CN103345842A - Road vehicle classification system and method - Google Patents
Road vehicle classification system and method Download PDFInfo
- Publication number
- CN103345842A CN103345842A CN2013103167878A CN201310316787A CN103345842A CN 103345842 A CN103345842 A CN 103345842A CN 2013103167878 A CN2013103167878 A CN 2013103167878A CN 201310316787 A CN201310316787 A CN 201310316787A CN 103345842 A CN103345842 A CN 103345842A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- signal
- road
- magnetic field
- carry out
- 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
Images
Abstract
The invention discloses a road vehicle classification system, which relates to the technical field of electronic traffic. The road vehicle classification system comprises an information acquisition unit, a filtering detection unit, a waveform extraction unit and a classificatory decision unit. A road vehicle classification method comprises the following steps: when a vehicle passes across a sensor in the middle of a road, the sensor carries out real-time detection on the magnetic field information of the vehicle, analyzes and extracts the magnetic field information of the vehicle, calculates the speed, length, magnetic field mean and standard magnetic field value of the vehicle, compares the data with a decision tree, and sends comparison results to a KNN (K Nearest Neighbor) neighboring method to carry out disaggregated classification, so that a classification result of the vehicle can be obtained in real time; a monitoring center counts the traffic state of the road according to the obtained classification result, and tracks vehicles outside a preset range so as to carry out road prediction and early-warning.
Description
Technical field
The present invention relates to the electronic communication technical field, particularly a kind of system and method for vehicle somatotype.
Background technology
Along with improving constantly of China's rapid economy development and living standards of the people, automobile enters people's family in a large number, has made things convenient for people's traffic trip.
Yet because the Urban Traffic Planning deficiency, the urban land area is limited, soil deficiency per capita, and city planning relatively lags behind, and traffic is limited in one's ability.Under the situation of limited traffic resource, utilize traffic resource substantially, this is the emphasis of present traffic problems.And in time grasp the situation of road vehicle, know the type of vehicle, to traffic control division management traffic resource, prediction traffic behavior, find to have special significance by special car.There is excavated pavement in existing various technology, and calculation of complex is practical inadequately, situations such as cost height.
Summary of the invention
One object of the present invention just provides a kind of road vehicle classification system, and it can in time grasp the situation of road vehicle to the vehicle somatotype on the road, knows type of vehicle, helps the resource that regulates the traffic, the prediction traffic behavior.
This purpose of the present invention is to realize by such technical scheme, and it includes information acquisition unit, filtering detecting unit, waveform extracting unit and judgement taxon;
Information acquisition unit includes and is arranged on the middle geomagnetic sensor of road, is used for collection vehicle through the vehicle field signal of former and later two check points;
Filtering detecting unit, the signal that information acquisition unit is collected carry out filtering to be handled, and adopts vehicle checking method to carry out vehicle detection, generates digital signal sequences rawData (n), represents to have or does not have a vehicle Magnetic Field with digital signal sequences;
The waveform extracting unit extracts the signal s (n) that includes the vehicle Magnetic Field that the filtering detecting unit generates, and carries out signal compression and normalized, obtains normalized signal S
K (i)
The judgement taxon, the vehicle field signal s (n) according to the waveform extracting unit extracts calculates vehicle length L (n), car speed V (n) and magnetic field average S
k(i)
G, and by contrasting with decision tree, carry out the big class of vehicle and divide; The big class of vehicle is divided the result in conjunction with normalized signal S
K (i), carry out careful classification by the KNN algorithm.
Further, described system also includes communication gate, telegon and monitoring host computer, communication gate will be adjudicated the type of vehicle result that taxon obtains and will be forwarded to telegon, telegon is sent to monitoring host computer again, monitoring host computer is added up road traffic state according to the type of vehicle result, and the vehicle outside the tracking preset range, carry out the road early warning.
Further, described geomagnetic sensor is three anisotropic magnetoresistive sensor.
