CN109389622A - Car tracing method, apparatus, identification equipment and storage medium - Google Patents
Car tracing method, apparatus, identification equipment and storage medium Download PDFInfo
- Publication number
- CN109389622A CN109389622A CN201811153051.2A CN201811153051A CN109389622A CN 109389622 A CN109389622 A CN 109389622A CN 201811153051 A CN201811153051 A CN 201811153051A CN 109389622 A CN109389622 A CN 109389622A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- tracking
- determined
- component
- overall profile
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Geometry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the present application discloses a kind of car tracing method, apparatus, identification equipment and storage medium, and this method obtains the vehicle image captured, and the vehicle that vehicle license can not be identified in the vehicle image is determined as to track vehicle;Determine the vehicle overall profile of the tracking vehicle and the component outline of preset component;Inquire the raw image data acquired in preset range, generation tracing path is tracked to the tracking vehicle according to the vehicle overall profile and the parameter logistic value of the component outline, this programme can efficiently, accurately to can not identify that the vehicle of license plate is tracked.
Description
Technical field
The invention relates to computer technology more particularly to a kind of car tracing method, apparatus, identification equipment and deposit
Storage media.
Background technique
Currently, based on Car license recognition " electronic police " technology pays dues in urban highway traffic, expressway, public security bayonet,
The every field such as parking lot and different regions popularization and application are driven by capturing vehicle image with determining whether vehicle is violating the regulations
It sails, however lacks in the prior art a kind of efficiently to unlicensed or block the means that the vehicle of number plate is tracked.
Summary of the invention
This application provides a kind of car tracing method, apparatus, identification equipment and storage mediums, can efficiently, accurately
The vehicle that can not identify license plate is tracked.
In a first aspect, the embodiment of the present application provides a kind of car tracing method, comprising:
The vehicle image captured is obtained, the vehicle that vehicle license can not be identified in the vehicle image is determined as to track vehicle
?;
Determine the vehicle overall profile of the tracking vehicle and the component outline of preset component;
The raw image data acquired in preset range is inquired, according to the vehicle overall profile and the component outline
Parameter logistic value is tracked generation tracing path to the tracking vehicle.
Second aspect, the embodiment of the present application also provides a kind of vehicle tracking devices, comprising:
Vehicle determining module is tracked, for obtaining the vehicle image captured, vehicle will can not be identified in the vehicle image
The vehicle of licence plate is determined as tracking vehicle;
Characteristic determination module, for determining the vehicle overall profile of the tracking vehicle and the component wheel of preset component
It is wide;
Comparison module is inquired, for inquiring the raw image data acquired in preset range, according to the vehicle monolithic wheel
The parameter logistic value of the wide and described component outline is tracked generation tracing path to the tracking vehicle.
The third aspect, the embodiment of the present application also provides a kind of identification equipment, comprising: processor, memory and storage
On a memory and the computer program that can run on a processor, the processor are realized such as when executing the computer program
Car tracing method described in the embodiment of the present application.
Fourth aspect, the embodiment of the present application also provides a kind of storage medium comprising identification machine executable instructions, institutes
Identification machine executable instructions are stated to chase after when being executed as identification device handler for executing vehicle described in the embodiment of the present application
Track method.
In the present solution, obtaining the vehicle image captured, it will can not identify that the vehicle of vehicle license is true in the vehicle image
It is set to tracking vehicle;Determine the vehicle overall profile of the tracking vehicle and the component outline of preset component;Inquire default model
The raw image data for enclosing interior acquisition, the parameter logistic value according to the vehicle overall profile and the component outline are chased after to described
Track vehicle is tracked generation tracing path, can efficiently, accurately to can not identify that the vehicle of license plate is tracked.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the application's is other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is a kind of flow chart of car tracing method provided by the embodiments of the present application;
Fig. 2 is the flow chart of another car tracing method provided by the embodiments of the present application;
Fig. 3 is the flow chart of another car tracing method provided by the embodiments of the present application;
Fig. 4 is the flow chart of another car tracing method provided by the embodiments of the present application;
Fig. 5 is a kind of structural block diagram of vehicle tracking device provided by the embodiments of the present application;
Fig. 6 is a kind of structural schematic diagram for identifying equipment provided by the embodiments of the present application.
Specific embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is for explaining the application, rather than the restriction to the application.It also should be noted that for the ease of retouching
It states, part relevant to the application is illustrated only in attached drawing rather than entire infrastructure.
Fig. 1 is a kind of flow chart of car tracing method provided by the embodiments of the present application, is applicable to can not identify vehicle
The vehicle of board is tracked, and this method can be executed by identification equipment provided by the embodiments of the present application, the vehicle of the identification equipment
The mode that software and/or hardware can be used in follow-up mechanism is realized, as shown in Figure 1, concrete scheme provided in this embodiment is as follows:
Step S101, the vehicle image captured is obtained, will can not identify that the vehicle of vehicle license is true in the vehicle image
It is set to tracking vehicle.
