CN110376585B - Carriage congestion degree detection method, device and system based on 3D radar scanning - Google Patents
Carriage congestion degree detection method, device and system based on 3D radar scanning Download PDFInfo
- Publication number
- CN110376585B CN110376585B CN201910666603.8A CN201910666603A CN110376585B CN 110376585 B CN110376585 B CN 110376585B CN 201910666603 A CN201910666603 A CN 201910666603A CN 110376585 B CN110376585 B CN 110376585B
- Authority
- CN
- China
- Prior art keywords
- target
- passengers
- train
- scanning
- carriage
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/89—Radar or analogous systems specially adapted for specific applications for mapping or imaging
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/415—Identification of targets based on measurements of movement associated with the target
Abstract
The embodiment of the invention provides a 3D radar scanning-based carriage congestion degree detection method, a device and a system, wherein point cloud data of passengers getting on and off a train scanned by a 3D radar arranged above a carriage door are obtained, two-dimensional characteristic data are obtained from the point cloud data, and then target two-dimensional characteristic data corresponding to the passengers are marked from the two-dimensional characteristic data through a pre-trained recognition model. And tracking the two-dimensional characteristic data of each target to obtain the walking direction of the corresponding passenger, counting the number of people getting on or off the train at the current station according to the walking direction of each passenger, calculating the number of passengers in the carriage when the train leaves the station, sending the number of the passengers to the next station, and displaying the number at the next station. Before the passengers arrive at the next station, the counted number of the passengers in each carriage is displayed, so that the waiting passengers can select the station according to the number of the passengers in each carriage, the blind waiting is avoided, and the carrying capacity of the train is improved.
Description
Technical Field
The invention relates to the technical field of train capacity, in particular to a method, a device and a system for detecting the degree of carriage congestion based on 3D radar scanning.
Background
At present, in the running process of a train, before the train arrives at a station, passengers on the station cannot know the number of passengers in each carriage. Therefore, the congestion of each train of cars cannot be predicted when waiting, and the waiting is only blind. Particularly, in peak time, the parking time of the vehicle is short, passengers cannot predict the degree of congestion of each train of carriages, so that some passengers in the carriages are very congested, and the space of some carriages is very loose, so that the space is wasted, and the carrying capacity of the train is reduced. When the number of passengers is too large, the passengers in the station can be detained to a certain extent, and the normal operation and management in the station are influenced.
In the practical application process, the inventor finds that in the existing train running process, passengers cannot know the number of passengers in each compartment of a train to be arrived, so that the passengers can wait for the train blindly and the train capacity is influenced.
Disclosure of Invention
The embodiment of the invention provides a carriage congestion degree detection method, a device and a system based on 3D radar scanning, which are used for solving the problems that in the running process of a train in the prior art, passengers cannot know the number of passengers in each carriage of the train to be arrived, so that the passengers can wait for the train blindly and the train capacity is influenced.
In view of the above technical problems, in a first aspect, an embodiment of the present invention provides a method for detecting a degree of congestion of a car based on 3D radar scanning, including:
for any target compartment of the train, point cloud data of passengers getting on or off the train at the current station through the doors of the target compartment, which is obtained through 3D radar scanning, is obtained, and two-dimensional characteristic data is obtained from the point cloud data;
marking scanning points formed by scanning passengers from the two-dimensional characteristic data through a pre-trained recognition model, using the scanning points as target two-dimensional characteristic data, tracking each target two-dimensional characteristic data, and obtaining the walking direction of the passengers corresponding to the target two-dimensional characteristic data;
counting the number of first passengers entering the target compartment and the number of second passengers leaving the target compartment at the current station according to the walking direction of each passenger, acquiring the number of existing passengers in the target compartment when the train leaves the previous station, calculating the number of target passengers in the target compartment when the train leaves the current station according to the number of the first passengers, the number of the second passengers and the number of the existing passengers, and sending the number of the target passengers so as to display the number of the target passengers at the next station;
the identification model is used for marking data which are in accordance with human-shaped features from the two-dimensional feature data and is used as target two-dimensional feature data formed by scanning passengers; the two-dimensional feature data refers to a set of scanning points on a two-dimensional plane including the scanning points and parallel to the target car door, which is cut out from the point cloud data.
Optionally, the training of the recognition model comprises:
the method comprises the steps of obtaining point cloud data obtained by scanning passengers getting on and off in advance, obtaining two-dimensional characteristic data obtained by the obtained point cloud data through two-dimensional peak searching, marking data formed by scanning the passengers in each two-dimensional characteristic data, taking the two-dimensional characteristic data before marking as an input parameter of deep learning, taking the two-dimensional characteristic data after marking as expected output of the deep learning, and taking a model trained through the deep learning as the recognition model.
Optionally, the tracking each target two-dimensional feature data to obtain a walking direction of the passenger corresponding to the target two-dimensional feature data includes:
for each target two-dimensional characteristic data, acquiring a first position in point cloud data obtained by scanning the target two-dimensional characteristic data at the last time or the next time, acquiring a second position in the point cloud data obtained by scanning the target two-dimensional characteristic data at this time, and determining the walking direction of a passenger corresponding to the target two-dimensional characteristic data according to the first position and the second position.
Optionally, the sending the target passenger number to display the target passenger number at a next stop includes:
acquiring a preset mapping relation between the congestion degree of a carriage and the number of passengers in the carriage, determining the congestion degree of the target carriage when a train drives away from the current station according to the mapping relation and the target passenger number, taking the congestion degree as a target congestion degree, and sending the target passenger number and the target congestion degree to a passenger information system PIS so as to display the target passenger number and the target congestion degree through a display device of a next station;
wherein the target congestion degree is represented by a color that is set in advance and corresponds to the target congestion degree.
Optionally, the mapping relationship includes:
when the number of passengers in the carriage is less than a first preset number, the degree of congestion of the carriage is that the carriage is provided with seats;
when the number of passengers in the carriage is greater than or equal to the first preset number and less than a second preset number, the degree of congestion of the carriage is that the carriage is not provided with seats but is loose;
when the number of passengers in the carriage is greater than or equal to the second preset number and less than a third preset number, the congestion degree of the carriage is that the carriage is relatively congested;
when the number of passengers in the carriage is greater than or equal to the third preset number, the degree of congestion of the carriage is that the carriage is very congested;
wherein the first preset number is equal to the number of seats configured in the vehicle cabin.