Further, described magnetic field mean value function is:
S
k(i)
g=(S
k(i)
x-S
kBaseLineX)
2+(S
k(i)
y-S
kBaseLineY)
2+(S
k(i)
z-S
kBaseLineZ)
2
S
k(i)
gBe the even value in magnetic field;
S
k(i)
X/y/zField signal for the x/y/z axle;
S
KBaseLineX/Y/ZAverage for the field signal of x/y/z axle;
K is for gathering the number of times of signal;
I is that every group of signal is divided into M
SampleIndividual group, i represent group's number.
Further, described magnetic field mean value function is:
S
k(i)
GBe magnetic field standard average;
S
k(i)
X/y/zField signal for the x/y/z axle;
K is for gathering the number of times of signal;
I is that every group of signal is divided into M
SampleIndividual group, i represent group's number.
Another object of the present invention just provides a kind of road vehicle classifying method, and it can be to the vehicle somatotype on road that travels.
This purpose of the present invention is to realize that by such technical scheme concrete steps are as follows:
1) collection vehicle is through the electromagnetic field signal of first and second check points;
2) signal that step 1) is collected carries out filtering and handles, and adopts vehicle checking method to carry out vehicle detection, generates digital signal sequences rawData (n), represents to have or does not have a vehicle Magnetic Field with digital signal sequences;
3) extraction step 2) in include the signal rawData (n) of vehicle Magnetic Field, and carry out signal compression and normalized, obtain normalized signal S
K (i)
4) the vehicle field signal s (n) that extracts according to step 3) calculates vehicle length L (n), car speed V (n) and magnetic field average S
k(i)
G, and by contrasting with decision tree, carry out the big class of vehicle and divide; The big class of vehicle is divided the result in conjunction with normalized signal S
K (i), carry out careful classification by the KNN algorithm.
Further, the length calculation of vehicle described in step 4) formula is:
L
vehicle=V
pass×(T
detectedNode1′-T
detectedNode1)。
L
VehicleBe vehicle commander's degree;
V
PassBe car speed;
T
DetectedNode1 'For detection node 1 detects the time that vehicle leaves;
T
DetectedNode1For detection node 1 detects the time that vehicle sails into.
The computing formula of car speed is: V
Pass=L
Fixed/ (T
DetectedNode2-T
DetectedNode1).
V
PassBe car speed;
L
FixedBe the distance of detection node 1 with detection node 2;
T
DetectedNode2For detection node 2 detects the time that vehicle leaves;
T
DetectedNode1For detection node 1 detects the time that vehicle sails into.
Further, the concrete grammar by the decision tree contrast is described in the step 4): at first ask for vehicle magnetic induction density value and tentatively judge, ask for vehicle length and car speed again and further adjudicate.
Further, the algorithm of KNN described in the step 4) is: training sample as the reference point, is calculated the distance of test sample book and training sample, adopt Euclidean distance, obtain value nearest in the distance as The classification basis.
Owing to adopted technique scheme, the present invention to have following advantage:
When the present invention passes through the sensor of road centre at vehicle, sensor detects the Magnetic Field of vehicle in real time, and analyze and extract the vehicle Magnetic Field, calculate vehicle speed, vehicle commander's degree and magnetic field average and standard Magnetic Field value, these data and decision tree are compared, the result of comparison is sent into row disaggregated classification in the KNN neighbor method, can obtain vehicle somatotype result in real time, Surveillance center is according to the classification results statistics road traffic state that obtains, and the vehicle outside the tracking preset range, carry out road prediction and early warning.
Other advantages of the present invention, target and feature will be set forth to a certain extent in the following description, and to a certain extent, based on being apparent to those skilled in the art to investigating hereinafter, perhaps can obtain instruction from the practice of the present invention.Target of the present invention and other advantages can realize and obtain by following instructions and claims.
Description of drawings
Description of drawings of the present invention is as follows.
Fig. 1 is structural representation of the present invention;
Fig. 2 is road vehicle classifying method process flow diagram;
Fig. 3 is judgement sorting technique process flow diagram.
