CN104766086A - Supervising method and system of way mark - Google Patents
Supervising method and system of way mark Download PDFInfo
- Publication number
- CN104766086A CN104766086A CN201510176310.3A CN201510176310A CN104766086A CN 104766086 A CN104766086 A CN 104766086A CN 201510176310 A CN201510176310 A CN 201510176310A CN 104766086 A CN104766086 A CN 104766086A
- Authority
- CN
- China
- Prior art keywords
- real
- time
- way mark
- image
- information
- 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
Abstract
The invention discloses a supervising method and system of a way mark. The method includes the steps of establishing a preprocessing standard model through a mark single-sequence mode according to a known way standard GPS and image data, obtaining the latest real-time GPS and image data through inspection operation, establishing a real-time model through a mark double-sequence mode, comparing real-time model data with standard model data through double-sequence matching search, matching the real-time optimal image obtained in the real-time model with the standard image in the standard model, comparing standard model image data through an image matching algorithm, determining the specific type of identification damage, renewing the standard model according to the recognition result and the maintenance state. According to the way identification position and the relationship between the images, the damage and type of the way mark are collected periodically in real time and recognized and positioned automatically, the way asset detection efficiency is improved, and the maintenance workloads are reduced.
Description
Technical field
The present invention relates to computer information technology field, particularly a kind of method and system adopting information system to supervise way mark.
Background technology
One of building based on road is the important component part of public assets; after road construction completes; need the normal use it being carried out to real-time monitoring and maintenance guarantee road, simultaneously real-time monitoring and maintenance is also one of most basic means of highway safety assets.Mainly contain pavement management system and bridge management system etc. for road supervision with the system of maintenance at present, and these systems are only for detecting and maintenance geology and highway pavement, cannot realize the supervision of way mark.
Above the both sides that way mark is arranged on highway usually or highway, staff is needed to carry out on-the-spot data acquisition and typing on the way when guarding it, the not only human and material resources of at substantial, time and resource, the situations such as easy appearance is undetected, error of omission, and to expend time in length due to sense cycle, the way mark that there will be damage can not get Timeliness coverage and replacing, have impact on the specification of road, attractive in appearance and safety index, produces passive impact to the trip instruction of people; In addition, due to the otherness artificially judged, the problems such as standard disunity are easily caused to occur.On highway, the intact importance to driver safety enforcement of way mark is self-evident especially, and as occurred on a highway, the severe traffic accidents such as driving appear in the vehicle that the disappearance of way mark is easy to cause running at high speed; The feature such as add the long distance property of highway and vehicle running velocity is too fast, also can have an impact to the operating efficiency of staff, the more important thing is the inherently safe going back entail dangers to staff.
Summary of the invention
The technical issues that need to address of the present invention are to provide a kind ofly can carry out Real-Time Monitoring to way mark without the need to staff to scene and failure identification be carried out to monitoring and managing method and the supervisory systems of accurately location.
For solving the problems of the technologies described above, the technical solution used in the present invention is as follows.
A monitoring and managing method for way mark, is characterized in that specifically comprising the following steps:
S101. the preparation standards model of way mark is set up;
S102. obtain the real-time information of way mark, and set up real-time model;
S103. the real-time optimized image of way mark in the real-time information collected by expert algorithm obtaining step S102;
S104. the real-time optimized image obtained in step S103 is mated by sequence search with the standard picture of preparation standards model in step S101, draw by expert algorithm the concrete classification that actual way mark damages, and store;
S105. judge whether to need repairing according to recognition result, and determine whether to need to upgrade the standard picture in preparation standards model according to the maintenance result of feedback;
S106. building database, manages the data in step S101 ~ S104;
S107. design host computer interface, in mode intuitively, data are shown, realize the actual demand that people supervise way mark.
Step S101 of the present invention specifically comprises following content:
S1011. determine camera model, and calculate according to parameters such as the height and positions of way mark, the correct position on inspection car installs camera;
S1012. the standard picture of way mark is gathered;
S1013. the standard GPS locating information of way mark is gathered;
S1014. according to the result that step S1012 and S1013 gathers, preparation standards model is set up by mark simple sequence mode.
Step S102 of the present invention specifically comprises following content:
S1021. the video mode of camera is adopted to obtain the real-time image information of way mark;
S1022. real time GPS location is carried out to way mark, obtain the real time GPS information of way mark;
S1023. real time GPS information is mated with corresponding realtime graphic, and set up real-time model by the two sequential manner of mark.
Step S1023 of the present invention specifically comprises following content:
First, the real time GPS information of way mark is gathered one by one, and carries out sequence mark;
Secondly, calculate the sample frequency of way mark real-time image information, and two sequence mark is carried out to sampled images;
Then, judge whether the real-time image information of way mark and the first sequence of real time GPS information mate, as coupling, then set up real-time model.
Step S103 of the present invention specifically comprises following content:
S1031. image carries out rough handling;
S1032. the real-time optimized image containing way mark is selected.
Adopt expert algorithm to carry out rough handling to image in step S1031 of the present invention, contents processing comprises the treatment step that the preliminary denoising, filtering, reduction, Slant Rectify, the motion blur that carry out the image collected in S102 are eliminated.
Step S1032 of the present invention specifically comprises following content:
First, the n two field picture that realtime graphic obtains after rough handling is detected (n=1...5);
Secondly, according to the singularity of way mark color, RGB is converted to hsv color space;
Then, whether judged in present image containing special color by hsv color space;
Again, by color region, image is split further;
Finally, compare the cut zone size between different images, choose the real-time optimized image of the maximum conduct of cut zone.
Step S104 of the present invention specifically comprises following content:
S1041, calculated threshold, makes real time GPS information mate with standard GPS longitude and latitude information;
S1042, is kept at the real time GPS information in threshold range, and preserves the GPS simple sequence of preparation standards model and pair sequence of the GPS in real-time model that match;
S1043, according to threshold requirement, mates real-time optimized image corresponding in standard picture corresponding with preparation standards model again for the real time GPS information of coupling and real-time model;
S1044, draws by expert algorithm the concrete classification that real-time best way mark damages, and stores.
A supervisory systems for way mark, this system comprises:
Image capture module 101, for carrying out image acquisition to way mark;
GPS information acquisition module 102, for gathering the GPS locating information of way mark;
Preparation standards model and real-time model set up module 103, for carrying out synchronizing sequence mark respectively, Criterion image information and standard GPS longitude and latitude information sequence way mark preparation standards model one to one by image capture module 101, GPS information acquisition module 102 to the standard picture information of fixed point way mark and standard GPS longitude and latitude information;
Gathered by the real time GPS information of image capture module 101, GPS information acquisition module 102 pairs of way marks and realtime graphic, extract the real time GPS information of way mark and image information corresponding to real time GPS information, set up the real-time model of way mark by image sampling and two sequence mark;
Two model fitting module 104, set up in module 103 to delete to select by sequences match and threshold value to preparation standards model and real-time model and extract key images, the key images chosen is calculated by parameter and expert algorithm control, the key images containing way mark corresponding to fixed point GPS processes, and therefrom draws real-time optimized image by process;
Image procossing and identification module 105, pattern match is carried out for the real-time optimized image containing way mark drawn after being added up by expert algorithm in two model fitting module 104 and preparation standards model and real-time model are set up the standard picture information of adding up in module 103, by the training of expert algorithm coupling, draw the types of damage of the way mark after actual match, and carry out classification storage;
Database module 106, for carrying out supervising in order, effectively to the data message in system, building database mechanism;
Upper computer control module 107, links with database in database module, the data after Graphics Processing directly perceived.
