CN112061065A - In-vehicle behavior recognition alarm method, device, electronic device and storage medium - Google Patents
In-vehicle behavior recognition alarm method, device, electronic device and storage medium Download PDFInfo
- Publication number
- CN112061065A CN112061065A CN202010732408.3A CN202010732408A CN112061065A CN 112061065 A CN112061065 A CN 112061065A CN 202010732408 A CN202010732408 A CN 202010732408A CN 112061065 A CN112061065 A CN 112061065A
- Authority
- CN
- China
- Prior art keywords
- information
- alarm
- vehicle
- image
- victim
- 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.)
- Granted
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R21/00—Arrangements or fittings on vehicles for protecting or preventing injuries to occupants or pedestrians in case of accidents or other traffic risks
- B60R21/01—Electrical circuits for triggering passive safety arrangements, e.g. airbags, safety belt tighteners, in case of vehicle accidents or impending vehicle accidents
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R21/00—Arrangements or fittings on vehicles for protecting or preventing injuries to occupants or pedestrians in case of accidents or other traffic risks
- B60R21/01—Electrical circuits for triggering passive safety arrangements, e.g. airbags, safety belt tighteners, in case of vehicle accidents or impending vehicle accidents
- B60R21/015—Electrical circuits for triggering passive safety arrangements, e.g. airbags, safety belt tighteners, in case of vehicle accidents or impending vehicle accidents including means for detecting the presence or position of passengers, passenger seats or child seats, and the related safety parameters therefor, e.g. speed or timing of airbag inflation in relation to occupant position or seat belt use
- B60R21/01512—Passenger detection systems
- B60R21/0153—Passenger detection systems using field detection presence sensors
- B60R21/01538—Passenger detection systems using field detection presence sensors for image processing, e.g. cameras or sensor arrays
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R21/00—Arrangements or fittings on vehicles for protecting or preventing injuries to occupants or pedestrians in case of accidents or other traffic risks
- B60R21/01—Electrical circuits for triggering passive safety arrangements, e.g. airbags, safety belt tighteners, in case of vehicle accidents or impending vehicle accidents
- B60R21/015—Electrical circuits for triggering passive safety arrangements, e.g. airbags, safety belt tighteners, in case of vehicle accidents or impending vehicle accidents including means for detecting the presence or position of passengers, passenger seats or child seats, and the related safety parameters therefor, e.g. speed or timing of airbag inflation in relation to occupant position or seat belt use
- B60R21/01512—Passenger detection systems
- B60R21/01552—Passenger detection systems detecting position of specific human body parts, e.g. face, eyes or hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/59—Context or environment of the image inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Alarm Systems (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
One or more embodiments of the present specification provide an in-vehicle behavior recognition alarm method, device, electronic device, and storage medium, including: acquiring video and audio information in a vehicle in real time; comparing the video information according to a preset database to judge whether illegal behaviors are happening in the vehicle; if yes, generating original alarm information, continuously acquiring the video information in the vehicle, identifying the detail information of the video information, and generating updating alarm information containing the detail information when the detail information is identified in the video information; and executing alarm operation and outputting updated alarm information. One or more embodiments of the present disclosure may acquire the audio-visual information at the first time, determine that an illegal action occurs, rapidly generate alarm information and alarm, and alarm at the first time when the illegal action occurs, thereby saving alarm time, protecting safety of people in a vehicle, saving law enforcement resources of law enforcement agencies, deterring illegal persons, and reducing the probability of social illegal crimes.
Description
Technical Field
One or more embodiments of the present disclosure relate to the field of in-vehicle monitoring technologies, and in particular, to an in-vehicle behavior recognition alarm method, device, electronic device, and storage medium.
Background
Along with the increasing of living standard of people, the use of automobiles in the life of people is more and more popular, the number of household automobiles is more and more, and the automobiles bring great convenience to the life of people. However, in recent years, with the increasing popularization of private cars and network appointment cars, illegal criminal behaviors occurring in cars are more and more, however, because the environment in a car is a relatively closed environment, ordinary pedestrians outside the car generally cannot concern the situation in the car, and meanwhile, people generally perform sun-screening or concealing treatment on a car window, so that people outside the car are more difficult to observe the specific situation in the car, and in addition, the tightness of modern cars is better and better, so that the sound is more difficult to transmit to the outside of the car. Which instead provides convenience for criminal information in the vehicle. The interior of the car has become a serious disaster area of illegal crimes.
At present, vehicles generally record videos of conditions in the vehicles through a camera, and the video data is only used as evidence when an accident happens afterwards. And cannot provide any help to the persons in the vehicle when the illegal criminal act is happening.
Disclosure of Invention
In view of the above, an object of one or more embodiments of the present disclosure is to provide an in-vehicle behavior recognition alarm method, device, electronic device, and storage medium.
In view of the above, one or more embodiments of the present specification provide an in-vehicle behavior recognition alarm method, including:
acquiring video and audio information in a vehicle in real time;
comparing the video information according to a preset database, and judging whether illegal behaviors are occurring in the vehicle;
if yes, generating original alarm information, continuously acquiring the audio-video information in the vehicle, identifying the detail information of the audio-video information, and generating updated alarm information containing the detail information when the detail information is identified in the audio-video information;
and executing alarm operation and outputting the updated alarm information.
In some embodiments, the audiovisual information comprises: image information;
the comparing the video information according to a preset database comprises:
comparing the illegal similarity of the image information according to an illegal image in a preset database;
if the comparison of the similarity of the illegal behaviors is passed, determining that the illegal behaviors are happening in the vehicle;
if the illegal similarity comparison fails, carrying out abnormal posture similarity comparison on the image information according to an abnormal posture image in a preset database;
and if the abnormal posture similarity comparison fails, determining that illegal behaviors do not occur in the vehicle.
In some embodiments, the audiovisual information comprises: sound information;
the comparing of the abnormal posture similarity of the image information according to the abnormal posture image in the preset data bank further comprises:
if the abnormal posture similarity comparison is passed, acquiring the sound information in the vehicle, and comparing the sound similarity of the sound information according to the damaged sound in a preset database;
and if the sound similarity comparison is passed, determining that the illegal action is occurring in the vehicle.
