CN113283374B - Face recognition station passenger state monitoring and early warning system based on Internet of things - Google Patents
Face recognition station passenger state monitoring and early warning system based on Internet of things Download PDFInfo
- Publication number
- CN113283374B CN113283374B CN202110644585.0A CN202110644585A CN113283374B CN 113283374 B CN113283374 B CN 113283374B CN 202110644585 A CN202110644585 A CN 202110644585A CN 113283374 B CN113283374 B CN 113283374B
- Authority
- CN
- China
- Prior art keywords
- passenger
- early warning
- smoke
- passengers
- monitoring
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 110
- 230000000391 smoking effect Effects 0.000 claims abstract description 49
- 239000000779 smoke Substances 0.000 claims description 109
- 238000012545 processing Methods 0.000 claims description 17
- 235000019504 cigarettes Nutrition 0.000 claims description 12
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 230000002093 peripheral effect Effects 0.000 claims description 6
- 230000006399 behavior Effects 0.000 claims description 3
- 238000013075 data extraction Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 3
- 230000006855 networking Effects 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims 1
- 238000000034 method Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
Classifications
-
- 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
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- 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
- G06V40/107—Static hand or arm
-
- 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
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B3/00—Audible signalling systems; Audible personal calling systems
- G08B3/10—Audible signalling systems; Audible personal calling systems using electric transmission; using electromagnetic transmission
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Electromagnetism (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a face recognition station passenger state monitoring and early warning system based on the Internet of things, which comprises the following steps: the system comprises an inbound image acquisition module, a passenger position locking module and a monitoring and early warning module, wherein the monitoring and early warning module comprises ticket checking monitoring and early warning and smoking monitoring and early warning. The invention can monitor the state of the passenger according to various conditions, implement different early warning modes according to different states of the passenger, and even remind the passenger point to point according to special conditions.
Description
Technical Field
The invention relates to the technical field of station passenger state monitoring, in particular to a face recognition station passenger state monitoring and early warning system based on the Internet of things.
Background
Along with the rapid development of the Internet of things, the Internet of things gradually enters the field of vision of people, and the actual demands of people are further met through the Internet of things, so that great convenience is brought to the life of people. Along with the popularization of the face recognition technology in actual life, people can recognize and confirm the faces of people, and further distinguish different people.
In the aspect of the current monitoring technology of the state of the station passenger, only the voice notification is carried out on the ticket checking vehicle when checking the ticket, but due to some special conditions, the passenger can not hear the broadcast content in time, and further the ticket checking time is missed, meanwhile, in the station, although smoking is forbidden, specific monitoring measures are not perfect, the monitoring degree is not high, and the monitoring effect is not good because of the consciousness of the passenger.
Aiming at the situation, the face recognition station passenger state monitoring and early warning system based on the Internet of things is needed, the states of passengers can be monitored according to various situations, different early warning modes are implemented according to the different states of the passengers, even the passengers are reminded in a point-to-point mode according to special situations, the monitoring and early warning effects of the mode are better, the monitoring efficiency of the passengers is higher, the situation of smoking of the passengers can be effectively avoided, and meanwhile the situation that the passengers miss corresponding train ticket checking time can be effectively avoided.
Disclosure of Invention
The invention aims to provide a face recognition station passenger state monitoring and early warning system based on the Internet of things, which aims to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: face recognition station passenger state monitoring and early warning system based on thing networking includes: the system comprises an inbound image acquisition module, a passenger position locking module and a monitoring and early-warning module, wherein the monitoring and early-warning module comprises a ticket checking monitoring and early-warning module and a smoking monitoring and early-warning module,
The inbound image acquisition module is used for carrying out face recognition and travel data extraction on a passenger when the passenger arrives at the station through security inspection equipment of the station, extracting the appearance characteristics of the passenger, and binding face information, appearance characteristics and travel data of the passenger;
The passenger position locking module is used for acquiring images of passengers in each waiting room through cameras in each waiting room, comparing the acquired images with face information and appearance characteristics of each inbound passenger, further determining the passenger corresponding to the acquired images, and binding the current position of the passenger with the passenger information;
the smoke monitoring and early warning module monitors smoke through the smoke collecting devices in each waiting room, and when a certain smoke collecting device monitors that the smoke content exceeds a specified index, the smoke monitoring and early warning module can mobilize the adjacent cameras of the smoke collecting device to collect images in the area, judge the source of the smoke, lock the identity of a smoker and give a smoke alarm;
And the ticket checking monitoring and early warning module performs early warning and reminding on passengers corresponding to the corresponding trains in corresponding time before and after ticket checking of the trains according to the travel information of the passengers entering the station and the positions of the passengers, which are acquired by the image acquisition module, acquired by the passenger position locking module.
The invention realizes the monitoring and early warning of the state of the passenger through the cooperation of the modules, the inbound image acquisition module mainly acquires the information of the inbound passenger, the passenger position locking module mainly determines the position of the passenger through the camera and binds the current position of the passenger with the passenger, the smoking monitoring and early warning module mainly monitors the smoking state of the passenger and adopts different early warning measures according to different monitoring results, and the ticket checking monitoring and early warning module mainly monitors the state of the passenger in different time periods according to the relative ticket checking beginning and adopts different early warning measures according to different time periods and different passenger states.
Further, the appearance features of the passengers in the inbound image acquisition module comprise: the hairstyle, the color, the pattern, the style, the size and the color of the carried luggage when the passenger enters the station,
The color, pattern and style of the clothes worn by the passengers are classified as the first appearance characteristics,
Classifying the hairstyle of the passenger when the passenger enters the station into a second type of appearance characteristic,
Classifying the size and the color of the baggage carried by the passenger into a third type of appearance characteristics;
The trip data includes: the number of the vehicle taken by the passenger when the passenger starts from the station, the corresponding waiting room number, the ticket number, the seat number and the reserved mobile phone number when the passenger purchases the ticket.