Wherein, the vehicle image of the candid photograph, which can be, captures equipment bat by the monitoring being arranged on the roads such as crossing, high speed
It takes the photograph to obtain.After getting the vehicle image, the identification of license plate is carried out to the vehicle for including in vehicle image, if there is can not
It identifies the vehicle of vehicle license, is then determined as the vehicle tracking vehicle, for carrying out the tracking of subsequent vehicle, wherein can not
The vehicle license of identification include license plate damage, be blocked etc. cause vehicle license can not identified situation, the knowledge of vehicle license
The process that Wei not be identified by brand number of the image recognition technology to vehicle license, when license plate number damaged or by
It blocks, then original clearly license plate number is unable to get by image recognition technology and is unable to get recognition result.
Step S102, the vehicle overall profile of the tracking vehicle and the component outline of preset component are determined.
After determining tracking vehicle, it is tracked further desirable for the tracking vehicle, in one embodiment, really
Make tracking vehicle after, further determine that the overall profile of the tracking vehicle and the profile of preset component, wherein vehicle it is whole
Body profile refers to the whole profile on the image of the appearance of vehicle, preset component profile be it is preset in vehicle it needs to be determined that
The profile of component, such as front car light, vehicle mark, skylight.
Specifically, by the image to tracking vehicle carry out limb recognition, feature extraction obtain vehicle overall profile and
The component outline of preset component, preset component can be one or more.
Step S103, the raw image data acquired in inquiry preset range, according to the vehicle overall profile and described
The parameter logistic value of component outline is tracked generation tracing path to the tracking vehicle.
Wherein, the photographic device that the raw image data acquired in preset range can be the vehicle image captured is default
The data that other photographic devices in range collect, the preset range illustratively can be 500 meters or 1 kilometer and differ.
Such as crossing A capture vehicle image in determine tracking vehicle after, then accordingly centered on the location A of crossing, obtain away from
From other crossings in the A1 kilometer range of crossing such as crossing B, crossing C and the image of crossing D acquisition as raw image data.
After getting raw image data, it is tracked the inquiry tracking of vehicle, in one embodiment, according to vehicle
Overall profile and the parameter logistic value of component outline are tracked tracking vehicle, wherein the parameter logistic value is default identification
The profile parameters of component and the ratio of vehicle overall profile parameter.Parameter can be area parameters, length parameter etc..In a reality
It applies in example, the tracking vehicle is tracked according to the vehicle overall profile and the parameter logistic value of component outline includes:
Vehicle overall profile and the corresponding overall profile area of component outline and component outline area are calculated separately, according to overall profile
The area ratio value of area and component outline area is tracked tracking vehicle.In another embodiment, it can also be point
The vehicle overall profile and the corresponding overall profile length of the component outline and component outline length are not calculated, according to institute
The length ratio value for stating overall profile length and the component outline length is tracked the tracking vehicle.
Specifically, it is whole to carry out vehicle to the vehicle for including in raw image data after getting raw image data
The identification of profile and preset component profile obtains corresponding parameter logistic value, and will can not equally identify that the vehicle of vehicle license is true
It is set to vehicle to be determined, by the parameter logistic value of the parameter logistic value of the vehicle to be determined in original image and the tracking vehicle
It is compared, the vehicle to be determined for meeting the first preset condition is determined as target vehicle;It determines original comprising target vehicle
The acquisition time and collecting location of image are simultaneously fed back, and the tracking of problem vehicle is achieved in.Wherein, the first preset condition can
To be that comparison value is greater than 0.9, i.e., the vehicle to be determined found in judgement raw image data is consistent with tracking vehicle characteristics, then will
The vehicle to be determined is determined as target vehicle, and feedback-related information.By a succession of relevant information of feedback to automatically generate
Tracing path, such as in crossing b, crossing e, crossing f successively at 3 points of time point 10 minutes, 3: 15 and 3: 18 have been tracked in crossing a
The line of the particular geographic location of crossing b, crossing e and crossing f is then determined as tracking rail by the tracking vehicle identified accordingly
Mark feeds back to tracking personnel.
As shown in the above, it after capturing to vehicle image, is somebody's turn to do if it find that the unrecognized vehicle of number plate then determines
The overall profile of vehicle and the profile of preset component, inquire original image number within a preset range after determining parameter logistic value
According to if it find that then carrying out vehicle to be determined there are the unrecognized vehicle of number plate in raw image data and tracking the ginseng of vehicle
The comparison of number ratio value regards as same vehicle, vehicle to be determined is determined as target vehicle and is fed back if compared unanimously
Relevant information such as acquisition time and the position of photographic device for acquiring the raw image data etc. are to be tracked, due to based on wheel
Tracking is compared in wide parameter, it is only necessary to carry out outline identification to the image of the vehicle of acquisition and obtain specific parameter logistic value
The tracking for completing the unrecognized vehicle of number plate, the details without carrying out image compare, and improve tracking efficiency, and due to using
The distance of the form of parameter logistic value, the image of candid photograph does not constitute influence to the tracking of final vehicle, expands tracking and compares
Range.
Fig. 2 is the flow chart of another car tracing method provided by the embodiments of the present application, optionally, described in the foundation
Vehicle overall profile and the parameter logistic value of the component outline tracking vehicle is tracked include: calculate separately it is described
Vehicle overall profile and the corresponding overall profile area of the component outline and component outline area, according to the overall profile
The area ratio value of area and the component outline area is tracked the tracking vehicle.As shown in Fig. 2, technical solution has
Body is as follows:
Step S201, the vehicle image captured is obtained, will can not identify that the vehicle of vehicle license is true in the vehicle image
It is set to tracking vehicle.
