used herein, the terms "first," "second," and the like may be used herein to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish one element from another. For example, the first millimeter-wave signal may be referred to as a second millimeter-wave signal, and similarly, the second millimeter-wave signal may be referred to as a first millimeter-wave signal, without departing from the scope of the present application. Both the first millimeter-wave signal and the second millimeter-wave signal are millimeter-wave signals, but they are not the same millimeter-wave signal.
The embodiment of the application also provides the electronic equipment. Fig. 1 is a schematic diagram of a millimeter wave signal processing circuit in one embodiment. As shown in fig. 1, for convenience of explanation, only various aspects of millimeter wave signal processing technology related to the embodiments of the present application are shown.
As shown in fig. 1, the millimeter wave signal processing circuit includes a processor 120 and control logic 130. The sensor 120 (e.g., gyroscope, distance sensor) may provide the acquired parameters (e.g., anti-shake parameters, distance parameters) to the processor 120 based on the type of interface of the sensor 120. The sensor 120 interface may utilize an SMIA (Standard Mobile Imaging Architecture) interface, other serial or parallel camera interfaces, or a combination of the above.
Further, the millimeter wave transceiver 110 may transmit a millimeter wave signal and transmit the received millimeter wave signal to the processor 120. The control logic 130 may control the millimeter wave transceiver 110, for example, to increase or decrease the transmission frequency of the millimeter wave transceiver 110.
The statistical data determined by the processor 120 may be sent to the control logic 120. For example, the statistical data may include a transmission frequency of the millimeter wave signal, a data amount of the received millimeter wave signal, a strength of the received millimeter wave signal, a propagation time length of the received millimeter wave signal, and the like. The control logic 130 may include a processor and/or microcontroller that executes one or more routines (e.g., firmware) that may determine control parameters of the millimeter wave transceiver 110 and control parameters of the processor 120 based on the received statistical data. For example, the control parameters of the millimeter-wave transceiver 110 may include a transmission frequency of the millimeter-wave signal, a transmission power of the millimeter-wave transceiver, a transmission direction of the millimeter-wave signal, or a combination of these parameters.
In one embodiment, processor 120 obtains head pose detection instructions and sends the head pose detection instructions to control logic 130. The control logic 130 controls the millimeter wave transceiver 110 to transmit the first millimeter wave signal to the target object according to the head posture detection instruction. A second millimeter wave signal corresponding to the first millimeter wave signal reflected by the target object is received by the millimeter wave transceiver 110 and sent to the processor 120. The processor 120 determines a target millimeter wave signal corresponding to the head of the target object from the second millimeter wave signal; the target head posture of the target object is determined based on the target millimeter wave signal, so that the influence of factors such as illumination change, background change and the like caused by shooting by a camera is avoided, and the target head posture of the target object can be determined more accurately.
FIG. 2 is a flow diagram of a method for head pose detection in one embodiment. As shown in fig. 2, the method of detecting a head pose includes steps 202 to 208.
In the electronic device, a millimeter wave transceiver is mounted, and a first millimeter wave signal can be transmitted to a target object. Here, the target object may be a person, an animal, or the like having a head, but is not limited thereto. Millimeter Wave (Millimeter Wave) refers to electromagnetic Wave with a wavelength of 1-10 mm, and is located in a wavelength range where microwave and far infrared Wave are overlapped, so that the Millimeter Wave has the characteristics of two Wave spectrums. The first millimeter wave signal refers to a millimeter wave signal emitted to a target object.
In one embodiment, a distance sensor is installed in the electronic device, and when the distance sensor detects that the distance between the target object and the electronic device is smaller than a preset distance, a head posture detection instruction is generated. When the distance between the target object and the electronic equipment is smaller than the preset distance, the head posture of the target object is detected, the head posture of the target object can be detected more accurately, and computer resources of the electronic equipment can be saved.
In another embodiment, the electronic device receives a head posture detection instruction sent by an external device, and transmits a first millimeter wave signal to the target object according to the received head posture detection instruction. The external device and the electronic device communicate through a network, and a user can initiate head posture detection on the external device, so that a head posture detection instruction is generated and sent to the electronic device. The external device may be a smart phone, smart band, or the like.
The number of target objects may be one or at least two.
And 204, receiving a second millimeter wave signal which is reflected by the target object and corresponds to the first millimeter wave signal.
It is understood that the millimeter wave signal is reflected when it contacts an object. The electronic equipment transmits a first millimeter wave signal to a target object, and when the first millimeter wave signal contacts the target object, the first millimeter wave signal is reflected, and the first millimeter wave signal, namely a second millimeter wave signal, is obtained through reflection.
A second millimeter wave signal corresponding to the first millimeter wave signal reflected by the target object may be received by the millimeter wave transceiver.
In step 206, a target millimeter wave signal corresponding to the head of the target object is determined from the second millimeter wave signal.
The target millimeter wave signal refers to a second millimeter wave signal reflected by the head of the target object.