The appearance characteristics are divided into three types by the inbound image acquisition module, because the hairstyle is least easy to change, the color, pattern and style of clothes worn by a passenger can be influenced by the temperature in a station or the personal wish of the passenger, when the passenger removes the coat, the appearance characteristics can be changed, and the appearance characteristics of a third type are also easy to change and even can be transferred to other passengers, so that the appearance characteristics are divided into three types, and the comparison is more convenient.
Further, the passenger position locking module analyzes images acquired by the serial number cameras in each waiting room at the same time in a multithreading mode, recognizes each passenger in the images according to a specific recognition mode, binds passenger information with the current position, and the areas shot by the serial number cameras in each waiting room are not intersected with each other.
The passenger position locking module controls more cameras, but in the aspect of data acquisition and analysis, the data are required to be analyzed and processed at the same time, so that the image analysis and processing speed can be increased by adopting a multithreading mode. The fact that the areas shot by the serial cameras in each waiting room are not intersected is to avoid that passengers shot by the intersecting parts of pictures acquired by the cameras are analyzed and processed many times, and the binding positions of the passengers are not fixed, so that the binding positions are displayed in multiple simultaneously.
Further, the specific identification mode in the passenger position locking module comprises the following steps:
S1, obtaining appearance characteristics and face information of a passenger obtained in an inbound image acquisition module;
S2, gray scale processing is carried out on images acquired by each serial number camera in each waiting room once every first unit time, the difference of gray scale values of adjacent pixel points is compared with a first preset value, when the difference is larger than the first preset value, the positions of the pixel points with larger gray scale values are recorded, and the corresponding picture information of the outline formed by the recorded pixel points in the original image is extracted;
S3, respectively comparing the extracted picture information with the appearance characteristics corresponding to each passenger, and when the picture information contains any two types of appearance characteristics corresponding to a certain passenger, listing the face information and the appearance characteristics corresponding to the passenger into a first comparison database corresponding to the picture information;
S4, extracting face information corresponding to each passenger in the first comparison database, and comparing the face information with the picture information respectively to acquire the similarity between the face information corresponding to each passenger and the picture information;
S5, taking the passenger corresponding to the highest similarity as the passenger corresponding to the picture information, marking the passenger with a time stamp, and binding the passenger with a camera number corresponding to a waiting room corresponding to the picture information;
S6, counting the number of the timestamp marks acquired in the second unit time of each passenger, performing abnormal marking on the timestamp marks acquired by the passenger in the second unit time when the number of the acquired timestamp marks is larger than a second preset value, and performing re-identification comparison on picture information corresponding to the abnormally marked timestamp marks, wherein in the acquisition of the similarity, the appearance features corresponding to the passengers are listed as reference factors, and the final similarity between the picture information and each passenger in the corresponding first comparison database is obtained;
And S7, taking the passenger corresponding to the highest final similarity as the passenger corresponding to the picture information, deleting the timestamp of the abnormal mark corresponding to the picture information and the corresponding camera number in the corresponding waiting room in a binding manner, and timestamp marking the passenger corresponding to the highest final similarity, and binding the passenger with the camera number corresponding to the waiting room corresponding to the picture information, wherein the position of the number camera corresponding to the waiting room corresponding to the picture information is the current position of the passenger.
Further, the smoke monitoring and early warning module acquires images acquired in the range of the area by the adjacent cameras of the smoke acquisition device, extracts the self and peripheral pictures of each passenger in the images,
Processing the extracted picture according to RGB values of each pixel point, comparing the RGB value of each pixel point in the extracted picture with a reference RGB value corresponding to smoke color in a second comparison database, further extracting the pixel points with RGB values conforming to the smoke color in the extracted picture, then processing gray values of the obtained result, comparing gray value differences between adjacent pixel points after gray value processing, marking the pixel points with larger gray values, corresponding to the first threshold value, with the gray value differences larger than the gray value, obtaining a contour surrounded by the marked pixel points according to the position relation between all the marked pixel points, overlapping the center point of the obtained contour with the center point of the smoke contour recorded in the second comparison database, executing a contour comparison mode, obtaining an error value w between the obtained contour and the comparison file,
When the error value w is smaller than or equal to the second threshold value, judging that the extracted picture contains smoke, listing the picture containing smoke into a third comparison database,
When the error value w is larger than the second threshold value, the extracted picture is judged to not contain smoke,
The contour comparison mode is to establish a same plane rectangular coordinate system by taking a coincident central point as an origin, in the plane rectangular coordinate system, equally dividing 360-degree peripheral angles corresponding to the origin by n, respectively taking the origin as a starting point, establishing each equal-divided ray along the direction of each equal-divided point, obtaining coordinates of each equal-divided ray in the plane rectangular coordinate system corresponding to the intersection point of the obtained contour and a comparison file respectively, calculating the distance between the coordinates, accumulating the distances corresponding to all the equal-divided rays, calculating an average value, wherein the obtained average value is the error value between the obtained contour and the comparison file,
Carrying out gray value processing on each picture in a third comparison database, comparing gray value differences between adjacent pixel points, further obtaining contours corresponding to objects in the mouth and the hands of passengers in the pictures, overlapping the center point of the contours corresponding to the objects in the mouth and the hands of the passengers in the pictures with the center point of the contours of the cigarettes recorded in a second comparison database, wherein the contours of the cigarettes recorded in the second comparison database are comparison files of the contours corresponding to the objects in the mouth and the hands of the passengers in the pictures, executing a contour comparison mode, obtaining error values m between the contours corresponding to the objects in the mouth and the hands of the passengers in the pictures and the comparison files,
When the error value w is smaller than or equal to a third threshold value, judging that the contours corresponding to the mouth and the objects in the hands of the passengers in the picture accord with the comparison file, and the picture corresponds to the smoke of the passengers;
When the error value w is larger than a third threshold value, determining that the contours corresponding to the mouth and the objects in the hands of the passengers in the picture are not consistent with the comparison file, wherein the picture corresponds to the passengers without smoking;
The smoking monitoring and early warning module carries out early warning and reminding on monitored passengers who smoke, and the modes of early warning and reminding are different according to the different duration time and smoking times of the monitored passengers.
