CN112804492B - Communication prompting method and device for electronic peepholes - Google Patents
Communication prompting method and device for electronic peepholes Download PDFInfo
- Publication number
- CN112804492B CN112804492B CN202011639747.3A CN202011639747A CN112804492B CN 112804492 B CN112804492 B CN 112804492B CN 202011639747 A CN202011639747 A CN 202011639747A CN 112804492 B CN112804492 B CN 112804492B
- Authority
- CN
- China
- Prior art keywords
- image
- terminal
- matching
- monitoring
- preset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004891 communication Methods 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000012544 monitoring process Methods 0.000 claims abstract description 167
- 241000282326 Felis catus Species 0.000 claims abstract description 77
- 238000001514 detection method Methods 0.000 claims abstract description 26
- 230000002776 aggregation Effects 0.000 claims description 15
- 238000004220 aggregation Methods 0.000 claims description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 15
- 210000003128 head Anatomy 0.000 description 11
- 238000010586 diagram Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
- G08B13/19613—Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
- G08B25/01—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium
- G08B25/08—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium using communication transmission lines
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Emergency Management (AREA)
- Human Computer Interaction (AREA)
- Business, Economics & Management (AREA)
- Signal Processing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The application discloses a communication prompting method and a device of an electronic cat eye, which are applied to a cradle head server, wherein the cradle head server is respectively connected with a terminal and the electronic cat eye, and the method comprises the following steps: receiving the field monitoring video acquired by the electronic cat eye; performing person detection on the field monitoring video; if the live monitoring video contains the figure image, carrying out matching detection on the figure image to obtain a matching result, and sending the matching result to the terminal so that the terminal carries out recognition prompt on the figure image according to the matching result; and if the scene monitoring video does not contain the character image, classifying the scene of the scene monitoring video to obtain a classification result, and sending the classification result to the terminal so that the terminal carries out scene prompt according to the classification result. The application can inform the user in time when an accident occurs, shortens the alarm time and reduces the disaster risk.
Description
Technical Field
The application relates to the technical field of intelligent cat eye equipment, in particular to a communication prompting method and device for an electronic cat eye.
Background
The peephole is commonly called a peephole, which is a small optical instrument arranged on a door of a residence, and is called a peephole because the peephole looks like a light emitted by a Persian peephole at night when the peephole looks away after being refracted.
The existing cat eye is installed on the door. When someone accesses, the user walks behind the door and approaches the eyes to the cat eye to observe the condition outside the door, and then whether the door is opened or not is determined. Since the user must walk behind the door to watch each time someone accesses, the operation is troublesome, and it is difficult for the user to determine the outdoor situation when the user cannot draw his body at home to watch. In order to solve the above problems, the prior art uses an electronic cat eye to shoot an outdoor scene and transmit the shot image to a television or a display screen in home for a user to view.
However, the following disadvantages exist in the prior art: once the user goes out, if there is a person to steal or an emergency such as a fire disaster occurs outdoors, the user is difficult to execute the alarm operation by receiving the image shot by the electronic cat eye, so that the alarm time is prolonged, and the risks of disaster damage and property loss are increased.
Disclosure of Invention
The application provides a communication prompting method and a communication prompting device for an electronic cat eye, which can transmit a monitoring image to a terminal in real time when a user goes out, and when an emergency occurs, the user can determine the site condition through the terminal and immediately alarm, so that the alarm time is shortened, and the disaster risk and the financial loss risk are reduced.
An embodiment of the application provides a communication prompting method of an electronic cat eye, which is applied to a cradle head server, wherein the cradle head server is respectively connected with a terminal and the electronic cat eye, and the method comprises the following steps:
receiving the field monitoring video acquired by the electronic cat eye;
performing person detection on the field monitoring video;
if the live monitoring video contains the figure image, carrying out matching detection on the figure image to obtain a matching result, and sending the matching result to the terminal so that the terminal carries out recognition prompt on the figure image according to the matching result;
and if the scene monitoring video does not contain the character image, classifying the scene of the scene monitoring video to obtain a classification result, and sending the classification result to the terminal so that the terminal carries out scene prompt according to the classification result.
Further, the step of performing person detection in the live surveillance video includes:
determining a starting node and an ending node according to a preset time interval;
dividing the field monitoring video into a plurality of frames of monitoring images, and acquiring one frame of monitoring image corresponding to the starting node and the ending node from the plurality of frames of monitoring images to obtain a starting monitoring image and an ending monitoring image;
performing feature matching on the starting monitoring image and the ending monitoring image, and extracting distinguishing image features between the starting monitoring image and the ending monitoring image;
matching and calculating the distinguishing image features and preset human body features to obtain an image matching value;
if the image matching value is larger than or equal to a preset value, determining that the on-site monitoring video contains a character image;
and if the image matching value is smaller than a preset value, determining that the live monitoring video does not contain the character image.
Further, the step of performing matching detection on the character image to obtain a matching result, and sending the matching result to the terminal, so that the terminal performs recognition prompt on the character image according to the matching result, and the method comprises the following steps:
extracting face features to be identified in the character image;
respectively matching the face features to be recognized with a plurality of preset face features, wherein the plurality of preset face features are face features respectively corresponding to a plurality of family member images added by a user;
if the face feature to be identified is matched with any one of a plurality of preset face features, a successful matching result is generated, and the successful matching result and a family member image corresponding to the face feature to be identified are sent to the terminal, so that the terminal displays the successful matching result and the family member image corresponding to the face feature to be identified to carry out identification prompt of the figure image;
if the face features to be recognized are not matched with the preset face features, an unsuccessful matching result is generated, and the unsuccessful matching result and the character image are sent to the terminal, so that the terminal displays the unsuccessful matching result and the character image to recognize and prompt the character image.
