CN110288831A - A kind of geomagnetism detecting device detection algorithm based on Neural Network Self-learning - Google Patents
A kind of geomagnetism detecting device detection algorithm based on Neural Network Self-learning Download PDFInfo
- Publication number
- CN110288831A CN110288831A CN201910611655.5A CN201910611655A CN110288831A CN 110288831 A CN110288831 A CN 110288831A CN 201910611655 A CN201910611655 A CN 201910611655A CN 110288831 A CN110288831 A CN 110288831A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- threshold
- threshold value
- detecting device
- geomagnetism detecting
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/042—Detecting movement of traffic to be counted or controlled using inductive or magnetic detectors
Abstract
The invention discloses a kind of geomagnetism detecting device detection algorithm based on Neural Network Self-learning, adaptive updates decision threshold is realized according to the characteristic of vehicle is passed through on earth magnetism, always guarantee the high-accuracy under longtime running, rule of thumb set the threshold value Vk of judgement, every time after a vehicle, record its changes of magnetic field value Ak+1, it subtracts initial threshold and obtains the changes of threshold amount △ Vk+1 of bicycle, then variable quantity is set to certain weight, to correct just fixed threshold value Vk, with the increase of vehicle sample number, threshold value is even more infinite approach theory decision content, reduce erroneous detection and missing inspection, the accuracy rate for the inspection vehicle that can be increased substantially, it is provided effectively for traffic signalization, stable vehicle flowrate data, save the cumbersome work of periodic manual adjustment inspection vehicle threshold value.
Description
Technical field
The present invention relates to field of intelligent transportation technology, specially a kind of geomagnetism detecting device inspection based on Neural Network Self-learning
Method of determining and calculating.
Background technique
Geomagnetism detecting device is the information collection means in intelligent transportation industry, installs simple, round-the-clock, Detection accuracy
The high, advantages such as long-time stability are good, are widely used in always the traffic flow acquisition of urban traffic intersection.Occupation rate of market is big, each
Crossing requires 10 or so geomagnetism detecting devices, and the ownership in each city can exceed that 2000 or more.However, different factories
Family, different crossing type of vehicle, geomagnetism detecting accuracy rate height is uneven, will if finely debugging to each geomagnetism detecting device
A large amount of debugging working hours can be routinely occupied, cost is very high, part of the manufacturer is caused to be unable to persistence maintenance geomagnetism detecting device, but not
Fine debugging, accuracy rate cannot be maintained at high-accuracy for a long time, can mislead the self-adapting operation of traffic signaling equipment, lead to crossing
Traffic congestion or traffic efficiency are low.
Therefore, under the complicated this overall background of as many as quantity, fine debugging, there is an urgent need to the ground that one kind is capable of self study
Magnetic detector detection algorithm is effectively intelligent transportation clothes to reduce the workload finely debugged, guarantee high Detection accuracy
Business promotes the benign development of earth magnetism industry.
Summary of the invention
The purpose of the present invention is to provide a kind of geomagnetism detecting device detection algorithm based on Neural Network Self-learning, to solve
The problems mentioned above in the background art.
To achieve the above object, the invention provides the following technical scheme: a kind of earth magnetism inspection based on Neural Network Self-learning
Device detection algorithm is surveyed, variable quantity is caused according to the vehicle passed through on earth magnetism, decision threshold is corrected always, after reaching longtime running
Geomagnetism detecting accuracy rate persistently increases, avoids the workload of periodically live accurate adjustment, includes the following steps, the coarse adjustment detection
The following steps are included:
A, the experience given threshold after starting, this threshold value is according to various vehicle classes such as the car at crossing and lorry, buses
The distribution condition of type and it is later accumulate experience, artificial setup parameter initial threshold;
B, there is vehicle to press through in geomagnetism detecting device, one is added to the counting of vehicle, for assessing the vehicle accounting for pressing through earth magnetism
And distribution situation;
C, vehicle is determined whether there is, is compared according to the magnetic field data of sampling and decision threshold, judges the data Ak+1 newly sampled
Whether previous threshold value Vk is greater than or equal to, if it is not, then return step B, into NextState, if so, it is determined with vehicle, it is defeated
There is vehicle signal out, and record and save △ Vk+1=Ak+1-Vk,
D, in decision threshold increment zone of reasonableness, rule of thumb experience, if threshold delta not in the reasonable scope, deletes this
Threshold value, no longer adjustment threshold value, then return to walk B, into NextState;If threshold delta is in the reasonable scope, threshold value, benefit are updated
Decision threshold Vk+1 is obtained with weight distribution formula Vk+1=Vk × (1- β)+△ Vk+1 × β, then executes step B, is entered
NextState.
