CN106448161A - Road monitoring method and road monitoring device - Google Patents
Road monitoring method and road monitoring device Download PDFInfo
- Publication number
- CN106448161A CN106448161A CN201610875518.9A CN201610875518A CN106448161A CN 106448161 A CN106448161 A CN 106448161A CN 201610875518 A CN201610875518 A CN 201610875518A CN 106448161 A CN106448161 A CN 106448161A
- Authority
- CN
- China
- Prior art keywords
- fire
- information
- image
- vehicle
- condition
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
Abstract
The invention discloses a monitoring method for road fire/smoke alarms. The method is realized by an intelligent monitoring information hierarchical structure model which includes an environment perception layer, an object layer, a feature layer, a semantic layer and a decision layer. The method comprises the following steps: acquiring a monitored image and a captured location; judging whether there is a vehicle having an abnormal reflection condition according to the monitored image; extracting a vehicle area image with abnormal reflection from the monitored image; using a neural network processing unit in a field camera to process the vehicle area image in order to identify whether fire occurs, if yes, acquiring and storing a fire parameter and the information of related vehicles in the feature layer; determining a fire category or level and storing the fire category or level in the semantic layer according to the fire parameter; generating early warning or advice information according to the captured location and the fire category or level and storing the early warning or advice information in the decision layer. It can analyze whether the vehicles on the road are fired and generate early warning or advice information to process and identify the monitored image. The invention also discloses a road monitoring device.
Description
Technical field
The present invention relates to road monitoring technology, particularly to a kind of road monitoring method and road monitoring apparatus.
Background technology
Current road monitoring meanss typically be only capable of obtain monitoring video, but can not to vehicle on road it may happen that fire
Feelings are identified judging, are unfavorable for understanding traffic as early as possible and in time the condition of a fire are processed.And by artificial checking monitoring
Image, not only takes time and effort, and judge accuracy and real-time it is difficult to ensure that.
Content of the invention
Embodiments of the present invention are intended at least solve one of technical problem present in prior art.For this reason, the present invention
Embodiment need to provide a kind of and road monitoring method and road monitoring apparatus.
The present invention provides a kind of road monitoring method, and described road monitoring method adopts information level structural model to realize,
Described information hierarchical structure model includes environment sensing layer, object layer, characteristic layer, semantic layer and decision-making level, described road monitoring
Method includes：
Obtain monitoring image and spot for photography and be stored in described environment sensing layer；
Determine whether that vehicle has abnormal reflective situation according to monitoring image；
If abnormal reflective with the presence of vehicle, extract from monitoring image and there is abnormal reflective vehicle region image and be stored in
Described object layer；
The magazine neural-network processing unit of site of deployment processes vehicle region image to recognize whether the condition of a fire, if
Exist, then obtain condition of a fire parametric image and be related to the information of vehicle and be stored in characteristic layer；
Condition of a fire classification or rank are judged according to condition of a fire parameter and is stored in semantic layer；
Produce early warning or advisory information and be stored in decision-making level according to spot for photography and condition of a fire classification or rank.
In embodiments of the present invention, by being processed to monitoring image and identifying, can analyze whether vehicle occurs fire
Feelings, and produce early warning or advisory information, thus being conducive to related personnel to understand the condition of a fire as early as possible and as early as possible situation is processed.Can
Solve some problems of prior art.
In some embodiments, described early warning or advisory information are produced simultaneously according to spot for photography and condition of a fire classification or rank
The step being stored in decision-making level produces described early warning or advisory information at Traffic monitoring end.
In some embodiments, described road monitoring method includes：
Produce information at Traffic monitoring end and be stored in described semantic layer；Described information include condition of a fire classification or
Rank, described spot for photography and/or shooting time, described shooting time be exist the condition of a fire described vehicle region image corresponding
The shooting time of described monitoring image.
In some embodiments, described road monitoring method includes：
Process the identity information to obtain described vehicle for the described vehicle region image；Described information includes described identity
Information.
In some embodiments, described road monitoring method includes：
Process the kinematic parameter to obtain described vehicle for the described vehicle region image；Described information also includes described fortune
Dynamic parameter.
In some embodiments, described road monitoring method also includes：
Send described early warning or advisory information to the corresponding described vehicle of described identity information.
In some embodiments, the magazine neural-network processing unit of described site of deployment processes vehicle region image
Judged whether with the presence or absence of flame or smog by detecting in described vehicle region image with the step recognizing whether the condition of a fire
There is the condition of a fire.