In some embodiments, the obtaining the audiovisual information in the vehicle in real time includes:
and determining the direction of a sound source according to the sound information, and adjusting the direction of a lens used for acquiring the image information according to the direction of the sound source.
In some embodiments, the obtaining the audio-visual information in the vehicle in real time further includes:
determining brightness information in the vehicle, and judging whether the brightness information exceeds a conversion threshold value;
if so, switching the lens for acquiring the image information in the vehicle to a normal lens;
and if not, switching the lens into an infrared night vision lens.
In some embodiments, when performing the matching of the image information, performing edge extraction on the image information includes:
carrying out gray level processing on the image information to generate a gray level image, removing impurities from the gray level image by a median filtering method, calculating a gradient image of the gray level image after removing the impurities by a Sobel operator, calculating a binary image of the gradient image according to a maximum inter-class variance method, carrying out multi-iteration expansion corrosion processing and region block filling processing on the binary image to obtain a comparison contour of the image information, and carrying out comparison with an image in a preset database according to the comparison contour.
In some embodiments, after the performing the alarm operation, the method further includes:
acquiring face image information of people in the vehicle, and determining face image information of a victim and face image information of a victim in the face image information according to the audio-video information;
determining the identity of a victim according to the face image information of the victim, determining the face image information of a victim related person and related persons corresponding to the victim related person according to the identity of the victim, and judging whether the face image information of the victim belongs to the face image information of the related persons;
if not, determining the communication information of the relevant personnel of the victim, and carrying out auxiliary help seeking according to the communication information.
In some embodiments, before performing the alarm operation, the method further includes:
carrying out wearable equipment detection;
when the wearable device is detected, sending a consultation message to the wearable device, and enabling the wearable device to perform alarm confirmation operation according to the consultation message;
and receiving a confirmation message sent by the wearable device, and determining whether to execute an alarm operation according to the confirmation message.
In some embodiments, the identifying the detail information of the audiovisual information includes:
determining a victim image according to the audio-visual information, and performing local wound image recognition and victim gesture recognition on the victim image;
generating the detail information according to the identified wound image information and/or victim pose information when the local wound image identification and/or the victim pose identification is passed.
In some embodiments, the identifying the detail information of the audiovisual information includes:
determining an image of a harmful person according to the audio and video information, and carrying out weapon identification on the image of the harmful person;
and when the weapon identification passes, generating the detail information according to the identified weapon information.
In some embodiments, the generating update alert information containing the detail information includes:
and determining a preset importing position in the original alarm information, importing the detail information at the preset importing position, and integrating to generate the updated alarm information.
In some embodiments, the performing an alert operation comprises:
when detecting that the current vehicle cannot finish the alarm operation, detecting whether the surrounding vehicles have auxiliary vehicles or not;
if so, sending an assistance alarm instruction to the assistance vehicle, and enabling the assistance vehicle to perform alarm operation according to the assistance alarm instruction.
Based on the same concept, one or more embodiments of the present specification further provide an in-vehicle behavior recognition alarm device, including:
the acquisition module acquires the audio-video information in the vehicle in real time;
the judgment module is used for comparing the audio-video information according to a preset database and judging whether illegal behaviors are occurring in the vehicle or not;
if yes, generating original alarm information, continuously acquiring the audio-video information in the vehicle, identifying the detail information of the audio-video information, and generating updated alarm information containing the detail information when the detail information is identified in the audio-video information;
and the alarm module executes alarm operation and outputs the updated alarm information.
Based on the same concept, one or more embodiments of the present specification further provide an electronic device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor implements the method according to any one of the above when executing the program.
Based on the same concept, one or more embodiments of the present specification also provide a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the method of any one of the above.
As can be seen from the above description, one or more embodiments of the present specification provide an in-vehicle behavior recognition alarm method, device, electronic device, and storage medium, including: acquiring video and audio information in a vehicle in real time; comparing the video information according to a preset database to judge whether illegal behaviors are happening in the vehicle; if yes, generating original alarm information, continuously acquiring the video information in the vehicle, identifying the detail information of the video information, and generating updating alarm information containing the detail information when the detail information is identified in the video information; and executing alarm operation and outputting updated alarm information. One or more embodiments of the present disclosure may acquire the audio-visual information at the first time, determine that an illegal action occurs, rapidly generate alarm information and alarm, and alarm at the first time when the illegal action occurs, thereby saving alarm time, protecting safety of people in a vehicle, saving law enforcement resources of law enforcement agencies, deterring illegal persons, and reducing the probability of social illegal crimes.
Drawings
In order to more clearly illustrate one or more embodiments or prior art solutions of the present specification, the drawings that are needed in the description of the embodiments or prior art will be briefly described below, and it is obvious that the drawings in the following description are only one or more embodiments of the present specification, and that other drawings may be obtained by those skilled in the art without inventive effort from these drawings.
Fig. 1 is a schematic flow chart of an in-vehicle behavior recognition alarm method according to one or more embodiments of the present disclosure;
fig. 2 is a schematic structural diagram of an in-vehicle behavior recognition alarm device according to one or more embodiments of the present disclosure;
fig. 3 is a schematic structural diagram of an electronic device according to one or more embodiments of the present disclosure.
Detailed Description
To make the objects, technical solutions and advantages of the present specification more apparent, the present specification is further described in detail below with reference to the accompanying drawings in combination with specific embodiments.
It should be noted that technical terms or scientific terms used in the embodiments of the present specification should have a general meaning as understood by those having ordinary skill in the art to which the present disclosure belongs, unless otherwise defined. The use of "first," "second," and similar terms in this disclosure is not intended to indicate any order, quantity, or importance, but rather is used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that a element, article, or method step that precedes the word, and includes the element, article, or method step that follows the word, and equivalents thereof, does not exclude other elements, articles, or method steps. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", and the like are used merely to indicate relative positional relationships, and when the absolute position of the object being described is changed, the relative positional relationships may also be changed accordingly.