Further, the electronic cat eye is provided with a communicator, and the method further comprises:
receiving voice information sent by the terminal, wherein the voice information is acquired by the terminal after the user identifies the unsuccessful matching result and the character image;
and sending the voice information to the electronic cat eye so that the electronic cat eye can play the voice information through the communicator.
Further, if the scene classification is performed on the on-site surveillance video to obtain a classification result, the classification result is sent to the terminal, including:
dividing the field monitoring video into a plurality of frames of field images according to a preset frame number, and mutually superposing the plurality of frames of field images to obtain a superposed image;
acquiring image pixel values of the superimposed image, and respectively calculating distance values between the image pixel values and a plurality of preset category center points by adopting the aggregation algorithm to obtain a plurality of category distance values;
searching a target category distance value with the smallest value from the plurality of category distance values, taking a category corresponding to the target category distance value as a classification result, and sending the classification result to the terminal.
Correspondingly, an embodiment of the present application further provides a communication prompting device for an electronic cat eye, which is applied to a cradle head server, wherein the cradle head server is connected with the electronic cat eye through terminals respectively, and the device comprises:
the receiving module is used for receiving the field monitoring video acquired by the electronic cat eye;
the detection module is used for detecting the characters in the field monitoring video;
the image matching module is used for carrying out matching detection on the person images to obtain matching results if the person images are determined to be contained in the live monitoring video, and sending the matching results to the terminal so that the terminal carries out recognition prompt on the person images according to the matching results;
and the scene classification module is used for classifying the scene of the on-site monitoring video to obtain a classification result if the on-site monitoring video does not contain the character image, and sending the classification result to the terminal so that the terminal carries out scene prompt according to the classification result.
Further, the detection module is further configured to:
determining a starting node and an ending node according to a preset time interval;
dividing the field monitoring video into a plurality of frames of monitoring images, and acquiring one frame of monitoring image corresponding to the starting node and the ending node from the plurality of frames of monitoring images to obtain a starting monitoring image and an ending monitoring image;
performing feature matching on the starting monitoring image and the ending monitoring image, and extracting distinguishing image features between the starting monitoring image and the ending monitoring image;
matching and calculating the distinguishing image features and preset human body features to obtain an image matching value;
if the image matching value is larger than or equal to a preset value, determining that the on-site monitoring video contains a character image;
and if the image matching value is smaller than a preset value, determining that the live monitoring video does not contain the character image.
Further, the portrait matching module is further configured to:
extracting face features to be identified in the character image;
respectively matching the face features to be recognized with a plurality of preset face features, wherein the plurality of preset face features are face features respectively corresponding to a plurality of family member images added by a user;
if the face feature to be identified is matched with any one of a plurality of preset face features, a successful matching result is generated, and the successful matching result and a family member image corresponding to the face feature to be identified are sent to the terminal, so that the terminal displays the successful matching result and the family member image corresponding to the face feature to be identified to carry out identification prompt of the figure image;
if the face features to be recognized are not matched with the preset face features, an unsuccessful matching result is generated, and the unsuccessful matching result and the character image are sent to the terminal, so that the terminal displays the unsuccessful matching result and the character image to recognize and prompt the character image.
Further, the electronic cat eye is provided with a communicator, and the device further comprises:
the receiving information module is used for receiving voice information sent by the terminal, wherein the voice information is acquired by the terminal after the user identifies the unsuccessful matching result and the character image;
and the information sending module is used for sending the voice information to the electronic cat eye so that the electronic cat eye can play the voice information through the communicator.
Further, the scene module is further configured to:
dividing the field monitoring video into a plurality of frames of field images according to a preset frame number, and mutually superposing the plurality of frames of field images to obtain a superposed image;
acquiring image pixel values of the superimposed image, and respectively calculating distance values between the image pixel values and a plurality of preset category center points by adopting the aggregation algorithm to obtain a plurality of category distance values;
searching a target category distance value with the smallest value from the plurality of category distance values, taking a category corresponding to the target category distance value as a classification result, and sending the classification result to the terminal.
Compared with the prior art, the communication prompting method and device for the electronic cat eye provided by the embodiment of the application have the beneficial effects that: according to the application, the on-site monitoring video can be obtained by monitoring the video on site through the electronic cat eye, and the on-site monitoring video is uploaded to the cloud deck server, so that the on-site real-time monitoring is realized, and the cloud deck server can perform portrait identification and scene classification on the on-site monitoring video, so that the on-site situation can be determined, and the on-site situation is sent to a user in real time. The outdoor situation can be known in real time no matter the user goes out or has something else but can't draw out the body to watch outdoors, once the accident happens, the user can be informed in time, the alarm time is shortened, and the risk of disaster or financial loss is reduced.