The smoke monitoring and early warning module considers that the position of smoke is relatively fixed when a passenger draws the smoke, and the smoke is in the hand or the mouth, so that the mouth of the passenger and objects in the hand are matched with the smoke pattern recorded in the second comparison database, and whether the passenger draws the smoke is judged.
Further, the smoke monitoring and early warning module is used for early warning the smoke-drawing passengers as follows:
when the smoke monitoring and early warning module monitors smoke of the passengers for the first time, the smoke monitoring and early warning module reminds the passengers in a short message reminding mode;
when the duration of one smoke of the passenger is less than or equal to a third preset value, the smoke monitoring and early warning module reminds the passenger in a short message mode every third unit time;
When the duration of one smoke of the passenger is longer than a third preset value, the smoke monitoring and early warning module reminds every third unit time in a short message mode in a range that the duration is shorter than or equal to the third preset value, and in a range that the duration is longer than the third preset value, the smoke monitoring and early warning module transmits the face image of the passenger and the current position of the passenger acquired by the passenger position locking module to patrol personnel in a station, and the patrol personnel in the station stop smoking behaviors of the passenger and make corresponding penalties;
when the number of smoking of the passenger is greater than or equal to two, the smoking monitoring and early warning module can directly transmit the face image of the passenger and the current position of the passenger acquired in the passenger position locking module to patrol personnel in the station when the passenger smokes for the second time or more, and the patrol personnel in the station can stop smoking of the passenger and make corresponding punishment.
The invention considers the duration time of smoking and the smoking times of the passengers, and performs point-to-point early warning on the passengers, namely, the passengers are warned and reminded only by monitoring the smoking of the passengers, and the early warning mode is different according to different conditions, and short message reminding is performed first to remind the passengers to prohibit smoking, but when the passengers are not corrected, the patrol personnel can stop smoking of the passengers and make corresponding penalties, so that the passengers are prevented from continuing smoking, and meanwhile, the passengers are led to give up.
Furthermore, the ticket checking monitoring and early warning module carries out early warning and reminding on passengers corresponding to corresponding trains in corresponding time before and after ticket checking of the trains, the time from the beginning of ticket checking is different, the early warning and reminding modes on the passengers are different,
When the time before ticket checking and the distance from the beginning of ticket checking is the fourth unit time, the ticket checking monitoring and early warning module automatically counts passengers with the same number as the train number when the train starts in the passenger information of the train ticket purchased at the local station and the travel information acquired by the inbound image acquisition module, compares the passenger information and the passenger information, and further obtains the passenger information of the train ticket purchased at the local station and not inbound, and sends a short message to the passenger of the train ticket purchased at the local station and not inbound for reminding and early warning through the reserved mobile phone number when the ticket is purchased;
When the time before ticket checking and the distance from the beginning of ticket checking is smaller than the fourth unit time, the ticket checking monitoring and early warning module counts the passengers with the same number as the train number when the passenger starts at the station in the passenger information of buying the train ticket at the station and the travel information acquired by the incoming image acquisition module in real time, further acquires the current position bound by the passengers in the passenger position locking module, judges whether the position belongs to a waiting room corresponding to the train,
If the position belongs to the waiting room corresponding to the train, no reminding is carried out,
If the position does not belong to the waiting room corresponding to the train, voice reminding is carried out on the position, which is closest to the current position of the passenger, of the position every fifth unit time, so that the passenger is reminded to return to the waiting room to wait as soon as possible;
when the ticket checking starts to stop, the ticket checking monitoring and early warning module counts passengers with the same number as the train number when the passenger starts from the stop in real time in the travel information acquired by the incoming image acquisition module, further acquires the current position bound by the passengers in the passenger position locking module, judges whether the position belongs to a waiting room corresponding to the train,
If the position belongs to the waiting room corresponding to the train, voice reminding is carried out through the loudspeaker in the waiting room,
If the position does not belong to the waiting room corresponding to the train, a short message is sent to a passenger purchasing the train ticket at the station and not checking the ticket through a reserved mobile phone number when the ticket is purchased, so that reminding and early warning are carried out, and the passenger is reminded to return to the waiting room to check the ticket as soon as possible.
The ticket checking monitoring and early warning module considers different time periods from ticket checking starting time, whether a passenger enters a station or not and the current position of the passenger, and adopts different early warning modes according to different conditions.
Further, after ticket checking starts, when the smoking monitoring and early warning module monitors smoking of the passenger, the duration time of smoking and the smoking times of the passenger are not considered any more, the smoking monitoring and early warning module can directly transmit the face image of the passenger and the current position of the passenger obtained in the passenger position locking module to patrol personnel in the station, and the patrol personnel in the station stop smoking of the passenger and make corresponding punishment.
When the smoker is monitored after the ticket checking starts, the invention directly penalizes the passenger by the patrol personnel, because the smoke-absorbing passenger is the most dangerous, when the smoke-absorbing passenger sees the ticket checking state, the cigarette end can be directly discarded under the condition that the cigarette end is not extinguished due to emergency and other conditions, so that the smoke-absorbing passenger is most likely to cause fire disaster due to the self-condition, therefore, the patrol personnel is required to stop in time, the extinguishment of the cigarette end is ensured, and meanwhile, the passenger can be reminded to check the ticket in time.
Compared with the prior art, the invention has the following beneficial effects: the invention can monitor the state of the passenger according to various conditions, implement different early warning modes according to different states of the passenger, and even remind the passenger point to point according to special conditions.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
fig. 1 is a schematic diagram of the components of a station passenger state monitoring and early warning system based on the face recognition of the internet of things;
Fig. 2 is a schematic flow chart of a specific recognition mode in a passenger position locking module of a face recognition station passenger state monitoring and early warning system based on the internet of things;
Fig. 3 is a flow chart of a smoke monitoring and early warning module of the face recognition station passenger state monitoring and early warning system based on the internet of things for early warning a smoke-drawing passenger;
Fig. 4 is a flow chart of a method for warning and reminding passengers by a ticket checking monitoring and early warning module of a face recognition station passenger state monitoring and early warning system based on the internet of things.
