CN114333120A - Bus passenger flow detection method and system - Google Patents
Bus passenger flow detection method and system Download PDFInfo
- Publication number
- CN114333120A CN114333120A CN202210247078.8A CN202210247078A CN114333120A CN 114333120 A CN114333120 A CN 114333120A CN 202210247078 A CN202210247078 A CN 202210247078A CN 114333120 A CN114333120 A CN 114333120A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- bus
- passengers
- passenger flow
- seat
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L5/00—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a method and a system for detecting public transport passenger flow, and belongs to the technical field of public transport passenger flow detection. The invention respectively counts the number of passengers getting on the bus, the number of passengers on the seat and the number of passengers standing up, and finally calculates the bus passenger flow according to the statistical data. The invention can accurately count the number of real-time passengers in the bus compartment, thereby detecting the number of passengers getting on and off the bus at each stop and the bus passenger flow information of a certain section, further obtaining the bus running indexes such as the full load rate of the bus, the passenger flow of each stop and the passenger flow of each bus line, and the like.
Description
Technical Field
The invention relates to the technical field of public transport passenger flow detection, in particular to a method and a system for detecting public transport passenger flow.
Background
With the development of the related art, buses have begun to employ sensors to detect bus passenger flow. Traditional bus passenger flow sensor detection schemes include gravity, infrared, and pressure pedal sensor detection. However, the infrared sensor is easy to miss detection when passengers pass through the sensor at the same time, the accuracy of the gravity sensor is too low, and the pressure pedal sensor is difficult to detect and is easy to damage when the number of passengers getting on and off is large. Therefore, these conventional detection methods have difficulty in meeting the requirement of accuracy. And if the current popular Bluetooth detector and the Wifi probe are adopted for detection, the passenger with Bluetooth or Wifi closed can not be detected. Therefore, the camera is used for detection at present.
However, the camera solution also has its own problems. That is, if the number of passengers getting on or off the train is directly detected by the camera, the real-time number of passengers in the train cannot be accurately obtained, because if the number of passengers getting on or off the train is detected at each station to have an error, the error will be brought to the next station to form an accumulated error. If with camera direct detection carriage in real-time number and the number of getting on the bus, can avoid appearing the condition of mutual influence between the website this moment, nevertheless because the passenger of standing in the carriage has different forms with the passenger of sitting on the seat, need set up different recognition model respectively, increased the degree of difficulty of camera discernment, especially when the passenger of sitting on the seat is sheltered from by the passenger of standing, more can cause the discernment mistake.
Disclosure of Invention
Aiming at the defects and shortcomings in the prior art, the invention aims to provide a method and a system for detecting the bus passenger flow.
The invention discloses a bus passenger flow detection method, which adopts the technical scheme that the method comprises the following steps:
counting the number of passengers getting on the bus: after the vehicle arrives at the station, the vehicle-mounted terminal counts the card swiping times and the code swiping times of the passengers getting on the vehicle through the card swiping machine, and the number of the passengers getting on the vehicle at the station is obtained by counting one person when the passengers swipe the card or swipe the two-dimensional code oncea；
Counting the number of passengers on the seat: when the vehicle normally runs after leaving the station, the vehicle-mounted terminal counts the number of passengers on the seat through the pressure sensor arranged on the bus seat to obtain the number of the passengers on the seatb；
Counting the number of standing passengers: when the vehicle normally runs after leaving the station, the vehicle-mounted camera shoots the interior of a carriage in the set shooting area, the shot image is transmitted to the vehicle-mounted terminal, the vehicle-mounted terminal operates the set personnel head detection model to detect the head number of passengers in the identification area defined on the image, and the head number of the passengers in the identification area on the image is obtained and is used as the number of standing passengers detected each time; continuously shooting a plurality of images, and taking an average value of the number of standing passengers detected each time as the counted number c of the standing passengers;
the method comprises the following steps of (1) counting the bus passenger flow: the vehicle-mounted terminal counts the bus passenger flow according to the counted number of passengers getting on the bus, the number of passengers on the seat and the number of passengers standing on the bus, wherein the number of real-time passengers of the vehicle before the vehicle arrives at the next stop after leaving the stop is b + c, and the number of passengers getting off the bus at the stop is the sum of the number of real-time passengers of the vehicle before the vehicle arrives at the stop and the number of passengers getting on the bus at the stopaAnd subtracting the number of real-time people of the vehicle before the vehicle arrives at the next station as b + c, and uploading the bus passenger flow data to the bus cloud platform by the vehicle-mounted terminal.
