CN109871853A - A kind of monitoring device that can finely identify vehicle - Google Patents

A kind of monitoring device that can finely identify vehicle Download PDF

Info

Publication number
CN109871853A
CN109871853A CN201910131729.5A CN201910131729A CN109871853A CN 109871853 A CN109871853 A CN 109871853A CN 201910131729 A CN201910131729 A CN 201910131729A CN 109871853 A CN109871853 A CN 109871853A
Authority
CN
China
Prior art keywords
vehicle
monitoring device
gradient
flush type
sound wave
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
Application number
CN201910131729.5A
Other languages
Chinese (zh)
Inventor
魏一凡
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Individual
Original Assignee
Individual
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Priority to CN201910131729.5A priority Critical patent/CN109871853A/en
Publication of CN109871853A publication Critical patent/CN109871853A/en
Pending legal-status Critical Current

Links

Landscapes

  • Traffic Control Systems (AREA)

Abstract

The invention discloses the monitoring devices that one kind can finely identify vehicle, including monitoring device and server, the monitoring device includes pressure sensor device and signal processing apparatus, the pressure sensor device includes flush type piezoelectric transducer, gravity sensor and electric storage device, the signal processing apparatus includes sonic generator and data source, vehicle generates pressure signal and gravitational cue to it when passing through the pressure sensor, after the sonic generator receives the pressure signal of the flush type piezoelectric transducer, transmitting sound wave obtains vehicle section graph data, then the graph data and the gravitational cue are fed back into server by data source, the server is combined analysis to the graph data and the gravitational cue;The configuration of the present invention is simple, environmental suitability is strong, can only effectively identify vehicle and judge whether vehicle is overweight.