The supervisory systems of above-mentioned a kind of way mark, the specific category after the information spinner of described upper computer control module display will comprise the GPS latitude and longitude information of fixed point way mark, the image of fixed point way mark, image recognition, the distress condition information of way mark and keep in repair the identification information whether completed.
Owing to have employed above technical scheme, the invention technological progress is as follows.
The present invention integrates the acquisition of way mark assets information, detection, identification, positioning function, whether can damage way mark, damage type and damage place and automatically detect, shorten the sense cycle of Asset, improve detection efficiency, decrease potential safety hazard, effectively ensure that the driving safety of highway.
The Assets collection being applied as highway of the present invention provides and gathers path easily, liquidation for highway provides simple passage, for staff safeguards that the driving safety of highway brings great convenience, certain positive role is had to minimizing road running security incident, compare traditional liquidation system more efficient, save manpower, financial resources, material resources.GPS positioning system of the present invention can position the position of way mark trouble spot and add up, and realizes intelligent positioning, accurately can obtain the particular location of damage way mark, and all practical, applied widely for any section of GPS covering.Image processing process adopts advanced expert algorithm, ensure that the accuracy of result; Meanwhile, all carried out feature extraction and calculating to the various fault that may occur, can identify the multiple way mark fault caused due to Different factor, covering scope is wide, and recognition performance is high.The present invention, by GPS and the integrated information of image and the Various types of data after identifying, forms database, can share, recovers data, unified and complete control.Present invention also offers rational interactive interface, the concrete condition making staff directly can understand way mark on interactive interface go forward side by side line correlation operation, convenient and practical.
Accompanying drawing explanation
Fig. 1 is that entirety of the present invention realizes block diagram;
Fig. 2 is the general structure block diagram of system of the present invention;
Fig. 3 is the process flow diagram of the method for the invention;
Fig. 4 is the installation site schematic diagram of camera in the present embodiment;
Fig. 5 is the travel range schematic diagram of inspection car in the present embodiment;
Fig. 6 is the process flow diagram that the present invention realizes extracting from pickup image in real time execution key frame;
Fig. 7 is the process flow diagram that the present invention realizes integral image process;
Fig. 8 be real time GPS information of the present invention mate with realtime graphic realize block diagram;
Fig. 9 be the real-time optimized image of the present invention mate with standard picture realize block diagram;
Figure 10 is the process flow diagram that the present invention realizes realtime graphic rough handling;
Figure 11 is the process flow diagram that the present invention selects containing the real-time optimized image of way mark;
Figure 12 is that the present invention is for the realtime graphic identification process figure of Point Pattern Matching;
Figure 13 is the structured flowchart of database of the present invention;
Figure 14 is the schematic diagram of upper computer control module interactive interface of the present invention.
Embodiment
Below in conjunction with the drawings and specific embodiments, the present invention is further elaborated.
A kind of supervisory systems of way mark, its structured flowchart as shown in Figure 2, comprises image capture module 101, GPS information acquisition module 102, preparation standards model and real-time model and sets up module 103, two model fitting module 104, image procossing and identification module 105, database module 106 and upper computer control module 107.The function of modules and the transmission of intermodule information as described below.
Image capture module 101, for carrying out image acquisition to way mark.Image capture module 101 comprises two parts content: one is carry out collection by the standard picture of vehicle-mounted industrial camera to fixed point way mark to store, and two is gather the realtime graphic of way mark in traveling process.
In the present embodiment, adopt Z30M industrial camera to gather image, Z30M camera is supported video and is taken pictures two kinds of patterns, therefore when setting up preparation standards model and gathering fixed point way mark standard picture, exposal model can be adopted manually to gather.And way mark is being carried out in the operation of Real-time Collection, then video mode can be adopted to carry out entirety collection to way mark on the way.
GPS information acquisition module 102, for gathering the GPS locating information of way mark.
GPS information acquisition module 102 comprises two parts content: one is gather the standard GPS locating information setting up way mark in preparation standards model, mark, store, and forms the standard GPS longitude and latitude information of way mark; Two is the real time GPS informations to way mark in traveling process on the way.
Preparation standards model and real-time model set up module 103, for being added up the standard picture information of fixed point way mark and standard GPS longitude and latitude information by image capture module 101, GPS information acquisition module 102, and carry out synchronous simple sequence mark respectively, set up the preparation standards model of way mark, using this model as realistic basis, realize it and mate with the real-time statistics of way mark.
Gathered by the real time GPS information of image capture module 101, GPS information acquisition module 102 pairs of way marks and realtime graphic, extract the real time GPS information of way mark and image information corresponding to real time GPS information, by image sampling and two sequence mark, both first sequence one_to_one corresponding, and set up the real-time model of way mark on this basis.
Two model fitting module 104, according to the GPS threshold range that the parameter of GPS information acquisition module 102 collection calculates, the standard GPS longitude and latitude information of way mark in comparison preparation standards model, preserve effective real time GPS information bar in threshold range, and carry out sequence mark and storage equally, for preparing for the coupling of realtime graphic and real time GPS information.
In the present invention, the GPS threshold range that the parameter that two model fitting module 104 can gather according to GPS information acquisition module 102 calculates, the standard GPS longitude and latitude information of way mark in comparison preparation standards model, preserves effective real time GPS information bar in threshold range.Extract in minimum zone the image that there is way mark, decrease storage space and process quantity, improve in the efficiency of real-time matching and Real-time Collection process the accuracy rate that may there is way mark section image zooming-out.
Real-time information in module 103 can be set up to preparation standards model and real-time model to delete to select by sequences match and threshold value and extract key images, the key images chosen is calculated by parameter and expert algorithm control, the key images containing way mark corresponding to fixed point GPS processes, and therefrom draws real-time optimized image by process.
Image procossing and identification module 105, the image information that process comprises extracting carries out the rough handlings such as frame flag, reduction, denoising, image with way mark information is detected, segmentation etc., obtain the real-time optimized image that can carry out with the way mark standard picture in preparation standards model mating.
The real-time optimized image containing way mark drawn after being added up by expert algorithm in two model fitting module 104 and preparation standards model and real-time model are set up the standard picture information of adding up in module 103 and carries out pattern match, by the training of expert algorithm coupling, draw the types of damage of the way mark after actual match, and carry out classification storage.
Database module 106, for carrying out supervising in order, effectively to the data message in system, building database mechanism, is convenient to data and extracts, checks.
Upper computer control module 107, links with database in database module, intuitively shows, be convenient to operated by personnel to total system of the present invention.Upper computer control module with the interactive interface of close friend by process after data more intuitively for related personnel, the information such as the identification information whether specific category after display information spinner will comprise the GPS latitude and longitude information of fixed point way mark, the fixed point image of way mark, image recognition, the distress condition of way mark and keeping in repair completes, so that staff takes corresponding replacing or maintenance measure in time.