Preferably, described with empirical threshold value is starting, rule of thumb sets the threshold value Vk of judgement, every to increase by one
Vehicle, a corresponding threshold value Vk+1, and record threshold value Vk+1 corresponding with the vehicle, according to the car at crossing and lorry,
The distribution condition of the various type of vehicle such as bus and it is later accumulate experience, artificial setup parameter initial threshold.
Compared with prior art, the beneficial effects of the present invention are:
Detection method of the invention automatically, is constantly adjusted and is repaired by acquiring the various vehicles pressed through on daily lane
Change detection threshold value, constantly guarantee the high-accuracy of geomagnetism detecting device, open the adjusting thresholds of self study, is not necessarily to manual debugging,
Strong operability, saving cost is more, is more conducive to the development of earth magnetism industry.
Detailed description of the invention
Fig. 1 is the algorithm flow chart that threshold value coarse adjustment proposed by the invention detects.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
It please refers to Fig. 1 present invention and a kind of technical solution is provided:
Cause variable quantity according to the vehicle passed through on earth magnetism, corrects decision threshold always, the earth magnetism after reaching longtime running
Detection accuracy persistently increases, avoids the workload of periodically live accurate adjustment, includes the following steps, the coarse adjustment detection includes
Following steps:
A, the experience given threshold after starting, this threshold value is according to various vehicle classes such as the car at crossing and lorry, buses
The distribution condition of type and it is later accumulate experience, artificial setup parameter initial threshold;
B, there is vehicle to press through in geomagnetism detecting device, one is added to the counting of vehicle, for assessing the vehicle accounting for pressing through earth magnetism
And distribution situation;
C, vehicle is determined whether there is, is compared according to the magnetic field data of sampling and decision threshold, judges the data Ak+1 newly sampled
Whether previous threshold value Vk is greater than or equal to, if it is not, then return step B, into NextState;If so, it is determined with vehicle, it is defeated
There is vehicle signal out, and records and save △ Vk+1=Ak+1-Vk;
D, in decision threshold increment zone of reasonableness, rule of thumb experience, if threshold delta not in the reasonable scope, deletes this
Threshold value, no longer adjustment threshold value, then return to walk B, into NextState;If threshold delta is in the reasonable scope, threshold value, benefit are updated
Decision threshold Vk+1 is obtained with weight distribution formula Vk+1=Vk × (1- β)+△ Vk+1 × β;Then step B is executed, is entered
NextState.
Experience given threshold after beginning, this threshold value is according to various type of vehicle such as the car at crossing and lorry, buses
Distribution condition and it is later accumulate experience, artificial setup parameter initial threshold, when thering is vehicle to press through in geomagnetism detecting device, to vehicle
Counting add one, for assessing the vehicle accounting and distribution situation that press through earth magnetism, according to the magnetic field data and decision threshold of sampling
Value comparison, judges whether the data Ak+1 newly sampled is greater than or equal to previous threshold value Vk, if it is not, then return step B, enters
NextState, if so, being determined with vehicle, output has vehicle signal, and records and save △ Vk+1=Ak+1-Vk, rule of thumb experience,
If threshold delta in the reasonable scope, does not delete this threshold value, threshold value is no longer adjusted, then returns to walk B, into NextState, if
Threshold delta in the reasonable scope, is updated threshold value, is obtained using weight distribution formula Vk+1=Vk × (1- β)+△ Vk+1 × β
Decision threshold Vk+1;Then step B is executed, into NextState.
Detection method of the invention is analyzed its bring geomagnetic field variation, is held by constantly collecting various public vehicles
It is continuous to update detection threshold value, a reasonable threshold value being more suitable on this lane is formed, Detection accuracy is improved, threshold value is opened and is not necessarily to people
Work debugging, strong operability, detection efficiency are high.
Certainly, the above description is not a limitation of the present invention, and the present invention is also not limited to the example above, this technology neck
The variations, modifications, additions or substitutions that the those of ordinary skill in domain is made within the essential scope of the present invention, also should belong to this hair
Bright protection scope.
The beneficial effects of the present invention are:
Detection method of the invention is analyzed its bring geomagnetic field variation, is held by constantly collecting various public vehicles
It is continuous to update detection threshold value, a reasonable threshold value being more suitable on this lane is formed, Detection accuracy is improved, threshold value is opened and is not necessarily to people
Work debugging, strong operability, detection efficiency are high.
It although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
A variety of variations, modification, replacement can be carried out to these embodiments without departing from the principles and spirit of the present invention by understanding
And modification, the scope of the present invention is defined by the appended.