In the step of counting the number of boarding persons, the number of times of card swiping or the number of times of code swiping counted before the vehicle arrives at the next station is taken as the number of boarding persons at the station.
In the step of counting the number of passengers in the seat, it is determined that a passenger is seated in the seat when a pressure sensor installed in the bus seat detects that the pressure is greater than a preset pressure threshold.
Further, in the step of counting the number of standing passengers, the vehicle-mounted camera is a front camera and a rear camera, and respectively shoots the front half part and the rear half part of the carriage, and the vehicle-mounted terminal takes the shot images to identify the heads of the passengers after the two cameras remove the overlapped areas of the visual fields.
Further, the human head detection model is obtained by training through a Yolox-Tiny algorithm.
Further, the vehicle-mounted terminal is connected with the card swiping machine, the pressure sensor and/or the vehicle-mounted camera through wireless communication.
Further, the wireless communication is Zigbee communication.
Further, the bus cloud platform counts the full load rate of each vehicle, the passenger flow of each station and/or the passenger flow of each bus route according to the bus passenger flow data uploaded by each vehicle.
Correspondingly, the bus passenger flow detection system comprises a bus cloud platform, vehicle-mounted terminals of all vehicles, card readers installed on all vehicles, pressure sensors and vehicle-mounted cameras, and is characterized in that the bus passenger flow is detected by adopting the method.
The invention has the following beneficial effects: the invention respectively adopts different identification means to respectively count the number of passengers getting on the bus, the number of passengers on a seat and the number of passengers standing, and finally calculates the bus passenger flow according to the statistical data, thereby more accurately counting the number of the passengers getting on or off the bus at each stop and the bus passenger flow information of a certain section, further obtaining the bus running indexes such as the full load rate of the bus, the passenger flow of each stop and the passenger flow of each bus line, and the like. The camera disclosed by the invention only needs to detect the number of standing passengers, so that the problem that seat passengers are shielded is effectively solved, and the camera has an accurate detection effect no matter the number of the standing passengers is more or less.
Drawings
FIG. 1 is a flow chart of steps of a bus passenger flow statistics method of the present invention.
Fig. 2 is a functional configuration diagram of the in-vehicle terminal system of the present invention.
Fig. 3 is a view showing the installation positions of the devices in the vehicle compartment.
Fig. 4 is a diagram of a standing passenger imaging person head detection area simulation.
Detailed Description
The invention is further described below with reference to the accompanying drawings and examples.
The bus passenger flow detection system of the embodiment is shown in fig. 2, and comprises a bus cloud platform, vehicle terminals of each vehicle, a card swiping machine, a pressure sensor and a vehicle camera, wherein the vehicle terminals are installed on each vehicle, the vehicle terminals comprise an embedded processing platform and a GPS positioning system, wireless communication is performed between the vehicle terminals and a data acquisition layer by using a Zigbee technology, and data is transmitted to the bus cloud platform by a 4g technology for data analysis. The data acquisition layer comprises a photoelectric switch arranged at the front door of the bus and used for detecting a door opening signal, a front camera and a rear camera in the carriage, an NFC card swiping and code swiping counter at the card swiping position of the bus door, a pressure sensor arranged at a seat and the like, the vehicle-mounted terminal is arranged at the top of the bus head, and a specific installation position is shown in figure 3.
The flow of the bus passenger flow detection method of the embodiment is shown in fig. 1, and it is assumed that a vehicle is at a stationiAnd siteiWhen the vehicle is driven between +1, the real-time number of people in the vehicle is pi+1And then, detecting the bus passenger flow according to the following steps:
s1, vehicle arrival stationiThe vehicle-mounted terminal is positioned at the station, acquires the door opening signal, controls a counter on the card swiping machine to count the card swiping times and the code swiping times of the passengers on the bus again, and when the bus arrives at the stationiEnding before +1 to obtain stationiThe number of passengers getting on the busa。
S2, when the vehicle normally runs, the position and state of the passenger tend to be stable, the pressure sensor at the bus seat enters into work to sense whether the passenger information is on the seat, if the passenger information is on the seat, a signal is sent to the vehicle-mounted terminal once, and the vehicle-mounted terminal counts the number of the signals, namely the number of the passengers on the seatb。
S3, shooting a plurality of images by the vehicle-mounted camera, transmitting the images to the vehicle-mounted terminal, and detecting the number of the heads of passengers in the area defined on the images by the vehicle-mounted terminal running the set personnel head detection model to obtain the number of the heads of the passengers in the area of each imagec1、c2、c3、c4、c5... is the number of standing passengers detected at each moment, averaged and rounded to get c.