It can be understood that the second millimeter wave signal is reflected by the target object, and therefore, when the millimeter wave transceiver receives the second millimeter wave signal, information such as a reflection direction, intensity, propagation time and the like included in the second millimeter wave signal can be acquired, and information such as an outline, a size and the like of the head of the target object can be determined by the information included in the second millimeter wave signal.
The head of the target object is usually located in the top area of the target object or in front of the target object, so that the head area of the target object can be determined from the outline of the target object, and then the second millimeter wave signal corresponding to the head area, namely the target millimeter wave signal, is obtained from the second millimeter wave signal.
In step 208, a target head pose of the target object is determined based on the target millimeter wave signal.
It can be understood that the head is the most important component of the target object, and the detection of the head pose of the target object can more accurately analyze the target object. For example, the head posture of a person frequently rotates in a short time, and the person can be judged to be comparatively hurried; when the vehicle is driven, the head posture of the person is in a low-drooping posture, and fatigue driving of the person can be judged; the dog is judged to be in a vigilant state by keeping the head of the dog still and erecting ears and opening eyes.
The target head pose may include normal, head up, head down, left turn, right turn, left head up, right head up, left head down, right head down, etc.
And determining a target millimeter wave signal corresponding to the head of the target object from the second millimeter wave signals, and then determining the target head posture of the target object based on the target millimeter wave signals, so that analysis based on all the second millimeter wave signals is avoided, the detection efficiency of the head posture can be improved, and the computer resources of the electronic equipment are saved.
The head posture detection method comprises the steps of obtaining a head posture detection instruction, and transmitting a first millimeter wave signal to a target object according to the head posture detection instruction; receiving a second millimeter wave signal corresponding to the first millimeter wave signal reflected by the target object; determining a target millimeter wave signal corresponding to the head of the target object from the second millimeter wave signal; the target head posture of the target object is determined based on the target millimeter wave signal, so that the influence of factors such as illumination change, background change and the like caused by shooting by a camera is avoided, and the target head posture of the target object can be determined more accurately.
In addition, in the conventional head posture detection method, a camera is adopted to shoot a target object, an image or a video of the target object is obtained, excessive information of the target object is easily obtained, and interference is caused on privacy or safety of the target object.
In one embodiment, determining a target head pose of a target object based on a target millimeter wave signal comprises: extracting target feature information of a head of a target object from the target millimeter wave signal; and matching the reference characteristic information of the reference head posture with the target characteristic information, and taking the reference head posture matched with the reference characteristic information as the target head posture of the target object.
The target feature information refers to feature information of a head of the target object. The target feature information may include the size of the header, the position of the header, the outline of the header, the position and size of various components in the header, frequency domain data conditions, and the like. The electronic device may extract the target feature information of the head of the target object by using machine learning, may extract the target feature information of the head of the target object by using deep learning, and is not limited thereto.
The reference feature information refers to feature information of a reference head pose. The electronic device may acquire the reference head pose and the reference feature information of the reference head pose in advance. The reference head pose may be set according to the user's needs.
In one embodiment, as shown in fig. 3, the 9 reference head poses are selected based on the difference in euler angles (yaw, pitch) of the reference head poses, including 302 normal head pose, 304 heads-up pose, 306 heads-down pose, 308 heads left turn pose, 310 heads right turn pose, 312 heads-up left pose, 314 heads-up right pose, 316 heads-down left pose, 318 heads-down pose, etc.
Further, the reference head pose may be determined based on euler angles within a preset range. For example, the head may be determined as a head left turn posture in an angular range between 30 degrees and 80 degrees of left turn; the head may be determined to be in a head-up attitude within an angular range of between 30 and 60 degrees of head-up. As shown in fig. 3, the 304 head-up gesture may include two head gestures raised at different euler angles, and similarly, the 306 head-down gesture, 308 head left-turn gesture, 310 head right-turn gesture, 312 head-up gesture, 314 head-up gesture, 316 head-down gesture, 318 head-down gesture may also include two head gestures at different euler angles.
For each reference head pose, there is specific reference feature information. For example, when the reference head pose is a left turn, the reference feature information may be that the right eye, half of the cheek, half of the mouth, and the right ear in the head are detected; when the head is raised, the reference characteristic information may be the detected chin, nostrils, mouth, and eyes in the head, and the chin, nostrils, mouth, and eyes are densely distributed in the upper region of the head. The profile of each reference head pose is also different.
Therefore, the electronic device can match the reference characteristic information of each reference head pose with the target characteristic information respectively, and the reference head pose matched with the reference characteristic information is taken as the target head pose of the target object, so that the target head pose of the target object can be accurately matched.
In another embodiment, when the reference feature information of each reference head pose is not matched with the target feature information, the matching degree of the reference feature information and the target feature information of each reference head pose is respectively obtained, and the reference head pose corresponding to the reference feature information with the highest matching degree is used as the target head pose of the target object. The reference head pose corresponding to the reference feature information with the highest matching degree can be used as the target head pose of the target object.