Optionally, the acquiring two-dimensional feature data from the point cloud data includes:
and intercepting a two-dimensional plane which contains a peak top formed by the scanning points and is parallel to the target compartment door from the point cloud data through two-dimensional peak searching, and taking a set of the intercepted scanning points on the two-dimensional plane as two-dimensional characteristic data.
Optionally, the method further comprises:
after receiving the train position and the car door opening state sent by the train control and management system TCMS, if the train is judged to be in the on-line running state and the car door is in the opening state, sending an opening prompt to the 3D radar so that the 3D radar starts to scan passengers getting on or off the train at the current station through the car door of the target compartment to obtain the point cloud data.
Optionally, the method further comprises:
and after receiving the train position and the car door opening state sent by the train control and management system TCMS, if the train is judged to be positioned at the terminal station or the car door is not opened, the opening prompt is not sent to the 3D radar.
In a second aspect, an embodiment of the present invention provides a car passenger number detection apparatus based on 3D radar scanning, including:
the system comprises an acquisition module, a data acquisition module and a data acquisition module, wherein the acquisition module is used for acquiring point cloud data of passengers getting on or off a train at a current station through a vehicle door of a target compartment, which is obtained by scanning through a 3D radar, for any target compartment of the train and acquiring two-dimensional characteristic data from the point cloud data;
the processing module is used for marking scanning points formed by scanning the passengers from the two-dimensional characteristic data through a pre-trained recognition model, using the scanning points as target two-dimensional characteristic data, tracking each target two-dimensional characteristic data, and obtaining the walking direction of the passengers corresponding to the target two-dimensional characteristic data;
the sending module is used for counting the number of first passengers entering the target compartment and the number of second passengers leaving the target compartment at the current station according to the walking direction of each passenger, acquiring the number of existing passengers in the target compartment when the train leaves the previous station, calculating the number of target passengers in the target compartment when the train leaves the current station according to the number of the first passengers, the number of the second passengers and the number of the existing passengers, and sending the number of the target passengers to the next station;
the identification model is used for marking data which are in accordance with human-shaped features from the two-dimensional feature data and is used as target two-dimensional feature data formed by scanning passengers; the two-dimensional feature data refers to a set of scanning points on a two-dimensional plane including the scanning points and parallel to the target car door, which is cut out from the point cloud data.
In a third aspect, an embodiment of the invention provides a train passenger number detection system based on 3D radar scanning, which includes a data processing unit and a 3D radar disposed above each train door;
each 3D radar is connected with a train control and management system TCMS and a data processing unit, and the data processing unit is connected with a PIS;
for any target compartment of the train, after receiving an opening prompt for scanning passengers getting on or off the train at the current station through the doors of the target compartment, the 3D radar arranged above the doors of the target compartment is started to scan the passengers getting on or off the train at the current station through the doors of the target compartment, so as to obtain point cloud data;
the data processing unit is used for executing the 3D radar scanning-based traffic congestion degree detection method.
In a fourth aspect, an embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the steps of the 3D radar scanning-based car congestion detection method described in any one of the above when executing the program.
In a fifth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium, on which a computer program is stored, the computer program, when being executed by a processor, implementing the steps of the 3D radar scanning-based car congestion detection method described in any one of the above.
The embodiment of the invention provides a 3D radar scanning-based carriage congestion degree detection method, a device and a system, wherein point cloud data of passengers getting on and off a train scanned by a 3D radar arranged above a carriage door are obtained, two-dimensional characteristic data are obtained from the point cloud data, and then target two-dimensional characteristic data corresponding to the passengers are marked from the two-dimensional characteristic data through a pre-trained recognition model. And tracking the two-dimensional characteristic data of each target to obtain the walking direction of the corresponding passenger, counting the number of people getting on or off the train at the current station according to the walking direction of each passenger, calculating the number of passengers in the carriage when the train leaves the station, sending the number of the passengers to the next station, and displaying the number at the next station. Before the passengers arrive at the next station, the counted number of the passengers in each carriage is displayed, so that the waiting passengers can select the station according to the number of the passengers in each carriage, the blind waiting is avoided, and the carrying capacity of the train is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, a brief description will be given below of the drawings required for the embodiments or the technical solutions in the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for detecting congestion degree of a car based on 3D radar scanning according to an embodiment of the present invention;
fig. 2 is a schematic diagram of the detection of the congestion status of the car according to another embodiment of the present invention;
FIG. 3 is a schematic view of a passenger ingress and egress direction determination process according to another embodiment of the present invention;
FIG. 4 is a schematic diagram of a statistical process for counting people in a car according to another embodiment of the present invention;
fig. 5 is a block diagram of a car passenger number detection device based on 3D radar scanning according to another embodiment of the present invention;
FIG. 6 is a schematic diagram illustrating a state flow of turning on and off a 3D radar according to another embodiment of the present invention;
fig. 7 is a block diagram of an electronic device according to another embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow chart of a method for detecting congestion degree of a car based on 3D radar scanning according to this embodiment, and with reference to fig. 1, the method includes:
101: for any target compartment of the train, point cloud data of passengers getting on or off the train at the current station through the doors of the target compartment, which is obtained through 3D radar scanning, is obtained, and two-dimensional characteristic data is obtained from the point cloud data;
102: marking scanning points formed by scanning passengers from the two-dimensional characteristic data through a pre-trained recognition model, using the scanning points as target two-dimensional characteristic data, tracking each target two-dimensional characteristic data, and obtaining the walking direction of the passengers corresponding to the target two-dimensional characteristic data;
103: counting the number of first passengers entering the target compartment and the number of second passengers leaving the target compartment at the current station according to the walking direction of each passenger, acquiring the number of existing passengers in the target compartment when the train leaves the previous station, calculating the number of target passengers in the target compartment when the train leaves the current station according to the number of the first passengers, the number of the second passengers and the number of the existing passengers, and sending the number of the target passengers so as to display the number of the target passengers at the next station;
the identification model is used for marking data which are in accordance with human-shaped features from the two-dimensional feature data and is used as target two-dimensional feature data formed by scanning passengers; the two-dimensional feature data refers to a set of scanning points on a two-dimensional plane including the scanning points and parallel to the target car door, which is cut out from the point cloud data.