Description

A kind of monitoring device that can finely identify vehicle
Technical field
The present invention relates to intelligent transportation field, in particular to a kind of monitoring device that can finely identify vehicle.
Background technique
Currently, with the development of science and technology, Chinese road traffic facility it is perfect, the trip of people is also more and more square Just, but simultaneously, the magnitude of traffic flow of the cash desks such as each highway crossings, bridge, tunnel also significantly improves.In order to improve passage Efficiency, reduces manual intervention, and automatic model recognition system is widely used.
Existing vehicle cab recognition technology mainly include the following types:
One kind is image recognition technology, as long as image recognition technology with local with highway mouth etc. at the parting of the ways, is adopted It is simple with the model recognition system structure of image recognition technology, but it is weaker to the adaptability of environment, it is suitable only for static or slow The vehicle vehicle cab recognition of speed movement, when speed is too fast, image recognition is easy distortion, so as to cause that can not identify.
Another kind is on-vehicle information monotechnics, and on board unit technology is generally used for CET charge crossing.In on board unit Store the information such as vehicle, the license plate of vehicle.When vehicle passes through area of charge, on board unit and roadside unit carry out data friendship Mutually, roadside unit reads the data such as the vehicle on board unit, to achieve the purpose that vehicle cab recognition.This vehicle type recognition device tool Have the advantages that high reliablity, easy to install and use, environmental suitability is strong, is at home and abroad widely used in a variety of applications.Use the dress The time for both having saved driver is set, also reduces human cost to each road and bridge unit of operation.But fake-licensed car, vehicle can not be solved The phenomenon that carrier unit disorderly pastes, while calutron has radiation, is detrimental to health.
Summary of the invention
The main purpose of the present invention is to provide a kind of monitoring device that can finely identify vehicle based on HOG technology leads to It crosses the appearance data that sensor measures vehicle, then carries out image procossing with HOG technology, and urged by vehicle driving face pressure of passing by one's way The gravitational cue that Force sensor generates judges whether vehicle overloads, and is suitable for various the intensive traffic sections, and structure is simple, and environment is suitable Ying Xingqiang can be improved the stability of work and reduce cost of labor.
To achieve the above objectives, the technical solution adopted by the present invention are as follows: one kind can finely identify the monitoring device of vehicle, packet Monitoring device and server are included, the monitoring device includes pressure sensor device and signal processing apparatus, the pressure sensing dress Set including flush type piezoelectric transducer, gravity sensor and electric storage device, the signal processing apparatus include sonic generator and Data source, vehicle generate pressure signal and gravitational cue, the sonic generator to it when passing through the pressure sensor After the pressure signal for receiving the flush type piezoelectric transducer, transmitting sound wave obtains vehicle section graph data, then by institute State graph data and the gravitational cue and server fed back to by data source, the server to the graph data and The gravitational cue is combined analysis.
As an improvement, the data source includes microprocessor, memory and transmitter, the microprocessor will be described The data that sonic generator is sent in real time are stored in the memory and are integrated, then are sent to traffic by the transmitter In the server at center.
As an improvement, the microprocessor uses a kind of HOG image processing techniques, the HOG technical idea is to pass through side The appearance profile being distributed to indicate image object in edge direction, the data packet that the sonic generator is sent to traffic hub carry out Decompression, then the lines image being collected into is divided into several regions by shape size, by obtaining the area image pixel gradient And carry out feature calculation and carry out accumulated gradient feature, so that the gradient orientation histogram of certain dimension is obtained, by calculating pixel The gradient of the coordinate direction of (x, y) obtains the gradient magnitude and gradient direction of the point.Specific formula for calculation such as formula (1), (2), (3) shown in:
In formula, Gx (x, y), Gy (x, y), H (x, y) respectively indicate pixel x-axis and y-axis side in two-dimensional surface vertical coordinate system To gradient and pixel value.G (x, y) and D (x, y) respectively indicates gradient magnitude and gradient direction at pixel;
Its algorithm can only calculate not comprehensive enough single of pixel it can be seen from the calculating process of above-mentioned HOG feature extraction Gradient direction information has certain defect, the direction character of vehicle image cannot be fully described.Therefore, controllable filter is calculated Method is a kind of method for being used to make up HOG defect well, and specific calculating process is as follows:
In formula,The second dervative of image slices vegetarian refreshments in the corresponding direction is respectively indicated, Three's linear combination, can be calculated the amplitude information of any direction by the base filter for indicating respective direction.
By the above-mentioned gradient magnitude and gradient direction that each pixel is calculated, pass through the essence of the available vehicle of curve matching True vehicle, then by being matched with a variety of models being previously stored in server, finally obtain monitored vehicle.
As an improvement, the flush type piezoelectric transducer is installed on the road of the 2m distance below the sonic generator In the following, the flush type piezoelectric transducer can discharge the electric signal of different powers according to the vehicle weight crossed.
As an improvement, the piezoelectric material that the flush type piezoelectric transducer uses is Kynoar.
As an improvement, the sonic generator is installed on the top apart from the flush type piezoelectric transducer 2m, the sound Wave producer is compared by the sound wave that front and back emits, and can obtain a series of vehicle section figure in Vehicle length sizes.
As an improvement, the monitoring device is also powered by the solar panel for being installed on column top.
It compares to obtain vehicle section figure number as an improvement, the pinger emits sound wave by interval time According to.
As an improvement, the monitoring device is respectively arranged in fast, fast traffic lane and slow train in highway multilane Road, and preset threshold respectively, when vehicle can root by generating gravitational cue, the gravitational cue when flush type piezoelectric sensing Strong and weak variation is generated according to the variation of the vehicle weight size crossed, when the gravitational cue intensity is more than preset threshold, institute After stating the pressure signal that sonic generator receives the flush type piezoelectric transducer, transmitting sound wave obtains vehicle section figure number According to, then by the graph data and the gravitational cue by data feedback to server.
The present invention has the advantages that
1. sonic generator is much smaller on radiation hazradial bundle for on-vehicle information unit, and can prevent The generation of on-vehicle information unit is usurped, and wants the identification of vehicle accurately more for camera technology;In the energy Use aspect can be realized really environmentally protective by piezoelectric material and solar powered.
2. the traffic speed where device is very fast, actual conditions do not need real-time display vehicle vehicle, Data transmitter need to only send data in the server of traffic hub and store, and can carry out HOG skill when needed Art precise restoration, the datarams that can accomplish quickly to monitor in real time, and upload in monitoring in this way are also small more.