In one embodiment, as shown in fig. 4, extracting target feature information of a head portion of a target object from a target millimeter wave signal includes:
The information included in the target millimeter wave signal may include, without limitation, the reflection direction, intensity, propagation time length, frequency domain data condition, and the like of the target millimeter wave signal. Through the reflection direction of the target millimeter wave signal, the direction between the point where the target millimeter wave signal is obtained by reflection and the electronic device can be judged. The distance between the point of the target millimeter wave signal obtained by reflection and the electronic equipment can be judged according to the strength and the propagation time of the target millimeter wave signal. The material of the point of the target millimeter wave signal obtained by reflection can be judged according to the frequency domain data condition of the target millimeter wave signal.
It can be understood that the stronger the intensity of the target millimeter wave signal is, the closer the point where the target millimeter wave signal is reflected is to the electronic device; the weaker the strength of the target millimeter wave signal, the farther the point from the electronic device from which the target millimeter wave signal is reflected. For example, when a person faces an electronic device, the tip of the nose is closer to the electronic device than the ear, and therefore the intensity of the target millimeter wave signal reflected by the tip of the nose is stronger than the intensity of the target millimeter wave signal reflected by the ear.
The longer the propagation time of the target millimeter wave signal is, the farther the point reflecting the target millimeter wave signal is from the electronic device; the shorter the propagation time of the target millimeter wave signal is, the closer the point at which the target millimeter wave signal is reflected is to the electronic device. For example, when a person raises his head, the chin is closer to the electronic device than the eyes, and thus the intensity of the target millimeter wave signal reflected by the chin is stronger than the intensity of the target millimeter wave signal reflected by the eyes.
The frequency domain data of the target millimeter wave signal obtained by reflecting the third millimeter wave signal on different materials are different. Therefore, the material of the point where the target millimeter wave signal is reflected can be determined based on the frequency domain data condition of the target millimeter wave signal. For example, when a person wears glasses, the frequency data of the target millimeter wave signal obtained by reflecting a point on the glasses is a first frequency domain, the frequency data of the target millimeter wave signal obtained by reflecting a point on the skin of the person is a second frequency domain, and when the frequency domain data of the received target millimeter wave signal is the first frequency domain, the region where the target millimeter wave signal is located is the glasses, so that the position of the eyes in the head can be determined.
The head sub-regions may be various component regions in the head, for example, eyes, nose, mouth, ears, forehead, hair, etc.
Specifically, based on the reflection direction of the target millimeter wave, the direction between the point reflecting the target millimeter wave signal and the electronic device may be determined, and then based on the intensity or the propagation duration of the target millimeter wave signal, the distance between the point reflecting the target millimeter wave signal and the electronic device may be determined, so that the position of the point reflecting the millimeter wave signal in the head region of the target object may be identified, and then, in combination with the contour of the head region of the target object, the head sub-region where the point reflecting the target millimeter wave signal is located may be determined.
Classifying the target millimeter wave signals according to the head sub-regions to obtain the target millimeter wave signals included by each head sub-region; for the target millimeter wave signal included in each head sub-region, the feature information of each head sub-region may be acquired, and then based on the feature information of each head sub-region, the target feature information of the head of the target object may be determined. The feature information of the head sub-region includes, among others, the size of the head sub-region, the position of the head sub-region, the outline of the head sub-region, and so on.
For example, since the feature information acquired in the head region of the eye is the positions of the right eye and the right eye in the head region, the feature information acquired in the head region of the ear is the positions of the right ear and the right ear in the head region, and the feature information acquired in the head region of the cheek is the right cheek, the target feature information of the head of the target object can be specified as the positions of the right eye, the right ear, the right cheek, and the right eye, the right ear, and the right cheek in the head region.
In this embodiment, information included in each target millimeter wave signal is acquired; respectively determining a head sub-region corresponding to each target millimeter wave signal based on information included in each target millimeter wave signal; based on the head sub-regions corresponding to the target millimeter wave signals, the target characteristic information of the head of the target object can be determined more accurately, so that the target characteristic information can be matched with the reference characteristic information of the reference head posture more accurately, and the more accurate head posture of the target object is obtained.
In one embodiment, as shown in fig. 5, the method further includes:
The sample object refers to an object for acquiring reference feature information for referring to a head pose, and may be an object having a head such as a person or an animal, without being limited thereto. The reference head pose may include normal, head up, head down, left turn, right turn, left head up, right head up, left head down, right head down, etc. The reference head pose may be set according to the user's needs. The third millimeter-wave signal refers to a millimeter-wave signal transmitted to the sample object.
In step 504, a fourth millimeter wave signal corresponding to the third millimeter wave signal reflected by the sample object is received.
It is understood that the millimeter wave signal is reflected when it contacts an object. The electronic device transmits a third millimeter wave signal to the sample object, and the third millimeter wave signal is reflected when contacting the sample object, and the reflected third millimeter wave signal is a fourth millimeter wave signal.