The present invention also provides a kind of road monitoring apparatus, and described road monitoring apparatus adopt information level structural model real
Existing, described information hierarchical structure model includes environment sensing layer, object layer, characteristic layer, semantic layer and decision-making level, described road prison
Control device includes：
Image collection module, for obtaining monitoring image and spot for photography and being stored in described environment sensing layer；
According to monitoring image, image judge module, for determining whether that vehicle has abnormal reflective situation；
Extraction module, for the presence of vehicle abnormal reflective when extract from monitoring image and there is abnormal reflective vehicle area
Area image is simultaneously stored in described object layer；
First processing module, processes vehicle region image to know for the magazine neural-network processing unit of site of deployment
Shi Foucun not the condition of a fire obtain condition of a fire parametric image and be related to the information of vehicle and be stored in characteristic layer in the presence of judging；
Parameter judge module, for judging condition of a fire classification or rank according to condition of a fire parameter and being stored in semantic layer；And
Decision-making module, produces early warning or advisory information and is stored in decision-making according to spot for photography and condition of a fire classification or rank
Layer.
In some embodiments, described decision-making module is used for producing described early warning or advisory information at Traffic monitoring end.
In some embodiments, described road monitoring apparatus include：
Reminding module, for producing information at Traffic monitoring end and being stored in described semantic layer；Described information
Including condition of a fire classification or rank, described spot for photography and/or shooting time, described shooting time is the described vehicle that there is the condition of a fire
The shooting time of the corresponding described monitoring image of area image.
In some embodiments, described road monitoring apparatus include：
Second processing module, for processing the identity information to obtain described vehicle for the described vehicle region image；Described carry
Show that information also includes described identity information.
In some embodiments, described road monitoring apparatus include：
3rd processing module, for processing the kinematic parameter to obtain described vehicle for the described vehicle region image；Described carry
Show that information also includes described kinematic parameter.
The additional aspect of embodiments of the present invention and advantage will be set forth in part in the description, partly will be from following
Description in become obvious, or recognized by the practice of embodiments of the present invention.
Brief description
The above-mentioned and/or additional aspect of embodiments of the present invention and advantage from reference to accompanying drawings below to embodiment
Will be apparent from description with easy to understand, wherein：
Fig. 1 is the schematic flow sheet of the road monitoring method of some embodiments of the present invention.
Fig. 2 is the high-level schematic functional block diagram of the road monitoring apparatus of some embodiments of the present invention.
Fig. 3 is the monitoring image of some embodiments of the present invention and the schematic diagram of vehicle region image.
Fig. 4 is the road monitoring method of some embodiments of the present invention or the Intelligent road monitoring of road monitoring apparatus employing
Message structure schematic diagram.
Fig. 5 is the road monitoring method of some embodiments of the present invention or the principle schematic of road monitoring apparatus.
Fig. 6 is the schematic flow sheet of the road monitoring method of some embodiments of the present invention.
Fig. 7 is the high-level schematic functional block diagram of the road monitoring apparatus of some embodiments of the present invention.
Fig. 8 is the schematic flow sheet of the road monitoring method of some embodiments of the present invention.
Fig. 9 is the high-level schematic functional block diagram of the road monitoring apparatus of some embodiments of the present invention.
Figure 10 is the schematic flow sheet of the road monitoring method of some embodiments of the present invention.
Figure 11 is the high-level schematic functional block diagram of the road monitoring apparatus of some embodiments of the present invention.
Specific embodiment
Embodiments of the present invention are described below in detail, the example of embodiment is shown in the drawings, wherein identical or class
As the label element that represents same or similar element from start to finish or there is same or like function.Below with reference to attached
The embodiment of figure description is exemplary, can only be used to explain embodiments of the present invention, and it is not intended that to the present invention
Embodiment restriction.
Refer to Fig. 1-5, the road monitoring method of embodiment of the present invention, road monitoring method adopts information level structure
Model realization, information level structural model may include environment sensing layer, object layer, characteristic layer, semantic layer and decision-making level, and road is supervised
Prosecutor method may include：
S1, obtains monitoring image 300 and spot for photography and is stored in environment sensing layer；
According to monitoring image 300, S2, determines whether that vehicle has abnormal reflective situation；
S3, if abnormal reflective with the presence of vehicle, extract from monitoring image 300 and there is abnormal reflective vehicle region image
310 and be stored in object layer；
S4, the magazine neural-network processing unit of site of deployment processes vehicle region image 310 to recognize whether
The condition of a fire, if existing, obtaining condition of a fire parametric image and being related to the information of vehicle and be stored in characteristic layer；
S5, judges condition of a fire classification or rank according to condition of a fire parameter and is stored in semantic layer；
S6, produces early warning or advisory information and is stored in decision-making level according to spot for photography and condition of a fire classification or rank.