Detailed description of the invention
Fig. 1 is positive structure schematic of the invention;
Fig. 2 is side structure schematic diagram of the invention;
Fig. 3 is the image processing flow figure of HOG technology;
Appended drawing reference: 1- road, 2- battery, 3- solar panel, 41,42- column, 5- sonic generator, 6- are horizontal Beam, 7- flush type piezoelectric transducer, 8- car, 9- lorry, 10- sound wave, 11- data source.
Specific embodiment
It is described below for disclosing the present invention so that those skilled in the art can be realized the present invention.It is excellent in being described below Embodiment is selected to be only used as illustrating, it may occur to persons skilled in the art that other obvious modifications.
The present invention includes monitoring device and server, and the monitoring device includes pressure sensor device and signal processing device It sets, the pressure sensor device includes flush type piezoelectric transducer, gravity sensor and electric storage device, the signal processing apparatus Including sonic generator and data source, vehicle generates pressure signal and gravity letter to it when passing through the pressure sensor Number, after the sonic generator receives the pressure signal of the flush type piezoelectric transducer, transmitting sound wave obtains vehicle section Then the graph data and the gravitational cue are fed back to server, the service by data source by graph data Device is combined analysis to the graph data and the gravitational cue.
Specifically, the data source includes microprocessor, memory and transmitter, the microprocessor is by the sound The data that wave producer is sent in real time are stored in the memory and are integrated, then are sent in traffic by the transmitter In the server of the heart.
Specifically, the microprocessor uses a kind of HOG image processing techniques, the HOG technical idea is to pass through edge The appearance profile being distributed to indicate image object in direction, the data packet that the sonic generator is sent to traffic hub are solved Pressure, then the lines image being collected into is divided into several regions by shape size, by obtaining the area image pixel gradient simultaneously Carry out feature calculation and carry out accumulated gradient feature, to obtain the gradient orientation histogram of certain dimension, by calculate pixel (x, Y) gradient of coordinate direction obtains the gradient magnitude and gradient direction of the point.Specific formula for calculation such as formula (1), (2), (3) It is shown:
In formula, Gx (x, y), Gy (x, y), H (x, y) respectively indicate pixel x-axis and y-axis side in two-dimensional surface vertical coordinate system To gradient and pixel value.G (x, y) and D (x, y) respectively indicates gradient magnitude and gradient direction at pixel;
Its algorithm can only calculate not comprehensive enough single of pixel it can be seen from the calculating process of above-mentioned HOG feature extraction Gradient direction information has certain defect, the direction character of vehicle image cannot be fully described.Therefore, controllable filter is calculated Method is a kind of method for being used to make up HOG defect well, and specific calculating process is as follows:
In formula,The second dervative of image slices vegetarian refreshments in the corresponding direction is respectively indicated, Three's linear combination, can be calculated the amplitude information of any direction by the base filter for indicating respective direction.
Specifically, the flush type piezoelectric transducer is installed under the road apart from 2m distance below the sonic generator Face, the flush type piezoelectric transducer can discharge the electric signal of different powers according to the vehicle weight crossed.
Specifically, the piezoelectric material that the flush type piezoelectric transducer uses is Kynoar.
Specifically, the sonic generator is installed on the top apart from the flush type piezoelectric transducer 2m, the sound wave Generator is compared by the sound wave that front and back emits, and can obtain a series of vehicle section figure in Vehicle length sizes.
Specifically, the monitoring device is also powered by the solar panel for being installed on column top.
It compares to obtain vehicle section figure number specifically, the pinger emits sound wave by interval time According to.
Specifically, the monitoring device is respectively arranged in fast, fast traffic lane and slow train in highway multilane Road, and preset threshold respectively, when vehicle can root by generating gravitational cue, the gravitational cue when flush type piezoelectric sensing Strong and weak variation is generated according to the variation of the vehicle weight size crossed, when the gravitational cue intensity is more than preset threshold, institute After stating the pressure signal that sonic generator receives the flush type piezoelectric transducer, transmitting sound wave obtains vehicle section figure number According to, then by the graph data and the gravitational cue by data feedback to server.
Flush type piezoelectric transducer 7, using the production of piezoelectric material Kynoar, and by flush type piezoelectric transducer 7 The road 1 apart from 11 lower section 2m distance of sonic generator is installed in the following, working as vehicle passes through the road surface for being embedded with pressure sensor 7 When, pressure conversion is that electric signal is sent to sonic generator 5, while the compression meeting of pressure material by flush type piezoelectric transducer 7 It produces electricl energy, and by this energy stores in battery 2;Due to car 8 and lorry 9 by when road surface to the pressure of pressure sensor Power is different, and flush type piezoelectric transducer 7 can detect the tonnage for crossing vehicle by generating the power of electric signal.
Sonic generator 5 is mounted on the crossbeam 6 above whole device, when the electric signal of pressure sensor 7 is received When, sonic generator 5 is activated simultaneously, the sound wave of ground rebound is also received while sending sound wave 10 to ground, when vehicle is sailed When crossing 5 lower section of sonic generator, the outer profile of vehicle can hinder a part of acoustic wave touch ground, be received by rebound in advance, at this time Sonic generator 5 will shift to an earlier date received sound wave and compare with for received sound wave in advance, an available vehicle section shape The data of shape, the vehicle section by the way that the launch time of sonic generator 5 is arranged, on a series of available Vehicle length scales This sectional view, is then incorporated into a data packet by figure by digitization.
Solar panel 3 is mounted on 41 top of a heel post, since sonic generator 5 and data source 11 all need Electricity consumption is wanted, if only powered by piezoelectric material, will be unable to meet use, and road ambient enviroment has good daylighting effect, Installation solar panel 3 is come to utilize solar energy be a kind of very environmentally protective power supply mode.
Data source 11 is mounted on another 42 top of heel post, including microprocessor, memory, transmitter etc., micro- place The data that sonic generator is sent in real time are stored in memory and integrate by reason device, pass through transmitter after the completion of integration again and send out It send into the server of traffic hub.
The basic principles, main features and advantages of the present invention have been shown and described above.The technology of the industry Personnel are it should be appreciated that the present invention is not limited to the above embodiments, and what is described in the above embodiment and the description is only the present invention Principle, various changes and improvements may be made to the invention without departing from the spirit and scope of the present invention, these variation and Improvement is both fallen in the range of claimed invention.The present invention claims protection scope by appended claims and its Equivalent defines.

