CN106407937A - Bus vehicle-mounted people flow statistical system based on depth image - Google Patents
Bus vehicle-mounted people flow statistical system based on depth image Download PDFInfo
- Publication number
- CN106407937A CN106407937A CN201610840255.8A CN201610840255A CN106407937A CN 106407937 A CN106407937 A CN 106407937A CN 201610840255 A CN201610840255 A CN 201610840255A CN 106407937 A CN106407937 A CN 106407937A
- Authority
- CN
- China
- Prior art keywords
- depth image
- vehicle
- image
- acquisition terminal
- fep
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to a bus vehicle-mounted people flow counting system based on a depth image. The bus vehicle-mounted people flow statistical system comprises an image acquisition terminal, a front-end processor and a control center, wherein the image acquisition terminal is installed at the top part of a vehicle door of a bus, and is used for acquiring a depth image of passengers at the vehicle door during a period from the opening of the vehicle door to the closing thereof; the front-end processor is used for performing counting statistics of the passengers according to the depth image of the passengers at the vehicle door which is acquired by the image acquisition terminal; and the control center is used for performing summary statistics of people flow on the bus according to a passenger counting statistic result of the front-end processor. Through acquiring the depth image of the passengers during the boarding and alighting process of the bus, and extracting, recognizing and tracking the passengers in the image, the bus vehicle-mounted people flow statistical system can count the passengers during the boarding and alighting process of the bus, and achieves the requirements of the people flow statistics.
Description
Technical field
The invention belongs to public transport artificial abortion's statistical technique field is and in particular to a kind of vehicle-mounted people of buses based on depth image
Stream statistics system.
Background technology
Traditional people's stream statistics are by carrying out motion tracking and counting to the personnel in a concrete scene, reaching
Effect to people's stream statistics.Be presently mainly that the gray scale of people or coloured image are obtained by photographic head, and using image procossing with
Analysis method carries out the identification of certain specific purpose, and because traditional camera is all two dimensional image, picture quality is affected by light
Larger, two dimensional image there is a problem of near big and far smaller simultaneously, and such work is big to the error of people's stream statistics, algorithm robustness
Low, poor to scene degrees of fusion, there is significant limitation.But it is with artificial intelligence and mode identification technology development, multi-modal
Data acquisition equipment is increasing and is widely used.
Content of the invention
It is an object of the invention to solving above-mentioned technical problem and providing a kind of buses based on depth image vehicle-mounted
Artificial abortion's statistical system.
For achieving the above object, the present invention adopts the following technical scheme that：
A kind of vehicle-mounted artificial abortion's statistical system of buses based on depth image, including：
Image acquisition terminal, is arranged on bus door mouth top, for the image according to FEP after vehicle start-up
Collecting device keying signal is opened and closed, to the depth image of down periods collecting vehicle doorway passenger after car door opening；
FEP, is connected with described image acquisition terminal and auto control system in vehicles, for according to from described vehicle
The Vehicular status signal that automatic control system transmits, output image collecting device keying signal, and gathered eventually according to described image
Car door mouth passenger's depth image of end collection carries out passenger's counting statisticses；
Control centre, is connected by described auto control system in vehicles with described FEP, for according to described front end
Passenger's counting statisticses result of processor, carries out collect statistics to flow of the people on buses.
Described image acquisition terminal includes depth image sensor.
Described image acquisition terminal also includes high clear colorful imageing sensor, for synchronous with described depth image sensor
Collection high clear colorful image, and the depth image of described depth image sensor collection is demarcated.
Described FEP include that dsp processor is connected with described dsp processor for passing to described depth image
The depth image of sensor collection processes the GPU APU to carry out passenger's counting statisticses work and is used for local picture number
Storage card according to storage；Described GPU APU connection figure as acquisition terminal and connects described storage card, described DSP process
Device is connected to obtain vehicle control signal with described auto control system in vehicles and obtains vehicle-state, including vehicle door status with
And state of motion of vehicle.
Between described FEP and auto control system in vehicles, described FEP and described image acquisition terminal
Between be connected by wireless communication module, realize the transmission of data.