The present invention realizes the overall flow figure of image procossing as shown in Figure 7, be specially: 1) collection is carried out to the standard picture of way mark and standard GPS locating information and form pre-service integrated information, then from this pre-service integrated information, obtain the standard picture feature of road criterion; 2) by standard GPS longitude and latitude information setting threshold value; 3) obtain realtime graphic letter and the real time GPS information of way mark, and choose realtime graphic and the real time GPS information of coupling according to threshold value, and form real-time integrated information; 4) to the realtime graphic of coupling obtained after the sequence of operations such as pre-service, detection, segmentation, be met the real-time optimized image of demand; 5) standard picture in real-time optimized image and preparation standards model is compared identify, draw way mark real time status information, and carry out classification and store.
A method for way mark supervision, as shown in Figure 1, the method comprises its process flow diagram: first, by existing road criterion GPS and view data, sets up preparation standards model by mark simple sequence mode; Secondly, determining optimal sampling frequency and patrol and examine operation automatic acquisition latest GPS and view data by highway, setting up real-time model by marking two sequential manner; Then real-time model data are compared with preparation standards model data through two sequences match search, obtain real-time optimized image by real-time model and mate with standard picture; And then the particular type utilizing dot pattern image matching algorithm contrast standard data determination way mark to damage; Finally upgrade preparation standards model according to recognition result, service mode.
The particular flow sheet of this method as shown in Figure 3, comprises the following steps:
S101. the preparation standards model of way mark is set up.
Gathered by the image of selected instrument to standard way mark, and the synchronous GPS locating information obtaining present image, the data obtained is stored, sets up preparation standards model.The foundation of preparation standards model specifically comprises the following steps.
S1011. determine camera model, and according to the correct position of height and position on inspection car of way mark, camera is installed.
First determine camera model, thus determine the parameter such as focal length, frame per second, according to the frame of video that the effective unit time absorbs, obtain corresponding actual range, and then determine the speed of a motor vehicle of inspection car, make it to be mated, also avoid simultaneously to same section repeat judge; At the ad-hoc location of inspection car, camera is installed, normal conditions get down the highway mark height and position have certain regulation, therefore the installation site of camera on inspection car and setting angle can be determined according to this height and position, and inspection car orbit, so that the real-time optimized image of camera picked-up way mark.
In the present embodiment, the selection of concrete camera model and being calculated as follows of installation site.
In the present embodiment, camera adopts Z30M color camera, pixel 360,000, resolution can provide 752*480 (54 frames/second), 640 × 480 (60 frames/seconds) or 320 × 240 (60 frames/seconds), and frame per second can be arranged as required; The sensor of camera lens is 1/3CMOS (black and white/colour), and sensor size is 4510um*2880um (wide * is high), and Z30M/Z30C default installation seat is CS model.
Be 10m according to the highest setting height(from bottom) of standard way mark, the full-size of way mark is 4*3m, and inspection car height is 1.5m, and the speed of inspection car is 14m/s, for guaranteeing that way mark can in coverage, it is the shooting distance of camera that the present embodiment is selected at distance way mark 14m place.
1, the angle of looking up that camera is installed calculates according to following formula.
Can obtain tan θ=0.82 as calculated, and then draw θ ≈ 40 °, when namely camera is installed, its upward view angle arranges and is about 40 °.The installation site schematic diagram of the present embodiment camera as shown in Figure 4.
2, the wide angular range of camera lens requires to calculate according to following formula.
Then θ
3=θ
1-θ
2=49 °-31 °=18 °, namely camera lens wide angular range at least needs to reach 18 °.
3, the selection of camera lens model.
According to the sensor model number 1/3COMS selecting camera lens, size sensor is 4510um*2880um (wide * is high), calculates the vertical focal length of camera lens and horizontal focal length by following formula:
Wherein, f
wfor horizontal focal length, f
hfor horizontal focal length, w is sensor width, and L is the distance of subject apart from camera lens, and W is the width of subject, and h is sensor height, and H is the height of subject.
In the present embodiment, the breadth extreme of subject and way mark is 4m, and the maximum height of subject is 3m, then:
Due in the present embodiment, first assume that subject and camera lens minor increment need reach 14m, then may much larger than this in the shooting process of reality, the minimum zone that therefore can obtain focal length is 13.44mm ~ 15.785mm.According to minimum field-of-view angle and the minimum focus scope of the camera lens selected, the camera lens model that the present embodiment is chosen is 0660MV.
Z30M industrial camera can provide one or more USB high-speed interface to be connected with PC, wiring is simple, data transmission is convenient, without the need to increasing connecting line in addition, easy to use, plug and play, support hot plug, aluminum alloy casing, shock resistance is strong, have powerful anti-electromagnetic interference capability, parameter meets the requirement of image acquisition of the present invention.The focal length of this camera lens can regulate between 6 ~ 60mm, range of adjustment is wide, Angle of View:44.5 ~ 4.6, horizontal field of view angle, meet the demand of multi-angle, and Z30M industrial camera can taken pictures and change between video, all can meet the video acquisition in the foundation of preparation standards model in the present invention and follow-up real-time detection.
Expressway Road is spacious, vehicle is various, patrol and examine vehicle to advance on fixing track, and there is certain restriction in the picked-up scope of image, therefore, the present invention needs to determine the travel range of inspection car, and the defining method of inspection car orbit is as follows.
If highway label is of a size of l*w, the industrial camera field-of-view angle chosen is θ
1, optimum distance L, as shown in Figure 5.Because way mark should to be arranged on the right side of road by GB, l
1for image center line is to the distance of label left side bearing, so, then have:
Just can draw thus and patrol and examine the concrete scope that vehicle can offset the traffic sign of road edge.
Determine the optimum position scope of image capture, just can carry out actual acquisition to image.And in the fixed point of reality gathers, how to determine also to need certain utility appliance to fixed position, the present invention utilizes infrared sensor to the distance S of camera distance way mark of reality and the range of operation l of vehicle
1measure, when reaching setting numerical value, then can press camera shutter by the joystick in inspection car, obtaining present image.
S1012. the standard picture of way mark is gathered.
The exposal model adopting camera to the standard picture of way mark, the form of taking pictures to fix a point gather.Only need to gather in the present invention once just can complete, the standard picture of the way mark of collection is used for setting up preparation standards model.
S1013. the standard GPS locating information of way mark is gathered.
GPS location is carried out to way mark, obtains the standard GPS locating information of way mark.Only need to gather in the present invention once just can complete, the standard GPS locating information of the way mark of collection is used for setting up preparation standards model.
S1014. according to the result that step S1012 and S1013 gathers, preparation standards model is set up by mark simple sequence mode.Described simple sequence mark mode is successively mark according to acquisition order the standard picture of synchronous acquisition and GPS information.
Standard GPS in preparation standards model and standard picture can not realize automatic collection, staff is needed manually to operate, the present invention determines the optimal acquisition point of image under the cooperation of related sensor, when patrolling and examining vehicle and moving in optimal acquisition point range, manual collection standard GPS and image after staff determines, and respectively simple sequence mark is carried out to both, successively sequence mark is carried out to image by the fixed point collection of standard picture, synchronous acquisition standard GPS locating information successively flag sequence, because standard picture obtains synchronous with standard GPS locating information in the process, flag sequence is also just consistent, by the coupling of sequence number, standard picture information and standard GPS locating information are carried out integrated fusion thus sets up preparation standards model.