As described in the background section, the conventional identification camera device mounted on a vehicle generally records the conditions outside the vehicle and the driving conditions of the vehicle, such as a drive recorder, and only provides video and audio recording, but does not give an alarm in real time when an accident occurs, which is mainly used for recording the conditions outside the vehicle, such as the drive recorder, and even if an accident occurs, the passenger in the vehicle is difficult to be harmed, the alarm can be completely sent to the passenger in the vehicle, and compared with a machine, a person can more easily express things clearly. However, for the illegal criminal act in the vehicle, the current car data recorder and the like are difficult to capture the specific picture, and meanwhile, because the personnel in the vehicle is probably in imminent danger, the personnel in the vehicle cannot give an alarm in time, so that the maintenance and treatment are delayed, and the delay is fatal to the personnel in the vehicle.
In combination with the above practical situations, one or more embodiments of the present specification provide an in-vehicle behavior recognition alarm scheme, which can acquire audio-video information at the first time, determine whether an illegal behavior such as binding, duress, etc. occurs, then quickly generate alarm information and quickly alarm, and can alarm and notify law enforcement agencies at the first time when the illegal behavior occurs, thereby saving alarm time, protecting personal and property safety of people in the vehicle, saving law enforcement resources of law enforcement agencies, deterring illegal persons, and reducing the probability of social illegal crimes.
Referring to fig. 1, a schematic flow chart of an in-vehicle behavior recognition alarm method according to an embodiment of the present specification specifically includes the following steps:
The step aims to acquire the information in the vehicle in real time. The video information refers to video image information, sound information, and the like in the vehicle. The video information and the image information can be acquired by a camera device such as a camera and a high-speed camera arranged at any position in the vehicle, and in order to acquire the video image information more comprehensively, the camera device can be arranged in front of each seat, enables a lens to face the seat and can shoot all head features of people, or similar positions on the inner side of the vehicle roof. The sound information can be collected through the sound collection device arranged at any position in the vehicle, and the sound information can be obtained by the sound collection device at any position in the vehicle clearly.
The step aims to compare the collected audio and video information and judge whether illegal behaviors occur. The preset database stores standard image information of various illegal behaviors, standard audio tracks of various distress sounds and other information. Comparing the captured current video information with the information to judge whether various illegal behaviors are met, wherein the illegal behaviors can be illegal behaviors which can be carried out on people in the vehicle in a way of binding, coercing, personal injury and the like.
Then, the comparison method can be image comparison, voice comparison or the combination of the two. For example: in the image comparison, judging according to the posture, position, expression and other information of the human body identified in the two compared images, and when the similarity is higher than a certain threshold value, determining that the currently acquired image is illegal; in the voice comparison, whether the voice is the call sound with continuous contact is judged according to the obtained voice, when the duration time exceeds a threshold value, the current illegal behavior in the vehicle is considered to be happening, or specific voice information is obtained, if the behaviors of binding up, coercion and the like just happen, a victim generally asks for help, and the shout is' the binding up is cheered! "," robbing "is a lot! "etc., recognizing that an illegal action is currently occurring in the vehicle according to the acquired specific sounds, etc. Simultaneously, can also distinguish normal behaviors such as the alarm between children, the game between the adult, because the normal behaviors such as alarm and game are similar with the image of behaviors such as kidnapping on the image, but sound, tone etc. that personnel sent in the car all can have obvious difference, and then can get rid of this type of behavior outside, promote the rate of accuracy of reporting to the police.
And 103, if yes, generating original alarm information, continuously acquiring the audio-video information in the vehicle, identifying the detail information of the audio-video information, and generating updated alarm information containing the detail information when the detail information is identified in the audio-video information.
The method comprises the steps of continuously identifying the audio-video information after generating original alarm information, and adjusting the alarm information according to the identified detail information. The detail information refers to information that can reflect the severity of the illegal action and is contained in the video information, for example: whether the victim is injured, the injury degree, whether the victim is covered by the mouth and the nose, whether the victim holds a weapon or not, and the like, the audio-visual information is continuously acquired, and the detail information is identified, so as to further determine the hazard level, for example: determining a victim and a victim in the vehicle through information such as the posture, the expression and the like of the vehicle, comparing local wound images in the body image range of the victim, and judging whether the victim is injured; or judging whether the harmer holds a weapon or not through image comparison; or judging whether the victim is covered or blocked the mouth part, and the like; or identifying the expression of the victim, etc.
Then, the original alarm information generally only includes the established information such as the current location information of the vehicle, and the original alarm information can be sound information or text information; the updated alarm information is information which can represent the severity of illegal behaviors, such as brief in-vehicle condition information and the like, inserted on the basis of the original alarm information. The in-vehicle situation information is corresponding voice information generated according to the further identified detail information, for example: if the person who is harmed holds the gun, repeated high-volume reminding is carried out at the front section of the alarm information; if the victim is injured, the injury of the victim is indicated in the alarm information, and the calling of first aid is recommended; and if the expression of the victim is painful, corresponding emphasis is performed in the alarm information.
And 104, executing alarm operation and outputting the updated alarm information.
The step aims to give an alarm and output edited alarm information. The alarm operation is to make an alarm call to perform voice alarm or log in a public security alarm network platform to perform character alarm, and the like. After the alarm is switched on, the generated updated alarm information is directly played. And the edited updated alarm text information is directly transmitted to on-duty law enforcement officers and the like on the public security alarm online platform. Meanwhile, the alarming operation may be continuous because the process of the illegal activity is not generally finished immediately after the illegal activity is recognized for the first time, and thus continuous alarming may be performed.