Described wireless communication module adopts 3G/4G or WIFI module.
The present invention, by the depth image of passenger during gathering buses and getting on or off the bus, and carries to the passenger in image
Take, identify and follow the tracks of, the passenger during buses can be got on or off the bus counts, reach the requirement of people's stream statistics.
Brief description
The mounting arrangements that Fig. 1 illustrates the vehicle-mounted artificial abortion statistical system of the buses based on depth image of the present invention are illustrated
Figure；
Fig. 2 illustrates the bitter edible plant schematic flow sheet of the vehicle-mounted artificial abortion statistical system of the buses based on depth image of the present invention.
Specific embodiment
Below, in conjunction with example, the substantive distinguishing features of the present invention and advantage are further described, but the present invention not office
It is limited to listed embodiment.
Shown in Figure 1, a kind of vehicle-mounted artificial abortion's statistical system of buses based on depth image, including：
Image acquisition terminal, is arranged on bus door mouth top, for the image according to FEP after vehicle start-up
Collecting device keying signal is opened and closed, to the depth image of down periods collecting vehicle doorway passenger after car door opening；
FEP, is connected with described image acquisition terminal and auto control system in vehicles, for according to from described vehicle
The Vehicular status signal that automatic control system transmits, output image collecting device keying signal, and gathered eventually according to described image
Car door mouth passenger's depth image of end collection carries out passenger's counting statisticses；
Control centre 30, is connected by described auto control system in vehicles 40 with described FEP, for according to described
Passenger's counting statisticses result of FEP, carries out collect statistics to flow of the people on buses.
It should be noted that in the present invention, described FEP can be realized by installing existing artificial abortion's algoritic module
Counting statisticses to artificial abortion, described control centre can realize the summary counts to artificial abortion by installing existing artificial abortion's statistical module
Statistics, this people's flow algorithm and people's stream statistics are prior art, and the present invention is no longer described in detail its people stream counting and collecting
Flow process.
Implement, described image acquisition terminal adopts depth image sensor, for gathering the depth of highest 640*480
Degree image, described depth image sensor is separately mounted to the entrance door of buses and the doorway top of exit door, buses
On have several entrance doors or multiple exit door, several depth image sensor are just installed, shown in Figure 1, the public transport shown in Fig. 1
Car 100 has 110, exit door 120 of an entrance door, then entrance door install a depth image sensor of getting on the bus, under
Car door installs a depth image sensor of getting off；Corresponding, the quantity of described FEP is sensed with described depth image
The quantity of device is consistent, including multiple FEPs, as shown in figure 1, include a FEP 11 of getting on the bus getting off with one
FEP 21, is corresponded to respectively and is connected 20 with corresponding depth image sensor 10 of getting on the bus, depth image sensor of getting off,
Realize respectively corresponding depth image sensor is controlled and carried out according to the depth image of depth image sensor collection
Passenger's counting statisticses, carry out image acquisition and carry out passenger's counting statisticses including starting depth image sensor, or close depth
The operations such as imageing sensor, stopping counting statisticses.
Described FEP, control centre and auto control system in vehicles 40 may be mounted at car body internal upper part 130
Relevant position, as shown in Figure 1.
As an embodiment, in the present invention, described FEP includes dsp processor and described dsp processor connects
The GPU APU connecing and the storage card for local view data storage；Described GPU APU connection figure picture is adopted
Collection terminal simultaneously connects described storage card, and described dsp processor is connected with described auto control system in vehicles, and described vehicle is automatic
Control system connects control centre, obtains vehicle-state for obtaining vehicle control signal, including vehicle door status and vehicle
Kinestate, as above vehicle door status（Open/close）, door state of getting off（Open/close）, state of motion of vehicle（Flame-out/to run
In）, and according to the vehicle-state obtaining, output counts instruction to described GPU APU, by described GPU APU
According to the counting instruction of described dsp processor, the depth image of described depth image sensor collection is processed, carries out passenger's meter
Number statistical work.