Step S202, the vehicle overall profile of the tracking vehicle and the component outline of preset component are determined.
Step S203, inquiry preset range in acquire raw image data, calculate separately the vehicle overall profile and
The corresponding overall profile area of the component outline and component outline area.
Step S204, according to the area ratio value of the overall profile area and the component outline area to the tracking
Vehicle is tracked generation tracing path.
In one embodiment, corresponding to count after overall profile and component outline that vehicle is identified by image border
Overall vehicle contour area and component outline area are calculated, as calculated using following functions in OpenCV:
Double contourArea (InputArray contour, bool oriented=false)
After obtaining vehicle overall profile and the corresponding overall profile area of component outline and component outline area, two are asked
The ratio of person obtains area ratio value, and similarly, the raw image data acquired in inquiry preset range determines vehicle to be determined
Area ratio value, method of determination is the same, if inquiring the area ratio value of vehicle to be determined and the area ratio of tracking vehicle
It is worth consistent in or greater than preset threshold (it is high that the ratio of the two is greater than 0.9 i.e. similarity), then determines the vehicle to be determined inquired
For target vehicle, and then generate tracing path.
It can be seen from the above, using the area ratio value of vehicle overall profile area and preset component area as inquiry tracking
The condition of vehicle can efficient, the accurately vehicle progress to that can not identify license plate without carrying out the detailed comparison of vehicle pictures
Tracking.
Fig. 3 is the flow chart of another car tracing method provided by the embodiments of the present application, optionally, described in the foundation
Vehicle overall profile and the parameter logistic value of the component outline tracking vehicle is tracked include: calculate separately it is described
Vehicle overall profile and the corresponding overall profile length of the component outline and component outline length, according to the overall profile
The length ratio value of length and the component outline length is tracked the tracking vehicle.As shown in figure 3, technical solution has
Body is as follows:
Step S301, the vehicle image captured is obtained, will can not identify that the vehicle of vehicle license is true in the vehicle image
It is set to tracking vehicle.
Step S302, the vehicle overall profile of the tracking vehicle and the component outline of preset component are determined.
Step S303, inquiry preset range in acquire raw image data, calculate separately the vehicle overall profile and
The corresponding overall profile length of the component outline and component outline length.
Step S304, according to the length ratio value of the overall profile length and the component outline length to the tracking
Vehicle is tracked.
In one embodiment, corresponding to count after overall profile and component outline that vehicle is identified by image border
Overall vehicle profile length and component outline length are calculated, as calculated using following functions in OpenCV:
double arcLength(InputArray curve,bool closed)
After obtaining vehicle overall profile and the corresponding overall profile length of component outline and component outline length, two are asked
The ratio of person obtains length ratio value, and similarly, the raw image data acquired in inquiry preset range determines vehicle to be determined
Length ratio value, method of determination is the same, if inquiring the length ratio value of vehicle to be determined and the length ratio of tracking vehicle
It is worth consistent in or greater than preset threshold (it is high that the ratio of the two is greater than 0.9 i.e. similarity), then determines the vehicle to be determined inquired
For target vehicle, and then generate tracing path.
It can be seen from the above, using the length ratio value of vehicle overall profile length and preset component length as inquiry tracking
The condition of vehicle can efficient, the accurately vehicle progress to that can not identify license plate without carrying out the detailed comparison of vehicle pictures
Tracking.
Fig. 4 is the flow chart of another car tracing method provided by the embodiments of the present application, optionally, if original image
In vehicle to be determined parameter logistic value and it is described tracking vehicle parameter logistic value be unsatisfactory for the first preset condition, then by institute
The image of the image and the vehicle to be determined of stating tracking vehicle is compared, will be described if meeting the second preset condition
Vehicle to be determined is determined as target vehicle.As shown in figure 4, technical solution is specific as follows:
Step S401, the vehicle image captured is obtained, will can not identify that the vehicle of vehicle license is true in the vehicle image
It is set to tracking vehicle.
Step S402, the vehicle overall profile of the tracking vehicle and the component outline of preset component are determined.
Step S403, the raw image data acquired in inquiry preset range, according to the vehicle overall profile and described
The parameter logistic value of component outline is tracked generation tracing path to the tracking vehicle.
Step S404, the raw image data acquired in inquiry preset range, by the vehicle to be determined in original image
Parameter logistic value and the parameter logistic value of the tracking vehicle are compared.
If the parameter ratio of the parameter logistic value of the vehicle to be determined step S405, in original image and the tracking vehicle
Example value comparison value be unsatisfactory for the first preset condition, then by it is described track vehicle image and the vehicle to be determined image into
Row compares, if meeting the second preset condition, the vehicle to be determined is determined as target vehicle.
Wherein, which can be the parameter logistic value of vehicle to be determined and the parameter logistic value of tracking vehicle
Comparison value be greater than 0.9, when comparison value is less than 0.9 then by it is described tracking vehicle image and the vehicle to be determined image
It is compared, specifically, extracting the local feature of the image of the tracking vehicle and the image of the vehicle to be determined, passes through
Local feature compares to obtain vehicle similarity, if the vehicle similarity is greater than preset threshold, by the vehicle to be determined
It is determined as target vehicle, illustratively, can be total similarity=weight 1* car light domain similarity+skylight Regional Similarity * power
Value 2+ car mark region similarity * weight 3+ ...;Determine that vehicle is target if total similarity is greater than given threshold (such as 80%)
Vehicle.