S102. obtain the real-time information of way mark, and set up real-time model.
Obtain in inspection car traveling process, the real-time video information of way mark and real time GPS information, calculated by parameter, determine GPS threshold value, draw the section needing to position, obtain the realtime graphic of the way mark in section, location, guarantee to comprise way mark in extracted image information.The acquisition of real-time information specifically comprises the following steps.
S1021. the video mode of camera is adopted to obtain the real-time image information of way mark.
The collection of way mark realtime graphic adopts the video mode of camera, according to the demand of onsite supervision plan, can carry out at any time.Video acquisition is connected with PC by industrial digital camera, by USB interface, information directly reached PC, and store.The installation site of camera need be considered, the calculating of each parameter of camera, the selection of camera lens and Sensor (sensor) during video acquisition; Need to consider that the impact of change on video image of hourly velocity patrolled and examined by vehicle simultaneously, so in the present invention inspection car adopt be that constant speed is patrolled and examined, when occur overtaking other vehicles etc. unexpected phenomenon time, then can operate brake or gearshift artificially, carry out constant speed again when removing situation about occurring and patrol and examine.
S1022. real time GPS location is carried out to way mark, obtain the real time GPS information of way mark.
The collection of way mark real time GPS information, according to the demand of onsite supervision plan, can carry out at any time.In the Real-time Collection process of way mark real time GPS information, mark if carry out sequences match when current GPS location place exists standard way mark.
Due to the long distance property of highway section, GPS location of the present invention adopts error GPS positioning system within the specific limits, adopts expert algorithm to ensure integrality, reliability that GPS locating information obtains, and real time GPS information is stored to relevant position.
S1023. real time GPS information (comprising time, longitude, latitude) is mated with corresponding realtime graphic, and set up real-time model by the two sequential manner of mark.Described pair of sequence mark mode is for sequence mark real time GPS information with the acquisition time of real-time information; To being first that sequence carries out first sequence mark with real-time time according to the realtime graphic of certain sample frequency collection, secondly again subsequence mark being carried out according to sampling order to the multiframe realtime graphic with same real-time time sequence number, thus setting up real-time model.
Below in conjunction with Fig. 6, the image containing way mark how extracting corresponding real time GPS information from the image of real time shooting is described.
First, the real time GPS information of way mark is gathered one by one, and carry out two sequence mark.When carrying out sequence mark one by one to real time GPS information, institute's flag sequence is the Real-time Obtaining time of GPS: year, month, day, hour, min, second, and namely length is the sequence field of 14.
In the present embodiment, pass through to mark to GPS frequency and image frame per second, carry out expert algorithm design, make to reach the effect of mating one by one between the two.GPS is connected with PC by USB serial ports, and the implementation procedure being received and extract GPS latitude and longitude information by VB is as follows:
// obtain latitude and longitude information
// judge when start to receive GPS information
If Strnum=vbLf Then' is when running into new line
If (StrArray (0)=" $ ") Then' runs into the first character " $ " that character string starts
G=g+1//GPS information the number gathered is added up
MyY1=TStrGps (5) ' extracts the longitude in character string
MyY＝""&Mid(MyY1,1,2)&"'"&Mid(MyY1,3,3)&"”"&Mid(MyY1,7,4)
Text4.Text=g & MyY//by the latitude information of extraction is undertaken marking and deposits in Text4.text
Open " C: GPS latitude " & d & " .txt " For Append As#4
Print#4,Text3.Text
Close#4//latitude information will be had deposit to computer relevant position
MyX1=TStrGps (3) ' extracts the latitude in character string
MyX＝""&Mid(MyX1,1,2)&"'"&Mid(MyX1,3,2)&"”"&Mid(MyX1,6,4)
Text3.Text=g & MyX//by the longitude information of extraction is undertaken marking and deposits in Text3.text
Open " C: GPS longitude " & d & " .txt " For Append As#5
Print#5,Text4.Text
Close#5//the document having longitude information is deposited to computer relevant position.
Secondly, calculate the sample frequency of way mark real-time image information, and two sequence mark is carried out to sampled images; In labeling process, need to carry out two sequence mark frame by frame to every frame pictorial information of the way mark image information gathered, the two sequences marked divide headed by sequence, subsequence, wherein first sequence is the real-time time that picture frame obtains: year, month, day, hour, min, second, length is the sequence field of 14, and order is classified as the sampling order of multiple image under same first sequence number.
In real-time model, image acquisition uninterruptedly gathers with visual form, because the frequency acquisition of camera is higher, if all processed each two field picture, is proposed high requirement to processing speed and disk storage.Based on this, the present invention, by calculating sampling frequency, samples to realtime graphic, reduces image procossing amount, ensures result simultaneously.If camera sample frequency is X frame/S, vehicle gait of march is Vm/s, then sample frequency F can be set as follows:
According to Z30M camera filming frequency X=60 frame of the present invention/S, V=14m/s, can be calculated: F=5 frame/m.
Then, can learn that the acquisition time of pictorial information and real time GPS information is consistent from real time GPS information and Image Acquisition approach, by Time Series Matching, realize the foundation of real-time model.
S103. the real-time optimized image of way mark in the real-time information collected by expert algorithm obtaining step S102.
Rough handling is carried out for the realtime graphic collected in step S102, and obtains the real-time optimized image information containing way mark by expert algorithm, row labels of going forward side by side, storage.The rough handling of image comprises carries out the treatment steps such as preliminary denoising, filtering, reduction, Slant Rectify, motion blur elimination to the image collected in S102, thus obtains containing way mark and can carry out with the standard picture in preparation standards model the real-time optimized image that mates.Concrete steps are as follows.
S1031. image carries out rough handling.
In practical application, the primary image problem that noise and motion blur cause is easy to affect follow-up image procossing, therefore needs first to carry out rough handling to image.The present invention realizes the process flow diagram of image rough handling as shown in Figure 10.
First, calculate according to parameters such as the inspection car speed of a motor vehicle, shooting camera frame per second, GPS location frequencies, obtain key frame matching parameter; Secondly, the video image of collection is converted to JPG format picture; Then, the process such as picture denoising, filtering, motion blur elimination, Slant Rectify are carried out to JPG format picture.The improved Median Filtering stress release treatment impact that picture denoising adopts denoising effect good, motion blur is eliminated and is adopted Wiener filtering and innovatory algorithm to process, and Slant Rectify adopts expert algorithm to correct inclination picture.
In the present embodiment, the realtime graphic obtained by the real time GPS information correspondence of preserving, according to the parameter of Z30M, be 5 frames, and in follow-up concrete identification, the present invention only needs the wherein real-time optimized image of a frame to realize at the preservation image of this corresponding GPS.
S1032. the real-time optimized image containing way mark is selected
The present invention selects process flow diagram containing the real-time optimized image of way mark as shown in figure 11, and specific implementation process is:
First, 5 two field pictures that realtime graphic obtains after rough handling are detected.
Secondly, according to the singularity of way mark color, RGB is converted to hsv color space.
Then, whether judged in present image containing special color by hsv color space.Special color refers to the color of red, blue, yellow look corresponding HSV space; If containing wherein a kind of, then think picked-up containing way mark in present image, mark storage is carried out to this picture.