By applying one or more embodiments of the present specification, an in-vehicle behavior recognition alarm method is provided, including: acquiring video and audio information in a vehicle in real time; comparing the video information according to a preset database to judge whether illegal behaviors are happening in the vehicle; if yes, generating original alarm information, continuously acquiring the video information in the vehicle, identifying the detail information of the video information, and generating updating alarm information containing the detail information when the detail information is identified in the video information; and executing alarm operation and outputting updated alarm information. One or more embodiments of the present disclosure may acquire the audio-visual information at the first time, determine that an illegal action occurs, rapidly generate alarm information and alarm, and alarm at the first time when the illegal action occurs, thereby saving alarm time, protecting safety of people in a vehicle, saving law enforcement resources of law enforcement agencies, deterring illegal persons, and reducing the probability of social illegal crimes.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
In an alternative embodiment of the present description, the false alarm probability is reduced in order to more accurately determine whether an illegal action is occurring. The video information comprises: image information;
the comparing the video information according to a preset database comprises:
comparing the illegal similarity of the image information according to an illegal image in a preset database;
if the comparison of the similarity of the illegal behaviors is passed, determining that the illegal behaviors are happening in the vehicle;
if the illegal similarity comparison fails, carrying out abnormal posture similarity comparison on the image information according to an abnormal posture image in a preset database;
and if the abnormal posture similarity comparison fails, determining that illegal behaviors do not occur in the vehicle.
In this embodiment, the images are compared first, if the images are directly matched with the standard images of the illegal activities or the similarity is very high, the illegal activities are considered to be occurring, when the similarity between the images and the illegal activities is slightly low, the images are further compared with the standard images in the abnormal posture, whether the user is in the abnormal posture or not is judged, and if the similarity does not exceed the threshold and does not meet the comparison condition, the illegal activities are considered to not occur in the vehicle.
The preset database stores a large amount of standard comparison image data when illegal behaviors occur in the vehicle, a large amount of image data of abnormal postures of human bodies in the vehicle and the like in advance, and the in-vehicle images collected in real time are compared through the data.
In an alternative embodiment of the present description, the false positive probability is reduced in order to further determine whether an illegal activity is occurring. The video information comprises: sound information;
the comparing of the abnormal posture similarity of the image information according to the abnormal posture image in the preset data bank further comprises:
if the abnormal posture similarity comparison is passed, acquiring the sound information in the vehicle, and comparing the sound similarity of the sound information according to the damaged sound in a preset database;
and if the sound similarity comparison is passed, determining that the illegal action is occurring in the vehicle.
In this embodiment, whether the user is in an abnormal posture is further determined, if the similarity exceeds the threshold value and meets the comparison condition, the in-vehicle sound is collected and compared with various audio file contents stored in the database when the victim is victimized, and similar pictures caused by children's annoyance and adult's playfulness are eliminated through sound, so that the misjudgment rate is reduced.
The preset database stores a large amount of standard comparison image data when illegal behaviors occur in the vehicle, a large amount of image data of abnormal postures of human bodies in the vehicle, a large amount of sound data when victims are infringed, and the like in advance, and the in-vehicle sound collected in real time is compared through the data.
In an alternative embodiment of the present specification, the image information at the position where the sound is being emitted is acquired accurately. The real-time audio-visual information of obtaining in the vehicle includes:
and determining the direction of a sound source according to the sound information, and adjusting the direction of a lens used for acquiring the image information according to the direction of the sound source.
When an illegal act is happening in the vehicle, the two acts generally contact with each other and make a sound, so that the illegal act can be better observed or recorded by carrying out image tracking through the sound. After that, the lens that acquires the image information may be a lens of a high-speed camera, a lens of a video camera, or the like, of an image pickup apparatus that can acquire a moving image or a still image.
In an alternative embodiment of the present description, the effect of the in-vehicle brightness on the acquisition of the in-vehicle image is prevented. The real-time audio-visual information of acquireing in the vehicle still includes:
determining brightness information in the vehicle, and judging whether the brightness information exceeds a conversion threshold value;
if so, switching the lens for acquiring the image information in the vehicle to a normal lens;
and if not, switching the lens into an infrared night vision lens.
The conversion threshold value is a limit brightness value for switching the lens, the normal lens is a lens used when the brightness is enough in a normal bright state, and the infrared night vision lens is a lens used when the brightness is insufficient in a dark state.
In an alternative embodiment of the present specification, in order to accurately determine the human body contour in the image information, the human body form is accurately determined. When the image information is aligned, performing edge extraction on the image information, including:
carrying out gray level processing on the image information to generate a gray level image, removing impurities from the gray level image by a median filtering method, calculating a gradient image of the gray level image after removing the impurities by a Sobel operator, calculating a binary image of the gradient image according to a maximum inter-class variance method, carrying out multi-iteration expansion corrosion processing and region block filling processing on the binary image to obtain a comparison contour of the image information, and carrying out comparison with an image in a preset database according to the comparison contour.
There are many image extraction methods or algorithms, such as: three algorithms for image feature extraction: HOG (Histogram of Oriented Gradient) feature extraction algorithm, LBP (Local Binary Pattern) feature extraction algorithm, Haar feature extraction algorithm, and the like. In the specific embodiment, graying processing is performed on image information, median filtering operation is performed on a grayscale image to remove fine impurities on the image, then gradient images are respectively obtained through Sobel (Sobel) gradient operators in the x direction and the y direction, the gradient images are converted into standard types, OTSU (maximum inter-class variance) binarization operation is performed on the converted gradient images in the x direction and the y direction to obtain binary images, and the two binary images are subjected to and operation according to corresponding pixel positions. And finally, performing repeated expansion corrosion operation and small-area block filling operation (performing contour search and filling by using a findContours (contour tracking) and drawContours (contour filling) interface) on the binary image to obtain a human body comparison contour in the image information. And comparing the image in the preset database according to the comparison outline.
In an alternative embodiment of the present specification, in order to notify relatives (relatives, colleagues, friends, etc.) of a victim in time while alarming, and not to notify them when it is found that an acquaintance has worked. After the alarm operation is executed, the method further comprises the following steps:
acquiring face image information of people in the vehicle, and determining face image information of a victim and face image information of a victim in the face image information according to the audio-video information;
determining the identity of a victim according to the face image information of the victim, determining the face image information of a victim related person and related persons corresponding to the victim related person according to the identity of the victim, and judging whether the face image information of the victim belongs to the face image information of the related persons;
if not, determining the communication information of the relevant personnel of the victim, and carrying out auxiliary help seeking according to the communication information.
The embodiment is to send out auxiliary help seeking to the emergency contact person of the victim in time when the victim is injured, and to not remind the offender to seek help when the acquaintance is found to crime.