Step S406, the acquisition time and collecting location of the determining original image comprising target vehicle are simultaneously fed back.
It can be seen from the above, when the comparison value of vehicle to be determined and tracking vehicle parameter logistic value is unsatisfactory for condition,
Whether the then detailed comparison of further progress characteristics of image is target vehicle with determination vehicle to be determined, avoids identification error
Caused by track failure the case where.
Fig. 5 is a kind of structural block diagram of vehicle tracking device provided by the embodiments of the present application, and the device is above-mentioned for executing
The car tracing method that embodiment provides, has the corresponding functional module of execution method and beneficial effect.As shown in figure 5, the dress
It sets and specifically includes: tracking vehicle determining module 101, characteristic determination module 102 and inquiry comparison module 103, wherein
Vehicle determining module 101 is tracked, for obtaining the vehicle image captured, vehicle will can not be identified in the vehicle image
The vehicle of licence plate is determined as tracking vehicle.
Wherein, the vehicle image of the candid photograph, which can be, captures equipment bat by the monitoring being arranged on the roads such as crossing, high speed
It takes the photograph to obtain.After getting the vehicle image, the identification of license plate is carried out to the vehicle for including in vehicle image, if there is can not
It identifies the vehicle of vehicle license, is then determined as the vehicle tracking vehicle, for carrying out the tracking of subsequent vehicle, wherein can not
The vehicle license of identification include license plate damage, be blocked etc. cause vehicle license can not identified situation, the knowledge of vehicle license
The process that Wei not be identified by brand number of the image recognition technology to vehicle license, when license plate number damaged or by
It blocks, then original clearly brand number is unable to get by image recognition technology and is unable to get recognition result.
Characteristic determination module 102, for determining the vehicle overall profile of the tracking vehicle and the component of preset component
Profile.
After determining tracking vehicle, it is tracked further desirable for the tracking vehicle, in one embodiment, really
Make tracking vehicle after, further determine that the overall profile of the tracking vehicle and the profile of preset component, wherein vehicle it is whole
Body profile refers to the whole profile on the image of the appearance of vehicle, preset component profile be it is preset in vehicle it needs to be determined that
The profile of component, such as front car light, vehicle mark, skylight.
Specifically, by the image to tracking vehicle carry out limb recognition, feature extraction obtain vehicle overall profile and
The component outline of preset component, preset component can be one or more.
Comparison module 103 is inquired, it is whole according to the vehicle for inquiring the raw image data acquired in preset range
The parameter logistic value of profile and the component outline is tracked generation tracing path to the tracking vehicle.
Wherein, the photographic device that the raw image data acquired in preset range can be the vehicle image captured is default
The data that other photographic devices in range collect, the preset range illustratively can be 500 meters or 1 kilometer and differ.
Such as crossing A capture vehicle image in determine tracking vehicle after, then accordingly centered on the location A of crossing, obtain away from
From other crossings in the A1 kilometer range of crossing such as crossing B, crossing C and the image of crossing D acquisition as raw image data.
After getting raw image data, it is tracked the inquiry tracking of vehicle, in one embodiment, according to vehicle
Overall profile and the parameter logistic value of component outline are tracked tracking vehicle, wherein the parameter logistic value is default identification
The profile parameters of component and the ratio of vehicle overall profile parameter.Parameter can be area parameters, length parameter etc..In a reality
It applies in example, the tracking vehicle is tracked according to the vehicle overall profile and the parameter logistic value of component outline includes:
Vehicle overall profile and the corresponding overall profile area of component outline and component outline area are calculated separately, according to overall profile
The area ratio value of area and component outline area is tracked tracking vehicle.In another embodiment, it can also be point
The vehicle overall profile and the corresponding overall profile length of the component outline and component outline length are not calculated, according to institute
The length ratio value for stating overall profile length and the component outline length is tracked the tracking vehicle.
Specifically, it is whole to carry out vehicle to the vehicle for including in raw image data after getting raw image data
The identification of profile and preset component profile obtains corresponding parameter logistic value, and will can not equally identify that the vehicle of vehicle license is true
It is set to vehicle to be determined, by the parameter logistic value of the parameter logistic value of the vehicle to be determined in original image and the tracking vehicle
It is compared, the vehicle to be determined for meeting the first preset condition is determined as target vehicle;It determines original comprising target vehicle
The acquisition time and collecting location of image are simultaneously fed back, and the tracking of problem vehicle is achieved in.Wherein, the first preset condition can
To be that the comparison value of parameter logistic value is greater than 0.9, i.e., the vehicle to be determined and tracking vehicle found in judgement raw image data
Feature is consistent, then the vehicle to be determined is determined as target vehicle, and feedback-related information.Pass through a succession of related letter of feedback
Breath is to automatically generate tracing path, and such as in crossing b, crossing e, crossing f successively at 3 points of time point 10 minutes, 3: 15 and 3: 18 are chased after
Track is to the tracking vehicle identified in crossing a, then accordingly by the company of the particular geographic location of crossing b, crossing e and crossing f
Line is determined as tracing path and feeds back to tracking personnel.