It should be noted that in the present invention, described GPU APU built-in type is provided with artificial abortion's algoritic module, use
In calculating and the operation of director's flow algorithm, passenger's depth image of collection is processed, including by foreground extraction and
Personnel positioning tracking technique, with the personnel in recognition and tracking depth image, realizes the function of personnel counting.Described artificial abortion calculates
Method module can be realized using prior art artificial abortion's statistical technique.
As an embodiment, between described FEP and auto control system in vehicles, described FEP with
Described image acquisition terminal can be connected by wireless communication module, realizes the transmission of data, such as will be from image acquisition terminal
The view data obtaining is wirelessly transmitted to FEP, and passenger's counting statisticses result of FEP is wirelessly transmitted to
Control centre, or view data is wirelessly transmitted to control centre, carry out data storage, and enter driving in described control centre
Interior artificial abortion's statistical computation completes to obtain artificial abortion's statistical computation result, artificial abortion's statistical computation result of acquisition is stored or is sent to remote
The Monitor Computer Control System of journey is stored.
Described wireless communication module can be to carry out radio communication data transmission using 3G/4G or WIFI.
It should be noted that in the present invention, described control centre is provided with artificial abortion's statistic device, for being calculated using people's stream statistics
Method, passenger's count results of multiple FEPs is carried out analysis of accounts and collects, and stores and transmit final people's stream statistics knot
Fruit is it is possible to play video image by the display connecting.
Described artificial abortion's statistic device can be realized using prior art artificial abortion's statistical technique.
Described control centre can be a single-chip microcomputer, and such as MCU controller etc. or minimum a control of ARM are
System.Described auto control system in vehicles can be the existing automatic control system of buses, and it can realize reflecting vehicle in real time
State, the state including car door and the running status of vehicle, the state of this vehicle can obtain by described FEP
And be used for taking this as a foundation to control being turned on and off of image capture device.
As an embodiment, described image acquisition terminal also includes high clear colorful imageing sensor, for depth
Imageing sensor together, the high clear colorful image of the depth image of synchronous acquisition highest 640*480 and 1080P, and enable right
The accurate calibration of passenger's depth image of depth image sensor collection, to improve the accuracy rate of people's stream statistics.
The control flow of the vehicle-mounted artificial abortion's statistical system of described buses based on depth image proposed by the present invention is concrete such as
Under, shown in Figure 2：
Step 1, vehicle launch；
S101:Control centre is activated, and control centre connects FEP by auto control system in vehicles, such as connects normal
After then obtaining vehicle-state, front-end processor sends vehicle launch signal；As malunion often, enter step 4；
S102:FEP activates image acquisition terminal, and tests the connection status with image acquisition terminal, test chart simultaneously
As the image acquisition state of acquisition terminal, such as all go well, then enter step 2；Otherwise enter step 4；
Step 2, FEP carry out following different operating according to the vehicle-state obtaining at auto control system in vehicles：
S201:Before car door opening, start depth image sensor, start to obtain original depth image at car door mouth, and update the back of the body
Scape model.
S202:Car door opening, carries out foreground extraction in real time to depth image and personnel positioning tracking is processed, and carries out passenger
Counting statisticses；
S203:Closing of the door, FEP stops depth image collection, and stops counting statisticses, passes count results simultaneously
It is defeated by control centre；
S204:After control centre obtains the counting statisticses result of all FEPs, signal front-end processor counts and completes, front
End processor is zeroed to count results, and prepares counting operation next time；Then repeat step S201-S204；
Step 3, control centre's vehicle occupant's stream statistics
After control centre obtains the count results of all FEPs, according to artificial abortion's statistic algorithm, vehicle occupant's stream is united
Meter, and label time stamp and location position information；And by statistical result pass through 3G/4G real-time Transmission to Surveillance center or specify connect
Receive place；Designated equipment can also be transferred to by WIFI；
Operate after step 4, vehicle stall
Control centre sends flameout state signal by auto control system in vehicles front-end processor vehicle, afterwards, does not have within 3 minutes
In the case of having new state change, FEP closes image acquisition terminal；5 minutes afterwards, and control centre closes at front end
Reason device；10 minutes afterwards control centre close, wait next time vehicle launch when be activated.