A fourth millimeter wave signal corresponding to the third millimeter wave signal reflected by the sample object may be received by the millimeter wave transceiver.
And step 506, extracting reference characteristic information corresponding to the reference head posture based on the fourth millimeter wave signal, adjusting the reference head posture of the sample object, and returning to execute the step of transmitting the third millimeter wave signal to the sample object with the reference head posture until the number of times of adjusting the reference head posture of the sample object reaches a threshold value.
Specifically, the electronic device may first determine a reference millimeter wave signal corresponding to the head of the sample object from the fourth millimeter wave signal, and then extract reference feature information corresponding to a reference head posture based on the reference millimeter wave signal.
The reference millimeter wave signal refers to a fourth millimeter wave signal reflected by the head of the sample object. It can be understood that the fourth millimeter wave signal is reflected by the sample object, and therefore, when the millimeter wave transceiver receives the fourth millimeter wave signal, information such as a reflection direction, intensity, propagation duration, and the like included in the fourth millimeter wave signal can be acquired, and then reference feature information corresponding to the reference head posture can be acquired from the information included in the fourth millimeter wave signal. The reference characteristic information may include a size of the header, a position of the header, an outline of the header, positions and sizes of respective components in the header, a frequency domain data case, and the like.
After the electronic equipment extracts the reference feature information of one reference head posture of the sample object, the reference head posture of the sample object is adjusted, and then the third millimeter wave signal is transmitted to the sample object of the adjusted reference head posture, so that the reference feature information of the adjusted reference head posture is extracted again, and by analogy, the reference feature information of each reference head posture of the sample object can be obtained.
Further, the third millimeter wave signal may be transmitted to a head region of the sample object of the reference head posture, a fourth millimeter wave signal corresponding to the third millimeter wave signal reflected by the head region of the sample object is received, the reference feature information corresponding to the reference head posture is extracted based on the fourth millimeter wave signal, and the reference head posture of the sample object is adjusted, and the step of transmitting the third millimeter wave signal to the head region of the sample object of the reference head posture is returned to be performed until the number of times of adjusting the reference head posture of the sample object reaches the threshold. Only the third millimeter wave signal is transmitted to the head region of the sample object, and computer resources of the electronic device can be saved.
In the present embodiment, the third millimeter wave signal is transmitted to the sample object of the reference head posture; receiving a fourth millimeter wave signal corresponding to the third millimeter wave signal reflected by the sample object; and extracting reference characteristic information corresponding to the reference head gestures based on the fourth millimeter wave signal, adjusting the reference head gestures of the sample object, returning to the step of transmitting the third millimeter wave signal to the sample object with the reference head gestures, and obtaining the reference characteristic information of each reference head gesture until the number of times of adjusting the reference head gestures of the sample object reaches a threshold value, wherein the reference characteristic information can be used for being subsequently matched with the target characteristic information of the target object, so that the head gestures of the target object can be accurately obtained.
In one embodiment, the reference feature information of the acquired reference head pose is deconstructed and then preprocessed, the preprocessed reference feature information of the reference head pose is input into the head pose detection model, and the head pose detection model is trained, so that a more accurate head pose detection model can be acquired and trained.
Here, deconstruction processing refers to structure decomposition. The preprocessing may include filtering, point filling, opening, and the like. For example, by performing filtering processing on the reference feature information of the reference head pose through gaussian filtering, smooth filtering, or the like, the reference feature information of the reference head pose can be denoised, and the reference feature information of the reference head pose with lower noise can be acquired. For another example, a point cloud sequence may be generated based on the reference feature information of the reference head pose, and points are filled in the point cloud sequence, so as to perform signal enhancement on the reference feature information of the reference head pose. The point cloud sequence refers to a sequence of point cloud data components. The point cloud data is data in which information is recorded in the form of points, each of which includes three-dimensional coordinates, and may also include color information (RGB) or reflection Intensity information (Intensity).
For another example, the opening operation processing is performed on the reference feature information of the reference head pose, so that the signal enhancement is performed on the reference feature information of the reference head pose. The open operation refers to the expansion process after the corrosion process.
The electronic equipment inputs the target millimeter wave signal into the trained head posture detection model, and can output the more accurate target head posture of the target object.
It should be noted that the same training method may be used to obtain the gesture detection models of other parts of the target object, such as a hand gesture detection model, a foot gesture detection model, and the like. The hand gesture of the target object is detected through the hand gesture detection model, and the foot gesture of the target object is detected through the foot gesture detection model.
In one embodiment, a point cloud sequence is generated based on reference feature information of a reference head pose, and the point cloud sequence is input into a neural network for learning, so that a classifier of a more accurate head pose can be obtained. The neural network can adopt algorithms such as a convolutional neural network and a cyclic neural network to learn. The electronic device inputs the target millimeter wave signal into the classifier of the head posture, and can output more accurate head posture categories. The head gestures may be normal, head up, head down, left turn, right turn, left head up, right head up, left head down, right head down, etc.