As shown in the above, it after capturing to vehicle image, is somebody's turn to do if it find that the unrecognized vehicle of number plate then determines
The overall profile of vehicle and the profile of preset component, inquire original image number within a preset range after determining parameter logistic value
According to if it find that then carrying out vehicle to be determined there are the unrecognized vehicle of number plate in raw image data and tracking the ginseng of vehicle
The comparison of number ratio value regards as same vehicle, vehicle to be determined is determined as target vehicle and is fed back if compared unanimously
Relevant information such as acquisition time and the position of photographic device for acquiring the raw image data etc. are to be tracked, due to based on wheel
Tracking is compared in wide parameter, it is only necessary to carry out outline identification to the image of the vehicle of acquisition and obtain specific parameter logistic value
The tracking for completing the unrecognized vehicle of number plate, the details without carrying out image compare, and improve tracking efficiency, and due to using
The distance of the form of parameter logistic value, the image of candid photograph does not constitute influence to the tracking of final vehicle, expands tracking and compares
Range.
In a possible embodiment, the inquiry comparison module 103 is specifically used for:
Calculate separately the vehicle overall profile and the corresponding overall profile area of the component outline and component outline
Area chases after the tracking vehicle according to the area ratio value of the overall profile area and the component outline area
Track.
In a possible embodiment, the inquiry comparison module 103 is specifically used for:
Calculate separately the vehicle overall profile and the corresponding overall profile length of the component outline and component outline
Length chases after the tracking vehicle according to the length ratio value of the overall profile length and the component outline length
Track.
In a possible embodiment, the preset component includes car light component, and the component outline length includes vehicle
The outer peripheral profile length of the car light of lamp part.
In a possible embodiment, the inquiry comparison module 103 is specifically used for:
The parameter logistic value of the parameter logistic value of vehicle to be determined in original image and the tracking vehicle is compared
It is right, the vehicle to be determined for meeting the first preset condition is determined as target vehicle, wherein the vehicle to be determined is in original graph
Vehicle as that can not identify vehicle license in data;
The acquisition time and collecting location of the determining original image comprising target vehicle are simultaneously fed back.
In a possible embodiment, it is described inquiry comparison module 103 be specifically used for: if in original image to true
The comparison value for determining the parameter logistic value of vehicle and the parameter logistic value of the tracking vehicle is unsatisfactory for the first preset condition, then by institute
The image of the image and the vehicle to be determined of stating tracking vehicle is compared, will be described if meeting the second preset condition
Vehicle to be determined is determined as target vehicle.
In a possible embodiment, the inquiry comparison module 103 is specifically used for: described by the tracking vehicle
The image of image and the vehicle to be determined is compared, if meeting the second preset condition, the vehicle to be determined is true
Being set to target vehicle includes:
The local feature for extracting the image of the tracking vehicle and the image of the vehicle to be determined, passes through local feature
Comparison obtains vehicle similarity, if the vehicle similarity is greater than preset threshold, the vehicle to be determined is determined as mesh
Mark vehicle.
The present embodiment provides a kind of identification equipment on the basis of the various embodiments described above, and Fig. 6 is that the embodiment of the present application mentions
The structural schematic diagram of a kind of identification equipment supplied, as shown in fig. 6, the identification equipment includes: memory 201, processor
(Central Processing Unit, CPU) 202, Peripheral Interface 203, camera 205, power management chip 208, input/
(I/O) subsystem 209, touch screen 212, Wifi module 213, other input/control devicess 210 and outside port 204 are exported,
These components are communicated by one or more communication bus or signal wire 207.
It should be understood that diagram identification equipment is only an example for identifying equipment, and identify that equipment can have
Have than shown in the drawings more or less component, two or more components can be combined, or can have not
Same component configuration.Various parts shown in the drawings can include one or more signal processings and/or dedicated integrated electricity
It is realized in the combination of hardware, software or hardware and software including road.
Just the identification equipment provided in this embodiment for fake license plate vehicle identification is described in detail below.
Memory 201, the memory 201 can be accessed by CPU202, Peripheral Interface 203 etc., and the memory 201 can
It can also include nonvolatile memory to include high-speed random access memory, such as one or more disk memory,
Flush memory device or other volatile solid-state parts.
The peripheral hardware that outputs and inputs of equipment can be connected to CPU202 and deposited by Peripheral Interface 203, the Peripheral Interface 203
Reservoir 201.
I/O subsystem 209, the I/O subsystem 209 can be by the input/output peripherals in equipment, such as touch screen 212
With other input/control devicess 210, it is connected to Peripheral Interface 203.I/O subsystem 209 may include 2091 He of display controller
For controlling one or more input controllers 2092 of other input/control devicess 210.Wherein, one or more input controls
Device 2092 processed receives electric signal from other input/control devicess 210 or sends electric signal to other input/control devicess 210,
Other input/control devicess 210 may include physical button (push button, rocker buttons etc.), slide switch, control stick, point
Hit idler wheel.It is worth noting that input controller 2092 can with it is following any one connect: keyboard, infrared port, USB interface
And the indicating equipment of such as mouse.