The vehicle-mounted artificial abortion's statistical system of buses based on depth image proposed by the present invention, it is possible to achieve public transport in real time online
People's stream statistics on car, due to employing depth transducer so that image is not affected by light, statistical result is more accurate.Pass through
The auto control system in vehicles of control centre is linked with FEP, efficiently solves the control of gate time data transmission
Problem, makes system more flexibly easy-to-use.
The above is only the preferred embodiment of the present invention it is noted that ordinary skill people for the art
For member, under the premise without departing from the principles of the invention, some improvements and modifications can also be made, these improvements and modifications also should
It is considered as protection scope of the present invention.
Claims (6)
1. a kind of vehicle-mounted artificial abortion's statistical system of buses based on depth image is it is characterised in that include：
Image acquisition terminal, is arranged on bus door mouth top, for the image according to FEP after vehicle start-up
Collecting device keying signal is opened and closed, to the depth image of down periods collecting vehicle doorway passenger after car door opening；
FEP, is connected with described image acquisition terminal and auto control system in vehicles, for according to from described vehicle
The Vehicular status signal that automatic control system transmits, output image collecting device keying signal, and gathered eventually according to described image
Car door mouth passenger's depth image of end collection carries out passenger's counting statisticses；
Control centre, is connected by described auto control system in vehicles with described FEP, for according to described front end
Passenger's counting statisticses result of processor, carries out collect statistics to flow of the people on buses.
2. according to claim 1 the vehicle-mounted artificial abortion statistical system of the buses based on depth image it is characterised in that described
Image acquisition terminal includes depth image sensor.
3. according to claim 2 the vehicle-mounted artificial abortion statistical system of the buses based on depth image it is characterised in that described
Image acquisition terminal also includes high clear colorful imageing sensor, for described depth image sensor synchronous acquisition high clear colorful
Image, and the depth image of described depth image sensor collection is demarcated.
4. the vehicle-mounted artificial abortion of the buses based on depth image statistical system according to any one of claim 1-3, its feature exists
In, described FEP include that dsp processor is connected with described dsp processor for described depth image sensor
The depth image of collection processes the GPU APU to carry out passenger's counting statisticses work and deposits for local view data
The storage card of storage；Described GPU APU connection figure as acquisition terminal and connects described storage card, described dsp processor with
Described auto control system in vehicles is connected to obtain vehicle control signal and obtains vehicle-state, including vehicle door status and car
Kinestate.
5. according to claim 4 the vehicle-mounted artificial abortion statistical system of the buses based on depth image it is characterised in that before described
Between end processor and auto control system in vehicles, between described FEP and described image acquisition terminal, pass through channel radio
Letter module is connected, and realizes the transmission of data.
6. according to claim 5 the vehicle-mounted artificial abortion statistical system of the buses based on depth image it is characterised in that described nothing
Line communication module adopts 3G/4G or WIFI module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610840255.8A CN106407937A (en) | 2016-09-21 | 2016-09-21 | Bus vehicle-mounted people flow statistical system based on depth image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610840255.8A CN106407937A (en) | 2016-09-21 | 2016-09-21 | Bus vehicle-mounted people flow statistical system based on depth image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106407937A true CN106407937A (en) | 2017-02-15 |
Family
ID=57997304
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610840255.8A Pending CN106407937A (en) | 2016-09-21 | 2016-09-21 | Bus vehicle-mounted people flow statistical system based on depth image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106407937A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107016349A (en) * | 2017-03-10 | 2017-08-04 | 中科唯实科技（北京）有限公司 | A kind of crowd's flow analysis method based on depth camera |