The method comprises the steps of obtaining image information of a face of a victim, and determining the face image information of the victim according to the image information of the face of the victim, wherein the image information of the face of the victim can be determined according to the posture, the expression, the language and the like of people in the vehicle reflected by the image information of the video and the audio, and then the image information of the face of the victim and the face image information of the victim can be determined according to the corresponding relation between the face image information. Then, the identity of the victim and the face image information of the associated person which is input in advance are determined according to the face image information of the victim, whether the face image information of the victim is matched with the face image information of the associated person or not is judged, if the face image information of the victim is matched with the face image information of the associated person, the acquaintance is proved to write a case, and the associated person is not contacted; if the two persons do not match, the person is a stranger to write a case and contact the related person.
In an optional embodiment of the present description, in order to obtain the alarm authorization of the wearer before the alarm is performed when the vehicle owner or the normal user wears the matched alarm wearable device, the alarm accuracy is further improved. Before the executing the alarm operation, the method further comprises the following steps:
carrying out wearable equipment detection;
when the wearable device is detected, sending a consultation message to the wearable device, and enabling the wearable device to perform alarm confirmation operation according to the consultation message;
and receiving a confirmation message sent by the wearable device, and determining whether to execute an alarm operation according to the confirmation message.
Wherein, wearing equipment refers to the special alarm device who is specially used for cooperating this scheme and designs, and it can be the sense of touch induction system of taking on the finger, wears breathing induction system etc. in the front. When an alarm needs to be given, the system can detect the short-distance wearable device, and the detection is not required to be carried out at a too long distance due to the space in the vehicle. The communication between the Bluetooth module and the NFC module can be realized through functional modules such as Bluetooth module and NFC module or through specific electromagnetic waves. When the wearable device is detected, the consultation message is directly sent to the wearable device, then the confirmation message sent back by the wearable device is received, and whether to alarm or not is determined according to the content of the confirmation message. After receiving the advisory message, the wearable device can consult the wearer to determine whether to alarm according to a predetermined mode, for example: through the breathing auxiliary alarm, when a consultation message is received, weak current can be sent to a wearer through the wearable device, and the wearer needs to secondarily confirm whether the alarm is needed or not through breathing, specifically, the method comprises the steps of firstly shocking, continuously breathing, clicking for a second breath holding ten seconds and the like; or the alarm is assisted through the touch of the fingers, specifically, the first electric shock is performed, the fingers are worn to be continuously contacted with the palm five times, the second electric shock is performed, the fingers are worn to be continuously contacted with the palm, and the like. When a given confirmation signal is received within a one-time confirmation time limit, confirming that alarming is needed to be carried out, and generating a confirmation message; and when the confirmation signal is not received, the alarm is not needed, and a confirmation message is generated.
In an alternative embodiment of the present specification, the detailed information for the offender is acquired in order to specifically identify the condition of the victim. The identifying the detail information of the video information comprises the following steps:
determining a victim image according to the audio-visual information, and performing local wound image recognition and victim gesture recognition on the victim image;
generating the detail information according to the identified wound image information and/or victim pose information when the local wound image identification and/or the victim pose identification is passed.
The image information can identify which human body image is the image of the victim by analyzing the posture, the expression and the like of the human body in the image. And then, local wound image recognition is carried out in the image range of the victim, and whether an image similar to the wound image exists in the image range of the victim can be judged through similarity comparison, so that whether the victim is injured or not is judged. Similarly, the posture identification of the victim is to perform image comparison identification on the limb posture of the victim, such as covering the mouth, blocking the mouth, binding the hands and the like. When it is judged that there is the above-described situation, detail information for describing the above-described situation is generated.
In an alternative embodiment of the present specification, in order to specifically identify the situation of the offender, the detailed information for the offender is acquired. The identifying the detail information of the video information comprises the following steps:
determining an image of a harmful person according to the audio and video information, and carrying out weapon identification on the image of the harmful person;
and when the weapon identification passes, generating the detail information according to the identified weapon information.
Similar to the previous embodiment, the image of the offender is recognized first, and then the weapon recognition is performed within the image range, and whether the offender holds the weapon is judged, for example: whether the attacker has a similar weapon is judged by recognizing the standard image of the tool, the standard image of the gun and the like in the image range of the attacker, and when the fact is judged, detail information describing the fact is generated.
In the optional embodiment of the specification, in order to enable the alarm information to describe the case more comprehensively based on the detail information, law enforcement personnel can conveniently make a correct treatment scheme, and law enforcement resources are saved. The generating of the update alarm information containing the detail information includes:
and determining a preset importing position in the original alarm information, importing the detail information at the preset importing position, and integrating to generate the updated alarm information.
The preset guiding position is an insertion node which is set in advance and needs to be inserted when the detail information exists. In this specific embodiment, after the detail information is acquired, the alarm information is adjusted accordingly, and the above situation may be emphasized in the alarm information, for example: inserting the voice of which the victim is injured into the original voice; the voice of what weapon the offender holds is inserted and emphasized in the original voice, etc.
In an alternative embodiment of the present specification, in order to solve the problem that when the current vehicle cannot transmit the warning information, the information is transmitted by other vehicles around the vehicle which can assist the vehicle. The executing of the alarm operation includes:
when detecting that the current vehicle cannot finish the alarm operation, detecting whether the surrounding vehicles have auxiliary vehicles or not;
if so, sending an assistance alarm instruction to the assistance vehicle, and enabling the assistance vehicle to perform alarm operation according to the assistance alarm instruction.
The assisting vehicle is a vehicle which is also provided with the system, can be integrated in the vehicle or mounted subsequently, and sends an assisting alarm instruction to the assisting vehicle after detecting that the assisting vehicle is around, so that the alarm information is transmitted through the assisting vehicle.
Based on the same concept, one or more embodiments of the present specification further provide an in-vehicle behavior recognition alarm device, which is shown in fig. 2 and includes:
the acquisition module 201 acquires audio and video information in a vehicle in real time;
the judgment module 202 compares the audio and video information according to a preset database to judge whether illegal behaviors occur in the vehicle;
if yes, the generating module 203 generates original alarm information, continues to acquire the audio-video information in the vehicle, identifies the detail information of the audio-video information, and generates updated alarm information containing the detail information when the detail information is identified in the audio-video information;
and the alarm module 204 executes alarm operation and outputs the updated alarm information.