Touch screen 212, the touch screen 212 are the input interface and output interface between user terminal and user, can
It is shown to user depending on output, visual output may include figure, text, icon, video etc..
Display controller 2091 in I/O subsystem 209 receives electric signal from touch screen 212 or sends out to touch screen 212
Electric signals.Touch screen 212 detects the contact on touch screen, and the contact that display controller 2091 will test is converted to and is shown
The interaction of user interface object on touch screen 212, i.e. realization human-computer interaction, the user interface being shown on touch screen 212
Object can be the icon of running game, the icon for being networked to corresponding network etc..It is worth noting that equipment can also include light
Mouse, light mouse are the extensions for the touch sensitive surface for not showing the touch sensitive surface visually exported, or formed by touch screen.
Power management chip 208, the hardware for being connected by CPU202, I/O subsystem and Peripheral Interface are powered
And power management.
It is arbitrarily real that the application can be performed in the vehicle tracking device and identification equipment of the identification equipment provided in above-described embodiment
The car tracing method for applying identification equipment provided by example has and executes the corresponding functional module of this method and beneficial effect.Not
The technical detail of detailed description in the above-described embodiments, reference can be made to the vehicle of identification equipment provided by the application any embodiment
Method for tracing.
The embodiment of the present application also provides a kind of storage medium comprising identifying machine executable instructions, and the identification equipment can
It executes instruction when being executed by identification device handler for executing a kind of car tracing method, this method comprises:
The vehicle image captured is obtained, the vehicle that vehicle license can not be identified in the vehicle image is determined as to track vehicle
?;
Determine the vehicle overall profile of the tracking vehicle and the component outline of preset component;
The raw image data acquired in preset range is inquired, according to the vehicle overall profile and the component outline
Parameter logistic value is tracked generation tracing path to the tracking vehicle.
In a possible embodiment, the parameter logistic according to the vehicle overall profile and the component outline
Value is tracked the tracking vehicle
Calculate separately the vehicle overall profile and the corresponding overall profile area of the component outline and component outline
Area chases after the tracking vehicle according to the area ratio value of the overall profile area and the component outline area
Track.
In a possible embodiment, the parameter logistic according to the vehicle overall profile and the component outline
Value is tracked the tracking vehicle
Calculate separately the vehicle overall profile and the corresponding overall profile length of the component outline and component outline
Length chases after the tracking vehicle according to the length ratio value of the overall profile length and the component outline length
Track.
In a possible embodiment, the preset component includes car light component, and the component outline length includes vehicle
The outer peripheral profile length of the car light of lamp part.
In a possible embodiment, the parameter logistic according to the vehicle overall profile and the component outline
Value is tracked the tracking vehicle
The parameter logistic value of the parameter logistic value of vehicle to be determined in original image and the tracking vehicle is compared
It is right, the vehicle to be determined for meeting the first preset condition is determined as target vehicle, wherein the vehicle to be determined is in original graph
Vehicle as that can not identify vehicle license in data;
The acquisition time and collecting location of the determining original image comprising target vehicle are simultaneously fed back.
In a possible embodiment, if the parameter logistic value and the tracking of the vehicle to be determined in original image
The comparison value of the parameter logistic value of vehicle is unsatisfactory for the first preset condition, then by the tracking image of vehicle and described to be determined
The image of vehicle is compared, if meeting the second preset condition, the vehicle to be determined is determined as target vehicle.
In a possible embodiment, it is described by it is described tracking vehicle image and the vehicle to be determined image into
Row compares, if meeting the second preset condition, the vehicle to be determined, which is determined as target vehicle, includes:
The local feature for extracting the image of the tracking vehicle and the image of the vehicle to be determined, passes through local feature
Comparison obtains vehicle similarity, if the vehicle similarity is greater than preset threshold, the vehicle to be determined is determined as mesh
Mark vehicle.
Storage medium --- any various types of memory devices or storage equipment.Term " storage medium " is intended to wrap
It includes: install medium, such as CD-ROM, floppy disk or magnetic tape equipment;Computer system memory or random access memory, such as
DRAM, DDR RAM, SRAM, EDO RAM, Lan Basi (Rambus) RAM etc.;Nonvolatile memory, such as flash memory, magnetic medium
(such as hard disk or optical storage);Register or the memory component of other similar types etc..Storage medium can further include other
Memory of type or combinations thereof.In addition, storage medium can be located at program in the first computer system being wherein performed,
Or can be located in different second computer systems, second computer system is connected to the by network (such as internet)
One computer system.Second computer system can provide program instruction to the first computer for executing." storage is situated between term
Matter " may include may reside in different location (such as by network connection different computer systems in) two or
More storage mediums.Storage medium can store the program instruction that can be performed by one or more processors and (such as implement
For computer program).
Certainly, a kind of storage medium comprising computer executable instructions, computer provided by the embodiment of the present application
The car tracing method operation that executable instruction is not limited to the described above, can also be performed provided by the application any embodiment
Relevant operation in car tracing method.
Note that above are only the preferred embodiment and institute's application technology principle of the application.It will be appreciated by those skilled in the art that
The application is not limited to specific embodiment described here, be able to carry out for a person skilled in the art it is various it is apparent variation,
The protection scope readjusted and substituted without departing from the application.Therefore, although being carried out by above embodiments to the application
It is described in further detail, but the application is not limited only to above embodiments, in the case where not departing from the application design, also
It may include more other equivalent embodiments, and scope of the present application is determined by the scope of the appended claims.