The method provided by the present embodiment is performed by a device installed with software for executing the method, where the device may be a computer, a dedicated processing device, or integrated with a 3D radar in the same device, and the present embodiment is not limited in this respect.
The 3D radar is usually arranged above a door of a carriage, and when the door is opened, the 3D radar scans the space below the door to obtain point cloud data of passengers getting on and off the train. The two-dimensional feature data refers to a set of scanning points on a two-dimensional plane parallel to the target compartment door, which is cut out from the point cloud data. In order to reduce the amount of computation, a two-dimensional plane containing scan points having certain characteristics may be algorithmically cut when the two-dimensional plane is cut, and for example, a two-dimensional plane containing peaks formed by scan points may be cut by two-dimensional peak finding. The two-dimensional peak searching algorithm is used for finding the position with the peak value from the three-dimensional point cloud data and intercepting a two-dimensional plane which has the peak value and is parallel to the plane where the vehicle door is located, and the point on the two-dimensional plane is the two-dimensional characteristic data. Usually, two-dimensional feature data can be obtained from point cloud data by calling a two-dimensional peak searching function in Matlab software. The recognition model is a pre-trained model which can distinguish whether the two-dimensional characteristic data is a point formed by scanning a person, and can accurately mark data formed by scanning a passenger.
The two-dimensional feature data is a set of points on a two-dimensional plane having a peak and parallel to the door, and the target two-dimensional feature data is a set of points formed by scanning a passenger in the two-dimensional plane. That is, each target two-dimensional feature data marked in one frame of two-dimensional feature data corresponds to one passenger.
Further, calculating the number of target passengers in the target compartment when the train leaves the current station according to the number of the first passengers, the number of the second passengers and the number of the existing passengers, comprising:
calculating a difference between the existing passenger number and the second passenger number, calculating a sum of the difference and the first passenger number, and taking the calculated sum as the target passenger number.
The embodiment provides a carriage congestion degree detection method based on 3D radar scanning, which includes the steps of obtaining point cloud data of passengers getting on and off a vehicle, scanned by the 3D radar, installed above a carriage door, obtaining two-dimensional feature data from the point cloud data, and marking target two-dimensional feature data corresponding to the passengers from the two-dimensional feature data through a pre-trained recognition model. And tracking the two-dimensional characteristic data of each target to obtain the walking direction of the corresponding passenger, counting the number of people getting on or off the train at the current station according to the walking direction of each passenger, calculating the number of passengers in the carriage when the train leaves the station, sending the number of the passengers to the next station, and displaying the number at the next station. Before the passengers arrive at the next station, the counted number of the passengers in each carriage is displayed, so that the waiting passengers can select the station according to the number of the passengers in each carriage, the blind waiting is avoided, and the carrying capacity of the train is improved.
Further, on the basis of the foregoing embodiments, the training of the recognition model includes:
the method comprises the steps of obtaining point cloud data obtained by scanning passengers getting on and off in advance, obtaining two-dimensional characteristic data obtained by the obtained point cloud data through two-dimensional peak searching, marking data formed by scanning the passengers in each two-dimensional characteristic data, taking the two-dimensional characteristic data before marking as an input parameter of deep learning, taking the two-dimensional characteristic data after marking as expected output of the deep learning, and taking a model trained through the deep learning as the recognition model.
Specifically, fig. 2 is a schematic diagram of a principle of detecting a crowded state of a carriage provided in this embodiment, and referring to fig. 2, the 3D radar is carried to the outer side of a door of the carriage to collect the conditions of passengers entering and exiting the carriage, the distribution of feature point values of the head and the shoulders in a two-dimensional space is obtained by two-dimensional peak finding, and the collected feature data is put into a recognition model trained in advance, so that the model can judge whether the passenger is a person or not by the transmitted feature values. After the human shape recognition is completed, the motion direction of each frame of human shape data is judged according to the conditions obtained by the 3D radar scanning, so that the number of people passing in and out is obtained. After the entering and exiting directions are judged, the number of people in the carriage is counted by subtracting the number of people going out from the number of people entering the carriage. And finally, the number of people in the carriage is sent to a PIS display system of the next station through a 3D radar scanning system, so that passengers can visually see the crowdedness condition of each carriage through a CCTV of a station of the next station.
Further, the point cloud data used for training the recognition model comprises point cloud data obtained by scanning children, point cloud data obtained by scanning parallel passengers with shielding and point cloud data obtained by scanning passengers with shielding. Wherein, the sheltering object comprises objects such as a schoolbag, a luggage, a passenger backpack and the like.
As shown in fig. 2, training and testing of the model are required before the detection of the congestion state of the car, and the data collected as training samples for model training needs to be of various types, which relate to various data situations, such as child 3D radar scan data and radar scan data for blocking of parallel passengers. And collecting feature point data to perform second-order derivation and smoothing processing through two-dimensional peak searching, and labeling the feature data. In this embodiment, a deep learning method is adopted for model training, for example, a tensrflow deep learning framework is used, and the acquired data and corresponding labels (tags) are placed in a model for model training to obtain an identification model. Furthermore, the model is adjusted by adopting the test set in the process of training the model, so that the human shape recognition rate of the model reaches more than ninety-two percent.
The embodiment provides a carriage congestion degree detection method based on 3D radar scanning, a model for identifying data corresponding to passengers in two-dimensional characteristic data is trained through deep learning, a deep learning algorithm is applied, data is input into a model channel, whether the data is a person or not can be accurately judged, interference of people and articles such as bags can be effectively avoided, the identification accuracy is high, and the anti-interference capability is strong.
Further, on the basis of the foregoing embodiments, the tracking each target two-dimensional feature data to obtain the walking direction of the passenger corresponding to the target two-dimensional feature data includes:
for each target two-dimensional characteristic data, acquiring a first position in point cloud data obtained by scanning the target two-dimensional characteristic data at the last time or the next time, acquiring a second position in the point cloud data obtained by scanning the target two-dimensional characteristic data at this time, and determining the walking direction of a passenger corresponding to the target two-dimensional characteristic data according to the first position and the second position.