As an optional embodiment, the video information includes: image information;
the determining module 202 compares the video information according to a preset database, including:
comparing the illegal similarity of the image information according to an illegal image in a preset database;
if the comparison of the similarity of the illegal behaviors is passed, determining that the illegal behaviors are happening in the vehicle;
if the illegal similarity comparison fails, carrying out abnormal posture similarity comparison on the image information according to an abnormal posture image in a preset database;
and if the abnormal posture similarity comparison fails, determining that illegal behaviors do not occur in the vehicle.
As an optional embodiment, the video information includes: sound information;
the determining module 202 compares the image information with abnormal pose similarity according to the abnormal pose image in the preset database, and further includes:
if the abnormal posture similarity comparison is passed, acquiring the sound information in the vehicle, and comparing the sound similarity of the sound information according to the damaged sound in a preset database;
and if the sound similarity comparison is passed, determining that the illegal action is occurring in the vehicle.
As an optional embodiment, the obtaining module 201 obtains the video information in the vehicle in real time, including:
and determining the direction of a sound source according to the sound information, and adjusting the direction of a lens used for acquiring the image information according to the direction of the sound source.
As an optional embodiment, the acquiring module 201 acquires audio-visual information in a vehicle in real time, and further includes:
determining brightness information in the vehicle, and judging whether the brightness information exceeds a conversion threshold value;
if so, switching the lens for acquiring the image information in the vehicle to a normal lens;
and if not, switching the lens into an infrared night vision lens.
As an alternative embodiment, when performing the comparison of the image information, the determining module 202 performs edge extraction on the image information, including:
carrying out gray level processing on the image information to generate a gray level image, removing impurities from the gray level image by a median filtering method, calculating a gradient image of the gray level image after removing the impurities by a Sobel operator, calculating a binary image of the gradient image according to a maximum inter-class variance method, carrying out multi-iteration expansion corrosion processing and region block filling processing on the binary image to obtain a comparison contour of the image information, and carrying out comparison with an image in a preset database according to the comparison contour.
As an optional embodiment, after the alarm module 204 performs the alarm operation, the method further includes:
acquiring face image information of people in the vehicle, and determining face image information of a victim and face image information of a victim in the face image information according to the audio-video information;
determining the identity of a victim according to the face image information of the victim, determining the face image information of a victim related person and related persons corresponding to the victim related person according to the identity of the victim, and judging whether the face image information of the victim belongs to the face image information of the related persons;
if not, determining the communication information of the relevant personnel of the victim, and carrying out auxiliary help seeking according to the communication information.
As an optional embodiment, before the alarm module 204 performs the alarm operation, the method further includes:
carrying out wearable equipment detection;
when the wearable device is detected, sending a consultation message to the wearable device, and enabling the wearable device to perform alarm confirmation operation according to the consultation message;
and receiving a confirmation message sent by the wearable device, and determining whether to execute an alarm operation according to the confirmation message.
As an optional embodiment, the generating module 203 identifies detail information of the video information, including:
determining a victim image according to the audio-visual information, and performing local wound image recognition and victim gesture recognition on the victim image;
generating the detail information according to the identified wound image information and/or victim pose information when the local wound image identification and/or the victim pose identification is passed.
As an optional embodiment, the generating module 203 identifies detail information of the video information, including:
determining an image of a harmful person according to the audio and video information, and carrying out weapon identification on the image of the harmful person;
and when the weapon identification passes, generating the detail information according to the identified weapon information.
As an optional embodiment, the generating module 203 generates the update alarm information containing the detail information, including:
and determining a preset importing position in the original alarm information, importing the detail information at the preset importing position, and integrating to generate the updated alarm information.
As an alternative embodiment, the alarm module 204 performs an alarm operation, including:
when detecting that the current vehicle cannot finish the alarm operation, detecting whether the surrounding vehicles have auxiliary vehicles or not;
if so, sending an assistance alarm instruction to the assistance vehicle, and enabling the assistance vehicle to perform alarm operation according to the assistance alarm instruction.
For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. Of course, the functionality of the modules may be implemented in the same one or more software and/or hardware implementations in implementing one or more embodiments of the present description.
The device of the foregoing embodiment is used to implement the corresponding method in the foregoing embodiment, and has the beneficial effects of the corresponding method embodiment, which are not described herein again.
One or more embodiments of the present specification further provide an electronic device based on the same inventive concept. The electronic device comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein when the processor executes the program, the in-vehicle behavior recognition alarm method is realized according to any one of the embodiments.
Fig. 3 is a schematic diagram illustrating a more specific hardware structure of an electronic device according to this embodiment, where the electronic device may include: a processor 310, a memory 320, an input/output interface 330, a communication interface 340, and a bus 350. Wherein the processor 310, memory 320, input/output interface 330, and communication interface 340 are communicatively coupled to each other within the device via bus 350.
The processor 310 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits, and is configured to execute related programs to implement the technical solutions provided in the embodiments of the present specification.
The Memory 320 may be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, or the like. The memory 320 may store an operating system and other application programs, and when the technical solution provided by the embodiments of the present specification is implemented by software or firmware, the relevant program codes are stored in the memory 320 and called to be executed by the processor 310.
The input/output interface 330 is used for connecting an input/output module to realize information input and output. The input/output module may be configured as a component in a device (not shown) or may be external to the device to provide a corresponding function. The input devices may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output devices may include a display, a speaker, a vibrator, an indicator light, etc.
The communication interface 340 is used for connecting a communication module (not shown in the figure) to implement communication interaction between the present device and other devices. The communication module can realize communication in a wired mode (such as USB, network cable and the like) and also can realize communication in a wireless mode (such as mobile network, WIFI, Bluetooth and the like).