Claims (10)
1. car tracing method characterized by comprising
The vehicle image captured is obtained, the vehicle that vehicle license can not be identified in the vehicle image is determined as to track vehicle;
Determine the vehicle overall profile of the tracking vehicle and the component outline of preset component;
Inquire the raw image data acquired in preset range, the parameter according to the vehicle overall profile and the component outline
Ratio value is tracked generation tracing path to the tracking vehicle.
2. the method according to claim 1, wherein described according to the vehicle overall profile and the component wheel
Wide parameter logistic value, which is tracked the tracking vehicle, includes:
The vehicle overall profile and the corresponding overall profile area of the component outline and component outline area are calculated separately,
The tracking vehicle is tracked according to the area ratio value of the overall profile area and the component outline area.
3. the method according to claim 1, wherein described according to the vehicle overall profile and the component wheel
Wide parameter logistic value, which is tracked the tracking vehicle, includes:
The vehicle overall profile and the corresponding overall profile length of the component outline and component outline length are calculated separately,
The tracking vehicle is tracked according to the length ratio value of the overall profile length and the component outline length.
4. according to the method described in claim 3, it is characterized in that, the preset component includes car light component, the component wheel
Wide length includes the outer peripheral profile length of car light of car light component.
5. method according to any of claims 1-4, which is characterized in that it is described according to the vehicle overall profile and
The parameter logistic value of the component outline is tracked the tracking vehicle
The parameter logistic value of the parameter logistic value of vehicle to be determined in original image and the tracking vehicle is compared, it will
The vehicle to be determined for meeting the first preset condition is determined as target vehicle, wherein the vehicle to be determined is in original image number
The vehicle of vehicle license can not be identified in;
The acquisition time and collecting location of the determining original image comprising target vehicle are simultaneously fed back.
6. according to the method described in claim 5, it is characterized in that, the if parameter logistic of the vehicle to be determined in original image
The comparison value of value and the parameter logistic value of the tracking vehicle is unsatisfactory for the first preset condition, then by the image of the tracking vehicle
It is compared with the image of the vehicle to be determined, if meeting the second preset condition, the vehicle to be determined is determined as
Target vehicle.
7. according to the method described in claim 6, it is characterized in that, described by the image of the tracking vehicle and described to be determined
The image of vehicle is compared, if meeting the second preset condition, the vehicle to be determined, which is determined as target vehicle, includes:
The local feature for extracting the image of the tracking vehicle and the image of the vehicle to be determined, is compared by local feature
Vehicle similarity is obtained, if the vehicle similarity is greater than preset threshold, the vehicle to be determined is determined as target carriage
?.
8. vehicle tracking device characterized by comprising
Vehicle determining module is tracked, for obtaining the vehicle image captured, vehicle license will can not be identified in the vehicle image
Vehicle be determined as track vehicle;
Characteristic determination module, for determining the vehicle overall profile of the tracking vehicle and the component outline of preset component;
Inquire comparison module, for inquiring the raw image data acquired in preset range, according to the vehicle overall profile and
The parameter logistic value of the component outline is tracked generation tracing path to the tracking vehicle.
9. a kind of identification equipment, comprising: processor, memory and storage are on a memory and the meter that can run on a processor
Calculation machine program, which is characterized in that the processor is realized when executing the computer program such as any one of claim 1-7 institute
The car tracing method stated.
10. a kind of storage medium comprising identifying machine executable instructions, which is characterized in that the identification machine executable instructions
When being executed by identification device handler for executing such as car tracing method of any of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811153051.2A CN109389622B (en) | 2018-09-30 | 2018-09-30 | Vehicle tracking method, device, identification equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811153051.2A CN109389622B (en) | 2018-09-30 | 2018-09-30 | Vehicle tracking method, device, identification equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109389622A true CN109389622A (en) | 2019-02-26 |
CN109389622B CN109389622B (en) | 2019-12-13 |
Family
ID=65418227
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811153051.2A Active CN109389622B (en) | 2018-09-30 | 2018-09-30 | Vehicle tracking method, device, identification equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109389622B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110135318A (en) * | 2019-05-08 | 2019-08-16 | 佳都新太科技股份有限公司 | Cross determination method, apparatus, equipment and the storage medium of vehicle record |
CN111444766A (en) * | 2020-02-24 | 2020-07-24 | 浙江科技学院 | Vehicle tracking method and device based on image processing, computer equipment and storage medium |
CN111474914A (en) * | 2020-02-24 | 2020-07-31 | 李娟娟 | Fault code big data storage system |