S4, calculating the number p of real-time people in the vehicle by the vehicle-mounted terminali+1= b + c, then at the siteiThe number of persons getting offd= pi+a-pi+1. And transmitting the data to a public transport cloud platform. The above is the general flow of the detection method of the present embodiment.
Specifically, when the photoelectric switch detects that the door is opened, the door opening signal is transmitted to the vehicle-mounted terminal, and the vehicle-mounted terminal controls the counter on the card swiping machine to count again. Every time a passenger swipes a card or swipes a two-dimensional code, the counter counts the boarding data once and transmits the data to the vehicle-mounted terminal. Considering that the situation that the card swiping or code swiping delay caused by the faults of the mobile phone and the IC card can occur when passengers get on the bus, the number of times counted by the counter between two stations is calculated as the number of passengers getting on the bus at the station.
Considering that the passenger may place personal belongings or carried packages on the seat, and the weight of the personal belongings or the carried packages is mostly not more than 10kg and is lower than the weight of a child capable of sitting on the seat, the seat is determined to be occupied when the pressure detected by the pressure sensor is more than 10kg (namely 10kg is used as a preset pressure threshold), and the pressure sensor sends a signal to the vehicle-mounted terminal, otherwise, the signal is not sent, so that the situation that the passenger places the personal belongings on the seat to cause false detection is avoided. The number of the pressure signals counted by the vehicle-mounted terminal is the number of passengers on the seat. The detection standard can be adjusted according to actual conditions.
The passengers can move in the carriage continuously just after getting on the bus, and the position change is large, so that the detection is not facilitated. Therefore, the present embodiment considers that the pressure sensor and the onboard camera start to detect only when the position and state of the passenger tend to be stable one minute after the vehicle has closed, i.e., when the vehicle is traveling normally after leaving the station. When the bus is about to arrive at a station, voice broadcast is carried out, and the position and the state of the passenger getting off at the station can change, and the detection should be stopped at the moment.
Cameras positioned in the front half and the rear half of the carriage acquire images of the front half and the rear half of the carriage, respectively. The vehicle-mounted camera is installed at the top of the left side of the carriage. If the length of the carriage is m, the camera placing positions are respectively m/4 away from the head and the tail of the vehicle, the selected view angle of the camera meets the condition that the view of the right end of the front camera can shoot 1/2 places of the carriage, and the view of the left end of the rear camera can shoot 1/2 places of the carriage. The selected camera can have better definition when the light in the vehicle is dim at night, and can clearly shoot the head of a passenger in the carriage. And the vehicle-mounted terminal processes the images of the cameras during recognition, and removes the overlapped areas of the fields of vision of the two cameras from the images shot by the cameras of the rear compartment.
Since the passenger is completely taller than the passenger on the seat while standing, the area where his head may be present has a significant extent in the image. Therefore, in the recognition, the region in which the head of the standing passenger may be present in the image may be defined as a specific recognition region, that is, the region of the head detection frame in fig. 4, which does not overlap the region in which the head of the seat passenger may be present. Therefore, the shooting visual angle of the embodiment can completely acquire the head image of the standing passenger, the situations of blocking by the sitting passenger and the like do not exist almost, the head does not need to be tracked, and the number of the heads in the image only needs to be detected, namely the number of the heads of the standing passenger.
In order to improve the detection precision, the embodiment adopts a Yolox algorithm newly opened in a deep learning algorithm to perform human head detection. Due to the particularity of the view angle and the environment of the bus scene camera, a special data set needs to be marked for training. Before detection, vehicle-mounted image data in the day and at night are collected respectively to serve as sample images, a human head frame in the images is marked by using a labelme marking tool, and a Yolox algorithm is trained for two scenes in the day and at night. As a latest algorithm of a Yolo series, the Yolo introduces Anchor free into the Yolo algorithm by Yolo, and based on a baseline model of YOLov3 baseline, an arkNet53+ SPP layer is adopted, Head is decoupled, namely a decoupling Head is used, the problems of classification and regression tasks are solved to a certain extent, and the detection precision and speed are greatly improved. And Yolox trains the global area of the image, can better distinguish the target from the background, and in the bus environment, the head of the passenger is obviously distinguished from the background area, so that the Yolox is more suitable. If the human head is detected on the bus cloud platform, a plurality of images can be detected simultaneously, so that the detection speed is greatly influenced, and the task of human head detection is carried out on the vehicle-mounted terminal. In consideration of the operation performance of the vehicle-mounted terminal microprocessor, the embodiment employs a Yolox-Tiny network inside Yolox.