Claims (2)
1. a kind of geomagnetism detecting device detection algorithm based on Neural Network Self-learning, it is characterised in that: according to what is passed through on earth magnetism
Vehicle causes variable quantity, corrects decision threshold always, and the geomagnetism detecting accuracy rate after reaching longtime running persistently increases, avoids week
Phase property live accurate adjustment workload, include the following steps, the coarse adjustment detection the following steps are included:
A, the experience given threshold after starting, this threshold value is according to various type of vehicle such as the car at crossing and lorry, buses
Distribution condition and it is later accumulate experience, artificial setup parameter initial threshold;
B, there is vehicle to press through in geomagnetism detecting device, one added to the counting of vehicle, for assess press through earth magnetism vehicle accounting and point
Cloth situation;
C, vehicle is determined whether there is, is compared according to the magnetic field data of sampling and decision threshold, whether judges the data Ak+1 newly sampled
More than or equal to previous threshold value Vk, if it is not, then return step B, into NextState;If so, being determined with vehicle, output has
Vehicle signal, and record and save △ Vk+1=Ak+1-Vk;
D, in decision threshold increment zone of reasonableness, rule of thumb experience, if threshold delta not in the reasonable scope, deletes this threshold
Value, no longer adjustment threshold value, then return to walk B, into NextState, if threshold delta is in the reasonable scope, updates threshold value, utilizes
Weight distribution formula Vk+1=Vk × (1- β)+△ Vk+1 × β obtains decision threshold Vk+1, step B is then executed, under
One state.
2. a kind of geomagnetism detecting device detection algorithm based on Neural Network Self-learning according to claim 1, feature exist
In: described with empirical threshold value is starting, rule of thumb sets the threshold value Vk of judgement, one vehicle of every increases, one threshold of correspondence
Value Vk+1, and threshold value Vk+1 corresponding with the vehicle is recorded, according to the various vehicles such as the car at crossing and lorry, bus
The distribution condition of type and it is later accumulate experience, artificial setup parameter initial threshold.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910611655.5A CN110288831B (en) | 2019-07-08 | 2019-07-08 | Neural network self-learning based geomagnetic detector detection algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910611655.5A CN110288831B (en) | 2019-07-08 | 2019-07-08 | Neural network self-learning based geomagnetic detector detection algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110288831A true CN110288831A (en) | 2019-09-27 |
CN110288831B CN110288831B (en) | 2020-12-25 |
Family
ID=68020969
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910611655.5A Active CN110288831B (en) | 2019-07-08 | 2019-07-08 | Neural network self-learning based geomagnetic detector detection algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110288831B (en) |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101807350A (en) * | 2010-03-24 | 2010-08-18 | 天津信电科技发展有限公司 | Method for improving accuracy of geomagnetic parking stall detector |
KR20110013580A (en) * | 2009-07-31 | 2011-02-10 | 강명수 | Ourdoor parking-lot occupancy detection unit with earth magnetic sensor |
CN102881171A (en) * | 2012-05-24 | 2013-01-16 | 中国科学院深圳先进技术研究院 | Vehicle detecting method, vehicle detecting system and vehicle path planning system |
WO2013187748A1 (en) * | 2012-06-12 | 2013-12-19 | Institute Of Electronics And Computer Science | System and method for video-based vehicle detection |
CN103632569A (en) * | 2013-11-13 | 2014-03-12 | 北京青创智通科技有限公司 | Double-axis geomagnetic stall detecting method and double-axis geomagnetic stall detecting device |
CN103824460A (en) * | 2014-03-13 | 2014-05-28 | 武汉恒达智慧城市交通研发有限公司 | Fully-buried type vehicle parking space detector and detection method |
CN104332057A (en) * | 2014-10-24 | 2015-02-04 | 青岛海信网络科技股份有限公司 | Adaptive environment vehicle detection method based on geomagnetism |
CN105096611A (en) * | 2015-08-17 | 2015-11-25 | 深圳市中科车港实业有限公司 | Road vehicle detection system and method |
US20160071414A1 (en) * | 2005-09-12 | 2016-03-10 | Skybitz, Inc. | System and Method for Adaptive Motion Sensing with Location Determination |
CN105788255A (en) * | 2016-03-30 | 2016-07-20 | 福建工程学院 | Automatic correction method for road jam state determination |
CN107945570A (en) * | 2017-12-18 | 2018-04-20 | 浙江工业大学 | A kind of geomagnetic parking stall inspection optimization method |