CN114373216A (en) * | 2021-12-07 | 2022-04-19 | 图湃(北京)医疗科技有限公司 | Eye movement tracking method, device, equipment and storage medium for anterior segment OCTA |
CN116453071A (en) * | 2023-04-17 | 2023-07-18 | 北京睿芯通量科技发展有限公司 | Identification method and device of vehicle attribute information, electronic equipment and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2010045350A1 (en) * | 2008-10-14 | 2010-04-22 | Hemisphere Gps Llc | Satellite based vehicle guidance control in straight and contour modes |
CN202422423U (en) * | 2011-12-20 | 2012-09-05 | 杭州海康威视系统技术有限公司 | Vehicle license plate recognition device and system |
CN105139659A (en) * | 2015-10-09 | 2015-12-09 | 东方网力科技股份有限公司 | Vehicle license plate recognition method and device |
CN105788286A (en) * | 2016-05-19 | 2016-07-20 | 湖南博广信息科技有限公司 | Intelligent red light running identifying system and vehicle behavior detecting and capturing method |
-
2018
- 2018-09-30 CN CN201811153051.2A patent/CN109389622B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2010045350A1 (en) * | 2008-10-14 | 2010-04-22 | Hemisphere Gps Llc | Satellite based vehicle guidance control in straight and contour modes |
CN202422423U (en) * | 2011-12-20 | 2012-09-05 | 杭州海康威视系统技术有限公司 | Vehicle license plate recognition device and system |
CN105139659A (en) * | 2015-10-09 | 2015-12-09 | 东方网力科技股份有限公司 | Vehicle license plate recognition method and device |
CN105788286A (en) * | 2016-05-19 | 2016-07-20 | 湖南博广信息科技有限公司 | Intelligent red light running identifying system and vehicle behavior detecting and capturing method |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110135318A (en) * | 2019-05-08 | 2019-08-16 | 佳都新太科技股份有限公司 | Cross determination method, apparatus, equipment and the storage medium of vehicle record |
CN111444766A (en) * | 2020-02-24 | 2020-07-24 | 浙江科技学院 | Vehicle tracking method and device based on image processing, computer equipment and storage medium |
CN111474914A (en) * | 2020-02-24 | 2020-07-31 | 李娟娟 | Fault code big data storage system |
CN111474914B (en) * | 2020-02-24 | 2020-12-01 | 安徽省华腾农业科技有限公司经开区分公司 | Fault code big data storage system |
CN111444766B (en) * | 2020-02-24 | 2021-07-20 | 浙江科技学院 | Vehicle tracking method and device based on image processing, computer equipment and storage medium |
CN114373216A (en) * | 2021-12-07 | 2022-04-19 | 图湃(北京)医疗科技有限公司 | Eye movement tracking method, device, equipment and storage medium for anterior segment OCTA |
CN116453071A (en) * | 2023-04-17 | 2023-07-18 | 北京睿芯通量科技发展有限公司 | Identification method and device of vehicle attribute information, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN109389622B (en) | 2019-12-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109389622A (en) | Car tracing method, apparatus, identification equipment and storage medium | |
Heikkila et al. | A real-time system for monitoring of cyclists and pedestrians | |
US7630515B2 (en) | Method of and apparatus for setting image-capturing conditions, and computer program | |
CN109376617A (en) | Counterfeit vehicle registration plate identification method, device, identification equipment and storage medium | |
KR100883889B1 (en) | Car type recognition apparatus and method using contours image of car | |
CN109325456A (en) | Target identification method, device, target identification equipment and storage medium | |
CN111476234B (en) | License plate character shielding recognition method and device, storage medium and intelligent equipment | |
KR102493930B1 (en) | Apparatus and method for controlling traffic signal based on reinforcement learning | |
WO2022077264A1 (en) | Object recognition method, object recognition apparatus, and electronic device | |
WO2021093625A1 (en) | Intelligent analysis algorithm selection method, apparatus and system, and electronic device | |
JP7303384B2 (en) | Passenger number counting system and passenger number counting device | |
CN113380069A (en) | Street lamp-based roadside parking system and method thereof | |
CN103778790B (en) | A kind of vehicle flowrate square wave statistic law based on video sequence | |
CN110880205A (en) | Parking charging method and device | |
JP2009169827A (en) | License plate recognition device, method, and program | |
KR20120114099A (en) | Apparatus and method for car type recognition and method for coming and going managing method based on car type recognition | |
CN113688717A (en) | Image recognition method and device and electronic equipment | |
CN108831158A (en) | It disobeys and stops monitoring method, device and electric terminal | |
CN117058912A (en) | Method and device for detecting abnormal parking of inspection vehicle, storage medium and electronic equipment | |
CN112270258A (en) | Violation information acquisition method and device for non-motor vehicle | |
CN114693722B (en) | Vehicle driving behavior detection method, detection device and detection equipment | |
US11917325B2 (en) | Automated scope limiting for video analytics | |
CN103366598A (en) | Vehicle in-place parking detection system and detecting method | |
CN111583215A (en) | Intelligent damage assessment method and device for damage image, electronic equipment and storage medium | |
TWI718459B (en) | Image analyzing method and related image analyzing device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CP01 | Change in the name or title of a patent holder |
Address after: Room 306, zone 2, building 1, Fanshan entrepreneurship center, Panyu energy saving technology park, No. 832 Yingbin Road, Donghuan street, Panyu District, Guangzhou City, Guangdong Province Patentee after: Jiadu Technology Group Co.,Ltd. Address before: Room 306, zone 2, building 1, Fanshan entrepreneurship center, Panyu energy saving technology park, No. 832 Yingbin Road, Donghuan street, Panyu District, Guangzhou City, Guangdong Province Patentee before: PCI-SUNTEKTECH Co.,Ltd. |
|
CP01 | Change in the name or title of a patent holder |