In the process of judging the walking direction, in order to avoid mixing the target two-dimensional characteristic data obtained by scanning different passengers, a step of verifying whether the target two-dimensional characteristic data obtained by scanning twice before and after corresponds to the same passenger can be added. For example, if the distance between the position of the target two-dimensional feature data in the point cloud data scanned last time and the position of the target two-dimensional feature data scanned this time is smaller, the target two-dimensional feature data scanned twice belongs to the same passenger, and the passenger walking direction can be judged according to the position change of the target two-dimensional feature data scanned twice, otherwise, the passenger walking direction is judged according to the target two-dimensional feature data obtained by the scanning this time and the scanning next time.
For example, the acquiring a first location in point cloud data obtained by last scanning or next scanning of the target two-dimensional feature data includes:
if the distance between the position of the peak value of the target two-dimensional feature data scanned last time and the position of the peak value of the target two-dimensional feature data scanned this time is smaller than or equal to the preset distance, the target two-dimensional feature data scanned twice is the target two-dimensional feature data corresponding to the same passenger, and the first position of the target two-dimensional feature data in the point cloud data obtained by scanning last time is obtained, otherwise, the target two-dimensional feature data scanned twice is not the target two-dimensional feature data corresponding to the same passenger, and the first position of the target two-dimensional feature data in the point cloud data obtained by scanning next time is obtained.
In the process of judging the walking direction of the passenger, if the first position of the target two-dimensional characteristic data scanned last time and the second position of the target two-dimensional characteristic data scanned this time point to the target compartment, the passenger corresponding to the target two-dimensional characteristic data enters the target compartment.
And if the position of the first place scanned last time to the position of the second place scanned this time are opposite to the target compartment, the passenger corresponding to the target two-dimensional characteristic data walks out of the target compartment.
Fig. 3 is a schematic diagram of a passenger entering and exiting direction determination process provided in this embodiment, and referring to fig. 3, after the human shape determination, the walking direction of the passenger is determined by the positions of the marked human shape (target two-dimensional feature data) in two consecutive frames. For example, the peak value of the target two-dimensional characteristic data is tracked, the movement direction of the peak value in two continuous frames is obtained, and the entering and exiting direction of the passenger is further determined.
The embodiment provides a carriage congestion degree detection method based on 3D radar scanning, which realizes judgment of passengers getting in and out of a carriage through tracking of target two-dimensional characteristic data and is convenient for counting the number of the passengers getting in and out of the carriage.
Further, on the basis of the above embodiments, the sending the target passenger number to display the target passenger number at the next stop includes:
acquiring a preset mapping relation between the congestion degree of a carriage and the number of passengers in the carriage, determining the congestion degree of the target carriage when a train drives away from the current station according to the mapping relation and the target passenger number, taking the congestion degree as a target congestion degree, and sending the target passenger number and the target congestion degree to a passenger information system PIS so as to display the target passenger number and the target congestion degree through a display device of a next station;
wherein the target congestion degree is represented by a color that is set in advance and corresponds to the target congestion degree.
Further, when the train is at the starting station and the doors are not opened, the number of the existing passengers, the number of the first passengers and the number of the second passengers are initialized to be zero.
Fig. 4 is a schematic diagram of the flow of counting the number of passengers in the car according to this embodiment, and referring to fig. 4, the system completes the initialization of the congestion status from the train start station, and sets the number of passengers entering or exiting the car and the number of passengers in the car to zero. When the train runs in an interval, the number of people getting in and out of the train compartment is accumulated by the 3D radar scanning system after the train door is opened, and the number of people getting out is subtracted from the number of people getting in the train compartment, so that the actual number of people in the train compartment is obtained. When the train reaches the operation terminal, the TCMS sends the position information and the car door state information to the 3D radar scanning system, the system automatically clears the number of passengers entering and exiting the train and the number of passengers in the carriage until the train reaches the real-time station to operate again, and the system counts the passengers entering and exiting the train again.
The embodiment provides a method for detecting the congestion degree of a carriage based on 3D radar scanning, which divides the congestion state of the carriage according to the mapping relation between the congestion degree of the carriage and the number of passengers in the carriage, and is convenient for visually representing the congestion degree in the carriage through a display device at the next station.
Further, on the basis of the foregoing embodiments, the mapping relationship includes:
when the number of passengers in the carriage is less than a first preset number, the degree of congestion of the carriage is that the carriage is provided with seats;
when the number of passengers in the carriage is greater than or equal to the first preset number and less than a second preset number, the degree of congestion of the carriage is that the carriage is not provided with seats but is loose;
when the number of passengers in the carriage is greater than or equal to the second preset number and less than a third preset number, the congestion degree of the carriage is that the carriage is relatively congested;
when the number of passengers in the carriage is greater than or equal to the third preset number, the degree of congestion of the carriage is congestion in the carriage;
wherein the first preset number is equal to the number of seats configured in the vehicle cabin.
The degree of congestion can also be represented by different colors to visually show the congestion state of each carriage, for example, if the number of passengers in the carriage is more than or equal to 310, the degree of congestion is very congested, and the result is returned to the PIS as a vehicle number and the carriage number is red; if the number of passengers in the carriage is more than or equal to 150 and less than 310, the degree of congestion is relatively crowded, and the result is returned to the PIS, wherein the number of the passengers is the number of the vehicle and the number of the carriage is colored yellow; if the number of passengers in the carriage is more than or equal to 40 and less than 150, the crowdedness degree is no seat but loose, and the result returned to the PIS is the vehicle number and the carriage number is added with green; if the number of passengers in the car is less than 40, the degree of congestion is that there are seats, and the result is returned to the PIS with the car number and the car number colored blue.
The crowding degree and the number of passengers are sent to a PIS system, the next station receives crowding information of each carriage of the train, and the results are sent to a station CCTV for result display in a unified mode. The display content comprises the number of each carriage, the corresponding color of the congestion degree of each carriage and the number of people in each carriage, and when the train in the station leaves and receives the congestion degree information of the train which arrives at the station, the PIS system finishes displaying information and updating. When the train stops running, the system does not receive the information of the train congestion degree any more until the next running time period starts, and the system is restarted.
The embodiment provides a method for detecting the congestion degree of a carriage based on 3D radar scanning, which is used for carrying out detailed grading on the congestion degree of the carriage and visually displaying the congestion degree of the carriage through colors.