Drawings
Fig. 1 is an application environment diagram of a communication prompting method of an electronic cat eye according to an embodiment of the present application;
fig. 2 is a flow chart of a communication prompting method for an electronic cat eye according to an embodiment of the application;
fig. 3 is a schematic structural diagram of a communication prompting device for an electronic cat eye according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The existing electronic cat eye can shoot outdoor scenes, and the shot images are transmitted to a television or a display screen in a home for a user to view. However, after the user goes out, if there is a person to steal or an emergency such as a fire disaster occurs outdoors, the user is difficult to execute operations such as protection or alarm by receiving the image shot by the electronic cat eye, thereby prolonging the alarm time and increasing the risks of disaster damage and property loss.
In order to solve the above problems, the following detailed description and explanation will be given for a communication prompting method of an electronic cat eye according to the embodiments of the present application.
Referring to fig. 1, an application environment diagram of a communication prompting method of an electronic cat eye according to an embodiment of the present application is shown. In this embodiment, the method for detecting the FPC may be applied to a cradle head server, where the cradle head server may be respectively connected and in communication with the electronic cat eye and the terminal. In particular, the pan-tilt server is also called a cloud server (Elastic Compute Service, ECS) and is a simple, efficient, safe and reliable computing service with elastically scalable processing capacity. The electronic peephole can be called a visual doorbell, integrates the functions of the peephole and the doorbell, and can be provided with a communication circuit for connecting and communicating with a holder server. The terminal can be a desktop terminal or a mobile terminal, and the mobile terminal can be at least one of a mobile phone, a tablet computer, a notebook computer and the like.
Referring to fig. 2, a flow chart of a communication prompting method for an electronic cat eye according to an embodiment of the application is shown.
For example, the communication prompting method of the electronic cat eye may include:
s11, receiving the field monitoring video acquired by the electronic cat eye.
The electronic cat eye is provided with the monitoring camera, and can acquire the on-site monitoring video through the control camera. The field monitoring video is video of a monitoring area of a monitoring camera of the electronic cat eye. When the electronic cat eye is used, the electronic cat eye can record the video on the monitoring site in time and upload the video to the holder server.
S12, performing person detection on the field monitoring video.
The cloud deck server can receive the on-site monitoring video of the electronic cat eye in real time and detect characters on the on-site monitoring video in real time. Through the person detection, whether the visitor appears on the site monitored by the electronic cat eye can be determined, so that the client can be notified.
In order to improve the accuracy of person detection, in this embodiment, step S12 may include the following sub-steps:
and step S121, determining a start node and an end node according to a preset time interval.
The preset time interval is a time interval between the start node and the end node, and the preset time interval may be 5 ms, 5 μs, 1 s or 2 s, and may be specifically adjusted according to actual needs. The acquisition of the starting node and the ending node can facilitate the sampling detection of the field monitoring video, and if the field monitoring video is detected in the whole process, the energy consumption is high. And determining a start node and an end node, and then sampling and detecting the field monitoring video through the start node and the end node, so that the detection efficiency can be improved.
And S122, dividing the on-site monitoring video into a plurality of frames of monitoring images, and acquiring one frame of monitoring image corresponding to the starting node and the ending node from the plurality of frames of monitoring images to obtain a starting monitoring image and an ending monitoring image.
In this embodiment, the pan-tilt server may divide the live monitoring video acquired in real time into monitoring video blocks of a preset time period according to the segmentation, and then divide the monitoring video blocks into multiple frames of monitoring images.
For example, the live monitoring video may be segmented into 5-minute monitoring video blocks according to a 5-minute time period, and then the 5-minute monitoring video blocks are divided into multiple frames of monitoring images. In addition, in order to improve the efficiency and accuracy of the detection, the dicing time period may be appropriately shortened, and may be 3 minutes, 2 minutes, or 1 minute.
And then respectively acquiring a start monitoring image corresponding to the start node and an end monitoring image corresponding to the end node from the multi-frame monitoring images according to the time points respectively corresponding to the start node and the end node.
For example, a monitoring video block with a duration of 5 minutes is divided into 300 frames of monitoring images in a one-second one-frame mode, and a time interval between a start node and an end node is 100 seconds, so that a first frame of monitoring image corresponding to the start node and a first hundred frames of monitoring image corresponding to the end node can be obtained and respectively recorded as a start monitoring image and an end monitoring image.
And step S123, performing feature matching on the starting monitoring image and the ending monitoring image, and extracting distinguishing image features between the starting monitoring image and the ending monitoring image.
In actual operation, the starting image feature of the starting monitoring image and the ending image feature of the ending monitoring image can be extracted respectively, the starting image feature and the ending image feature are matched as features, the same image feature is removed, different image features are obtained, and the distinguishing image features are obtained.
And S124, carrying out matching calculation on the distinguishing image features and preset human body features to obtain image matching values.
The preset human body characteristics may be human body image characteristics preset by a user, and the preset human body characteristics may be stored in a database of the pan-tilt server.
In specific implementation, the distinguishing image features and the preset human body features are subjected to matching calculation to obtain image matching values.
And step S125, if the image matching value is greater than or equal to a preset value, determining that the live monitoring video contains the character image.
And step S126, if the image matching value is smaller than a preset value, determining that the live monitoring video does not contain the character image.
In actual operation, when the calculated image matching value is greater than or equal to a preset value, the captured live monitoring video block with the preset duration can be determined to include the character image, otherwise, when the calculated image matching value is less than the preset value, the captured live monitoring video block with the preset duration can be determined to not include the character image.