Again, by color region, image is split further.
Finally, compare the cut zone size between different images, choose the real-time optimized image of the maximum conduct of cut zone.
In actual applications, due to shooting distance and other factors impact, the effect of way mark shooting is not quite similar.The present invention assert cut zone scope maximum for real-time optimized image, because cut zone is larger, then prove the position of camera distance actual way mark closer to, in the image absorbed, shared by way mark, region is also larger, more clear, namely image effect is more close to the real-time optimized image that the present invention is desirable.
S104. the real-time optimized image obtained in step S103 is mated with the standard picture of preparation standards model in step S101, draw by expert algorithm the concrete classification that way mark damages, and store.
S1041, calculated threshold, makes real time GPS information mate with the standard GPS longitude and latitude information of standard.
From above, all carried out sequence mark respectively to both when the present invention extracts GPS information in preparation standards model and real-time model, calculated the threshold range that can obtain both and can realize mating by parameter, concrete computation process is as follows.
Warp, the latitude information of known A point and B point two, derive according to the knowledge about circle and triangle, show that the formula of earth surface point distance is as follows:
C＝sin(MLatA)*sin(MLatB)*cos(MLonA-MLonB)+cos(MLatA)*cos(MLatB)
Distance＝R*Arccos(C)*π/180
Can be obtained by above formula: Arccos (C)=Distance*180/ (R* π)
Wherein, the unit of R with Distance is identical.
In the present embodiment, it be 14m/s, GPS location frequency is 1S/ time that way mark patrols and examines the speed of a motor vehicle, and therefore the present invention selects threshold value earth surface distance to be 15m, and namely Dis tan ce=15 (m) can be calculated Arccos (C)=1.34 × 10
-4, C=cos (1.34 × 10 can be obtained further
-4) ≈ 1.
And from above formula, when A point and B point are in same Longitude In System:
C＝sin(MLatA)*sin(MLatB)*cos(0°)+cos(MLatA)*cos(MLatB)
C＝sin(MLatA)*sin(MLatB)*1+cos(MLatA)*cos(MLatB)
By C ≈ 1, and mathematics trigonometric function theorem is known, as MLatA ≈ MLatB,
C≈sin
2(MLatA)+cos
2(MLatA)＝1，
Therefore, when A point and B point latitude are also in same position, when namely latitude threshold value reaches 0, the requirement of ground distance threshold value 15m can be reached, but threshold range so accurately can not be had in actual application, therefore, make
C＝sin(MLatA)*sin(MLatB)*1+cos(MLatA)*cos(MLatB)≈
sin
2(MLatA)+cos
2(MLatA)＝1
I.e. sin (MLatA) ≈ sin (MLatB), cos (MLatA) ≈ cos (MLatB)
Detect according to sine and cosine and experimental data, when longitude is consistent, suppose to get radix point two for effectively calculating, sin (θ)=0.0044 can be obtained through consulting databook, getting 2 significant digits effective, sin (θ) ≈ 0, and now θ ≈ 0.25 °=15 "; therefore, latitude threshold range is determined at 0.25 °, can effective location be obtained.In like manner, when being in Same Latitude at 2, the determination of longitude threshold value also can be realized by above method, and longitude threshold value is also defined as 0.25 ° as calculated.
S1042, is kept at the real time GPS information in threshold range, and preserves the GPS simple sequence of preparation standards model and pair sequence of the GPS in real-time model that match.
When coupling is between the two in threshold range, the real time GPS information of current extraction is preserved, the GPS sequence in the preparation standards model matched is carried out corresponding stored simultaneously; And necessarily there is way mark in the ground areas corresponding to real time GPS information preserved.Therefore be easy to the realtime graphic containing way mark corresponding to real time GPS information finding this to retain according to the flag sequence interface started, complete the acquisition of real-time information.
S1043, according to threshold requirement, mates real-time optimized image corresponding in standard picture corresponding with preparation standards model again for the real time GPS information of coupling and real-time model.
When the first sequences match of the first sequence of the real-time image information of way mark and real time GPS information, then the real-time image information with the first sequences match of real time GPS locating information is defined as key frame images, and preserves, surely containing way mark in these images; The sequence of preparation standards model Plays GPS locating information is carried out corresponding stored again simultaneously, just achieve in real time execution the image acquisition of GPS place containing way mark of fixing a point.
In the present embodiment, realize the process flow diagram mated one by one of real time GPS information and realtime graphic as shown in Figure 8.First mark frame by frame with two sequence form for the way mark realtime graphic extracted, namely shape is as ij.jpg (i is the real-time time sequence of 14, j=1....5).And the real time GPS information of correspondence is labeled as k.GSA.GSV (k is 14 real-time time sequences) one by one with sequence, wherein GSA represents longitude, and GSV represents latitude.Extract realtime graphic and real time GPS label information, initial character is mated, if coupling, then the GPS information after photo current Corresponding matching, thus achieve the pairing of realtime graphic and real time GPS information.
In the present embodiment, C language is adopted to realize the two sequence permutation process of image as follows:
When in the present invention, real time GPS information and realtime graphic realize mating: i=g, then mate between the two, implementation procedure is:
Ifstream in (" 5.txt "); // read the txt document containing longitude information
string string；
While (getline (in, string)) // row read data and be stored in string, until data all read
Char c1=string [0]; // read character string string initial character
Int g=atoi (c1); // initial character c1 is changed into digital value
If (i==g) // judge whether GPS initial character mates with picture name initial character.
Correspondence image in the real-time optimized image extracted after above-mentioned Real-time Collection and preparation standards model carries out the process flow diagram of pattern match as shown in Figure 9.The present invention is the identification carrying out way mark types of damage after the correspondence image in real-time optimized image by extracting after Real-time Collection and preparation standards model carries out pattern match, therefore how to guarantee that coupling is between the two also just particularly important.
The present invention is when setting up preparation standards model and process real-time information, just respectively standard GPS locating information, standard picture, real time GPS information and realtime graphic are marked respectively, wherein standard picture is corresponding consistent with real time GPS information, and realtime graphic is corresponding consistent with real time GPS information.Therefore when real time GPS information has been mated with standard GPS locating information, just the corresponding of real time GPS information and standard picture can be realized, and real time GPS information and real-time image sequences are consistent, thus the real-time optimized image that can realize extract real-time realizes corresponding with standard picture, for follow-up pattern-recognition provides basis.
S1044, draws by expert algorithm the concrete classification that real-time best way mark damages, and stores.
The real-time optimized image obtained in step S103 is consistent with the sequence mark of the standard picture of preparation standards model in step S101, therefore both consistent for sequence mark images are carried out the pattern match under expert algorithm control, obtain actual recognition result, and carry out classification storage.
Image recognition process flow diagram under realtime graphic pattern match is see Figure 12.The damage type that actual way mark may exist is various, in the present embodiment, is described for Point Pattern Matching.
The standard angle point of rectangle way mark is four angle points, first extracts so as to the angle point of SUSAN algorithm to standard way mark, Criterion model; Secondly, the angle point of realtime graphic is extracted in the real-time optimized image after extraction process; Then, both are trained via Point Pattern Matching, draws final matching result; As consistent with corner location in both angle point numbers, then judge that current real-time way mark is normal, as inconsistent, assert that Current Highway mark exists damaged location, as trouble spot, in conjunction with GPS location, classify as abnormal classification.In the present embodiment, concrete methods of realizing is as follows.