Further, on the basis of the foregoing embodiments, the acquiring two-dimensional feature data from the point cloud data includes:
and intercepting a two-dimensional plane which contains a peak top formed by the scanning points and is parallel to the target compartment door from the point cloud data through two-dimensional peak searching, and taking a set of the intercepted scanning points on the two-dimensional plane as two-dimensional characteristic data.
The embodiment provides a carriage congestion degree detection method based on 3D radar scanning, two-dimensional feature data are obtained through two-dimensional peak searching, scanning points formed by scanning passengers are included in the obtained two-dimensional feature data with high probability, the calculated amount of target two-dimensional feature data identification through an identification model is reduced, and the calculation efficiency is improved.
Further, on the basis of the above embodiments, the method further includes:
after receiving the train position and the car door opening state sent by the train control and management system TCMS, if the train is judged to be in the on-line running state and the car door is in the opening state, sending an opening prompt to the 3D radar so that the 3D radar starts to scan passengers getting on or off the train at the current station through the car door of the target compartment to obtain the point cloud data.
Further, on the basis of the above embodiments, the method further includes:
and after receiving the train position and the vehicle door opening state sent by the TCMS, if the train is judged to be positioned at the terminal station or the vehicle door is not opened, the opening prompt is not sent to the 3D radar.
And when the train is judged to be in the positive running state and the train door is in the opening state according to the train position and the train door opening state sent by the TCMS, the 3D radar sends an opening prompt to the 3D radar, and after the 3D radar receives the opening prompt, the 3D radar starts to scan passengers passing through the train door of the target train carriage at the current station to get on and off the train to obtain point cloud data, otherwise, the 3D radar does not send the opening prompt. The 3D radar will only start scanning passengers getting on or off the doors of the target compartment when receiving the turn-on prompt.
For example, in this embodiment, the algorithm for executing the method for detecting the degree of congestion of a car based on 3D radar scanning is integrated in the 3D radar scanning system, and when the 3D radar scanning system receives the position information and the door state of the train sent by the on-board TCMS system, if it is determined that the train is in the on-line operation and the door is in the open state, an open prompt is sent to the 3D radar to control the 3D radar to start scanning, so as to obtain the point cloud data.
The embodiment provides a carriage congestion degree detection method based on 3D radar scanning, which is characterized in that the 3D radar is triggered to scan by sending a starting prompt to the 3D radar, so that point cloud data is acquired. Meanwhile, when scanning is not needed, the 3D radar is not started, and unnecessary resource loss is avoided.
The utility model provides a carriage crowdedness degree detection method based on 3D radar scanning, through discernment business turn over passenger quantity, through calculating the number of people in every carriage, the PIS system of next platform is sent to data expert after the discernment is handled, through platform CCTV display screen, show each carriage crowdedness degree condition, including carriage serial number, the number in the carriage, and set up the crowdedness degree colour information that the threshold value fed back according to the number, make the passenger that next station waited for can select the platform of waiting according to the crowded state in carriage, rationally use the carriage space, improve train capacity.
Fig. 5 is a block diagram of the structure of the 3D radar scanning-based car passenger number detection apparatus provided in the present embodiment, and referring to fig. 5, the apparatus includes an acquisition module 501, a processing module 502 and a sending module 503, wherein,
the acquisition module 501 is configured to acquire point cloud data, which is obtained by scanning a 3D radar, of a passenger getting on or off a train at a current station through a door of a target compartment, and acquire two-dimensional feature data from the point cloud data;
the processing module 502 is configured to mark scanning points formed by scanning passengers from the two-dimensional feature data through a pre-trained recognition model, and track each target two-dimensional feature data to obtain a walking direction of the passenger corresponding to the target two-dimensional feature data;
a sending module 503, configured to count, according to a traveling direction of each passenger, the number of first passengers entering the target car at the current station and the number of second passengers exiting the target car, obtain the number of existing passengers in the target car when the train departs from the previous station, calculate, according to the number of first passengers, the number of second passengers, and the number of existing passengers, the number of target passengers in the target car when the train departs from the current station, and send the number of target passengers to the next station;
the identification model is used for marking data which are in accordance with human-shaped features from the two-dimensional feature data and is used as target two-dimensional feature data formed by scanning passengers; the two-dimensional feature data refers to a set of scanning points on a two-dimensional plane including the scanning points and parallel to the target car door, which is cut out from the point cloud data.
The device for detecting the number of passengers in the car based on 3D radar scanning provided by this embodiment is suitable for the method for detecting the congestion degree of the car based on 3D radar scanning provided by the above embodiment, and is not described herein again.
The embodiment provides a carriage passenger quantity detection device based on 3D radar scanning, which is used for acquiring point cloud data of passengers getting on and off a vehicle scanned by the 3D radar arranged above a carriage door, obtaining two-dimensional characteristic data from the point cloud data, and marking target two-dimensional characteristic data corresponding to the passengers from the two-dimensional characteristic data through a pre-trained recognition model. And tracking the two-dimensional characteristic data of each target to obtain the walking direction of the corresponding passenger, counting the number of people getting on or off the train at the current station according to the walking direction of each passenger, calculating the number of passengers in the carriage when the train leaves the station, sending the number of the passengers to the next station, and displaying the number at the next station. Before the passengers arrive at the next station, the counted number of the passengers in each carriage is displayed, so that the waiting passengers can select the station according to the number of the passengers in each carriage, the blind waiting is avoided, and the carrying capacity of the train is improved.
The embodiment also provides a passenger number detection system of the carriage based on 3D radar scanning, which comprises a data processing unit and a 3D radar arranged above each carriage door of the train;
each 3D radar is connected with a train control and management system TCMS and a data processing unit, and the data processing unit is connected with a PIS;
for any target compartment of the train, after receiving an opening prompt for scanning passengers getting on or off the train at the current station through the doors of the target compartment, the 3D radar arranged above the doors of the target compartment is started to scan the passengers getting on or off the train at the current station through the doors of the target compartment, so as to obtain point cloud data;
the data processing unit is used for executing the 3D radar scanning-based traffic congestion degree detection method.
The method comprises the steps that a 3D radar is arranged above a vehicle door of each carriage of the train, the 3D radar is used for scanning passengers getting on and off the train to obtain point cloud data, a data processing unit is integrated in a 3D radar scanning system and used for processing the point cloud data obtained by scanning the 3D radar and controlling the 3D radar to be started through the method of each embodiment, the number of the passengers in each carriage is obtained through the data processing unit, the number of the passengers in the carriage and the crowding state are sent to a PIS system to be displayed at the next station, the passengers at the next station are prevented from waiting for the train blindly, and the train capacity is improved.