Embodiment
The invention will be further described below in conjunction with drawings and Examples.
Fig. 1 is the structural drawing of road vehicle classification system, and this road vehicle classification system comprises: Surveillance center and vehicles classification module.
Monitoring host computer obtains the real-time results of vehicle somatotype by telegon, and analyzes, predicts action according to this result.Obtain information of vehicles according to the vehicle through system, obtain the information of vehicles post analysis and handle information of vehicles and extract information of vehicles, judge type of vehicle according to information of vehicles, classification results is sent into monitoring host computer by Communication Gateway.
Vehicles classification module comprises information acquisition unit, filtering detecting unit, waveform extracting unit, judgement taxon and communication gate;
Information acquisition unit be used for to be collected the information of vehicles in the presumptive area, the filtering detecting unit, and the filtering that is used for signals of vehicles is handled, and adopts vehicle checking method to detect vehicle, and the information that produces is the sequence of 1-0, and expression has car-there be not car information.The waveform extracting unit is that 1 the car signal that has extracts with sequence, and with signal compress, normalized.The judgement taxon is carried out careful classification for the input information of vehicles is adjudicated with decision tree earlier again by the KNN algorithm.Output unit is sent to Surveillance center by Communication Gateway with classified information.
Fig. 2 is the process flow diagram of road vehicle classifying method.
Analyze according to the vehicle field signal, the signal difference of every kind of vehicle, and the signals of vehicles waveform of same-type is more consistent, and this provides foundation for the classification based on geomagnetic sensor.As shown in Figure 2, when second detection node detects vehicle, the speed of a motor vehicle is calculated, the vehicle speed value after the calculating is used for calculating the vehicle length value.Then vehicle is come out by the waveform extracting of Magnetic Sensor, carry out conversion process earlier, conversion process is exactly the process of the value of the number of samples of the speed generation of vehicle being carried out standard.
The result who has classified handles in two steps, and the value of a part is asked for the magnetic field average, and this value can be extracted the intensity in vehicle magnetic field to greatest extent.Send in the decision tree according to above several values and tentatively to judge, belong to which or several type.Another part is done normalized exactly, and the result of normalized sends into and continues classification in the KNN algorithm behind the decision tree classification.Owing to carry out the division of preliminary big class by decision tree, the sample that KNN judges is extremely simplified, and makes the speed of somatotype and precision be greatly improved like this.
Fig. 3 is the process flow diagram of judgement sorting technique.
The judgement sorting technique uses decision tree to carry out the division of big class earlier, again the value after the original signal normalization is sent into the KNN algorithm and carries out careful classification.The contiguous algorithm of K need be learnt sample earlier, classify, and the data of type of vehicle can be classified in advance according to normalized value, classify by KNN again.
Among this embodiment, S1, S2, the value of three magnetic induction density of S3 is sent the magnetic field average into decision tree and 3 values compare.3 values have determined the vehicle of several types.L1, L2, L3 are the length value of 3 types of vehicles, the V1 value is vehicle speed value, in order to reduce the influence that high speed car brings the vehicle somatotype, distinguishes according to certain speed per hour.Be lower than this speed, directly judge, be higher than this value, need to use the normalized value that calculates to send into the contiguous algorithm of KNN and judge.4 parameters have been determined 4 classification samples at last, and each classification contains 2 samples.Because reduced the number of samples of KNN, speed is faster, the result will be more accurate.
If x
j(i) proper vector of training, S have been learnt in the sample storehouse
k(i) for waiting to judge the proper vector after the vehicle normalization, X is sample space, x
j(i) ∈ X, N are number of samples, and k is neighbour's number, k<N.According to above analysis, sample space is 2.Adopt classical Euclidean distance to calculate the distance of sample space:
If D<key, value〉a store M distance value value, and apart from corresponding sample classification position key.After calculating the distance in new samples space, if less than the value of Max (D<key, value 〉), then substitute this value, otherwise, continue to calculate the distance in new samples space, finish up to sample space.Can calculate the number of classification under the key during end, number is big is sorting result.