In one embodiment, as shown in fig. 6, the electronic device performs step 602 to enable the millimeter wave transceiver. Step 604 is executed to transmit a third millimeter wave signal to the head region of the sample object with reference to the head pose. Step 606 is performed to receive a fourth millimeter wave signal corresponding to the third millimeter wave signal reflected by the head region of the sample object. Step 608 is executed to extract the reference feature information corresponding to the reference head pose.
Step 610 is executed to determine whether the adjustment times reaches a threshold. If the judgment is no, that is, the adjustment times do not reach the threshold value, step 612 is executed to adjust the reference head posture; returning to step 604, the third millimeter wave signal is transmitted to the head region of the sample object with reference to the head pose. When the determination is yes, that is, the number of times of adjustment reaches the threshold value, step 614 is executed to output a sample set of reference feature information of the reference head pose. Step 616 is performed to train the head pose detection model using the sample set.
In one embodiment, as shown in fig. 7, when the electronic device acquires the head gesture detection instruction, step 702 is executed to start the millimeter wave transceiver. Step 704 is performed to transmit the first millimeter wave signal to the head region of the target object. Step 706 is performed to receive a second millimeter wave signal corresponding to the first millimeter wave signal reflected by the head region of the target object. Step 708 is executed to input the second millimeter wave signal into the head posture detection model after training. Step 710 is executed to output a target head pose of the target object.
In one embodiment, applied to a driving vehicle scenario, the method further comprises: when the target head posture of the target object is in the preset head posture, counting the time length of the target head posture of the target object in the preset head posture; the vertical included angle of the head with the preset head posture is smaller than the preset included angle; and when the duration is greater than the duration threshold, generating warning information.
The vertical included angle of the head with the preset head posture refers to the included angle between the head and the vertical direction. And when the vertical included angle of the head of the preset head posture is smaller than the preset included angle, the preset head posture is in a head-lowering posture or a head-raising posture.
Traffic accidents caused by driving fatigue are usually much more serious than general traffic accidents, usually serious traffic accidents, and the death probability of drivers in the accidents is higher. According to related researches, the probability of successfully avoiding the traffic accident can reach about 90% by reminding a driver before the traffic accident occurs. Therefore, real-time detection and early warning are carried out on the fatigue degree of the driver, and the method has important significance for avoiding traffic accidents.
It can be understood that, when the target head pose of the target object is in the preset head pose, the sight line of the target object is not in front of the vehicle, and the duration of the target head pose of the target object in the preset head pose is counted; when the time length is larger than the time length threshold value, the head of the target object is in the preset head posture for a long time, namely the head is in the head-lowering posture or the head-raising posture for a long time, the fatigue degree of the target object is serious, the fatigue driving condition possibly exists, and the traffic accident is easy to happen, so that the warning information is generated to remind the target object, and the safety of driving the vehicle is improved. The warning information may be, but is not limited to, sound, vibration, smell, and the like.
In one embodiment, the method is applied to a teaching scene and comprises the following steps: acquiring each target head posture of a target object within a preset time length; counting the number of target head posture changes of a target object within a preset time length; the learning state of the target object is determined based on the number of times the target head pose changes.
The preset duration can be set according to the needs of the user.
It can be understood that, in the teaching scene, the target head pose of the target object within the preset time length changes less times, and the change frequency of the target head pose of the target object within the preset time length is slow, which indicates that the target object is in a focused learning state; the target head posture of the target object in the preset time length changes for a plurality of times, so that the change frequency of the target head posture of the target object in the preset time length is high, and the target object is not in the focused learning state.
Further, determining a learning state of the target object based on the number of times the target head pose changes includes: when the number of times of the change of the target head posture is smaller than the number threshold, the learning state of the target object is a first learning state; when the number of times of the target head posture change is greater than or equal to the number-of-times threshold, the learning state of the target object is a second learning state. The number threshold can be set according to the user requirement.
When the number of times of the change of the target head posture is smaller than the number threshold, the target object is shown to be concentrated in learning within the preset time length, and the learning state of the target object is a first learning state; when the number of times of the change of the target head posture is larger than or equal to the number threshold, the target object is not focused on learning within the preset time length, and the learning state of the target object is a second learning state. It will be appreciated that the target object is more focused on learning when in the first learning state than when in the second learning state. By detecting the target head posture of the target object, the learning state of the target object is judged, and the teaching effect can be assisted to be improved.
In one embodiment, the method further comprises: detecting the brightness of the ambient light; and when the brightness of the ambient light is lower than the preset brightness, executing the step of acquiring the head posture detection instruction.
Ambient light brightness refers to the brightness of light in the environment in which the electronic device is located. The brightness of the ambient light is lower than the preset brightness, which indicates that the electronic device is in a dark ambient light or in a dark environment. When the brightness of the ambient light is lower than the preset brightness, the step of obtaining the head posture detection instruction is executed, the target head posture of the target object is determined, the problem that the target object is affected by the ambient light brightness when a camera is used for shooting the target object is solved, and the target head posture of the target object can be accurately determined even in a dark or dark environment.