Detailed Description
The following description of the embodiments of the present invention 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 invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-4, the present invention provides the following technical solutions: face recognition station passenger state monitoring and early warning system based on thing networking includes: the system comprises an inbound image acquisition module, a passenger position locking module and a monitoring and early-warning module, wherein the monitoring and early-warning module comprises a ticket checking monitoring and early-warning module and a smoking monitoring and early-warning module,
The inbound image acquisition module is used for carrying out face recognition and travel data extraction on a passenger when the passenger arrives at the station through security inspection equipment of the station, extracting the appearance characteristics of the passenger, and binding face information, appearance characteristics and travel data of the passenger;
The passenger position locking module is used for acquiring images of passengers in each waiting room through cameras in each waiting room, comparing the acquired images with face information and appearance characteristics of each inbound passenger, further determining the passenger corresponding to the acquired images, and binding the current position of the passenger with the passenger information;
the smoke monitoring and early warning module monitors smoke through the smoke collecting devices in each waiting room, and when a certain smoke collecting device monitors that the smoke content exceeds a specified index, the smoke monitoring and early warning module can mobilize the adjacent cameras of the smoke collecting device to collect images in the area, judge the source of the smoke, lock the identity of a smoker and give a smoke alarm;
And the ticket checking monitoring and early warning module performs early warning and reminding on passengers corresponding to the corresponding trains in corresponding time before and after ticket checking of the trains according to the travel information of the passengers entering the station and the positions of the passengers, which are acquired by the image acquisition module, acquired by the passenger position locking module.
The invention realizes the monitoring and early warning of the state of the passenger through the cooperation of the modules, the inbound image acquisition module mainly acquires the information of the inbound passenger, the passenger position locking module mainly determines the position of the passenger through the camera and binds the current position of the passenger with the passenger, the smoking monitoring and early warning module mainly monitors the smoking state of the passenger and adopts different early warning measures according to different monitoring results, and the ticket checking monitoring and early warning module mainly monitors the state of the passenger in different time periods according to the relative ticket checking beginning and adopts different early warning measures according to different time periods and different passenger states.
Appearance characteristics of passengers in the inbound image acquisition module comprise: the hairstyle, the color, the pattern, the style, the size and the color of the carried luggage when the passenger enters the station,
The color, pattern and style of the clothes worn by the passengers are classified as the first appearance characteristics,
Classifying the hairstyle of the passenger when the passenger enters the station into a second type of appearance characteristic,
Classifying the size and the color of the baggage carried by the passenger into a third type of appearance characteristics;
The trip data includes: the number of the vehicle taken by the passenger when the passenger starts from the station, the corresponding waiting room number, the ticket number, the seat number and the reserved mobile phone number when the passenger purchases the ticket.
The appearance characteristics are divided into three types by the inbound image acquisition module, because the hairstyle is least easy to change, the color, pattern and style of clothes worn by a passenger can be influenced by the temperature in a station or the personal wish of the passenger, when the passenger removes the coat, the appearance characteristics can be changed, and the appearance characteristics of a third type are also easy to change and even can be transferred to other passengers, so that the appearance characteristics are divided into three types, and the comparison is more convenient.
The passenger position locking module analyzes images acquired by the serial number cameras in each waiting room at the same time in a multithreading mode, recognizes each passenger in the images according to a specific recognition mode, binds passenger information with the current position, and the areas shot by the serial number cameras in each waiting room are not intersected with each other.
The passenger position locking module controls more cameras, but in the aspect of data acquisition and analysis, the data are required to be analyzed and processed at the same time, so that the image analysis and processing speed can be increased by adopting a multithreading mode. The fact that the areas shot by the serial cameras in each waiting room are not intersected is to avoid that passengers shot by the intersecting parts of pictures acquired by the cameras are analyzed and processed many times, and the binding positions of the passengers are not fixed, so that the binding positions are displayed in multiple simultaneously.
The specific identification mode in the passenger position locking module comprises the following steps:
S1, obtaining appearance characteristics and face information of a passenger obtained in an inbound image acquisition module;
S2, gray scale processing is carried out on images acquired by each serial number camera in each waiting room once every first unit time, the difference of gray scale values of adjacent pixel points is compared with a first preset value, when the difference is larger than the first preset value, the positions of the pixel points with larger gray scale values are recorded, and the corresponding picture information of the outline formed by the recorded pixel points in the original image is extracted;
S3, respectively comparing the extracted picture information with the appearance characteristics corresponding to each passenger, and when the picture information contains any two types of appearance characteristics corresponding to a certain passenger, listing the face information and the appearance characteristics corresponding to the passenger into a first comparison database corresponding to the picture information;
S4, extracting face information corresponding to each passenger in the first comparison database, and comparing the face information with the picture information respectively to acquire the similarity between the face information corresponding to each passenger and the picture information;
S5, taking the passenger corresponding to the highest similarity as the passenger corresponding to the picture information, marking the passenger with a time stamp, and binding the passenger with a camera number corresponding to a waiting room corresponding to the picture information;
S6, counting the number of the timestamp marks acquired in the second unit time of each passenger, performing abnormal marking on the timestamp marks acquired by the passenger in the second unit time when the number of the acquired timestamp marks is larger than a second preset value, and performing re-identification comparison on picture information corresponding to the abnormally marked timestamp marks, wherein in the acquisition of the similarity, the appearance features corresponding to the passengers are listed as reference factors, and the final similarity between the picture information and each passenger in the corresponding first comparison database is obtained;
And S7, taking the passenger corresponding to the highest final similarity as the passenger corresponding to the picture information, deleting the timestamp of the abnormal mark corresponding to the picture information and the corresponding camera number in the corresponding waiting room in a binding manner, and timestamp marking the passenger corresponding to the highest final similarity, and binding the passenger with the camera number corresponding to the waiting room corresponding to the picture information, wherein the position of the number camera corresponding to the waiting room corresponding to the picture information is the current position of the passenger.