When the present invention passes through the vehicle sensors of road centre at vehicle, detect vehicle in real time, and analyze and extract signals of vehicles, calculate vehicle speed, vehicle commander's degree, magnetic field average and standard Magnetic Field value, these values and decision tree are compared, the result of comparison is sent in the KNN neighbor method and classifies, can obtain classification results in real time.Surveillance center adds up road traffic state according to the classification results that obtains, and follows the tracks of the vehicle that should not occur, and predicts behaviors such as early warning.
Explanation is at last, above embodiment is only unrestricted in order to technical scheme of the present invention to be described, although with reference to preferred embodiment the present invention is had been described in detail, those of ordinary skill in the art is to be understood that, can make amendment or be equal to replacement technical scheme of the present invention, and not breaking away from aim and the scope of the technical program, it all should be encompassed in the middle of the claim scope of the present invention.
Claims (9)
1. road vehicle classification system is characterized in that: described system includes information acquisition unit, filtering detecting unit, waveform extracting unit and judgement taxon;
Information acquisition unit includes and is arranged on the middle geomagnetic sensor of road, is used for collection vehicle through the vehicle field signal of former and later two check points;
Filtering detecting unit, the signal that information acquisition unit is collected carry out filtering to be handled, and adopts vehicle checking method to carry out vehicle detection, generates digital signal sequences rawData (n), represents to have or does not have a vehicle Magnetic Field with digital signal sequences;
The waveform extracting unit extracts the signal s (n) that includes the vehicle Magnetic Field that the filtering detecting unit generates, and carries out signal compression and normalized, obtains normalized signal S
K (i)
The judgement taxon, the vehicle field signal s (n) according to the waveform extracting unit extracts calculates vehicle length L (n), car speed V (n) and magnetic field average S
k(i)
G, and by contrasting with decision tree, carry out the big class of vehicle and divide; The big class of vehicle is divided the result in conjunction with normalized signal S
K (i), carry out careful classification by the KNN algorithm.
2. a kind of road vehicle classification system as claimed in claim 1, it is characterized in that: described system also includes communication gate, telegon and monitoring host computer, communication gate will be adjudicated the type of vehicle result that taxon obtains and will be forwarded to telegon, telegon is sent to monitoring host computer again, monitoring host computer is added up road traffic state according to the type of vehicle result, and the vehicle outside the tracking preset range, carry out the road early warning.
3. a kind of road vehicle classification system as claimed in claim 1, it is characterized in that: described geomagnetic sensor is three anisotropic magnetoresistive sensor.
4. a kind of road vehicle classification system as claimed in claim 1 is characterized in that, described magnetic field mean value function is:
S
k(i)
g=(S
k(i)
x-S
kBaseLineX)
2+(S
k(i)
y-S
kBaseLineY)
2+(S
k(i)
z-S
kBaseLineZ)
2
S
k(i)
gBe the even value in magnetic field;
S
k(i)
X/y/zField signal for the x/y/z axle;
S
KBaseLineX/Y/ZAverage for the field signal of x/y/z axle;
K is for gathering the number of times of signal;
I is that every group of signal is divided into M
SampleIndividual group, i represent group's number.
5. a kind of road vehicle classification system as claimed in claim 1 is characterized in that, described magnetic field mean value function is:
S
k(i)
GBe magnetic field standard average;
S
k(i)
X/y/zField signal for the x/y/z axle;
K is for gathering the number of times of signal;
I is that every group of signal is divided into M
SampleIndividual group, i represent group's number.