| CN109250616A (en) * | 2018-09-28 | 2019-01-22 | 绍兴市特种设备检测院 | A kind of staircase entrance congestion detection system and method |
| CN110443100A (en) * | 2018-05-04 | 2019-11-12 | 郑州宇通客车股份有限公司 | A kind of passenger flow statistical method, passenger flow statistical system and school bus |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104112309A (en) * | 2014-08-01 | 2014-10-22 | 西安电子科技大学 | Device and method for automatically recording passenger flow of bus by adopting video monitor |
| 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 |
| CN104835323A (en) * | 2015-05-19 | 2015-08-12 | 银江股份有限公司 | Multi-target public transport passenger flow detection method combining with electronic fence |
| 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 |
-
2016
- 2016-09-21 CN CN201610840255.8A patent/CN106407937A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104112309A (en) * | 2014-08-01 | 2014-10-22 | 西安电子科技大学 | Device and method for automatically recording passenger flow of bus by adopting video monitor |
| 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 |
| CN104835323A (en) * | 2015-05-19 | 2015-08-12 | 银江股份有限公司 | Multi-target public transport passenger flow detection method combining with electronic fence |
| 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 |
Non-Patent Citations (1)
| Title |
|---|
| 崔莫磊: "公交视频人数统计***的设计与开发", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107016349A (en) * | 2017-03-10 | 2017-08-04 | 中科唯实科技（北京）有限公司 | A kind of crowd's flow analysis method based on depth camera |
| CN107016349B (en) * | 2017-03-10 | 2020-11-06 | 中科唯实科技（北京）有限公司 | Crowd flow analysis method based on depth camera |
| CN110443100A (en) * | 2018-05-04 | 2019-11-12 | 郑州宇通客车股份有限公司 | A kind of passenger flow statistical method, passenger flow statistical system and school bus |
| CN109250616A (en) * | 2018-09-28 | 2019-01-22 | 绍兴市特种设备检测院 | A kind of staircase entrance congestion detection system and method |
| CN109250616B (en) * | 2018-09-28 | 2020-05-19 | 绍兴市特种设备检测院 | Escalator entrance and exit congestion detection system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105957354A (en) | Road side parking management system based on terrestrial magnetism and camera array linkage and method thereof | |
| CN100533491C (en) | Device and method for collecting public traffic vehicle passenger flow | |
| CN102622798B (en) | Passenger flow statistical analysis system | |
| CN203025787U (en) | Vehicle charging system free of taking card | |
| CN111311799A (en) | Gate control system based on intelligent identification | |
| CN108986539A (en) | Parking management system, method, vehicle information collecting device and management server | |
| CN107123274A (en) | Double parking stall video detecting devices and method | |
| CN106530818A (en) | Intelligent parking lot management system based on video processing technology | |
| CN106541968B (en) | The recognition methods of the subway carriage real-time prompt system of view-based access control model analysis | |
| CN106407937A (en) | Bus vehicle-mounted people flow statistical system based on depth image | |
| CN206039714U (en) | Electric automobile fills electric pile charging management system | |
| CN108537935A (en) | A kind of parking management system based on polymorphic type multi-view image | |
| CN109544946A (en) | Tunnel real-time monitoring and managing system and its implementation based on vehicle flowrate big data | |
| CN110281748A (en) | A kind of automatic driving vehicle bus stop passenger's control method, system and vehicle up and down | |
| CN104574977B (en) | Vehicle passing information identification matching system | |
| CN110278409A (en) | A kind of subway shield door passenger flow guidance system based on intensity of passenger flow estimation | |
| CN109920404A (en) | Possess the information collecting device and acquisition method of the automatic selling Advertising Management System of Intellisense effect | |
| CN110084196A (en) | A kind of monitor video identifying system for cloud computing | |
| KR101917783B1 (en) | Parking lot management system | |
| CN109657555A (en) | It is a kind of to get off the detection device and method of omission for school bus student | |
| CN107886730B (en) | A kind of vehicle information acquisition system and method | |
| CN113313844A (en) | Video stream based bidirectional triggering vehicle intelligent management system and method | |
| CN202058208U (en) | Outdoor medium audience investigation system | |
| CN201181488Y (en) | Passenger traffic collection apparatus for public traffic vehicle | |
| CN104156737B (en) | A kind of passenger on public transport Safe getting-off automatic testing method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into 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: 20170215 |