It should be noted that although the above-mentioned device only shows the processor 310, the memory 320, the input/output interface 330, the communication interface 340 and the bus 350, in a specific implementation, the device may also include other components necessary for normal operation. In addition, those skilled in the art will appreciate that the above-described apparatus may also include only those components necessary to implement the embodiments of the present description, and not necessarily all of the components shown in the figures.
Based on the same inventive concept, one or more embodiments of the present specification further provide a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute an in-vehicle behavior recognition alarm method according to any one of the embodiments described above.
Computer-readable media of the present embodiments, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device.
Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant to be exemplary only, and is not intended to intimate that the scope of the disclosure, including the claims, is limited to these examples; within the spirit of the present disclosure, features from the above embodiments or from different embodiments may also be combined, steps may be implemented in any order, and there are many other variations of different aspects of one or more embodiments of the present description as described above, which are not provided in detail for the sake of brevity.
In addition, well-known power/ground connections to Integrated Circuit (IC) chips and other components may or may not be shown in the provided figures, for simplicity of illustration and discussion, and so as not to obscure one or more embodiments of the disclosure. Further, devices may be shown in block diagram form in order to avoid obscuring the understanding of one or more embodiments of the present description, and this also takes into account the fact that specifics with respect to implementation of such block diagram devices are highly dependent upon the platform within which the one or more embodiments of the present description are to be implemented (i.e., such specifics should be well within purview of one skilled in the art). Where specific details (e.g., circuits) are set forth in order to describe example embodiments of the disclosure, it should be apparent to one skilled in the art that one or more embodiments of the disclosure can be practiced without, or with variation of, these specific details. Accordingly, the description is to be regarded as illustrative instead of restrictive.
While the present disclosure has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic ram (dram)) may use the discussed embodiments.
It is intended that the one or more embodiments of the present specification embrace all such alternatives, modifications and variations as fall within the broad scope of the appended claims. Therefore, any omissions, modifications, substitutions, improvements, and the like that may be made without departing from the spirit and principles of one or more embodiments of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (15)
1. An in-vehicle behavior recognition alarm method is characterized by comprising the following steps:
acquiring video and audio information in a vehicle in real time;
comparing the video information according to a preset database, and judging whether illegal behaviors are occurring in the vehicle;
if yes, generating original alarm information, continuously acquiring the audio-video information in the vehicle, identifying the detail information of the audio-video information, and generating updated alarm information containing the detail information when the detail information is identified in the audio-video information;
and executing alarm operation and outputting the updated alarm information.
2. The method of claim 1, wherein the audiovisual information comprises: image information;
the comparing the video information according to a preset database comprises:
comparing the illegal similarity of the image information according to an illegal image in a preset database;
if the comparison of the similarity of the illegal behaviors is passed, determining that the illegal behaviors are happening in the vehicle;
if the illegal similarity comparison fails, carrying out abnormal posture similarity comparison on the image information according to an abnormal posture image in a preset database;
and if the abnormal posture similarity comparison fails, determining that illegal behaviors do not occur in the vehicle.
3. The method of claim 2, wherein the audiovisual information comprises: sound information;
the comparing of the abnormal posture similarity of the image information according to the abnormal posture image in the preset data bank further comprises:
if the abnormal posture similarity comparison is passed, acquiring the sound information in the vehicle, and comparing the sound similarity of the sound information according to the damaged sound in a preset database;
and if the sound similarity comparison is passed, determining that the illegal action is occurring in the vehicle.
4. The method of claim 3, wherein the obtaining the audiovisual information in the vehicle in real time comprises:
and determining the direction of a sound source according to the sound information, and adjusting the direction of a lens used for acquiring the image information according to the direction of the sound source.
5. The method of claim 3, wherein the obtaining of audiovisual information in the vehicle in real time further comprises:
determining brightness information in the vehicle, and judging whether the brightness information exceeds a conversion threshold value;
if so, switching the lens for acquiring the image information in the vehicle to a normal lens;
and if not, switching the lens into an infrared night vision lens.
6. The method of claim 2, wherein performing edge extraction on the image information when performing the alignment of the image information comprises:
carrying out gray level processing on the image information to generate a gray level image, removing impurities from the gray level image by a median filtering method, calculating a gradient image of the gray level image after removing the impurities by a Sobel operator, calculating a binary image of the gradient image according to a maximum inter-class variance method, carrying out multi-iteration expansion corrosion processing and region block filling processing on the binary image to obtain a comparison contour of the image information, and carrying out comparison with an image in a preset database according to the comparison contour.
7. The method of claim 1, wherein after performing the alert operation, further comprising:
acquiring face image information of people in the vehicle, and determining face image information of a victim and face image information of a victim in the face image information according to the audio-video information;
determining the identity of a victim according to the face image information of the victim, determining the face image information of a victim related person and related persons corresponding to the victim related person according to the identity of the victim, and judging whether the face image information of the victim belongs to the face image information of the related persons;
if not, determining the communication information of the relevant personnel of the victim, and carrying out auxiliary help seeking according to the communication information.
8. The method of claim 1, wherein prior to performing the alert operation, further comprising:
carrying out wearable equipment detection;
when the wearable device is detected, sending a consultation message to the wearable device, and enabling the wearable device to perform alarm confirmation operation according to the consultation message;
and receiving a confirmation message sent by the wearable device, and determining whether to execute an alarm operation according to the confirmation message.
9. The method of claim 1, wherein the identifying the detail information of the audiovisual information comprises:
determining a victim image according to the audio-visual information, and performing local wound image recognition and victim gesture recognition on the victim image;
generating the detail information according to the identified wound image information and/or victim pose information when the local wound image identification and/or the victim pose identification is passed.
10. The method of claim 1, wherein the identifying the detail information of the audiovisual information comprises:
determining an image of a harmful person according to the audio and video information, and carrying out weapon identification on the image of the harmful person;
and when the weapon identification passes, generating the detail information according to the identified weapon information.
11. The method according to any one of claims 9 or 10, wherein the generating update alert information containing the detail information comprises:
and determining a preset importing position in the original alarm information, importing the detail information at the preset importing position, and integrating to generate the updated alarm information.