6. utilize the right strategic point to ask 1 to 5 any described road vehicle classification system to carry out the method for vehicle somatotype, it is characterized in that concrete steps are as follows:
1) collection vehicle is through the electromagnetic field signal of first and second check points;
2) signal that step 1) is collected carries out filtering and handles, and adopts vehicle checking method to carry out vehicle detection, generates digital signal sequences rawData (n), represents to have or does not have a vehicle Magnetic Field with digital signal sequences;
3) extraction step 2) in include the signal rawData (n) of vehicle Magnetic Field, and carry out signal compression and normalized, obtain normalized signal S
K (i)
4) the vehicle field signal s (n) that extracts according to step 3) calculates vehicle length L (n), car speed V (n) and magnetic field average S
k(i)
G, and by contrasting with decision tree, carry out the big class of vehicle and divide; The big class of vehicle is divided the result in conjunction with normalized signal S
K (i), carry out careful classification by the KNN algorithm.
7. a kind of road vehicle classifying method as claimed in claim 6 is characterized in that:
The length calculation of vehicle described in step 4) formula is: L
Vehicle=V
Pass* (T
DetectedNode1 '-T
DetectedNode1).
L
VehicleBe vehicle commander's degree;
V
PassBe car speed;
T
DetectedNode1 'For detection node 1 detects the time that vehicle leaves;
T
DetectedNode1For detection node 1 detects the time that vehicle sails into.
The computing formula of car speed is: V
Pass=L
Fixed/ (T
DetectedNode2-T
DetectedNode1).
V
PassBe car speed;
L
FixedBe the distance of detection node 1 with detection node 2;
T
DetectedNode2For detection node 2 detects the time that vehicle leaves;
T
DetectedNode1For detection node 1 detects the time that vehicle sails into.
8. a kind of road vehicle classifying method as claimed in claim 6, it is characterized in that, concrete grammar by the decision tree contrast described in the step 4) is: at first ask for vehicle magnetic induction density value and tentatively judge, ask for vehicle length and car speed again and further adjudicate.
9. a kind of road vehicle classifying method as claimed in claim 6, it is characterized in that the algorithm of KNN described in the step 4) is: training sample as the reference point, is calculated the distance of test sample book and training sample, adopt Euclidean distance, obtain value nearest in the distance as The classification basis.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310316787.8A CN103345842B (en) | 2013-07-25 | 2013-07-25 | A kind of road vehicle classification system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310316787.8A CN103345842B (en) | 2013-07-25 | 2013-07-25 | A kind of road vehicle classification system and method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103345842A true CN103345842A (en) | 2013-10-09 |
CN103345842B CN103345842B (en) | 2016-01-20 |
Family
ID=49280633
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310316787.8A Expired - Fee Related CN103345842B (en) | 2013-07-25 | 2013-07-25 | A kind of road vehicle classification system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103345842B (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103794058A (en) * | 2014-03-05 | 2014-05-14 | 武汉慧联无限科技有限公司 | Method and device for detecting vehicle based on state machine |
CN105046946A (en) * | 2014-12-23 | 2015-11-11 | 北京交通大学 | Method for detecting traffic flow parameters based on compound sensor |
CN105321343A (en) * | 2014-07-06 | 2016-02-10 | 临安巨丰城市配套设备有限公司 | A system and method for detecting traffic conditions of large vehicles on a road based on manhole covers |
CN105321354A (en) * | 2015-09-22 | 2016-02-10 | 中国科学院上海微系统与信息技术研究所 | Simple vehicle detection, classification and identification method based on geomagnetic sensor |
CN105957355A (en) * | 2016-06-08 | 2016-09-21 | 东莞理工学院 | Vehicle speed measuring method |