SrcImage=cvLoadImage (" picture-storage position ", 1); // Load Image
grayImage＝cvCreateImage(cvGetSize(srcImage),IPL_DEPTH_8U,1)；
// by former figure gray processing
cvCvtColor(srcImage,grayImage,CV_BGR2GRAY)；
// the company of an establishment intermediate images identical with former figure size
corners1＝cvCreateImage(cvGetSize(srcImage),IPL_DEPTH_32F,1)；
corners2＝cvCreateImage(cvGetSize(srcImage),IPL_DEPTH_32F,1)；
// Corner Detection
cvGoodFeaturesToTrack(grayImage,corners1,corners2,corners,
&cornerCount,qualityLevel,minDistance,0)；
printf("num corners found:％d\n",cornerCount)；
// in former figure, angle point is marked
After above-mentioned algorithm calculates, actual way mark edge angle point is shown to standard picture, also real-time edge angle point can be obtained equally to realtime graphic, then the angle point quantity both statistics, if consistent, then retention criteria image, judge that way mark is as normal mark, if angle point quantity is inconsistent, then way mark is improper.
S105. the recognition result obtained according to step S104 judges whether to need repairing, and determines whether to need to upgrade the standard picture in preparation standards model according to the maintenance result of feedback;
By background work personnel whether keeped in repair judge original image renewal whether, maintenance does not complete, then do not process, maintenance completes, then by the complete image after current maintenance in order to upgrade the standard picture in preparation standards model.
S106. building database, manages the data in step S101 ~ S104.
Because the data volume of image procossing is huge, simple storage can not meet the demand of people to data, the structure of database, for related personnel makes correct decisions, carries out efficient process give security for data.
Information Monitoring and process data are incorporated to database and manage by the present invention, and database import information comprises: the Asset image integrated information etc. mating integrated information, there is obstacle after the best realtime graphic frame comprising way mark image that expert algorithm calculates, metadatabase (namely in order to train the standard picture storehouse generating sorter), Classification and Identification of the realtime graphic video information of the standard picture of way mark, the standard GPS locating information of way mark, way mark, the real time GPS information of way mark, GPS and image.
In the present invention, the structured flowchart of database as shown in figure 13, and database comprises metadatabase, real-time data base, image management storehouse, personal management storehouse, backstage and storehouse, five points, time management storehouse, and the function in each point of storehouse is as described below.
Metadatabase: the concrete image storing in preparation standards model the flag sequence of the standard picture of way mark of fixing a point, memory location and store in a binary format in a database; The flag sequence of standard GPS locating information and the longitude of correspondence, latitude; The rise time etc. of each correspondence image and GPS integrated information.
Real-time data base: to the management of the locating information of the key video sequence frame after the video-frequency band gathered in real-time model and cycle GPS information, process and flag sequence, sampling (through, latitude) and flag sequence, according to above to key frame and sampling locating information extraction, can realize well coupling between both and be directly connected to final process result, therefore the management of real-time model is not allowed to make mistakes.
Image management storehouse: the existence having image in preparation standards model and real-time model, after image in real-time model finds the image in preparation standards model corresponding with it according to sequence, under the control of expert algorithm, a net result will be obtained.Image management function of the present invention further manages image library according to recognition result, and recognition result is normal, then the image in preparation standards model does not process, retention criteria image; If improper, then need to upgrade the image in preparation standards model.And this upgrades and links up with whether keep in repair, keep in repair, image zooming-out has been carried out to the label after maintenance, upgraded pretreatment image, if do not have to keep in repair, then kept undetermined.
Background work personal management storehouse.Background work personnel comprise: the statistics of preparation standards model collector, in real time patrol officer, statistics trouble spot and fault type and the middle transition personnel of contact maintenance, maintenance personal, check personnel according to maintenance personal's feedback result identification maintenance result.To improper mark via after maintenance personal's maintenance, maintenance result is determined, and the improper mark completing maintenance is marked, thus determine to upgrade the standard picture in preparation standards model, to ensure the real-time follow-up of metadatabase.
Time management storehouse: due to the whether normal personal safety and safety of property being seriously related to people of highway label, therefore the efficiency particular importance that namely works of time.Time comprises: preparation standards model Time Created, in real time monitoring time, result qualification time, maintenance personal contact time and maintenance deadline etc.Monitoring time rule of thumb can set polling period in real time in the present invention, thus the date is patrolled and examined in setting, can propose warning if expire not patrol and examine in time; Can the time limit be limited to the maintenance deadline, exceed the time limit, sentence certain punishment.
S107. design upper computer control module interface, in mode intuitively, data are shown, realize the actual demand that people supervises way mark, embody hommization of the present invention and intellectuality.
In the present invention, upper computer control module and database are by the formulation of the signal wiring between serial ports and communication protocol, and ensure that the data stored can accurately be uploaded to upper computer control module interactive interface, inquiry, report printing etc. for people provide convenient.
In the present embodiment, the realtime graphic of way mark, real time GPS information and image actual classification result with reference to figure as shown in figure 14, can show, facilitate staff to contrast information and carry out associated maintenance to Asset by upper computer control module interface.
Claims (10)
1. a monitoring and managing method for way mark, is characterized in that specifically comprising the following steps:
S101. the preparation standards model of way mark is set up;
S102. obtain the real-time information of way mark, and set up real-time model;
S103. the real-time optimized image of way mark in the real-time information collected by expert algorithm obtaining step S102;
S104. the real-time optimized image obtained in step S103 is mated by sequence search with the standard picture of preparation standards model in step S101, draw by expert algorithm the concrete classification that actual way mark damages, and store;
S105. judge whether to need repairing according to recognition result, and determine whether to need to upgrade the standard picture in preparation standards model according to the maintenance result of feedback;
S106. building database, manages the data in step S101 ~ S104;
S107. design host computer interface, in mode intuitively, data are shown, realize the actual demand that people supervise way mark.
2. the monitoring and managing method of a kind of way mark according to claim 1, is characterized in that step S101 specifically comprises following content:
S1011. determine camera model, and calculate according to the height and position of way mark, the correct position on inspection car installs camera;
S1012. the standard picture of way mark is gathered;
S1013. the standard GPS locating information of way mark is gathered;
S1014. according to the result that step S1012 and S1013 gathers, preparation standards model is set up by mark simple sequence mode.
3. the monitoring and managing method of a kind of way mark according to claim 1, is characterized in that step S102 specifically comprises following content:
S1021. the video mode of camera is adopted to obtain the real-time image information of way mark;
S1022. real time GPS location is carried out to way mark, obtain the real time GPS information of way mark;
S1023. real time GPS information is mated with corresponding realtime graphic, and set up real-time model by the two sequential manner of mark.
4. the monitoring and managing method of a kind of way mark according to claim 3, is characterized in that step S1023 specifically comprises following content:
First, the real time GPS information of way mark is gathered one by one, and carries out sequence mark;
Secondly, calculate the sample frequency of way mark real-time image information, and two sequence mark is carried out to sampled images;
Then, judge whether the real-time image information of way mark and the first sequence of real time GPS information mate, as coupling, then set up real-time model.