And S13, if the live monitoring video contains the character image, carrying out matching detection on the character image to obtain a matching result, and sending the matching result to the terminal so that the terminal carries out identification prompt on the character image according to the matching result.
In this embodiment, when it is determined that the live monitoring video includes a person image, the user needs to be notified in time. The appearing portrait may be a visitor or guest, or a family member coming home, or a passerby. Therefore, after the person image is determined, the person image is required to be matched and detected, and the person image can be matched with the family member image, if the person image is not a family member, the user can be notified to perform person identification, and the user can conveniently determine visiting persons.
The matching result may include a matching success result and a matching unsuccessful result. The cloud platform server can send the matching result to the terminal, the terminal can prompt the user in a short message or voice mode and the like, and the user can identify visiting persons or character images through the matching result to determine whether the visiting persons or passers-by currently pass through are dangerous or safe and reliable.
Specifically, step S13 may include the following sub-steps:
and S131, extracting face features to be identified in the character image.
After the fact that the live monitoring video contains the person image is determined, a frame of monitoring image containing the person image can be obtained from the multi-frame monitoring image, the person image is taken as the monitoring image containing the person image, the face feature is extracted from the person image, and the face feature is taken as the face feature to be identified.
And step S132, respectively matching the face features to be recognized with a plurality of preset face features, wherein the plurality of preset face features are face features respectively corresponding to a plurality of family member images added by the user.
The preset face features are face features preset by a user, and specifically comprise face features corresponding to each family member preset by the user. In actual operation, a user can upload face images of a plurality of family members, and the cradle head server can extract a plurality of face features from the plurality of face images respectively, wherein each family member can correspond to one or a plurality of face features, and each face feature corresponds to one family member.
Specifically, the face features to be identified can be respectively matched with a plurality of preset face features, and whether the face features to be identified are matched with any one of the plurality of preset face features is determined.
For example, the number of the preset plurality of face features is 5, and the face features to be recognized can be respectively matched with the 5 face features to obtain 5 matching results.
And S133, if the face feature to be identified is matched with any one of a plurality of preset face features, generating a successful matching result, and sending the successful matching result and a family member image corresponding to the face feature to be identified to the terminal, so that the terminal displays the successful matching result and the family member image corresponding to the face feature to be identified to carry out identification prompt of the figure image.
In this embodiment, if the face feature to be identified is matched with any one of a plurality of preset face features, it may be determined that the person corresponding to the face feature to be identified is one of a plurality of family members preset by the user. The cloud deck server can generate a successful matching result, and sends a family member image corresponding to the face feature to be identified to the terminal, wherein the family member image is an image preset at the cloud deck server by a user.
After receiving the successful matching result and the family member image, the terminal can play the successful matching result to the user for listening in a voice broadcasting mode, and the family member image is displayed in the terminal plane. The user can recognize the image of the family member through the family member image displayed in the terminal screen, and the user can also determine whether he returns home or not through informing or contacting the family member corresponding to the family member image.
And step 134, if the face features to be recognized are not matched with the preset face features, generating a unsuccessful matching result, and sending the unsuccessful matching result and the character image to the terminal so that the terminal displays the unsuccessful matching result and the character image to recognize and prompt the character image.
In this embodiment, when the face feature to be recognized is not matched with the preset face features, it is determined that the person corresponding to the face feature to be recognized is not a family member preset by the user, the person can be determined to be a visitor, the cradle head server can generate a unsuccessful matching result, send the unsuccessful matching result and the person image to the terminal, and the terminal can play the unsuccessful matching result to the user for listening through a voice broadcasting mode and display the person image corresponding to the face feature to be recognized in the terminal plane. The user can learn the current visiting person through the person image corresponding to the face feature to be identified, and the user makes visiting judgment to determine whether to allow the visiting person to enter home.
In an alternative embodiment, when the matching result is an unsuccessful matching result, the current visitor may be a friend of the user, or may be a person with unknown calendar, so as to further ensure the family safety of the user, protect the property of the user, and enable the user to communicate with the visitor.
Specifically, step S13 may further include the following sub-steps:
and S135, receiving voice information sent by the terminal, wherein the voice information is acquired by the terminal after the user identifies the unsuccessful matching result and the character image.
In this embodiment, after the user obtains the unsuccessful matching result and identifies the character image, the user may record the voice information in the terminal and send the voice information to the pan-tilt server by the terminal.
And step 136, transmitting the voice information to the electronic cat eye so that the electronic cat eye plays the voice information through the communicator.
After receiving the voice information, the holder server can send the voice information to the electronic cat eye.
In a specific implementation, the electronic cat eye may be provided with a communicator, which may be provided with a broadcaster or a loudspeaker, and may also be provided with a microphone to receive voice information. After receiving the voice information, the electronic cat eye plays the language information of the user through the communicator, so that the user can talk with the visitor corresponding to the character image.
And S14, if the scene monitoring video does not contain the character image, classifying the scene of the scene monitoring video to obtain a classification result, and transmitting the classification result to the terminal so that the terminal carries out scene prompt according to the classification result.
In this embodiment, when the image matching value is smaller than the preset value, it may be determined that the live monitor video uploaded by the electronic cat eye does not include the character image, and the pan-tilt server may classify the scenes of the live monitor video, so as to determine whether the scene corresponding to the live monitor video is abnormal according to the classification of the live monitor video.