CN106205146A (en) * | 2016-07-27 | 2016-12-07 | 北方工业大学 | Vehicle information acquisition and processing system and method based on dual-vector magnetic sensor |
CN107886727A (en) * | 2017-11-13 | 2018-04-06 | 深圳先进技术研究院 | A kind of separation vehicle method, system and electronic equipment based on geomagnetic sensor |
CN108399794A (en) * | 2018-02-27 | 2018-08-14 | 吉林大学 | Tunnel driving safety pre-warning system and method based on vehicle running state detection |
CN109949181A (en) * | 2019-03-22 | 2019-06-28 | 华立科技股份有限公司 | The power grid type judgement method and device of algorithm are closed on based on KNN |
CN112611313A (en) * | 2020-12-11 | 2021-04-06 | 交控科技股份有限公司 | Rail vehicle length measuring device, rail vehicle length measuring method and traffic facility |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106971539A (en) * | 2017-04-27 | 2017-07-21 | 上海博历机械科技有限公司 | A kind of information of vehicles obtains comprehensive vehicle detecting system |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1193662B1 (en) * | 2000-09-29 | 2004-09-29 | Reinhard Zachmann | Method and apparatus for detecting traffic data by means of detection and classification of moving or non-moving vehicles |
CN101923782A (en) * | 2010-07-28 | 2010-12-22 | 北京交通大学 | Method for acquiring transportation traffic speed based on geomagnetic sensing technology |
CN101923781A (en) * | 2010-07-28 | 2010-12-22 | 北京交通大学 | Vehicle type recognizing method based on geomagnetic sensing technology |
-
2013
- 2013-07-25 CN CN201310316787.8A patent/CN103345842B/en not_active Expired - Fee Related
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1193662B1 (en) * | 2000-09-29 | 2004-09-29 | Reinhard Zachmann | Method and apparatus for detecting traffic data by means of detection and classification of moving or non-moving vehicles |
CN101923782A (en) * | 2010-07-28 | 2010-12-22 | 北京交通大学 | Method for acquiring transportation traffic speed based on geomagnetic sensing technology |
CN101923781A (en) * | 2010-07-28 | 2010-12-22 | 北京交通大学 | Vehicle type recognizing method based on geomagnetic sensing technology |
Non-Patent Citations (2)
Title |
---|
任保利: "地磁车辆检测与车型分类算法研究", 《中国优秀硕士学位论文全文数据库》 * |
马吉甫: "基于小波变换及支持向量机的车型识别研究", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103794058B (en) * | 2014-03-05 | 2016-04-13 | 武汉慧联无限科技有限公司 | Based on vehicle checking method and the device of state machine |
CN103794058A (en) * | 2014-03-05 | 2014-05-14 | 武汉慧联无限科技有限公司 | Method and device for detecting vehicle based on state machine |
CN105321343B (en) * | 2014-07-06 | 2017-08-25 | 临安巨丰城市配套设备有限公司 | A kind of system and method that cart traffic status in road is detected based on inspection well cover |
CN105321343A (en) * | 2014-07-06 | 2016-02-10 | 临安巨丰城市配套设备有限公司 | A system and method for detecting traffic conditions of large vehicles on a road based on manhole covers |
CN105046946B (en) * | 2014-12-23 | 2017-07-14 | 北京交通大学 | Traffic flow parameters detection method based on compound sensor |
CN105046946A (en) * | 2014-12-23 | 2015-11-11 | 北京交通大学 | Method for detecting traffic flow parameters based on compound sensor |
CN105321354A (en) * | 2015-09-22 | 2016-02-10 | 中国科学院上海微系统与信息技术研究所 | Simple vehicle detection, classification and identification method based on geomagnetic sensor |
CN105957355B (en) * | 2016-06-08 | 2018-06-22 | 东莞理工学院 | A kind of vehicle speed measuring method |
CN105957355A (en) * | 2016-06-08 | 2016-09-21 | 东莞理工学院 | Vehicle speed measuring method |
CN106205146B (en) * | 2016-07-27 | 2019-04-02 | 北方工业大学 | Vehicle information acquisition and processing system and method based on dual-vector magnetic sensor |
CN106205146A (en) * | 2016-07-27 | 2016-12-07 | 北方工业大学 | Vehicle information acquisition and processing system and method based on dual-vector magnetic sensor |
CN107886727A (en) * | 2017-11-13 | 2018-04-06 | 深圳先进技术研究院 | A kind of separation vehicle method, system and electronic equipment based on geomagnetic sensor |
CN107886727B (en) * | 2017-11-13 | 2020-04-14 | 深圳先进技术研究院 | Geomagnetic sensor-based automobile classification method and system and electronic equipment |