The vehicle-mounted terminal realizes station location through a vehicle-mounted GPS (global positioning system), the detected boarding data are the boarding data of a station just parked, the detected real-time number of people in the carriage is the real-time number between the station just parked and the next station, and the calculated getting-off number is the getting-off data of the station just parked. The bus cloud platform can obtain the passenger flow of the bus passengers passing through a certain section and the passenger flow of the bus passengers in a certain section at a certain moment through the data sent by each vehicle-mounted terminal. And further obtaining the full load rate of the vehicle, the passenger flow of each station and the passenger flow of each bus line. By utilizing the data, a public transport company can monitor the peak time of passenger flow of each bus and also can identify supersaturated bus stations, so that a basis is provided for the design of a public transport analysis system, and effective data support is provided for intelligent dispatching of the public transport.
The above description is only a preferred embodiment of the present invention, and should not be construed as limiting the scope of the present invention. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.
Claims (9)
1. A bus passenger flow detection method is characterized by comprising the following steps:
counting the number of passengers getting on the bus: after the vehicle arrives at the station, the vehicle-mounted terminal counts the card swiping times and the code swiping times of the passengers getting on the vehicle through the card swiping machine, and the number of the passengers getting on the vehicle at the station is obtained by counting one person when the passengers swipe the card or swipe the two-dimensional code oncea；
Counting the number of passengers on the seat: the vehicle leaves the stationWhen the bus runs normally, the vehicle-mounted terminal counts the number of passengers on the seat through the pressure sensor arranged on the bus seat to obtain the number of the passengers on the seatb；
Counting the number of standing passengers: when the vehicle normally runs after leaving the station, the vehicle-mounted camera shoots the interior of a carriage in the set shooting area, the shot image is transmitted to the vehicle-mounted terminal, the vehicle-mounted terminal operates the set personnel head detection model to detect the head number of passengers in the identification area defined on the image, and the head number of the passengers in the identification area on the image is obtained and is used as the number of standing passengers detected each time; continuously shooting a plurality of images, and taking an average value of the number of standing passengers detected each time as the counted number c of the standing passengers;
the method comprises the following steps of (1) counting the bus passenger flow: the vehicle-mounted terminal counts the bus passenger flow according to the counted number of passengers getting on the bus, the number of passengers on the seat and the number of passengers standing on the bus, wherein the number of real-time passengers of the vehicle before the vehicle arrives at the next stop after leaving the stop is b + c, and the number of passengers getting off the bus at the stop is the sum of the number of real-time passengers of the vehicle before the vehicle arrives at the stop and the number of passengers getting on the bus at the stopaAnd subtracting the number of real-time people of the vehicle before the vehicle arrives at the next station as b + c, and uploading the bus passenger flow data to the bus cloud platform by the vehicle-mounted terminal.
2. The method as claimed in claim 1, wherein in the step of counting the number of passengers getting on the bus, the counted number of times of swiping a card or the counted number of times of swiping a code before the vehicle arrives at the next stop is taken as the number of passengers getting on the bus at the stop.
3. The method as set forth in claim 1, wherein in said step of counting the number of passengers in a seat, a passenger is considered to be in the seat when a pressure sensor installed in the bus seat detects a pressure greater than a predetermined pressure threshold.
4. The method for detecting bus passenger flow according to claim 1, wherein in the step of counting the number of standing passengers, the vehicle-mounted cameras are a front camera and a rear camera, respectively, and are used for shooting the front half part and the rear half part of the carriage, and the vehicle-mounted terminal is used for removing the overlapped area of the fields of vision of the two cameras from the shot images and then identifying the heads of the passengers.