In another embodiment, the method for detecting the head pose may also be applied to a preset ambient light condition. The preset ambient light conditions may be set according to the user's needs. The head posture detection method avoids the situation that the head posture of the target object is detected by shooting the target object by the camera, thereby avoiding the influence of various ambient light conditions, and still can accurately detect the target head posture of the target object under various preset ambient light conditions.
It should be understood that, although the steps in the flowcharts of fig. 2, 4 to 7 are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2, 4 through 7 may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternatingly with other steps or at least some of the sub-steps or stages of other steps.
Fig. 8 is a block diagram of a head posture detection apparatus according to an embodiment. As shown in fig. 8, there is provided a head posture detection apparatus 800 including: a first millimeter wave signal transmitting module 802, a second millimeter wave signal receiving module 804, a target millimeter wave signal determining module 806, and a target head pose determining module 808, wherein:
the first millimeter wave signal transmitting module 802 is configured to obtain a head posture detection instruction, and transmit a first millimeter wave signal to a target object according to the head posture detection instruction.
The second millimeter wave signal receiving module 804 is configured to receive a second millimeter wave signal corresponding to the first millimeter wave signal reflected by the target object.
And a target millimeter wave signal determining module 806, configured to determine, from the second millimeter wave signal, a target millimeter wave signal corresponding to the head of the target object.
A target head pose determination module 808, configured to determine a target head pose of the target object based on the target millimeter wave signal.
The head posture detection device acquires a head posture detection instruction and transmits a first millimeter wave signal to a target object according to the head posture detection instruction; receiving a second millimeter wave signal corresponding to the first millimeter wave signal reflected by the target object; determining a target millimeter wave signal corresponding to the head of the target object from the second millimeter wave signal; the target head posture of the target object is determined based on the target millimeter wave signal, so that the influence of factors such as illumination change, background change and the like caused by shooting by a camera is avoided, and the target head posture of the target object can be determined more accurately.
In one embodiment, the target head pose determination module 808 is further configured to extract target feature information of the head of the target object from the target millimeter wave signal; and matching the reference characteristic information of the reference head posture with the target characteristic information, and taking the reference head posture matched with the reference characteristic information as the target head posture of the target object.
In one embodiment, the target head pose determination module 808 is further configured to obtain information included in each target millimeter wave signal; respectively determining a head sub-region corresponding to each target millimeter wave signal based on information included in each target millimeter wave signal; and determining target characteristic information of the head of the target object based on the head sub-region corresponding to each target millimeter wave signal.
In one embodiment, the apparatus 800 for detecting a head pose further includes an adjusting module, configured to transmit a third millimeter wave signal to the sample object with reference to the head pose; receiving a fourth millimeter wave signal corresponding to the third millimeter wave signal reflected by the sample object; and extracting reference characteristic information corresponding to the reference head posture based on the fourth millimeter wave signal, adjusting the reference head posture of the sample object, and returning to the step of transmitting the third millimeter wave signal to the sample object with the reference head posture until the number of times of adjusting the reference head posture of the sample object reaches a threshold value.
In one embodiment, the head pose detection apparatus 800 further includes a driving vehicle scene module, configured to count a duration of the target head pose of the target object being in the preset head pose when the target head pose of the target object is in the preset head pose; the vertical included angle of the head with the preset head posture is smaller than the preset included angle; and when the duration is greater than the duration threshold, generating warning information.
In one embodiment, the head pose detection apparatus 800 further includes a teaching scene module, configured to obtain each target head pose of the target object within a preset time length; counting the number of target head posture changes of a target object within a preset time length; the learning state of the target object is determined based on the number of times the target head pose changes.
In one embodiment, the teaching scene module is further configured to, when the number of times of the change of the target head pose is smaller than a number threshold, set the learning state of the target object to be a first learning state; when the number of times of the target head posture change is greater than or equal to the number-of-times threshold, the learning state of the target object is a second learning state.
In one embodiment, the head posture detecting apparatus 800 further includes an ambient light detecting module for detecting the brightness of ambient light; and when the brightness of the ambient light is lower than the preset brightness, executing the step of acquiring the head posture detection instruction.
The division of each module in the head posture detection device is only used for illustration, and in other embodiments, the head posture detection device may be divided into different modules as needed to complete all or part of the functions of the head posture detection device.
For specific definition of the head pose detection device, reference may be made to the above definition of the head pose detection method, which is not described herein again. The modules in the head posture detection device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
Fig. 9 is a schematic diagram of an internal structure of an electronic device in one embodiment. As shown in fig. 9, the electronic device includes a processor and a memory connected by a system bus. Wherein, the processor is used for providing calculation and control capability and supporting the operation of the whole electronic equipment. The memory may include a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The computer program can be executed by a processor for implementing a method for detecting a head pose provided in the following embodiments. The internal memory provides a cached execution environment for the operating system computer programs in the non-volatile storage medium. The electronic device may be any terminal device such as a mobile phone, a tablet computer, a PDA (Personal Digital Assistant), a Point of Sales (POS), a vehicle-mounted computer, and a wearable device.