5. the monitoring and managing method of a kind of way mark according to claim 1, is characterized in that step S103 specifically comprises following content:
S1031. image carries out rough handling;
S1032. the real-time optimized image containing way mark is selected.
6. the monitoring and managing method of a kind of way mark according to claim 5, it is characterized in that: adopt expert algorithm to carry out rough handling to image in step S1031, contents processing comprises the treatment step that the preliminary denoising, filtering, reduction, Slant Rectify, the motion blur that carry out the image collected in S102 are eliminated.
7. the monitoring and managing method of a kind of way mark according to claim 5, is characterized in that step S1032 specifically comprises following content:
First, the n two field picture that realtime graphic obtains after rough handling is detected (n=1...5);
Secondly, according to the singularity of way mark color, RGB is converted to hsv color space;
Then, whether judged in present image containing special color by hsv color space;
Again, by color region, image is split further;
Finally, compare the cut zone size between different images, choose the real-time optimized image of the maximum conduct of cut zone.
8. the monitoring and managing method of a kind of way mark according to claim 1, is characterized in that step S104 specifically comprises following content:
S1041, calculated threshold, makes real time GPS information mate with standard GPS longitude and latitude information;
S1042, is kept at the real time GPS information in threshold range, and preserves the GPS sequence in the GPS simple sequence of preparation standards model and real-time model matched;
S1043, according to threshold requirement, mates real-time optimized image corresponding in standard picture corresponding with preparation standards model again for the real time GPS information of coupling and real-time model;
S1044, draws by expert algorithm the concrete classification that real-time best way mark damages, and stores.
9. a supervisory systems for way mark, is characterized in that: this system comprises
Image capture module 101, for carrying out image acquisition to way mark;
GPS information acquisition module 102, for gathering the GPS locating information of way mark;
Preparation standards model and real-time model set up module 103, for carrying out synchronous simple sequence mark respectively to the standard picture information of fixed point way mark and standard GPS longitude and latitude information by image capture module 101, GPS information acquisition module 102, and set up preparation standards model;
Gathered by the real time GPS information of image capture module 101, GPS information acquisition module 102 pairs of way marks and realtime graphic, extract the real time GPS information of way mark and image information corresponding to real time GPS information, by image sampling and two sequence mark, set up real-time model;
Two model fitting module 104, set up real-time information in module 103 to preparation standards model and real-time model to delete to select by sequences match and threshold value and extract key images, the key images chosen is calculated by parameter and expert algorithm control, the key images containing way mark corresponding to fixed point GPS processes, and therefrom draws real-time optimized image by process;
Image procossing and identification module 105, set up the standard picture information of adding up in module 103 containing the real-time optimized image of way mark and preparation standards model and real-time model carry out pattern match by what draw in two model fitting module 104, by the training of expert algorithm coupling, draw the types of damage of the way mark after actual match, and carry out classification storage;
Database module 106, for carrying out supervising in order, effectively to the data message in system, building database mechanism;
Upper computer control module 107, links with database in database module, the data after Graphics Processing directly perceived.
10. the supervisory systems of a kind of way mark according to claim 9, is characterized in that: the specific category after the information spinner of described upper computer control module display will comprise the GPS latitude and longitude information of fixed point way mark, the image of fixed point way mark, image recognition, the distress condition information of way mark and keep in repair the identification information whether completed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510176310.3A CN104766086B (en) | 2015-04-15 | 2015-04-15 | The monitoring and managing method and system of a kind of way mark |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510176310.3A CN104766086B (en) | 2015-04-15 | 2015-04-15 | The monitoring and managing method and system of a kind of way mark |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104766086A true CN104766086A (en) | 2015-07-08 |
| CN104766086B CN104766086B (en) | 2017-08-25 |
Family
ID=53647900
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510176310.3A Active CN104766086B (en) | 2015-04-15 | 2015-04-15 | The monitoring and managing method and system of a kind of way mark |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104766086B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105375392A (en) * | 2015-12-04 | 2016-03-02 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | Helicopter power line inspection realization method and realization system |
| CN105807682A (en) * | 2016-03-07 | 2016-07-27 | 福建亿通软件有限公司 | Intelligent place name sign board, place name sign board monitoring system and place name sign board daily maintenance method |
| CN106127169A (en) * | 2016-06-28 | 2016-11-16 | 广州地铁集团有限公司 | Train running information analyzes system and method |
| CN107357894A (en) * | 2017-07-13 | 2017-11-17 | 杭州智诚惠通科技有限公司 | A kind of road traffic facility data acquisition method for correcting error and system |
| CN107590511A (en) * | 2017-08-30 | 2018-01-16 | 武汉华星光电技术有限公司 | A kind of defect identification method and identifying system the defects of for automatic check machine |
| CN108460465A (en) * | 2017-12-29 | 2018-08-28 | 福建工程学院 | A kind of method of rapid-maintenance road |
| CN108803312A (en) * | 2018-04-19 | 2018-11-13 | 彭楷文 | A kind of new road damage detecting system |
| CN109033199A (en) * | 2018-06-29 | 2018-12-18 | 珠海爱路达信息科技有限公司 | A kind of inspection audio video synchronization broadcasting and intelligent comparison method and device |
| CN109426822A (en) * | 2017-08-25 | 2019-03-05 | 无锡市明大交通科技咨询有限公司 | A kind of means of transportation Check System and its investigation method |
| CN109639966A (en) * | 2018-12-11 | 2019-04-16 | 四川睿盈源科技有限责任公司 | Vehicle-mounted control method based on Asset supervision |
| CN109782364A (en) * | 2018-12-26 | 2019-05-21 | 中设设计集团股份有限公司 | Traffic mark board based on machine vision lacks detection method |
| CN110006897A (en) * | 2019-03-15 | 2019-07-12 | 上海电气集团股份有限公司 | A kind of flow battery system monitoring device and application method |
| CN110188889A (en) * | 2019-04-28 | 2019-08-30 | 温州市兴海市政建设有限公司 | A kind of urban road surfaces maintenance management system based on preventative maintenance |
| CN112926371A (en) * | 2019-12-06 | 2021-06-08 | 中国移动通信集团设计院有限公司 | Road surveying method and system |
| TWI736245B (en) * | 2020-05-04 | 2021-08-11 | 覺華工程科技股份有限公司 | Artificial intelligence road inspection and detection system |