CN108986483A (en) * | 2018-08-10 | 2018-12-11 | 苏万军 | A kind of traffic control method of the intersection based on geomagnetism detecting |
-
2019
- 2019-07-08 CN CN201910611655.5A patent/CN110288831B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160071414A1 (en) * | 2005-09-12 | 2016-03-10 | Skybitz, Inc. | System and Method for Adaptive Motion Sensing with Location Determination |
KR20110013580A (en) * | 2009-07-31 | 2011-02-10 | 강명수 | Ourdoor parking-lot occupancy detection unit with earth magnetic sensor |
CN101807350A (en) * | 2010-03-24 | 2010-08-18 | 天津信电科技发展有限公司 | Method for improving accuracy of geomagnetic parking stall detector |
CN102881171A (en) * | 2012-05-24 | 2013-01-16 | 中国科学院深圳先进技术研究院 | Vehicle detecting method, vehicle detecting system and vehicle path planning system |
WO2013187748A1 (en) * | 2012-06-12 | 2013-12-19 | Institute Of Electronics And Computer Science | System and method for video-based vehicle detection |
CN103632569A (en) * | 2013-11-13 | 2014-03-12 | 北京青创智通科技有限公司 | Double-axis geomagnetic stall detecting method and double-axis geomagnetic stall detecting device |
CN103824460A (en) * | 2014-03-13 | 2014-05-28 | 武汉恒达智慧城市交通研发有限公司 | Fully-buried type vehicle parking space detector and detection method |
CN104332057A (en) * | 2014-10-24 | 2015-02-04 | 青岛海信网络科技股份有限公司 | Adaptive environment vehicle detection method based on geomagnetism |
CN105096611A (en) * | 2015-08-17 | 2015-11-25 | 深圳市中科车港实业有限公司 | Road vehicle detection system and method |
CN105788255A (en) * | 2016-03-30 | 2016-07-20 | 福建工程学院 | Automatic correction method for road jam state determination |
CN107945570A (en) * | 2017-12-18 | 2018-04-20 | 浙江工业大学 | A kind of geomagnetic parking stall inspection optimization method |
CN108986483A (en) * | 2018-08-10 | 2018-12-11 | 苏万军 | A kind of traffic control method of the intersection based on geomagnetism detecting |
Non-Patent Citations (1)
Title |
---|
游佳: "地磁车辆检测算法研究与停车场检测系统的设计与实现", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Also Published As
Publication number | Publication date |
---|---|
CN110288831B (en) | 2020-12-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104299415B (en) | Based on distributed traffic condition detecting system and the method thereof of Bluetooth technology | |
O’Loingsigh et al. | The Dust Storm Index (DSI): a method for monitoring broadscale wind erosion using meteorological records | |
CN107798876B (en) | Road traffic abnormal jam judging method based on event | |
CN103544837B (en) | Traffic information estimation method and system combining cross-regional position updating and communication | |
CN102087788B (en) | Method for estimating traffic state parameter based on confidence of speed of float car | |
CN107038168A (en) | A kind of user's commuting track management method, apparatus and system | |
CN107180270A (en) | Passenger flow forecasting and system | |
CN104978858A (en) | Highway real-time traffic monitoring method based on mobile phone signaling | |
Liu et al. | The calculation method of road travel time based on license plate recognition technology | |
CN106060776B (en) | A kind of Urban population distribution dynamic cognitive method based on data in mobile phone | |
CN110718047A (en) | Geological disaster early warning method and device | |
CN103065497B (en) | A kind of method and system of parking stall measure | |
CN105390022A (en) | Intelligent parking system | |
CN104064027A (en) | Method and system for obtaining traffic information | |
CN112309117A (en) | Traffic incident fusion system and method based on density clustering | |
CN110288831A (en) | A kind of geomagnetism detecting device detection algorithm based on Neural Network Self-learning | |
CN111369810A (en) | Vehicle travel characteristic acquisition method and device, electronic equipment and storage medium | |
CN112579915B (en) | Analysis method and device for trip chain | |
CN113706871A (en) | Multisource data fusion system in urban traffic big data processing | |
CN109615727B (en) | Riding endpoint extraction method and system based on shared bicycle static GPS data | |
CN108986466B (en) | Traffic OD information acquisition system based on WiFi probe and processing method | |
CN203055179U (en) | Parking stall detecting device and parking stall detecting system | |
Rashid et al. | Automated traffic measurement system based on FCD and image processing | |
CN114639241B (en) | Method and system for judging road section interruption state | |
CN107591003B (en) | Urban road network dissipating capacity extraction method based on vehicle identification data |
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 |