Fig. 6 is a schematic flow chart of the 3D radar turning on and off state provided in this embodiment, referring to fig. 6, the vehicle TCMS sends the door state and the position information to the 3D radar scanning system. In the train on-line running process (namely when the train position is in an operation interval except a terminal station), after the train door is opened, the 3D radar system receives train door opening information and immediately starts a scanning function, and after the train door is closed, the TCMS sends the position information and the train door closing information to the 3D radar scanning system to close the 3D radar.
The method, the device and the system provided by the embodiment have the following advantages: (1) whether the congestion degree detection function is started or not can be judged only from the vehicle door state and the vehicle position information, multi-system linkage and mass data interaction are not needed, and functions of automatic starting, automatic identification detection, automatic signal transmission, automatic display of CCTV carriage congestion degree and the like can be realized without human intervention; (2) through the fusion of the 3D radar scanning and the deep learning algorithm, the application scene root is diversified, and the identification result is more accurate; (3) the carriage crowdedness grade division is more careful, including sitting, loose, comparatively crowded degree, very crowded four grades, can provide more careful crowdedness for the passenger and show the function, and it has perfected PIS system display function, can promote the capacity of train to a certain extent, reduces the risk that the passenger is detained by a large scale.
Fig. 7 is a block diagram showing the structure of the electronic apparatus provided in the present embodiment.
Referring to fig. 7, the electronic device includes: a processor (processor)710, a communication Interface (Communications Interface)720, a memory (memory)730, and a communication bus 740, wherein the processor 710, the communication Interface 720, and the memory 730 communicate with each other via the communication bus 740. Processor 710 may call logic instructions in memory 730 to perform the following method: for any target compartment of the train, point cloud data of passengers getting on or off the train at the current station through the doors of the target compartment, which is obtained through 3D radar scanning, is obtained, and two-dimensional characteristic data is obtained from the point cloud data; marking scanning points formed by scanning passengers from the two-dimensional characteristic data through a pre-trained recognition model, using the scanning points as target two-dimensional characteristic data, tracking each target two-dimensional characteristic data, and obtaining the walking direction of the passengers corresponding to the target two-dimensional characteristic data; counting the number of first passengers entering the target compartment and the number of second passengers leaving the target compartment at the current station according to the walking direction of each passenger, acquiring the number of existing passengers in the target compartment when the train leaves the previous station, calculating the number of target passengers in the target compartment when the train leaves the current station according to the number of the first passengers, the number of the second passengers and the number of the existing passengers, and sending the number of the target passengers so as to display the number of the target passengers at the next station; the identification model is used for marking data which are in accordance with human-shaped features from the two-dimensional feature data and is used as target two-dimensional feature data formed by scanning passengers; the two-dimensional feature data refers to a set of scanning points on a two-dimensional plane including the scanning points and parallel to the target car door, which is cut out from the point cloud data.
In addition, the logic instructions in the memory 730 can be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The present embodiments provide a non-transitory computer readable storage medium having stored thereon a computer program, the computer program being executable by a processor to perform the method of: for any target compartment of the train, point cloud data of passengers getting on or off the train at the current station through the doors of the target compartment, which is obtained through 3D radar scanning, is obtained, and two-dimensional characteristic data is obtained from the point cloud data; marking scanning points formed by scanning passengers from the two-dimensional characteristic data through a pre-trained recognition model, using the scanning points as target two-dimensional characteristic data, tracking each target two-dimensional characteristic data, and obtaining the walking direction of the passengers corresponding to the target two-dimensional characteristic data; counting the number of first passengers entering the target compartment and the number of second passengers leaving the target compartment at the current station according to the walking direction of each passenger, acquiring the number of existing passengers in the target compartment when the train leaves the previous station, calculating the number of target passengers in the target compartment when the train leaves the current station according to the number of the first passengers, the number of the second passengers and the number of the existing passengers, and sending the number of the target passengers so as to display the number of the target passengers at the next station; the identification model is used for marking data which are in accordance with human-shaped features from the two-dimensional feature data and is used as target two-dimensional feature data formed by scanning passengers; the two-dimensional feature data refers to a set of scanning points on a two-dimensional plane including the scanning points and parallel to the target car door, which is cut out from the point cloud data.
The present embodiments disclose a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the methods provided by the above-described method embodiments, for example, comprising: for any target compartment of the train, point cloud data of passengers getting on or off the train at the current station through the doors of the target compartment, which is obtained through 3D radar scanning, is obtained, and two-dimensional characteristic data is obtained from the point cloud data; marking scanning points formed by scanning passengers from the two-dimensional characteristic data through a pre-trained recognition model, using the scanning points as target two-dimensional characteristic data, tracking each target two-dimensional characteristic data, and obtaining the walking direction of the passengers corresponding to the target two-dimensional characteristic data; counting the number of first passengers entering the target compartment and the number of second passengers leaving the target compartment at the current station according to the walking direction of each passenger, acquiring the number of existing passengers in the target compartment when the train leaves the previous station, calculating the number of target passengers in the target compartment when the train leaves the current station according to the number of the first passengers, the number of the second passengers and the number of the existing passengers, and sending the number of the target passengers so as to display the number of the target passengers at the next station; the identification model is used for marking data which are in accordance with human-shaped features from the two-dimensional feature data and is used as target two-dimensional feature data formed by scanning passengers; the two-dimensional feature data refers to a set of scanning points on a two-dimensional plane including the scanning points and parallel to the target car door, which is cut out from the point cloud data.