| WO2021217859A1 (en) * | 2020-04-30 | 2021-11-04 | 平安国际智慧城市科技股份有限公司 | Target anomaly identification method and apparatus, and electronic device and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101458871A (en) * | 2008-12-25 | 2009-06-17 | 北京中星微电子有限公司 | Intelligent traffic analysis system and application system thereof |
| CN102853821A (en) * | 2012-08-31 | 2013-01-02 | 浙江中是科技有限公司 | Ship GPS positioning and checking method and ship GPS interactive system |
| CN103699108A (en) * | 2014-01-03 | 2014-04-02 | 中天新能源农业科技投资有限公司 | OBD (on-board diagnostics) technology-based motor vehicle real-time monitoring system |
| US20140351053A1 (en) * | 2009-02-23 | 2014-11-27 | Hti Ip, Llc | Method and system for providing targeted marketing and services in an SDARS network |
| US8989914B1 (en) * | 2011-12-19 | 2015-03-24 | Lytx, Inc. | Driver identification based on driving maneuver signature |
-
2015
- 2015-04-15 CN CN201510176310.3A patent/CN104766086B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101458871A (en) * | 2008-12-25 | 2009-06-17 | 北京中星微电子有限公司 | Intelligent traffic analysis system and application system thereof |
| US20140351053A1 (en) * | 2009-02-23 | 2014-11-27 | Hti Ip, Llc | Method and system for providing targeted marketing and services in an SDARS network |
| US8989914B1 (en) * | 2011-12-19 | 2015-03-24 | Lytx, Inc. | Driver identification based on driving maneuver signature |
| CN102853821A (en) * | 2012-08-31 | 2013-01-02 | 浙江中是科技有限公司 | Ship GPS positioning and checking method and ship GPS interactive system |
| CN103699108A (en) * | 2014-01-03 | 2014-04-02 | 中天新能源农业科技投资有限公司 | OBD (on-board diagnostics) technology-based motor vehicle real-time monitoring system |
Non-Patent Citations (2)
| Title |
|---|
| 郑哲: "基于GPS数据的城市交通分析系统的研究与实现", 《中国优秀硕士学位论文全文数据库 工程科技||辑》 * |
| 陈晓红等: "基于区间数群决策矩阵的专家权重确定方法及其算法实现", 《系统工程与电子技术》 * |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105375392A (en) * | 2015-12-04 | 2016-03-02 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | Helicopter power line inspection realization method and realization system |
| CN105807682A (en) * | 2016-03-07 | 2016-07-27 | 福建亿通软件有限公司 | Intelligent place name sign board, place name sign board monitoring system and place name sign board daily maintenance method |
| CN106127169A (en) * | 2016-06-28 | 2016-11-16 | 广州地铁集团有限公司 | Train running information analyzes system and method |
| CN107357894A (en) * | 2017-07-13 | 2017-11-17 | 杭州智诚惠通科技有限公司 | A kind of road traffic facility data acquisition method for correcting error and system |
| CN107357894B (en) * | 2017-07-13 | 2020-06-02 | 杭州智诚惠通科技有限公司 | Road traffic facility data acquisition and correction method and system |
| CN109426822A (en) * | 2017-08-25 | 2019-03-05 | 无锡市明大交通科技咨询有限公司 | A kind of means of transportation Check System and its investigation method |
| CN107590511A (en) * | 2017-08-30 | 2018-01-16 | 武汉华星光电技术有限公司 | A kind of defect identification method and identifying system the defects of for automatic check machine |
| CN108460465A (en) * | 2017-12-29 | 2018-08-28 | 福建工程学院 | A kind of method of rapid-maintenance road |
| CN108803312A (en) * | 2018-04-19 | 2018-11-13 | 彭楷文 | A kind of new road damage detecting system |
| CN108803312B (en) * | 2018-04-19 | 2021-07-09 | 西安交通大学 | Novel road damage detecting system |
| CN109033199A (en) * | 2018-06-29 | 2018-12-18 | 珠海爱路达信息科技有限公司 | A kind of inspection audio video synchronization broadcasting and intelligent comparison method and device |
| CN109639966A (en) * | 2018-12-11 | 2019-04-16 | 四川睿盈源科技有限责任公司 | Vehicle-mounted control method based on Asset supervision |
| CN109639966B (en) * | 2018-12-11 | 2021-02-26 | 四川睿盈源科技有限责任公司 | Vehicle-mounted control method based on highway asset supervision |
| CN109782364A (en) * | 2018-12-26 | 2019-05-21 | 中设设计集团股份有限公司 | Traffic mark board based on machine vision lacks detection method |
| CN110006897A (en) * | 2019-03-15 | 2019-07-12 | 上海电气集团股份有限公司 | A kind of flow battery system monitoring device and application method |
| CN110188889A (en) * | 2019-04-28 | 2019-08-30 | 温州市兴海市政建设有限公司 | A kind of urban road surfaces maintenance management system based on preventative maintenance |
| CN112926371A (en) * | 2019-12-06 | 2021-06-08 | 中国移动通信集团设计院有限公司 | Road surveying method and system |
| CN112926371B (en) * | 2019-12-06 | 2023-11-03 | 中国移动通信集团设计院有限公司 | Road survey method and system |
| WO2021217859A1 (en) * | 2020-04-30 | 2021-11-04 | 平安国际智慧城市科技股份有限公司 | Target anomaly identification method and apparatus, and electronic device and storage medium |
| TWI736245B (en) * | 2020-05-04 | 2021-08-11 | 覺華工程科技股份有限公司 | Artificial intelligence road inspection and detection system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104766086B (en) | 2017-08-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104766086A (en) | Supervising method and system of way mark | |
| CN102867417B (en) | Taxi anti-forgery system and taxi anti-forgery method | |
| CN110619279B (en) | Road traffic sign instance segmentation method based on tracking | |
| CN105702048B (en) | Highway front truck illegal road occupation identifying system based on automobile data recorder and method | |
| CN109782364B (en) | Traffic sign board missing detection method based on machine vision | |
| CN104951775A (en) | Video technology based secure and smart recognition method for railway crossing protection zone | |
| CN106251695A (en) | Destination's parking stall intelligent recommendation system and method based on parking space state monitoring | |
| CN106331636A (en) | Intelligent video monitoring system and method of oil pipelines based on behavioral event triggering | |
| CN101894482A (en) | Video technology-based roadside vacant parking position wireless network detection system and method | |
| CN105046966A (en) | System and method for automatically detecting illegal parking behaviors in drop-off areas | |
| CN113887418A (en) | Method and device for detecting illegal driving of vehicle, electronic equipment and storage medium | |
| CN106339657A (en) | Straw incineration monitoring method and device based on monitoring video | |
| JP3466169B2 (en) | Management system for roads and surrounding facilities | |
| CN112633722A (en) | Vehicle-mounted road safety risk assessment system and method | |
| CN103914682A (en) | Vehicle license plate recognition method and system | |
| US11580659B2 (en) | Method for size estimation by image recognition of specific target using given scale | |
| CN103000067A (en) | Right angle turning detection system and detecting method thereof | |
| CN113903008A (en) | Ramp exit vehicle violation identification method based on deep learning and trajectory tracking | |
| CN110852236A (en) | Target event determination method and device, storage medium and electronic device | |
| CN112532921A (en) | Water conservancy system intelligent monitoring implementation method and system | |
| Chowdhury et al. | An adaptive technique for computer vision based vehicles license plate detection system | |
| CN110807415B (en) | Traffic checkpoint vehicle intelligent retrieval system and method based on annual inspection marks | |
| CN202887450U (en) | Taxi anti-fake system | |
| CN202257940U (en) | License plate identification video server | |
| CN116311205A (en) | License plate recognition method, license plate recognition device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20150708 Assignee: Changsha Chaolei Intelligent Technology Co.,Ltd. Assignor: HUNAN NORMAL University Contract record no.: X2023980033667 Denomination of invention: A Supervision Method and System for Highway Signs Granted publication date: 20170825 License type: Common License Record date: 20230316 |
|
| EE01 | Entry into force of recordation of patent licensing contract |