The smoke monitoring and early warning module acquires images acquired in the range of the area by the adjacent cameras of the smoke acquisition device, extracts the self and peripheral pictures of each passenger in the images,
Processing the extracted picture according to RGB values of each pixel point, comparing the RGB value of each pixel point in the extracted picture with a reference RGB value corresponding to smoke color in a second comparison database, further extracting the pixel points with RGB values conforming to the smoke color in the extracted picture, then processing gray values of the obtained result, comparing gray value differences between adjacent pixel points after gray value processing, marking the pixel points with larger gray values, corresponding to the first threshold value, with the gray value differences larger than the gray value, obtaining a contour surrounded by the marked pixel points according to the position relation between all the marked pixel points, overlapping the center point of the obtained contour with the center point of the smoke contour recorded in the second comparison database, executing a contour comparison mode, obtaining an error value w between the obtained contour and the comparison file,
When the error value w is smaller than or equal to the second threshold value, judging that the extracted picture contains smoke, listing the picture containing smoke into a third comparison database,
When the error value w is larger than the second threshold value, the extracted picture is judged to not contain smoke,
The contour comparison mode is to establish a same plane rectangular coordinate system by taking a coincident central point as an origin, in the plane rectangular coordinate system, equally dividing 360-degree peripheral angles corresponding to the origin by n, respectively taking the origin as a starting point, establishing each equal-divided ray along the direction of each equal-divided point, obtaining coordinates of each equal-divided ray in the plane rectangular coordinate system corresponding to the intersection point of the obtained contour and a comparison file respectively, calculating the distance between the coordinates, accumulating the distances corresponding to all the equal-divided rays, calculating an average value, wherein the obtained average value is the error value between the obtained contour and the comparison file,
Carrying out gray value processing on each picture in a third comparison database, comparing gray value differences between adjacent pixel points, further obtaining contours corresponding to objects in the mouth and the hands of passengers in the pictures, overlapping the center point of the contours corresponding to the objects in the mouth and the hands of the passengers in the pictures with the center point of the contours of the cigarettes recorded in a second comparison database, wherein the contours of the cigarettes recorded in the second comparison database are comparison files of the contours corresponding to the objects in the mouth and the hands of the passengers in the pictures, executing a contour comparison mode, obtaining error values m between the contours corresponding to the objects in the mouth and the hands of the passengers in the pictures and the comparison files,
When the error value w is smaller than or equal to a third threshold value, judging that the contours corresponding to the mouth and the objects in the hands of the passengers in the picture accord with the comparison file, and the picture corresponds to the smoke of the passengers;
When the error value w is larger than a third threshold value, determining that the contours corresponding to the mouth and the objects in the hands of the passengers in the picture are not consistent with the comparison file, wherein the picture corresponds to the passengers without smoking;
The smoking monitoring and early warning module carries out early warning and reminding on monitored passengers who smoke, and the modes of early warning and reminding are different according to the different duration time and smoking times of the monitored passengers.
The smoke monitoring and early warning module considers that the position of smoke is relatively fixed when a passenger draws the smoke, and the smoke is in the hand or the mouth, so that the mouth of the passenger and objects in the hand are matched with the smoke pattern recorded in the second comparison database, and whether the passenger draws the smoke is judged.
The smoke monitoring and early warning module is used for early warning the smoke-drawing passengers in the following modes:
when the smoke monitoring and early warning module monitors smoke of the passengers for the first time, the smoke monitoring and early warning module reminds the passengers in a short message reminding mode;
when the duration of one smoke of the passenger is less than or equal to a third preset value, the smoke monitoring and early warning module reminds the passenger in a short message mode every third unit time;
When the duration of one smoke of the passenger is longer than a third preset value, the smoke monitoring and early warning module reminds every third unit time in a short message mode in a range that the duration is shorter than or equal to the third preset value, and in a range that the duration is longer than the third preset value, the smoke monitoring and early warning module transmits the face image of the passenger and the current position of the passenger acquired by the passenger position locking module to patrol personnel in a station, and the patrol personnel in the station stop smoking behaviors of the passenger and make corresponding penalties;
when the number of smoking of the passenger is greater than or equal to two, the smoking monitoring and early warning module can directly transmit the face image of the passenger and the current position of the passenger acquired in the passenger position locking module to patrol personnel in the station when the passenger smokes for the second time or more, and the patrol personnel in the station can stop smoking of the passenger and make corresponding punishment.
The invention considers the duration time of smoking and the smoking times of the passengers, and performs point-to-point early warning on the passengers, namely, the passengers are warned and reminded only by monitoring the smoking of the passengers, and the early warning mode is different according to different conditions, and short message reminding is performed first to remind the passengers to prohibit smoking, but when the passengers are not corrected, the patrol personnel can stop smoking of the passengers and make corresponding penalties, so that the passengers are prevented from continuing smoking, and meanwhile, the passengers are led to give up.
The ticket checking monitoring and early warning module carries out early warning and reminding on passengers corresponding to corresponding trains in corresponding time before and after ticket checking of the trains, the time from the beginning of ticket checking is different, the early warning and reminding modes on the passengers are different,
When the time before ticket checking and the distance from the beginning of ticket checking is the fourth unit time, the ticket checking monitoring and early warning module automatically counts passengers with the same number as the train number when the train starts in the passenger information of the train ticket purchased at the local station and the travel information acquired by the inbound image acquisition module, compares the passenger information and the passenger information, and further obtains the passenger information of the train ticket purchased at the local station and not inbound, and sends a short message to the passenger of the train ticket purchased at the local station and not inbound for reminding and early warning through the reserved mobile phone number when the ticket is purchased;
When the time before ticket checking and the distance from the beginning of ticket checking is smaller than the fourth unit time, the ticket checking monitoring and early warning module counts the passengers with the same number as the train number when the passenger starts at the station in the passenger information of buying the train ticket at the station and the travel information acquired by the incoming image acquisition module in real time, further acquires the current position bound by the passengers in the passenger position locking module, judges whether the position belongs to a waiting room corresponding to the train,
If the position belongs to the waiting room corresponding to the train, no reminding is carried out,
If the position does not belong to the waiting room corresponding to the train, voice reminding is carried out on the position, which is closest to the current position of the passenger, of the position every fifth unit time, so that the passenger is reminded to return to the waiting room to wait as soon as possible;
when the ticket checking starts to stop, the ticket checking monitoring and early warning module counts passengers with the same number as the train number when the passenger starts from the stop in real time in the travel information acquired by the incoming image acquisition module, further acquires the current position bound by the passengers in the passenger position locking module, judges whether the position belongs to a waiting room corresponding to the train,
If the position belongs to the waiting room corresponding to the train, voice reminding is carried out through the loudspeaker in the waiting room,
If the position does not belong to the waiting room corresponding to the train, a short message is sent to a passenger purchasing the train ticket at the station and not checking the ticket through a reserved mobile phone number when the ticket is purchased, so that reminding and early warning are carried out, and the passenger is reminded to return to the waiting room to check the ticket as soon as possible.