The above-described embodiments of the electronic device and the like are merely illustrative, where the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may also be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the embodiments of the present invention, and are not limited thereto; although embodiments of the present invention have been described in detail with reference to the foregoing embodiments, those skilled in the art will understand that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (7)
1. A carriage congestion degree detection method based on 3D radar scanning is characterized by comprising the following steps:
after receiving the train position and the car door opening state sent by the train control and management system TCMS, if the train is judged to be in the positive line running state and the car door is in the opening state, sending an opening prompt to the 3D radar so that the 3D radar starts to scan passengers getting on or off the train at the current station through the car door of the target compartment to obtain point cloud data;
acquiring point cloud data of passengers getting on or off a train door passing through a target compartment at a current station, which is obtained by scanning through a 3D radar, for any target compartment of a train, intercepting a two-dimensional plane which contains a peak top formed by scanning points and is parallel to the door of the target compartment from the point cloud data through two-dimensional peak searching, and taking a set of the intercepted scanning points on the two-dimensional plane as two-dimensional characteristic data;
marking scanning points formed by scanning passengers from the two-dimensional characteristic data through a pre-trained recognition model, using the scanning points as target two-dimensional characteristic data, tracking each target two-dimensional characteristic data, and obtaining the walking direction of the passengers corresponding to the target two-dimensional characteristic data; each target two-dimensional feature data marked in one frame of two-dimensional feature data corresponds to one passenger;
counting the number of first passengers entering the target compartment and the number of second passengers leaving the target compartment at the current station according to the walking direction of each passenger, acquiring the number of existing passengers in the target compartment when the train leaves the previous station, calculating the number of target passengers in the target compartment when the train leaves the current station according to the number of the first passengers, the number of the second passengers and the number of the existing passengers, and sending the number of the target passengers so as to display the number of the target passengers at the next station;
the identification model is used for marking data which are in accordance with human-shaped features from the two-dimensional feature data and is used as target two-dimensional feature data formed by scanning passengers; the two-dimensional characteristic data refers to a set of scanning points which are intercepted from the point cloud data and are arranged on a two-dimensional plane which comprises the scanning points and is parallel to the target compartment door;
the training of the recognition model comprises:
the method comprises the steps of obtaining point cloud data obtained by scanning passengers getting on and off in advance, obtaining two-dimensional characteristic data obtained by the obtained point cloud data through two-dimensional peak searching, marking data formed by scanning the passengers in each two-dimensional characteristic data, taking the two-dimensional characteristic data before marking as an input parameter of deep learning, taking the two-dimensional characteristic data after marking as expected output of the deep learning, and taking a model trained through the deep learning as the recognition model.
2. The method for detecting the degree of congestion of a car based on 3D radar scanning according to claim 1, wherein the tracking each target two-dimensional feature data to obtain the traveling direction of the passenger corresponding to the target two-dimensional feature data includes:
for each target two-dimensional characteristic data, acquiring a first position in point cloud data obtained by scanning the target two-dimensional characteristic data at the last time or the next time, acquiring a second position in the point cloud data obtained by scanning the target two-dimensional characteristic data at this time, and determining the walking direction of a passenger corresponding to the target two-dimensional characteristic data according to the first position and the second position.
3. The method for detecting the degree of congestion of a passenger compartment based on 3D radar scanning according to claim 1, wherein the transmitting the number of target passengers to display the number of target passengers at a next stop includes:
acquiring a preset mapping relation between the congestion degree of a carriage and the number of passengers in the carriage, determining the congestion degree of the target carriage when a train drives away from the current station according to the mapping relation and the target passenger number, taking the congestion degree as a target congestion degree, and sending the target passenger number and the target congestion degree to a passenger information system PIS so as to display the target passenger number and the target congestion degree through a display device of a next station;
wherein the target congestion degree is represented by a color that is set in advance and corresponds to the target congestion degree.
4. The method according to claim 3, wherein the mapping relationship comprises:
when the number of passengers in the carriage is less than a first preset number, the degree of congestion of the carriage is that the carriage is provided with seats;
when the number of passengers in the carriage is greater than or equal to the first preset number and less than a second preset number, the degree of congestion of the carriage is that the carriage is not provided with seats but is loose;
when the number of passengers in the carriage is greater than or equal to the second preset number and less than a third preset number, the congestion degree of the carriage is that the carriage is relatively congested;
when the number of passengers in the carriage is greater than or equal to the third preset number, the degree of congestion of the carriage is that the carriage is very congested;
wherein the first preset number is equal to the number of seats configured in the vehicle cabin.
5. The method for detecting the degree of congestion of a car based on 3D radar scanning according to claim 1, further comprising:
and after receiving the train position and the car door opening state sent by the train control and management system TCMS, if the train is judged to be positioned at the terminal station or the car door is not opened, the opening prompt is not sent to the 3D radar.
6. A carriage congestion degree detection device based on 3D radar scanning, characterized by comprising:
the train door opening prompting device comprises an acquisition module, a 3D radar and a control module, wherein the acquisition module is used for sending an opening prompt to the 3D radar if the train door is in an opening state and the train door is in an on-line running state after receiving the train position and the train door opening state sent by a Train Control and Management System (TCMS); scanning any target compartment of a train, acquiring point cloud data of passengers getting on or off the train through a train door of the target compartment at a current station, wherein the point cloud data is obtained through scanning of a 3D radar, intercepting a two-dimensional plane which comprises a peak top formed by scanning points and is parallel to the train door of the target compartment from the point cloud data through two-dimensional peak searching, and taking a set of the intercepted scanning points on the two-dimensional plane as two-dimensional characteristic data;
the processing module is used for marking scanning points formed by scanning the passengers from the two-dimensional characteristic data through a pre-trained recognition model, using the scanning points as target two-dimensional characteristic data, tracking each target two-dimensional characteristic data, and obtaining the walking direction of the passengers corresponding to the target two-dimensional characteristic data; each target two-dimensional feature data marked in one frame of two-dimensional feature data corresponds to one passenger;
the sending module is used for counting the number of first passengers entering the target compartment and the number of second passengers leaving the target compartment at the current station according to the walking direction of each passenger, acquiring the number of existing passengers in the target compartment when the train leaves the previous station, calculating the number of target passengers in the target compartment when the train leaves the current station according to the number of the first passengers, the number of the second passengers and the number of the existing passengers, and sending the number of the target passengers to the next station;
the identification model is used for marking data which are in accordance with human-shaped features from the two-dimensional feature data and is used as target two-dimensional feature data formed by scanning passengers; the two-dimensional characteristic data refers to a set of scanning points which are intercepted from the point cloud data and are arranged on a two-dimensional plane which comprises the scanning points and is parallel to the target compartment door;
the training of the recognition model comprises:
the method comprises the steps of obtaining point cloud data obtained by scanning passengers getting on and off in advance, obtaining two-dimensional characteristic data obtained by the obtained point cloud data through two-dimensional peak searching, marking data formed by scanning the passengers in each two-dimensional characteristic data, taking the two-dimensional characteristic data before marking as an input parameter of deep learning, taking the two-dimensional characteristic data after marking as expected output of the deep learning, and taking a model trained through the deep learning as the recognition model.