5. The method as claimed in claim 4, wherein the human head detection model is trained by using Yolox-Tiny algorithm.
6. The bus passenger flow detection method according to claim 1, wherein the vehicle-mounted terminal is connected with the card swiping machine, the pressure sensor and/or the vehicle-mounted camera through wireless communication.
7. The method of detecting bus passenger flow according to claim 6, wherein the wireless communication is Zigbee communication.
8. The bus passenger flow detection method according to any one of claims 1 to 7, wherein the bus cloud platform counts the full load rate of each vehicle, the passenger flow of each station and/or the passenger flow of each bus route according to the bus passenger flow data uploaded by each vehicle.
9. A bus passenger flow detection system comprises a bus cloud platform, vehicle-mounted terminals of all vehicles, card readers installed on all vehicles, pressure sensors and vehicle-mounted cameras, and is characterized in that the bus passenger flow is detected by the method according to any one of claims 1 to 8.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210247078.8A CN114333120A (en) | 2022-03-14 | 2022-03-14 | Bus passenger flow detection method and system |
| PCT/CN2023/081239 WO2023174240A1 (en) | 2022-03-14 | 2023-03-14 | Bus passenger flow detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210247078.8A CN114333120A (en) | 2022-03-14 | 2022-03-14 | Bus passenger flow detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114333120A true CN114333120A (en) | 2022-04-12 |
Family
ID=81033526
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210247078.8A Pending CN114333120A (en) | 2022-03-14 | 2022-03-14 | Bus passenger flow detection method and system |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN114333120A (en) |
| WO (1) | WO2023174240A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023174240A1 (en) * | 2022-03-14 | 2023-09-21 | 南京理工大学 | Bus passenger flow detection method and system |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117408436B (en) * | 2023-12-01 | 2024-03-26 | 智达信科技术股份有限公司 | Method and system for estimating number of passengers in bus route stations |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102063613A (en) * | 2010-12-28 | 2011-05-18 | 北京智安邦科技有限公司 | People counting method and device based on head recognition |
| CN102523261A (en) * | 2011-12-06 | 2012-06-27 | 北京经纬信息技术公司 | Distributed data processing system |
| CN102521902A (en) * | 2011-11-21 | 2012-06-27 | 长安大学 | Passenger detection system of passenger car |
| CN102867408A (en) * | 2012-09-17 | 2013-01-09 | 北京理工大学 | Method and system for selecting bus trip route |
| CN104809344A (en) * | 2015-04-23 | 2015-07-29 | 中山大学 | IC (Integrated Circuit) card data-based estimation method for passenger flow in bus station interval |
| CN204557612U (en) * | 2015-04-14 | 2015-08-12 | 清华大学苏州汽车研究院（吴江） | A kind of bus passenger flow statistical system based on machine vision |
| CN104899947A (en) * | 2015-05-25 | 2015-09-09 | 郑州天迈科技股份有限公司 | Public transport passenger flow statistical method |
| CN105005959A (en) * | 2015-07-24 | 2015-10-28 | 吴江智远信息科技发展有限公司 | Bus passenger flow volume calculation and statistical analysis method with characteristic attributes |
| CN107610282A (en) * | 2017-08-21 | 2018-01-19 | 深圳市海梁科技有限公司 | A kind of bus passenger flow statistical system |
| CN107878361A (en) * | 2016-09-30 | 2018-04-06 | 法乐第(北京)网络科技有限公司 | A kind of overcrowding monitoring method of automobile and device, automobile |
| CN109633769A (en) * | 2018-11-27 | 2019-04-16 | 安徽安凯汽车股份有限公司 | A kind of bus passenger flow monitoring system and its working method |
| CN109858389A (en) * | 2019-01-10 | 2019-06-07 | 浙江新再灵科技股份有限公司 | Vertical ladder demographic method and system based on deep learning |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2019059315A (en) * | 2017-09-26 | 2019-04-18 | 富士通フロンテック株式会社 | Vehicle congestion condition notification system, vehicle congestion condition notification method, and vehicle congestion condition notification device |
| KR20200046178A (en) * | 2018-10-18 | 2020-05-07 | 주식회사 케이티 | Head region detection method and head region detection device |
| CN114333120A (en) * | 2022-03-14 | 2022-04-12 | 南京理工大学 | Bus passenger flow detection method and system |
-
2022
- 2022-03-14 CN CN202210247078.8A patent/CN114333120A/en active Pending
-
2023
- 2023-03-14 WO PCT/CN2023/081239 patent/WO2023174240A1/en unknown