Claims (10)

1. one kind can finely identify the monitoring device of vehicle, including monitoring device and server, it is characterised in that: the monitoring dress It sets including pressure sensor device and signal processing apparatus, the pressure sensor device includes flush type piezoelectric transducer, gravity biography Sensor and electric storage device, the signal processing apparatus include sonic generator and data source, and vehicle is passed by the pressure Pressure signal and gravitational cue are generated when sensor to it, the sonic generator receives the pressure of the flush type piezoelectric transducer After force signal, transmitting sound wave obtains vehicle section graph data, and the graph data and the gravitational cue are then passed through number Server is fed back to according to transmitter, the server is combined analysis to the graph data and the gravitational cue.
2. the monitoring device that one kind according to claim 1 can finely identify vehicle, it is characterised in that: the data transmitting Device includes microprocessor, memory and transmitter, and the microprocessor deposits the data that the sonic generator is sent in real time Enter and integrated in the memory, then is sent in the server of traffic hub by the transmitter.
3. the monitoring device that one kind according to claim 1 can finely identify vehicle, it is characterised in that: the microprocessor Vehicle section graph data is analyzed in such a way that HOG image processing techniques and controllable filter algorithm combine, passes through the HOG The distribution of technology edge direction indicates the appearance profile of image object, i.e., the described microprocessor by the lines image being collected by Shape size is divided into several regions, by obtaining the area image pixel gradient and carrying out feature calculation accumulated gradient feature, The gradient magnitude and gradient direction of the point are obtained by the gradient of the coordinate direction of calculating pixel (x, y).It is specific to calculate public affairs Formula such as formula (1), (2), (3) are shown:
In formula, Gx (x, y), Gy (x, y), H (x, y) respectively indicate pixel x-axis and y-axis side in two-dimensional surface vertical coordinate system To gradient and pixel value, G (x, y) and D (x, y) respectively indicate gradient magnitude and gradient direction at pixel, to obtain one Determine the gradient orientation histogram of dimension;Then pass through controllable filter algorithm
In formula,The second dervative of image slices vegetarian refreshments in the corresponding direction is respectively indicated, Three's linear combination, can be calculated the amplitude information of any direction by the base filter for indicating respective direction.
4. the monitoring device that one kind according to claim 1 can finely identify vehicle, it is characterised in that: the flush type pressure Electric transducer is installed below the road of 2m distance below the sonic generator.
5. the monitoring device that one kind according to claim 1 can finely identify vehicle, it is characterised in that: the flush type pressure The piezoelectric material that electric transducer uses is Kynoar.
6. the monitoring device that one kind according to claim 1 can finely identify vehicle, it is characterised in that: the sound wave occurs Device is installed on the top apart from the flush type piezoelectric transducer 2m, the sound wave pair that the sonic generator is emitted by front and back Than a series of vehicle section figure in Vehicle length sizes can be obtained.
7. the monitoring device that one kind according to claim 1 can finely identify vehicle, it is characterised in that: the monitoring device Also powered by the solar panel for being installed on column top.
8. the monitoring device that one kind according to claim 1 can finely identify vehicle, it is characterised in that: the electric storage device It powers for the signal processing apparatus, the weight that the electric storage device is generated by the pressure sensor device in vehicle travels The power generation of power potential energy.
9. the monitoring device that one kind according to claim 1 can finely identify vehicle, it is characterised in that: the sound wave transmitting Device emits sound wave by interval time and compares to obtain vehicle section graph data.
10. a kind of one kind according to claim 1 can finely identify the method that the monitoring device of vehicle is monitored, special Sign is: in highway multilane, the monitoring device is respectively arranged in fast, fast traffic lane and slow lane, and respectively Preset threshold, when vehicle understands what basis crossed by generating gravitational cue, the gravitational cue when flush type piezoelectric sensing The variation of vehicle weight size and generate strong and weak variation, when the gravitational cue intensity is more than preset threshold, sound wave hair After raw device receives the pressure signal of the flush type piezoelectric transducer, transmitting sound wave obtains vehicle section graph data, then By the graph data and the gravitational cue by data feedback to server.
CN201910131729.5A 2019-02-22 2019-02-22 A kind of monitoring device that can finely identify vehicle Pending CN109871853A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910131729.5A CN109871853A (en) 2019-02-22 2019-02-22 A kind of monitoring device that can finely identify vehicle