7. A train carriage congestion degree detection system based on 3D radar scanning is characterized by comprising a data processing unit and a 3D radar arranged above each train carriage door of a train;
each 3D radar is connected with a train control and management system TCMS and a data processing unit, and the data processing unit is connected with a PIS;
for any target compartment of the train, after receiving an opening prompt for scanning passengers getting on or off the train at the current station through the doors of the target compartment, the 3D radar arranged above the doors of the target compartment is started to scan the passengers getting on or off the train at the current station through the doors of the target compartment, so as to obtain point cloud data;
the data processing unit is used for executing the 3D radar scanning-based car congestion degree detection method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910666603.8A CN110376585B (en) | 2019-07-23 | 2019-07-23 | Carriage congestion degree detection method, device and system based on 3D radar scanning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910666603.8A CN110376585B (en) | 2019-07-23 | 2019-07-23 | Carriage congestion degree detection method, device and system based on 3D radar scanning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110376585A CN110376585A (en) | 2019-10-25 |
| CN110376585B true CN110376585B (en) | 2022-02-15 |
Family
ID=68255188
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910666603.8A Active CN110376585B (en) | 2019-07-23 | 2019-07-23 | Carriage congestion degree detection method, device and system based on 3D radar scanning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110376585B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112561971A (en) * | 2020-12-16 | 2021-03-26 | 珠海格力电器股份有限公司 | People flow statistical method, device, equipment and storage medium |
| CN114782469B (en) * | 2022-06-16 | 2022-08-19 | 西南交通大学 | Method and device for identifying degree of congestion of public traffic, electronic device and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104268506A (en) * | 2014-09-15 | 2015-01-07 | 郑州天迈科技股份有限公司 | Passenger flow counting detection method based on depth images |
| CN104517040A (en) * | 2014-12-31 | 2015-04-15 | 青岛海信网络科技股份有限公司 | Method for calculating in-carriage congestion degree of public traffic vehicle based on IC card data |
| CN106846297A (en) * | 2016-12-21 | 2017-06-13 | 深圳市镭神智能系统有限公司 | Pedestrian's flow quantity detecting system and method based on laser radar |
| CN206696862U (en) * | 2017-03-22 | 2017-12-01 | 西南交通大学 | Subway number identifies and delivery system |
| CN108269219A (en) * | 2017-12-25 | 2018-07-10 | 河南辉煌软件有限公司 | A kind of rail transit cars passengers quantity counting and displaying method |
| CN108710818A (en) * | 2018-03-09 | 2018-10-26 | 唐义 | A kind of real-time monitoring and statistics system and method for number based on three-dimensional laser radar |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106022460B (en) * | 2016-05-25 | 2018-08-10 | 重庆市勘测院 | Crowd density method of real-time based on laser radar |
-
2019
- 2019-07-23 CN CN201910666603.8A patent/CN110376585B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104268506A (en) * | 2014-09-15 | 2015-01-07 | 郑州天迈科技股份有限公司 | Passenger flow counting detection method based on depth images |
| CN104517040A (en) * | 2014-12-31 | 2015-04-15 | 青岛海信网络科技股份有限公司 | Method for calculating in-carriage congestion degree of public traffic vehicle based on IC card data |
| CN106846297A (en) * | 2016-12-21 | 2017-06-13 | 深圳市镭神智能系统有限公司 | Pedestrian's flow quantity detecting system and method based on laser radar |
| CN206696862U (en) * | 2017-03-22 | 2017-12-01 | 西南交通大学 | Subway number identifies and delivery system |
| CN108269219A (en) * | 2017-12-25 | 2018-07-10 | 河南辉煌软件有限公司 | A kind of rail transit cars passengers quantity counting and displaying method |
| CN108710818A (en) * | 2018-03-09 | 2018-10-26 | 唐义 | A kind of real-time monitoring and statistics system and method for number based on three-dimensional laser radar |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110376585A (en) | 2019-10-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6570731B2 (en) | Method and system for calculating passenger congestion | |
| CN108289203B (en) | Video monitoring system for rail transit | |
| CN102289660B (en) | Method for detecting illegal driving behavior based on hand gesture tracking | |
| CN102622798B (en) | Passenger flow statistical analysis system | |
| CN110376585B (en) | Carriage congestion degree detection method, device and system based on 3D radar scanning | |
| CN103985182B (en) | A kind of bus passenger flow automatic counting method and automatic counter system | |
| CN106541968B (en) | The recognition methods of the subway carriage real-time prompt system of view-based access control model analysis | |
| CN109243181A (en) | Traffic accident method for early warning, device, terminal device and storage medium | |
| CN105843810A (en) | Method and device for planning travel route | |
| CN105427613B (en) | The means of proof and its system that a kind of rule-breaking vehicle is jumped a queue | |
| CN107145819A (en) | A kind of bus crowding determines method and apparatus | |
| CN112347814A (en) | Passenger flow estimation and display method, system and computer readable storage medium | |
| CN110490103A (en) | Track traffic for passenger flow Density Detection method and device | |
| CN105046950A (en) | System and method for judging degree of crowdedness of bus based on base stations | |
| CN108073886B (en) | A kind of passenger on public transport amount evaluation method based on machine learning | |
| CN103761870A (en) | System for counting bus loads | |
| CN108596688A (en) | A kind of taxi passenger information acquisition methods and medium | |
| CN112700473B (en) | Carriage congestion degree judging system based on image recognition | |
| CN110992678A (en) | Bus passenger flow statistical method based on big data face recognition | |
| KR101714723B1 (en) | Method and service server for providing crowd density information | |
| CN108447273A (en) | A kind of remaining parking stall prediction technique based on intelligent parking system | |
| CN110633609B (en) | Positioning platform based on face object position analysis | |
| CN108241866A (en) | A kind of method, apparatus guided to driving behavior and vehicle | |
| CN106296869B (en) | Processing method, processing system and the automobile data recorder of running information | |
| CN111666879A (en) | Bus passenger flow analysis and planning system and method based on big data frame |
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 |