The ticket checking monitoring and early warning module considers different time periods from ticket checking starting time, whether a passenger enters a station or not and the current position of the passenger, and adopts different early warning modes according to different conditions.
When the smoke monitoring and early warning module monitors the smoke of the passenger after the ticket checking starts, the smoke duration and the smoke drawing times of the passenger are not considered any more, the smoke monitoring and early warning module can directly transmit the face image of the passenger and the current position of the passenger obtained in the passenger position locking module to patrol personnel in the station, and the patrol personnel in the station can stop the smoke of the passenger and make corresponding punishment.
When the smoker is monitored after the ticket checking starts, the invention directly penalizes the passenger by the patrol personnel, because the smoke-absorbing passenger is the most dangerous, when the smoke-absorbing passenger sees the ticket checking state, the cigarette end can be directly discarded under the condition that the cigarette end is not extinguished due to emergency and other conditions, so that the smoke-absorbing passenger is most likely to cause fire disaster due to the self-condition, therefore, the patrol personnel is required to stop in time, the extinguishment of the cigarette end is ensured, and meanwhile, the passenger can be reminded to check the ticket in time.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (5)
1. Face recognition station passenger state monitoring and early warning system based on thing networking, characterized by comprising: the system comprises an inbound image acquisition module, a passenger position locking module and a monitoring and early-warning module, wherein the monitoring and early-warning module comprises a ticket checking monitoring and early-warning module and a smoking monitoring and early-warning module,
The inbound image acquisition module is used for carrying out face recognition and travel data extraction on a passenger when the passenger arrives at the station through security inspection equipment of the station, extracting the appearance characteristics of the passenger, and binding face information, appearance characteristics and travel data of the passenger;
The passenger position locking module is used for acquiring images of passengers in each waiting room through cameras in each waiting room, comparing the acquired images with face information and appearance characteristics of each inbound passenger, further determining the passenger corresponding to the acquired images, and binding the current position of the passenger with the passenger information;
the smoke monitoring and early warning module monitors smoke through the smoke collecting devices in each waiting room, and when a certain smoke collecting device monitors that the smoke content exceeds a specified index, the smoke monitoring and early warning module can mobilize the adjacent cameras of the smoke collecting device to collect images in the area, judge the source of the smoke, lock the identity of a smoker and give a smoke alarm;
The ticket checking monitoring and early warning module performs early warning and reminding on passengers corresponding to the corresponding trains in corresponding time before and after ticket checking according to the travel information of the passengers at the stops acquired by the image acquisition module at the stops and the positions of the passengers acquired by the passenger position locking module;
Appearance characteristics of passengers in the inbound image acquisition module comprise: the hairstyle, the color, the pattern, the style, the size and the color of the carried luggage when the passenger enters the station,
The color, pattern and style of the clothes worn by the passengers are classified as the first appearance characteristics,
Classifying the hairstyle of the passenger when the passenger enters the station into a second type of appearance characteristic,
Classifying the size and the color of the baggage carried by the passenger into a third type of appearance characteristics;
the trip data includes: the number of the vehicle taken by the passenger when the passenger starts from the station, the corresponding waiting room number, the ticket number, the seat number and the reserved mobile phone number when the ticket is purchased;
The passenger position locking module analyzes images acquired by each serial number camera in each waiting room at the same time in a multithreading mode, recognizes each passenger in the images according to a specific recognition mode, binds passenger information with the current position, and the areas shot by each serial number camera in each waiting room are not intersected with each other;
The specific identification mode in the passenger position locking module comprises the following steps:
S1, obtaining appearance characteristics and face information of a passenger obtained in an inbound image acquisition module;
S2, gray scale processing is carried out on images acquired by each serial number camera in each waiting room once every first unit time, the difference of gray scale values of adjacent pixel points is compared with a first preset value, when the difference is larger than the first preset value, the positions of the pixel points with larger gray scale values are recorded, and the corresponding picture information of the outline formed by the recorded pixel points in the original image is extracted;
S3, respectively comparing the extracted picture information with the appearance characteristics corresponding to each passenger, and when the picture information contains any two types of appearance characteristics corresponding to a certain passenger, listing the face information and the appearance characteristics corresponding to the passenger into a first comparison database corresponding to the picture information;
S4, extracting face information corresponding to each passenger in the first comparison database, and comparing the face information with the picture information respectively to acquire the similarity between the face information corresponding to each passenger and the picture information;
S5, taking the passenger corresponding to the highest similarity as the passenger corresponding to the picture information, marking the passenger with a time stamp, and binding the passenger with a camera number corresponding to a waiting room corresponding to the picture information;
S6, counting the number of the timestamp marks acquired in the second unit time of each passenger, performing abnormal marking on the timestamp marks acquired by the passenger in the second unit time when the number of the acquired timestamp marks is larger than a second preset value, and performing re-identification comparison on picture information corresponding to the abnormally marked timestamp marks, wherein in the acquisition of the similarity, the appearance features corresponding to the passengers are listed as reference factors, and the final similarity between the picture information and each passenger in the corresponding first comparison database is obtained;
And S7, taking the passenger corresponding to the highest final similarity as the passenger corresponding to the picture information, deleting the timestamp of the abnormal mark corresponding to the picture information and the corresponding camera number in the corresponding waiting room in a binding manner, and timestamp marking the passenger corresponding to the highest final similarity, and binding the passenger with the camera number corresponding to the waiting room corresponding to the picture information, wherein the position of the number camera corresponding to the waiting room corresponding to the picture information is the current position of the passenger.