The respective modules in the head pose detection apparatus provided in the embodiments of the present application may be implemented in the form of a computer program. The computer program may be run on a terminal or a server. Program modules constituted by such computer programs may be stored on the memory of the electronic device. Which when executed by a processor, performs the steps of the method described in the embodiments of the present application.
The embodiment of the application also provides a computer readable storage medium. One or more non-transitory computer-readable storage media containing computer-executable instructions that, when executed by one or more processors, cause the processors to perform the steps of a method of detecting head gestures.
A computer program product containing instructions which, when run on a computer, cause the computer to perform a method of detecting head gestures.
Any reference to memory, storage, database, or other medium used herein may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM), which acts as external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), Enhanced SDRAM (ESDRAM), synchronous Link (Synchlink) DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and bus dynamic RAM (RDRAM).
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (11)
1. A method for detecting a head posture, comprising:
acquiring a head posture detection instruction, and transmitting a first millimeter wave signal to a target object according to the head posture detection instruction;
receiving a second millimeter wave signal corresponding to the first millimeter wave signal reflected by the target object;
determining a target millimeter wave signal corresponding to the head of the target object from the second millimeter wave signal;
determining a target head pose of the target object based on the target millimeter wave signal.
2. The method of claim 1, wherein said determining a target head pose of the target object based on the target millimeter wave signals comprises:
extracting target feature information of a head of the target object from the target millimeter wave signal;
and matching the reference characteristic information of the reference head gesture with the target characteristic information, and taking the reference head gesture matched with the reference characteristic information as the target head gesture of the target object.
3. The method according to claim 2, wherein said extracting target feature information of the head of the target object from the target millimeter wave signal comprises:
acquiring information included in each target millimeter wave signal;
respectively determining a head sub-region corresponding to each target millimeter wave signal based on information included in each target millimeter wave signal;
and determining target characteristic information of the head of the target object based on the head sub-region corresponding to each target millimeter wave signal.
4. The method of claim 2, further comprising:
transmitting a third millimeter wave signal to the sample object of the reference head pose;
receiving a fourth millimeter wave signal corresponding to the third millimeter wave signal reflected by the sample object;
and extracting reference characteristic information corresponding to the reference head posture based on the fourth millimeter wave signal, adjusting the reference head posture of the sample object, and returning to execute the step of transmitting the third millimeter wave signal to the sample object with the reference head posture until the number of times of adjusting the reference head posture of the sample object reaches a threshold value.
5. The method of claim 1, applied to a driving vehicle scenario, further comprising:
when the target head posture of the target object is in a preset head posture, counting the time length of the target head posture of the target object in the preset head posture; the vertical included angle of the head with the preset head posture is smaller than a preset included angle;
and when the duration is greater than the duration threshold, generating warning information.
6. The method of claim 1, applied to a teaching scene, comprising:
acquiring each target head posture of the target object within a preset time length;
counting the number of target head posture changes of the target object within a preset time length;
determining a learning state of the target object based on the number of times the target head pose changes.
7. The method of claim 6, wherein determining the learning state of the target object based on the number of changes in the target head pose comprises:
when the number of times of the target head posture change is smaller than a number threshold, the learning state of the target object is a first learning state;
when the number of times of the target head pose change is greater than or equal to a number threshold, the learning state of the target object is a second learning state.
8. The method according to any one of claims 1 to 7, further comprising:
detecting the brightness of the ambient light;
and when the brightness of the ambient light is lower than the preset brightness, executing the step of obtaining the head posture detection instruction.
9. A head posture detection device, comprising:
the first millimeter wave signal transmitting module is used for acquiring a head posture detection instruction and transmitting a first millimeter wave signal to a target object according to the head posture detection instruction;
the second millimeter wave signal receiving module is used for receiving a second millimeter wave signal which is reflected by the target object and corresponds to the first millimeter wave signal;
a target millimeter wave signal determination module, configured to determine a target millimeter wave signal corresponding to the head of the target object from the second millimeter wave signal;
a target head pose determination module to determine a target head pose of the target object based on the target millimeter wave signal.
10. An electronic device comprising a memory and a processor, the memory having stored therein a computer program, characterized in that the computer program, when executed by the processor, causes the processor to carry out the steps of the method of detecting a head pose as claimed in any one of claims 1 to 8.