12. The method of claim 1, wherein the performing an alarm operation comprises:
when detecting that the current vehicle cannot finish the alarm operation, detecting whether the surrounding vehicles have auxiliary vehicles or not;
if so, sending an assistance alarm instruction to the assistance vehicle, and enabling the assistance vehicle to perform alarm operation according to the assistance alarm instruction.
13. An in-vehicle behavior recognition alarm device, comprising:
the acquisition module acquires the audio-video information in the vehicle in real time;
the judgment module is used for comparing the audio-video information according to a preset database and judging whether illegal behaviors are occurring in the vehicle or not;
if yes, generating original alarm information, continuously acquiring the audio-video information in the vehicle, identifying the detail information of the audio-video information, and generating updated alarm information containing the detail information when the detail information is identified in the audio-video information;
and the alarm module executes alarm operation and outputs the updated alarm information.
14. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1 to 12 when executing the program.
15. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1 to 12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010732408.3A CN112061065B (en) | 2020-07-27 | 2020-07-27 | In-vehicle behavior recognition alarm method, device, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010732408.3A CN112061065B (en) | 2020-07-27 | 2020-07-27 | In-vehicle behavior recognition alarm method, device, electronic device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112061065A true CN112061065A (en) | 2020-12-11 |
| CN112061065B CN112061065B (en) | 2022-05-10 |
Family
ID=73656819
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010732408.3A Active CN112061065B (en) | 2020-07-27 | 2020-07-27 | In-vehicle behavior recognition alarm method, device, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112061065B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112786219A (en) * | 2021-03-09 | 2021-05-11 | 中南大学 | Medical care management method, system and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201188246Y (en) * | 2008-03-25 | 2009-01-28 | 秦磊 | Anti-theft and anti-grabbing alarm device for vehicle |
| CN104821060A (en) * | 2015-05-19 | 2015-08-05 | 深圳市保千里电子有限公司 | Robbery early warning method and device |
| CN105292052A (en) * | 2015-11-12 | 2016-02-03 | 福州大学 | Automatic monitoring and alarming system for vehicle traffic safety |
| CN108986400A (en) * | 2018-09-03 | 2018-12-11 | 深圳市尼欧科技有限公司 | A kind of third party based on image procossing, which multiplies, drives safety automatic-alarming method |
| CN110399767A (en) * | 2017-08-10 | 2019-11-01 | 北京市商汤科技开发有限公司 | Occupant's dangerous play recognition methods and device, electronic equipment, storage medium |
| CN111191545A (en) * | 2019-12-20 | 2020-05-22 | 郑州嘉晨电器有限公司 | Real-time monitoring and analyzing system and method for driver behavior |
-
2020
- 2020-07-27 CN CN202010732408.3A patent/CN112061065B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201188246Y (en) * | 2008-03-25 | 2009-01-28 | 秦磊 | Anti-theft and anti-grabbing alarm device for vehicle |
| CN104821060A (en) * | 2015-05-19 | 2015-08-05 | 深圳市保千里电子有限公司 | Robbery early warning method and device |
| CN105292052A (en) * | 2015-11-12 | 2016-02-03 | 福州大学 | Automatic monitoring and alarming system for vehicle traffic safety |
| CN110399767A (en) * | 2017-08-10 | 2019-11-01 | 北京市商汤科技开发有限公司 | Occupant's dangerous play recognition methods and device, electronic equipment, storage medium |
| CN108986400A (en) * | 2018-09-03 | 2018-12-11 | 深圳市尼欧科技有限公司 | A kind of third party based on image procossing, which multiplies, drives safety automatic-alarming method |
| CN111191545A (en) * | 2019-12-20 | 2020-05-22 | 郑州嘉晨电器有限公司 | Real-time monitoring and analyzing system and method for driver behavior |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112786219A (en) * | 2021-03-09 | 2021-05-11 | 中南大学 | Medical care management method, system and device |
| CN112786219B (en) * | 2021-03-09 | 2024-03-19 | 中南大学 | Medical care management method, system and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112061065B (en) | 2022-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Dasgupta et al. | A smartphone-based drowsiness detection and warning system for automotive drivers | |
| CN108351968B (en) | Alarming method, device, storage medium and server for criminal activities | |
| US10311289B2 (en) | Face recognition method and device and apparatus | |
| US9354615B2 (en) | Device, operating method and computer-readable recording medium for generating a signal by detecting facial movement | |
| CN112364696B (en) | Method and system for improving family safety by utilizing family monitoring video | |
| CN111063162A (en) | Silent alarm method and device, computer equipment and storage medium | |
| JP4569190B2 (en) | Suspicious person countermeasure system and suspicious person detection device | |
| WO2007074842A1 (en) | Image processing apparatus | |
| US10839204B2 (en) | Sharing identification data with audio/video recording and communication devices and local processing of the shared data | |
| JP2017211888A (en) | Image information authentification system | |
| US10733857B1 (en) | Automatic alteration of the storage duration of a video | |
| CN108563985B (en) | Method for identifying pickpocket, monitoring center, public transport equipment and storage medium | |
| JP2020042785A (en) | Method, apparatus, device and storage medium for identifying passenger state in unmanned vehicle | |
| CN112061065B (en) | In-vehicle behavior recognition alarm method, device, electronic device and storage medium | |
| Sathesh et al. | Allowance of driving based on drowsiness detection using audio and video processing | |
| CN111178194A (en) | Intrusion detection method, device and equipment | |
| CN103247150A (en) | Fatigue driving preventing system | |
| Jin et al. | An intelligent multi-sensor surveillance system for elderly care | |
| CN104050785A (en) | Safety alert method based on virtualized boundary and face recognition technology | |
| TWI520076B (en) | Method and apparatus for detecting person to use handheld device | |
| JP3088880B2 (en) | Person recognition device | |
| Soman et al. | Internet-of-Things-Assisted Artificial Intelligence-Enabled Drowsiness Detection Framework | |
| CN109214316B (en) | Perimeter protection method and device | |
| KR101437406B1 (en) | an emergency management and crime prevention system for cars and the method thereof | |
| US11518345B2 (en) | Vehicle and method of controlling the same |
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 |