The classification result may be a classification result obtained by the pan-tilt server after performing scene classification. In this embodiment, the category may be preset by the user, or may be obtained from a network scene category database by the pan-tilt server. In practice, the categories may include fire category, leakage category, normal category, theft category, blockage category, and so forth.
After the cloud deck server classifies the scene of the field monitoring video to obtain classification results, the classification results can be sent to the terminal, and the terminal can display the classification results in a screen, so that the effect of scene prompt for a user is achieved.
In order to improve the accuracy of scene classification, in this embodiment, step S14 may include the following sub-steps:
and S141, cutting the field monitoring video into multi-frame field images according to a preset frame number, and mutually superposing the multi-frame field images to obtain a superposed image.
In actual operation, the cradle head server can divide the field monitoring video into monitoring video blocks with the duration of 3 minutes according to the time period of 3 minutes, then divide the monitoring video blocks with the duration of 3 minutes into multi-frame field images according to the preset frame number, and carry out image superposition on the multi-frame field images to obtain a superposition image.
And S142, acquiring image pixel values of the superimposed image, and respectively calculating distance values between the image pixel values and a plurality of preset category center points by adopting the aggregation algorithm to obtain a plurality of category distance values.
The image pixel values of the superimposed image are acquired and then aggregated using an aggregation algorithm. The class center points are pixel center points corresponding to different image classes set by a user. Each category corresponds to a category center point.
In actual operation, the aggregation algorithm may aggregate the same or similar image pixel values together, and separate different or dissimilar image pixel values, thereby implementing classification of the image pixel values of the superimposed image. And when the aggregation algorithm is used for classifying, if no change occurs in the monitoring video blocks with preset time length, the image pixel values of the superimposed images are classified into one class, if the change occurs in the monitoring video blocks with preset time length, the image pixel values of the superimposed images are classified into two or more classes, and then the classified image pixel values are subjected to distance value calculation. If one category exists, the distances between the category and a plurality of preset category center points can be calculated respectively, and a plurality of distance values corresponding to the category are obtained. If two or more categories exist, the distance value between each category and a plurality of preset category center points can be calculated respectively, so that a plurality of distance values corresponding to each category are obtained.
In this embodiment, the aggregation algorithm may be a K-means (K-means) aggregation algorithm, a DBSCAN aggregation algorithm, a DPEAK aggregation algorithm, a media aggregation algorithm, or a cap aggregation algorithm.
And step S143, searching a target category distance value with the smallest value from the plurality of category distance values, taking the category corresponding to the target category distance value as a classification result, and sending the classification result to the terminal.
If one category exists, searching a distance value with the smallest value in a plurality of distance values corresponding to the category, and taking the center point category corresponding to the distance value with the smallest value as a classification result. Since the distance value is the smallest, the image pixel value and the category can be determined, and the current scene can be determined as the scene corresponding to the category.
If a plurality of categories exist, the distance value with the smallest value in the plurality of distance values corresponding to each category can be searched for respectively to obtain the distance value with the smallest value corresponding to each category, the distance values with the smallest values corresponding to each category are compared to obtain a plurality of minimum distance values, the distance value with the smallest value is obtained from the plurality of minimum distance values, the minimum distance value is used as a target distance value, and the category corresponding to the target distance value is used as a classification result.
After the holder server obtains the classification result, the classification result can be sent to the terminal, and the terminal can display the classification result, so that the effect of prompting the user is achieved. The user can perform corresponding operation according to the classification result, for example, if the classification result is fire, the user can perform alarm operation, if the classification result is blockage, the user can inform the property manager to clean.
In addition, if the classification result is normal and the result is sent to the user once, the user is disturbed, and meanwhile, the energy consumption is increased.
In order to reduce the harassment to the user, if the classification result of the pan-tilt server is normal, the classification result can be sent to the terminal according to a preset time interval or according to a preset time node. For example, at 10 a.m. and 4 a.m. respectively, the user can know the outdoor situation in real time even if he/she goes out or goes to work and is not at home.
In this embodiment, the embodiment of the present application provides a communication prompting method for an electronic cat eye, which has the following beneficial effects: according to the application, the on-site monitoring video can be obtained by monitoring the video on site through the electronic cat eye, and the on-site monitoring video is uploaded to the cloud deck server, so that the on-site real-time monitoring is realized, and the cloud deck server can perform portrait identification and scene classification on the on-site monitoring video, so that the on-site situation can be determined, and the on-site situation is sent to a user in real time. The outdoor situation can be known in real time no matter the user goes out or has something else but can't draw out the body to watch outdoors, once the accident happens, the user can be informed in time, the alarm time is shortened, and the risk of disaster or financial loss is reduced.
The embodiment of the application also provides a communication prompting device of the electronic cat eye, and referring to fig. 3, a schematic structural diagram of the communication prompting device of the electronic cat eye is shown. The communication prompt device of the electronic cat eye can be applied to a cradle head server, and the cradle head server is connected with the electronic cat eye through terminals respectively.