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910131729.5A CN109871853A (en) 2019-02-22 2019-02-22 A kind of monitoring device that can finely identify vehicle

Publications (1)

Publication Number Publication Date
CN109871853A true CN109871853A (en) 2019-06-11

Family

ID=66919051

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910131729.5A Pending CN109871853A (en) 2019-02-22 2019-02-22 A kind of monitoring device that can finely identify vehicle

Country Status (1)

Country Link
CN (1) CN109871853A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110796872A (en) * 2019-11-13 2020-02-14 佛山科学技术学院 A collection system for lane collection vehicle model

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105160888A (en) * 2015-10-12 2015-12-16 合肥工业大学 No-parking vehicle weight information collection and matching system and method
CN108252550A (en) * 2018-02-13 2018-07-06 五冶集团上海有限公司 The rotatable sliding rail Forward parking apparatus of piezoelectricity

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105160888A (en) * 2015-10-12 2015-12-16 合肥工业大学 No-parking vehicle weight information collection and matching system and method
CN108252550A (en) * 2018-02-13 2018-07-06 五冶集团上海有限公司 The rotatable sliding rail Forward parking apparatus of piezoelectricity

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
杨松等: "基于改进HOG特征的建筑物识别方法", 《计算机工程与应用》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110796872A (en) * 2019-11-13 2020-02-14 佛山科学技术学院 A collection system for lane collection vehicle model
CN110796872B (en) * 2019-11-13 2020-11-06 佛山科学技术学院 A collection system for lane collection vehicle model

Similar Documents

Publication Publication Date Title
CN101388145B (en) Auto alarming method and device for traffic safety
CN201266435Y (en) Automatic warning device for road traffic safety
CN105640748B (en) One kind vibration guide clothes
CN201134765Y (en) Piezoelectric noise vibrating self-generation apparatus
CN108717540A (en) The method and device of pedestrian and vehicle are distinguished based on 2D laser radars
CN101853399A (en) Method for realizing blind road and pedestrian crossing real-time detection by utilizing computer vision technology
CN205068768U (en) Categorised statistical system of regional vehicle
CN113029327B (en) Tunnel fan embedded foundation damage identification method based on metric attention convolutional neural network
CN103236158B (en) Method for warning traffic accidents in real time on basis of videos
CN107358166A (en) A kind of staircase mouth passenger flow congestion detection means and its passenger flow congestion level method of discrimination
KR20200009559A (en) System for providing information of vehicle traffic queue and travel delay time according to road work zone, and method for the same
CN101425128A (en) People stream detecting method based on laser sensor depth image
CN204537469U (en) A kind of traffic indicating equipment
CN104159088A (en) System and method of remote monitoring of intelligent vehicle
CN104881661A (en) Vehicle detection method based on structure similarity
CN106710139A (en) Portable protective alarm device for construction area
CN109871853A (en) A kind of monitoring device that can finely identify vehicle
CN203838855U (en) Urban waterlogging and traffic safety guarantee early warning system
Wu et al. A novel skateboarder-related near-crash identification method with roadside LiDAR data
CN206594305U (en) A kind of wild animal monitoring device
CN105369749A (en) Flexible early warning multi-functional height limiting portal frame
CN203258602U (en) Street lamp pole provided with wireless inclination alarm device
CN107301781B (en) Road surface self-powered traffic monitoring device and method
CN114155710B (en) Underground road confluence road section guiding control system and control method
CN208013716U (en) A kind of passenger flow prior-warning device

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

Application publication date: 20190611

RJ01 Rejection of invention patent application after publication