11. 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 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010235978.1A CN113456058A (en) | 2020-03-30 | 2020-03-30 | Head posture detection method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010235978.1A CN113456058A (en) | 2020-03-30 | 2020-03-30 | Head posture detection method and device, electronic equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113456058A true CN113456058A (en) | 2021-10-01 |
Family
ID=77864809
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010235978.1A Withdrawn CN113456058A (en) | 2020-03-30 | 2020-03-30 | Head posture detection method and device, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113456058A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106228293A (en) * | 2016-07-18 | 2016-12-14 | 重庆中科云丛科技有限公司 | teaching evaluation method and system |
| CN107665330A (en) * | 2016-07-29 | 2018-02-06 | 本田技研工业株式会社 | Detect dispersion attention and the downward vertically system and method for head pose |
| CN108021902A (en) * | 2017-12-19 | 2018-05-11 | 珠海瞳印科技有限公司 | Head pose recognition methods, head pose identification device and storage medium |
| CN109875568A (en) * | 2019-03-08 | 2019-06-14 | 北京联合大学 | A kind of head pose detection method for fatigue driving detection |
| CN110020633A (en) * | 2019-04-12 | 2019-07-16 | 腾讯科技（深圳）有限公司 | Training method, image-recognizing method and the device of gesture recognition model |
| CN110287755A (en) * | 2018-03-19 | 2019-09-27 | 广东欧珀移动通信有限公司 | Information processing method and device, electronic equipment, computer readable storage medium |
| CN110450784A (en) * | 2019-07-30 | 2019-11-15 | 深圳普捷利科技有限公司 | A kind of driver status monitoring method and system based on fmcw radar |
-
2020
- 2020-03-30 CN CN202010235978.1A patent/CN113456058A/en not_active Withdrawn
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106228293A (en) * | 2016-07-18 | 2016-12-14 | 重庆中科云丛科技有限公司 | teaching evaluation method and system |
| CN107665330A (en) * | 2016-07-29 | 2018-02-06 | 本田技研工业株式会社 | Detect dispersion attention and the downward vertically system and method for head pose |
| CN108021902A (en) * | 2017-12-19 | 2018-05-11 | 珠海瞳印科技有限公司 | Head pose recognition methods, head pose identification device and storage medium |
| CN110287755A (en) * | 2018-03-19 | 2019-09-27 | 广东欧珀移动通信有限公司 | Information processing method and device, electronic equipment, computer readable storage medium |
| CN109875568A (en) * | 2019-03-08 | 2019-06-14 | 北京联合大学 | A kind of head pose detection method for fatigue driving detection |
| CN110020633A (en) * | 2019-04-12 | 2019-07-16 | 腾讯科技（深圳）有限公司 | Training method, image-recognizing method and the device of gesture recognition model |
| CN110450784A (en) * | 2019-07-30 | 2019-11-15 | 深圳普捷利科技有限公司 | A kind of driver status monitoring method and system based on fmcw radar |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11182592B2 (en) | Target object recognition method and apparatus, storage medium, and electronic device | |
| US11392131B2 (en) | Method for determining driving policy | |
| CN106952303B (en) | Vehicle distance detection method, device and system | |
| US10318831B2 (en) | Method and system for monitoring the status of the driver of a vehicle | |
| US10372972B2 (en) | Face detection apparatus, face detection method, and program | |
| CN105512632B (en) | Biopsy method and device | |
| EP3478557A1 (en) | System and method for driver monitoring | |
| US11527077B2 (en) | Advanced driver assist system, method of calibrating the same, and method of detecting object in the same | |
| EP2234086A1 (en) | Vehicle periphery monitoring device, vehicle, vehicle periphery monitoring program, and vehicle periphery monitoring method | |
| CN106919908B (en) | Obstacle identification method and device, computer equipment and readable medium | |
| US10655978B2 (en) | Controlling an autonomous vehicle based on passenger behavior | |
| US11087224B2 (en) | Out-of-vehicle communication device, out-of-vehicle communication method, information processing device, and computer readable medium | |
| CN111434553B (en) | Brake system, method and device, and fatigue driving model training method and device | |
| CN111598065B (en) | Depth image acquisition method, living body identification method, apparatus, circuit, and medium | |
| KR101914362B1 (en) | Warning system and method based on analysis integrating internal and external situation in vehicle | |
| US10945888B2 (en) | Intelligent blind guide method and apparatus | |
| WO2020243968A1 (en) | Facial recognition apparatus and method, and electronic device | |
| US7599546B2 (en) | Image information processing system, image information processing method, image information processing program, and automobile | |
| CN111582077A (en) | Safety belt wearing detection method and device based on artificial intelligence software technology | |
| KR20220117218A (en) | Information processing apparatus, information processing system, information processing program and information processing method | |
| CN114119955A (en) | Method and device for detecting potential dangerous target | |
| CN210166794U (en) | Face recognition device and electronic equipment | |
| EP3553556A1 (en) | Light modulating lidar apparatus | |
| CN113456058A (en) | Head posture detection method and device, electronic equipment and readable storage medium | |
| KR101680833B1 (en) | Apparatus and method for detecting pedestrian and alert |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20211001 |
|
| WW01 | Invention patent application withdrawn after publication |