Wherein, as an example, the communication prompting device of the electronic cat eye may include:
the receiving module 301 is configured to receive a field monitoring video acquired by the electronic cat eye;
the detection module 302 is configured to detect a person in the on-site surveillance video;
the portrait matching module 303 is configured to, if it is determined that the live surveillance video includes a portrait image, perform matching detection on the portrait image to obtain a matching result, and send the matching result to the terminal, so that the terminal performs recognition prompt on the portrait image according to the matching result;
and the scene classification module 304 is configured to, if it is determined that the live surveillance video does not include the character image, classify the scene of the live surveillance video to obtain a classification result, and send the classification result to the terminal, so that the terminal performs scene prompt according to the classification result.
Further, the detection module is further configured to:
determining a starting node and an ending node according to a preset time interval;
dividing the field monitoring video into a plurality of frames of monitoring images, and acquiring one frame of monitoring image corresponding to the starting node and the ending node from the plurality of frames of monitoring images to obtain a starting monitoring image and an ending monitoring image;
performing feature matching on the starting monitoring image and the ending monitoring image, and extracting distinguishing image features between the starting monitoring image and the ending monitoring image;
matching and calculating the distinguishing image features and preset human body features to obtain an image matching value;
if the image matching value is larger than or equal to a preset value, determining that the on-site monitoring video contains a character image;
and if the image matching value is smaller than a preset value, determining that the live monitoring video does not contain the character image.
Further, the portrait matching module is further configured to:
extracting face features to be identified in the character image;
respectively matching the face features to be recognized with a plurality of preset face features, wherein the plurality of preset face features are face features respectively corresponding to a plurality of family member images added by a user;
if the face feature to be identified is matched with any one of a plurality of preset face features, a successful matching result is generated, and the successful matching result and a family member image corresponding to the face feature to be identified are sent to the terminal, so that the terminal displays the successful matching result and the family member image corresponding to the face feature to be identified to carry out identification prompt of the figure image;
if the face features to be recognized are not matched with the preset face features, an unsuccessful matching result is generated, and the unsuccessful matching result and the character image are sent to the terminal, so that the terminal displays the unsuccessful matching result and the character image to recognize and prompt the character image.
Further, the electronic cat eye is provided with a communicator, and the device further comprises:
the receiving information module is used for receiving voice information sent by the terminal, wherein the voice information is acquired by the terminal after the user identifies the unsuccessful matching result and the character image;
and the information sending module is used for sending the voice information to the electronic cat eye so that the electronic cat eye can play the voice information through the communicator.
Further, the scene module is further configured to:
dividing the field monitoring video into a plurality of frames of field images according to a preset frame number, and mutually superposing the plurality of frames of field images to obtain a superposed image;
acquiring image pixel values of the superimposed image, and respectively calculating distance values between the image pixel values and a plurality of preset category center points by adopting the aggregation algorithm to obtain a plurality of category distance values;
searching a target category distance value with the smallest value from the plurality of category distance values, taking a category corresponding to the target category distance value as a classification result, and sending the classification result to the terminal.
Further, an embodiment of the present application further provides an electronic device, including: the system comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes the communication prompting method of the electronic cat eye according to the embodiment when executing the program.
Further, an embodiment of the present application further provides a computer readable storage medium, where computer executable instructions are stored, where the computer executable instructions are configured to cause a computer to execute the communication prompting method of the electronic cat eye according to the foregoing embodiment.
While the foregoing is directed to the preferred embodiments of the present application, it will be appreciated by those skilled in the art that changes and modifications may be made without departing from the principles of the application, such changes and modifications are also intended to be within the scope of the application.
Claims (8)
1. The communication prompting method of the electronic cat eye is characterized by being applied to a cradle head server, wherein the cradle head server is respectively connected with a terminal and the electronic cat eye, and the method comprises the following steps:
receiving the field monitoring video acquired by the electronic cat eye;
performing person detection on the field monitoring video;
if the live monitoring video contains the figure image, carrying out matching detection on the figure image to obtain a matching result, and sending the matching result to the terminal so that the terminal carries out recognition prompt on the figure image according to the matching result;
if the scene monitoring video does not contain the character image, classifying the scene of the scene monitoring video to obtain a classification result, and sending the classification result to the terminal so that the terminal carries out scene prompt according to the classification result;
wherein, the person detection for the on-site monitoring video includes:
determining a starting node and an ending node according to a preset time interval;
dividing the field monitoring video into a plurality of frames of monitoring images, and acquiring one frame of monitoring image corresponding to the starting node and the ending node from the plurality of frames of monitoring images to obtain a starting monitoring image and an ending monitoring image;
performing feature matching on the starting monitoring image and the ending monitoring image, and extracting distinguishing image features between the starting monitoring image and the ending monitoring image;
matching and calculating the distinguishing image features and preset human body features to obtain an image matching value;
if the image matching value is larger than or equal to a preset value, determining that the on-site monitoring video contains a character image;
if the image matching value is smaller than a preset value, determining that the on-site monitoring video does not contain the character image;
the determining the starting node and the ending node according to the preset time interval comprises the following steps:
the preset time interval is the time interval between the starting node and the ending node, the starting node and the ending node are determined, and then the on-site monitoring video is sampled and detected through the starting node and the ending node.