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102063613A (en) * | 2010-12-28 | 2011-05-18 | 北京智安邦科技有限公司 | People counting method and device based on head recognition |
| CN102521902A (en) * | 2011-11-21 | 2012-06-27 | 长安大学 | Passenger detection system of passenger car |
| CN102523261A (en) * | 2011-12-06 | 2012-06-27 | 北京经纬信息技术公司 | Distributed data processing system |
| CN102867408A (en) * | 2012-09-17 | 2013-01-09 | 北京理工大学 | Method and system for selecting bus trip route |
| CN204557612U (en) * | 2015-04-14 | 2015-08-12 | 清华大学苏州汽车研究院（吴江） | A kind of bus passenger flow statistical system based on machine vision |
| CN104809344A (en) * | 2015-04-23 | 2015-07-29 | 中山大学 | IC (Integrated Circuit) card data-based estimation method for passenger flow in bus station interval |
| CN104899947A (en) * | 2015-05-25 | 2015-09-09 | 郑州天迈科技股份有限公司 | Public transport passenger flow statistical method |
| CN105005959A (en) * | 2015-07-24 | 2015-10-28 | 吴江智远信息科技发展有限公司 | Bus passenger flow volume calculation and statistical analysis method with characteristic attributes |
| CN107878361A (en) * | 2016-09-30 | 2018-04-06 | 法乐第(北京)网络科技有限公司 | A kind of overcrowding monitoring method of automobile and device, automobile |
| CN107610282A (en) * | 2017-08-21 | 2018-01-19 | 深圳市海梁科技有限公司 | A kind of bus passenger flow statistical system |
| CN109633769A (en) * | 2018-11-27 | 2019-04-16 | 安徽安凯汽车股份有限公司 | A kind of bus passenger flow monitoring system and its working method |
| CN109858389A (en) * | 2019-01-10 | 2019-06-07 | 浙江新再灵科技股份有限公司 | Vertical ladder demographic method and system based on deep learning |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023174240A1 (en) * | 2022-03-14 | 2023-09-21 | 南京理工大学 | Bus passenger flow detection method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023174240A1 (en) | 2023-09-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109285376B (en) | Bus passenger flow statistical analysis system based on deep learning | |
| CN111310994B (en) | Bus route prediction method and system based on data calibration | |
| CN109815882B (en) | Subway carriage passenger flow density monitoring system and method based on image recognition | |
| CN106541968B (en) | The recognition methods of the subway carriage real-time prompt system of view-based access control model analysis | |
| CN114333120A (en) | Bus passenger flow detection method and system | |
| CN102855475B (en) | School bus monitoring method and school bus monitoring system | |
| CN105390021B (en) | The detection method and device of parking space state | |
| CN108765970B (en) | Method and device for automatically identifying license plate of automobile during roadside parking | |
| CN102324024B (en) | Airport passenger recognition and positioning method and system based on target tracking technique | |
| CN103021059A (en) | Video-monitoring-based public transport passenger flow counting method | |
| EP2397995A1 (en) | Anti fare evasion system | |
| CN108268849A (en) | Public transport vehicle-mounted Visual intelligent sensory perceptual system based on AI technologies | |
| CN105185118B (en) | A kind of vehicles peccancy detection means and its method based on video detection | |
| KR102109647B1 (en) | System for counting ride of public transportation using deep learning and method thereof | |
| CN112124379B (en) | Platform guiding method based on subway passenger flow analysis | |
| CN110085029A (en) | Highway cruising inspection system and method based on rail mounted crusing robot | |
| CN105383381B (en) | For the control method for vehicle and its device of driving safety | |
| CN107123270A (en) | A kind of intelligent managing and control system in building site for slag-soil truck | |
| JP2019197268A (en) | Bus boarding/alighting/stopping time prediction device | |
| CN109712395A (en) | A kind of system and method obtaining traffic flow parameter | |
| CN108008666A (en) | One kind building neutral net and its method of work | |
| CN105225489B (en) | The method and apparatus that non-bus take bus dedicated Lanes evidence collection | |
| CN112597965A (en) | Driving behavior recognition method and device and computer readable storage medium | |
| CN110936988A (en) | Automatic judgment and guide system for congestion degree of subway train carriage | |
| CN114926422B (en) | Method and system for detecting passenger flow of getting on and off vehicles |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220412 |