2. The face recognition station passenger state monitoring and early warning system based on the internet of things according to claim 1, wherein: the smoke monitoring and early warning module acquires images acquired in the range of the area by the adjacent cameras of the smoke acquisition device, extracts the self and peripheral pictures of each passenger in the images,
Processing the extracted picture according to RGB values of each pixel point, comparing the RGB value of each pixel point in the extracted picture with a reference RGB value corresponding to smoke color in a second comparison database, further extracting the pixel points with RGB values conforming to the smoke color in the extracted picture, then processing gray values of the obtained result, comparing gray value differences between adjacent pixel points after gray value processing, marking the pixel points with larger gray values, corresponding to the first threshold value, with the gray value differences larger than the gray value, obtaining a contour surrounded by the marked pixel points according to the position relation between all the marked pixel points, overlapping the center point of the obtained contour with the center point of the smoke contour recorded in the second comparison database, executing a contour comparison mode, obtaining an error value w between the obtained contour and the comparison file,
When the error value w is smaller than or equal to the second threshold value, judging that each passenger and the surrounding extraction pictures in the image contain smoke, listing the pictures containing the smoke into a third comparison database,
When the error value w is larger than the second threshold value, judging that the extracted pictures of the passengers and the surrounding in the image do not contain smoke,
The contour comparison mode is to establish a same plane rectangular coordinate system by taking a coincident central point as an origin, in the plane rectangular coordinate system, equally dividing 360-degree peripheral angles corresponding to the origin by n, respectively taking the origin as a starting point, establishing each equal-divided ray along the direction of each equal-divided point, obtaining coordinates of each equal-divided ray in the plane rectangular coordinate system corresponding to the intersection point of the obtained contour and a comparison file respectively, calculating the distance between the coordinates, accumulating the distances corresponding to all the equal-divided rays, calculating an average value, wherein the obtained average value is the error value between the obtained contour and the comparison file,
Carrying out gray value processing on each picture in a third comparison database, comparing gray value differences between adjacent pixel points, further obtaining contours corresponding to objects in the mouth and the hands of passengers in the pictures, overlapping the center point of the contours corresponding to the objects in the mouth and the hands of the passengers in the pictures with the center point of the contours of the cigarettes recorded in a second comparison database, wherein the contours of the cigarettes recorded in the second comparison database are comparison files of the contours corresponding to the objects in the mouth and the hands of the passengers in the pictures, executing a contour comparison mode, obtaining error values m between the contours corresponding to the objects in the mouth and the hands of the passengers in the pictures and the comparison files,
When the error value w is smaller than or equal to a third threshold value, judging that the contours corresponding to the mouth and the objects in the hands of the passengers in the picture accord with the comparison file, and the picture corresponds to the smoke of the passengers;
When the error value w is larger than a third threshold value, determining that the contours corresponding to the mouth and the objects in the hands of the passengers in the picture are not consistent with the comparison file, wherein the picture corresponds to the passengers without smoking;
The smoking monitoring and early warning module carries out early warning and reminding on monitored passengers who smoke, and the modes of early warning and reminding are different according to the different duration time and smoking times of the monitored passengers.
3. The face recognition station passenger state monitoring and early warning system based on the internet of things according to claim 2, wherein: the smoke monitoring and early warning module is used for early warning the smoke-drawing passengers in the following modes:
when the smoke monitoring and early warning module monitors smoke of the passengers for the first time, the smoke monitoring and early warning module reminds the passengers in a short message reminding mode;
when the duration of one smoke of the passenger is less than or equal to a third preset value, the smoke monitoring and early warning module reminds the passenger in a short message mode every third unit time;
When the duration of one smoke of the passenger is longer than a third preset value, the smoke monitoring and early warning module reminds every third unit time in a short message mode in a range that the duration is shorter than or equal to the third preset value, and in a range that the duration is longer than the third preset value, the smoke monitoring and early warning module transmits the face image of the passenger and the current position of the passenger acquired by the passenger position locking module to patrol personnel in a station, and the patrol personnel in the station stop smoking behaviors of the passenger and make corresponding penalties;
when the number of smoking of the passenger is greater than or equal to two, the smoking monitoring and early warning module can directly transmit the face image of the passenger and the current position of the passenger acquired in the passenger position locking module to patrol personnel in the station when the passenger smokes for the second time or more, and the patrol personnel in the station can stop smoking of the passenger and make corresponding punishment.
4. The face recognition station passenger state monitoring and early warning system based on the internet of things according to claim 1, wherein: the ticket checking monitoring and early warning module carries out early warning and reminding on passengers corresponding to corresponding trains in corresponding time before and after ticket checking of the trains, the time from the beginning of ticket checking is different, the early warning and reminding modes on the passengers are different,
When the time before ticket checking and the distance from the beginning of ticket checking is the fourth unit time, the ticket checking monitoring and early warning module automatically counts passengers with the same number as the train number when the train starts in the passenger information of the train ticket purchased at the local station and the travel information acquired by the inbound image acquisition module, compares the passenger information and the passenger information, and further obtains the passenger information of the train ticket purchased at the local station and not inbound, and sends a short message to the passenger of the train ticket purchased at the local station and not inbound for reminding and early warning through the reserved mobile phone number when the ticket is purchased;
When the time before ticket checking and the distance from the beginning of ticket checking is smaller than the fourth unit time, the ticket checking monitoring and early warning module counts the passengers with the same number as the train number when the passenger starts at the station in the passenger information of buying the train ticket at the station and the travel information acquired by the incoming image acquisition module in real time, further acquires the current position bound by the passengers in the passenger position locking module, judges whether the position belongs to a waiting room corresponding to the train,
If the position belongs to the waiting room corresponding to the train, no reminding is carried out,
If the position does not belong to the waiting room corresponding to the train, voice reminding is carried out on the position, which is closest to the current position of the passenger, of the position every fifth unit time, so that the passenger is reminded to return to the waiting room to wait as soon as possible;
when the ticket checking starts to stop, the ticket checking monitoring and early warning module counts passengers with the same number as the train number when the passenger starts from the stop in real time in the travel information acquired by the incoming image acquisition module, further acquires the current position bound by the passengers in the passenger position locking module, judges whether the position belongs to a waiting room corresponding to the train,
If the position belongs to the waiting room corresponding to the train, voice reminding is carried out through the loudspeaker in the waiting room,
If the position does not belong to the waiting room corresponding to the train, a short message is sent to a passenger purchasing the train ticket at the station and not checking the ticket through a reserved mobile phone number when the ticket is purchased, so that reminding and early warning are carried out, and the passenger is reminded to return to the waiting room to check the ticket as soon as possible.