2. The communication prompting method of an electronic cat eye according to claim 1, wherein the performing the matching detection on the character image to obtain a matching result, and sending the matching result to the terminal, so that the terminal performs the recognition prompting of the character image according to the matching result, includes:
extracting face features to be identified in the character image;
respectively matching the face features to be recognized with a plurality of preset face features, wherein the plurality of preset face features are face features respectively corresponding to a plurality of family member images added by a user;
if the face feature to be identified is matched with any one of a plurality of preset face features, a successful matching result is generated, and the successful matching result and a family member image corresponding to the face feature to be identified are sent to the terminal, so that the terminal displays the successful matching result and the family member image corresponding to the face feature to be identified to carry out identification prompt of the figure image;
if the face features to be recognized are not matched with the preset face features, an unsuccessful matching result is generated, and the unsuccessful matching result and the character image are sent to the terminal, so that the terminal displays the unsuccessful matching result and the character image to recognize and prompt the character image.
3. The communication prompting method of an electronic cat eye according to claim 2, wherein the electronic cat eye is provided with a communicator, the method further comprising:
receiving voice information sent by the terminal, wherein the voice information is acquired by the terminal after the user identifies the unsuccessful matching result and the character image;
and sending the voice information to the electronic cat eye so that the electronic cat eye can play the voice information through the communicator.
4. The method for prompting communication of an electronic cat eye according to claim 1, wherein if the scene classification is performed on the live monitoring video to obtain a classification result, sending the classification result to the terminal comprises:
dividing the field monitoring video into a plurality of frames of field images according to a preset frame number, and mutually superposing the plurality of frames of field images to obtain a superposed image;
acquiring image pixel values of the superimposed image, and respectively calculating distance values between the image pixel values and a plurality of preset category center points by adopting an aggregation algorithm to obtain a plurality of category distance values;
searching a target category distance value with the smallest value from the plurality of category distance values, taking a category corresponding to the target category distance value as a classification result, and sending the classification result to the terminal.
5. The utility model provides a communication suggestion device of electron cat eye, its characterized in that is applied to cloud platform server, cloud platform server is terminal and electron cat eye connection respectively, the device includes:
the receiving module is used for receiving the field monitoring video acquired by the electronic cat eye;
the detection module is used for detecting the characters in the field monitoring video;
the image matching module is used for carrying out matching detection on the person images to obtain matching results if the person images are determined to be contained in the live monitoring video, and sending the matching results to the terminal so that the terminal carries out recognition prompt on the person images according to the matching results;
the scene classification module is used for classifying the scene of the on-site monitoring video to obtain a classification result if the on-site monitoring video does not contain the character image, and sending the classification result to the terminal so that the terminal carries out scene prompt according to the classification result;
wherein, the detection module is further used for:
determining a starting node and an ending node according to a preset time interval;
dividing the field monitoring video into a plurality of frames of monitoring images, and acquiring one frame of monitoring image corresponding to the starting node and the ending node from the plurality of frames of monitoring images to obtain a starting monitoring image and an ending monitoring image;
performing feature matching on the starting monitoring image and the ending monitoring image, and extracting distinguishing image features between the starting monitoring image and the ending monitoring image;
matching and calculating the distinguishing image features and preset human body features to obtain an image matching value;
if the image matching value is larger than or equal to a preset value, determining that the on-site monitoring video contains a character image;
if the image matching value is smaller than a preset value, determining that the on-site monitoring video does not contain the character image;
the determining the starting node and the ending node according to the preset time interval comprises the following steps:
the preset time interval is the time interval between the starting node and the ending node, the starting node and the ending node are determined, and then the on-site monitoring video is sampled and detected through the starting node and the ending node.
6. The electronic cat eye communication prompting device according to claim 5, wherein said portrait matching module is further configured to:
extracting face features to be identified in the character image;
respectively matching the face features to be recognized with a plurality of preset face features, wherein the plurality of preset face features are face features respectively corresponding to a plurality of family member images added by a user;
if the face feature to be identified is matched with any one of a plurality of preset face features, a successful matching result is generated, and the successful matching result and a family member image corresponding to the face feature to be identified are sent to the terminal, so that the terminal displays the successful matching result and the family member image corresponding to the face feature to be identified to carry out identification prompt of the figure image;
if the face features to be recognized are not matched with the preset face features, an unsuccessful matching result is generated, and the unsuccessful matching result and the character image are sent to the terminal, so that the terminal displays the unsuccessful matching result and the character image to recognize and prompt the character image.
7. The communication prompting device of claim 6 wherein said electronic cat eye is provided with a communicator, said device further comprising:
the receiving information module is used for receiving voice information sent by the terminal, wherein the voice information is acquired by the terminal after the user identifies the unsuccessful matching result and the character image;
and the information sending module is used for sending the voice information to the electronic cat eye so that the electronic cat eye can play the voice information through the communicator.