CN108399794A (en) * | 2018-02-27 | 2018-08-14 | 吉林大学 | Tunnel driving safety pre-warning system and method based on vehicle running state detection |
CN108399794B (en) * | 2018-02-27 | 2021-03-30 | 吉林大学 | Tunnel driving safety early warning system and method based on vehicle driving state detection |
CN109949181A (en) * | 2019-03-22 | 2019-06-28 | 华立科技股份有限公司 | The power grid type judgement method and device of algorithm are closed on based on KNN |
CN109949181B (en) * | 2019-03-22 | 2021-05-25 | 华立科技股份有限公司 | Power grid type judgment method and device based on KNN proximity algorithm |
CN112611313A (en) * | 2020-12-11 | 2021-04-06 | 交控科技股份有限公司 | Rail vehicle length measuring device, rail vehicle length measuring method and traffic facility |
Also Published As
Publication number | Publication date |
---|---|
CN103345842B (en) | 2016-01-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103345842B (en) | A kind of road vehicle classification system and method | |
TWI430212B (en) | Abnormal behavior detection system and method using automatic classification of multiple features | |
CN105744232B (en) | A kind of method of the transmission line of electricity video external force damage prevention of Behavior-based control analytical technology | |
CN106980113B (en) | Object detection device and object detection method | |
CN103456175B (en) | Accompanying vehicle real-time detection method based on vehicle registration plate recognition and meshing monitoring | |
CN103839409B (en) | Based on the traffic flow modes method of discrimination of multibreak facial vision sensing cluster analysis | |
CN103985182B (en) | A kind of bus passenger flow automatic counting method and automatic counter system | |
CN116644373B (en) | Automobile flow data analysis management system based on artificial intelligence | |
CN101394316B (en) | Network intrusion classification method based on Bayes of total indirected graph | |
CN108229256A (en) | A kind of road construction detection method and device | |
CN112512020B (en) | Traffic state weak signal perception studying and judging method based on multi-source data fusion | |
CN100466010C (en) | Different species traffic information real time integrating method | |
CN103246896A (en) | Robust real-time vehicle detection and tracking method | |
CN103473932A (en) | Sound signal vehicle type identification system combined with oscillation mark line | |
CN109670449B (en) | Vehicle illegal judgment method based on vertical snapshot mode | |
CN103679214A (en) | Vehicle detection method based on online area estimation and multi-feature decision fusion | |
Thiruppathiraj et al. | Automatic pothole classification and segmentation using android smartphone sensors and camera images with machine learning techniques | |
CN109720353B (en) | Driving behavior detection method based on smart phone | |
CN104794896B (en) | Overpass congestion spacial hot spots extraction method based on lift height-limiting frame | |
Tobe et al. | vcity map: Crowdsensing towards visible cities | |
Yang et al. | Recognition of taxi violations based on semantic segmentation of PSPNet and improved YOLOv3 | |
CN104616495A (en) | Bus GPS (Global Positioning System) probe vehicle based urban traffic state recognition method | |
Cruz et al. | Classified counting and tracking of local vehicles in manila using computer vision | |
CN114329074B (en) | Traffic energy efficiency detection method and system for ramp road section | |
CN104008378B (en) | Passenger number counting method based on behavior characteristics |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20210611 Address after: 400050 c-16-5, No. 200, Keyuan 1st Road, Jiulongpo District, Chongqing Patentee after: Chongqing Zhongtian yunchuang Human Resource Management Consulting Co.,Ltd. Address before: 400065 Chongqing Nan'an District huangjuezhen pass Chongwen Road No. 2 Patentee before: CHONGQING University OF POSTS AND TELECOMMUNICATIONS |
|
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160120 Termination date: 20210725 |