5. The face recognition station passenger state monitoring and early warning system based on the internet of things according to claim 3, wherein: when the smoke monitoring and early warning module monitors the smoke of the passenger after the ticket checking starts, the smoke duration and the smoke drawing times of the passenger are not considered any more, the smoke monitoring and early warning module can directly transmit the face image of the passenger and the current position of the passenger obtained in the passenger position locking module to patrol personnel in the station, and the patrol personnel in the station can stop the smoke of the passenger and make corresponding punishment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110644585.0A CN113283374B (en) | 2021-06-09 | 2021-06-09 | Face recognition station passenger state monitoring and early warning system based on Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110644585.0A CN113283374B (en) | 2021-06-09 | 2021-06-09 | Face recognition station passenger state monitoring and early warning system based on Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113283374A CN113283374A (en) | 2021-08-20 |
| CN113283374B true CN113283374B (en) | 2024-05-03 |
Family
ID=77284030
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110644585.0A Active CN113283374B (en) | 2021-06-09 | 2021-06-09 | Face recognition station passenger state monitoring and early warning system based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113283374B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113920592A (en) * | 2021-09-07 | 2022-01-11 | 海南太美航空股份有限公司 | Flight service management system, method and storage medium |
| CN114613145B (en) * | 2022-05-12 | 2022-08-19 | 中运科技股份有限公司 | Passenger traffic flow perception early warning system and method under big data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107516086A (en) * | 2017-08-31 | 2017-12-26 | 北京中科奥森科技有限公司 | A kind of passenger traffic face identification system and method |
| CN207352667U (en) * | 2017-10-17 | 2018-05-11 | 郑州中软高科信息技术有限公司 | People-card based on recognition of face-ticket homogeneity people's row gate system |
| CN207352679U (en) * | 2017-09-01 | 2018-05-11 | 江苏阅衡智能科技有限公司 | Automatic ticket checking system based on recognition of face |
| CN112084824A (en) * | 2019-06-14 | 2020-12-15 | 杭州海康威视数字技术股份有限公司 | Passenger reminding method and device, electronic equipment and storage medium |
-
2021
- 2021-06-09 CN CN202110644585.0A patent/CN113283374B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107516086A (en) * | 2017-08-31 | 2017-12-26 | 北京中科奥森科技有限公司 | A kind of passenger traffic face identification system and method |
| CN207352679U (en) * | 2017-09-01 | 2018-05-11 | 江苏阅衡智能科技有限公司 | Automatic ticket checking system based on recognition of face |
| CN207352667U (en) * | 2017-10-17 | 2018-05-11 | 郑州中软高科信息技术有限公司 | People-card based on recognition of face-ticket homogeneity people's row gate system |
| CN112084824A (en) * | 2019-06-14 | 2020-12-15 | 杭州海康威视数字技术股份有限公司 | Passenger reminding method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113283374A (en) | 2021-08-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113283374B (en) | Face recognition station passenger state monitoring and early warning system based on Internet of things | |
| US9143843B2 (en) | Automated monitoring and control of safety in a production area | |
| US20140324281A1 (en) | Driver identification based on face data | |
| EP2553313B1 (en) | Automated monitoring and control of safety in a production area | |
| CN108537140B (en) | Method and system for identifying people in vehicle | |
| CN111209868A (en) | Passenger and luggage information association method and device for passenger station | |
| CN109544838B (en) | Artificial intelligence cognitive recognition system for special area | |
| CN108583592A (en) | A kind of subway service on buses or trains job information acquisition intelligent detecting method | |
| CN104574547A (en) | Method for preventing fee evasion on highways on basis of face recognition technologies | |
| CN109801421A (en) | A kind of subway intelligent and safe detection system and method | |
| CN103700220A (en) | Fatigue driving monitoring device | |
| CN112241696A (en) | Image processing method and device, electronic device and storage medium | |
| KR100948382B1 (en) | Security service method and system | |
| CN113239754A (en) | Dangerous driving behavior detection and positioning method and system applied to Internet of vehicles | |
| CN111899546A (en) | Smart city public traffic safety real-time monitoring and early warning system based on big data | |
| CN111404874A (en) | Taxi suspect vehicle discrimination analysis system architecture | |
| CN106327876B (en) | A kind of fake-licensed car capture system and method based on automobile data recorder | |
| CN114926824A (en) | Method for judging bad driving behavior | |
| CN109919134A (en) | A kind of vehicle in use personnel's anomaly detection method of view-based access control model | |
| CN113052140A (en) | Video-based substation personnel and vehicle violation detection method and system | |
| CN109214316B (en) | Perimeter protection method and device | |
| CN108460863A (en) | The monitoring method of personnel and vehicle, device and system in a kind of tunnel | |
| CN111694981A (en) | Gas station fee evasion alarm system and method based on machine vision | |
| CN111611966A (en) | Target person detection method, device, equipment and storage medium | |
| CN111126292A (en) | Safety monitoring method, device and system |
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 |