8. The electronic cat eye communication prompting device according to claim 5, wherein said scene module is further configured to:
dividing the field monitoring video into a plurality of frames of field images according to a preset frame number, and mutually superposing the plurality of frames of field images to obtain a superposed image;
acquiring image pixel values of the superimposed image, and respectively calculating distance values between the image pixel values and a plurality of preset category center points by adopting an aggregation algorithm to obtain a plurality of category distance values;
searching a target category distance value with the smallest value from the plurality of category distance values, taking a category corresponding to the target category distance value as a classification result, and sending the classification result to the terminal.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011639747.3A CN112804492B (en) | 2020-12-31 | 2020-12-31 | Communication prompting method and device for electronic peepholes |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011639747.3A CN112804492B (en) | 2020-12-31 | 2020-12-31 | Communication prompting method and device for electronic peepholes |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112804492A CN112804492A (en) | 2021-05-14 |
CN112804492B true CN112804492B (en) | 2023-12-01 |
Family
ID=75809070
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011639747.3A Active CN112804492B (en) | 2020-12-31 | 2020-12-31 | Communication prompting method and device for electronic peepholes |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112804492B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113946701B (en) * | 2021-09-14 | 2024-03-19 | 广州市城市规划设计有限公司 | Dynamic updating method and device for urban and rural planning data based on image processing |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101017591A (en) * | 2007-02-06 | 2007-08-15 | 重庆大学 | Video safety prevention and monitoring method based on biology sensing and image information fusion |
CN102547241A (en) * | 2011-12-31 | 2012-07-04 | 深圳市永达电子股份有限公司 | Home anomaly detection method and home anomaly detection device as well as home anomaly detection system on basis of wireless network camera |
CN103268680A (en) * | 2013-05-29 | 2013-08-28 | 北京航空航天大学 | Intelligent monitoring and anti-theft system for family |
WO2017079891A1 (en) * | 2015-11-10 | 2017-05-18 | 深圳市奥芯博电子科技有限公司 | Smart door viewer system and smart door viewer |
CN107506755A (en) * | 2017-09-26 | 2017-12-22 | 云丁网络技术(北京)有限公司 | Monitoring video recognition methods and device |
CN107563352A (en) * | 2017-09-26 | 2018-01-09 | 云丁网络技术(北京)有限公司 | A kind of method and device of the outer visitor's identity of recognitiion gate |
CN109767594A (en) * | 2019-01-30 | 2019-05-17 | 长视科技股份有限公司 | A kind of household monitor video intelligent linkage early warning system |
CN110223474A (en) * | 2019-07-04 | 2019-09-10 | 无锡睿勤科技有限公司 | A kind of intelligent monitoring and alarming method, system and storage medium |
-
2020
- 2020-12-31 CN CN202011639747.3A patent/CN112804492B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101017591A (en) * | 2007-02-06 | 2007-08-15 | 重庆大学 | Video safety prevention and monitoring method based on biology sensing and image information fusion |
CN102547241A (en) * | 2011-12-31 | 2012-07-04 | 深圳市永达电子股份有限公司 | Home anomaly detection method and home anomaly detection device as well as home anomaly detection system on basis of wireless network camera |
CN103268680A (en) * | 2013-05-29 | 2013-08-28 | 北京航空航天大学 | Intelligent monitoring and anti-theft system for family |
WO2017079891A1 (en) * | 2015-11-10 | 2017-05-18 | 深圳市奥芯博电子科技有限公司 | Smart door viewer system and smart door viewer |
CN107506755A (en) * | 2017-09-26 | 2017-12-22 | 云丁网络技术(北京)有限公司 | Monitoring video recognition methods and device |
CN107563352A (en) * | 2017-09-26 | 2018-01-09 | 云丁网络技术(北京)有限公司 | A kind of method and device of the outer visitor's identity of recognitiion gate |
CN109767594A (en) * | 2019-01-30 | 2019-05-17 | 长视科技股份有限公司 | A kind of household monitor video intelligent linkage early warning system |
CN110223474A (en) * | 2019-07-04 | 2019-09-10 | 无锡睿勤科技有限公司 | A kind of intelligent monitoring and alarming method, system and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN112804492A (en) | 2021-05-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108073577A (en) | A kind of alarm method and system based on recognition of face | |
US20080136934A1 (en) | Flame Detecting Method And Device | |
CN109040693B (en) | Intelligent alarm system and method | |
CN101404107A (en) | Internet bar monitoring and warning system based on human face recognition technology | |
CN107403165B (en) | Data management architecture of intelligent face recognition system and use method | |
CN102521578A (en) | Method for detecting and identifying intrusion | |
CN109117821A (en) | A kind of face identification system and method for law-enforcing recorder | |
US10657783B2 (en) | Video surveillance method based on object detection and system thereof | |
KR20190035186A (en) | Intelligent unmanned security system using deep learning technique | |
CN110852306A (en) | Safety monitoring system based on artificial intelligence | |
KR101084914B1 (en) | Indexing management system of vehicle-number and man-image | |
CN112188164A (en) | AI vision-based violation real-time monitoring system and method | |
CN111629184A (en) | Video monitoring alarm system and method capable of identifying personnel in monitoring area | |
CN111178241A (en) | Intelligent monitoring system and method based on video analysis | |
CN112102574B (en) | Intelligent alarm system for security room | |
CN112804492B (en) | Communication prompting method and device for electronic peepholes | |
JP5088463B2 (en) | Monitoring system | |
CN212181464U (en) | Intelligent monitoring system capable of comparing large databases | |
CN112989993A (en) | Recording method, recording system, and computer-readable storage medium | |
CN112312084A (en) | Intelligent image monitoring system | |
CN115762030A (en) | Big data and artificial intelligence security monitoring system | |
CN113645439B (en) | Event detection method and system, storage medium and electronic device | |
CN112601054B (en) | Pickup picture acquisition method and device, storage medium and electronic equipment | |
KR20230167549A (en) | The apparatus and method of monitoring cctv with control moudule | |
US20230306711A1 (en) | Monitoring system, camera, analyzing device, and ai model generating method |
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 |