Refer to Fig. 2, the road monitoring apparatus 100 of embodiment of the present invention may include image collection module 110, image is sentenced
Disconnected module 120, extraction module 130, first processing module 140, parameter judge module 150 and decision-making module 160, can be separately available
In realizing S1, S2, S3, S4, S5 and S6.That is, image collection module 110 can be used for obtaining monitoring image 300 and shoots
Place is simultaneously stored in environment sensing layer；Image judge module 120 can be used for determining whether that vehicle exists according to monitoring image 300
Abnormal reflective situation；Extraction module 130 can be used for the presence of vehicle abnormal reflective when from monitoring image 300 extract exist abnormal
Reflective vehicle region image 310 is simultaneously stored in object layer；First processing module 140 can be used for the magazine nerve of site of deployment
Network processing unit processes vehicle region image 310 to recognize whether the condition of a fire and to obtain condition of a fire Parameter Map in the presence of judging
Picture is simultaneously stored in characteristic layer；Parameter judge module 150 can be used for judging condition of a fire classification or rank according to condition of a fire parameter and being stored in
Semantic layer；Decision-making module 160 produces early warning or advisory information and is stored in decision-making according to spot for photography and condition of a fire classification or rank
Layer.
Wherein image collection module 110 may include image collecting device 111, such as monitoring camera, can be used for obtaining prison
Control image 300.Spot for photography obtains the place of monitoring image 300, the place that for example image collecting device 111 is located.Vehicle
Area image 310 may include the region of vehicle and the condition of a fire.The information being related to vehicle may include identity information or the motion ginseng of vehicle
Number information etc..
Current road monitoring meanss typically be only capable of obtain monitoring video, but can not to vehicle on road it may happen that fire
Feelings are identified judging, are unfavorable for understanding traffic as early as possible and in time the condition of a fire are processed.By artificial checking monitoring figure
As 300, not only take time and effort, and the accuracy and the real-time that judge it is difficult to ensure that.In embodiments of the present invention, by prison
Control image 300 is processed and is identified, can analyze whether vehicle occurs the condition of a fire, and produce early warning or advisory information, thus favorably
Understand the condition of a fire as early as possible in related personnel and as early as possible situation is processed.
Wherein, please refer to Fig. 3, in some embodiments, whether S4 can be by detecting in vehicle region image 310
There is flame or smog judges whether the condition of a fire.The first processing module 140 of some embodiments can be used for detecting vehicle area
Whether there is flame in area image 310 or smog judges whether the condition of a fire.Flame or smog are to can be used to determine whether fire
The distinguishing feature of feelings, and to be presented in monitoring image 300 be obvious feature, is easier to know using conventional images processing means
Not.
Refer to Fig. 3, existing image processing techniquess can achieve identification and the segmented extraction in vehicle and condition of a fire region, therefore
Vehicle region image 310 can be extracted in monitoring image 300, vehicle region image 310 can only may include vehicle and condition of a fire region
(as smog or flame region), to facilitate follow-up identifying processing.Extract vehicle region image 310 and can facilitate further identification point
Analysis.Please refer to Fig. 4, vehicle region image 310 is storable in object layer, carried by the monitoring image 300 of environment sensing layer
An area image 310 of picking up the car arrives object layer.
Refer to Fig. 4, in some embodiments of the present invention, road monitoring method or road monitoring apparatus 100 are using letter
Breath hierarchical structure model realization, this structure is a kind of intelligent monitoring information level structural model, it may include environment sensing layer, geography
Reference lamina, object layer, characteristic layer, semantic layer and decision-making level etc..Each level may be respectively used in storage information and processes different phase
Information, organic connection between level and level, from last layer, recalls information is processed, and result can be stored in next layer
Level.Wherein, geographical sign layer is not applied in embodiments of the present invention.
The bind mode of each level of intelligent monitoring information level structural model and information transmission order see Fig. 3.Wherein,
Environment sensing layer is the level on basis.Front-end collection equipment, is such as arranged at the monitoring camera of road, can be used for obtaining monitoring figure
As 300 and each frame monitoring image 300 corresponding time, place, these Back ground Informations can be stored in environment sensing layer and as
The basis that follow-up is processed.The corresponding place of monitoring image 300 can be the place that photographic head is located.
If detecting in monitoring image 300 with the presence of the vehicle condition of a fire, can carry from the monitoring image 300 of environment sensing layer
Take out and only comprise the vehicle region image 310 of vehicle and be stored in object layer.Vehicle region image 310 can be used as subsequent analysis fire
The basis of feelings, vehicle movable information and vehicle identity information.
From object layer transfer vehicle region image 310 and do analysis can obtain condition of a fire parametric image, vehicle movable information and
The related image of vehicle identity information, and it is stored in characteristic layer, and the basis as subsequent analysis.Condition of a fire parameter can be flame
Or the design parameter such as the size of smog, shade.Condition of a fire parametric image can be flame, the image of smog intercepting,
Can be used for subsequent treatment to analyze to obtain condition of a fire parameter.Similarly, the figure related to vehicle movable information and vehicle identity information
As carrying out Treatment Analysis, movable information and identity information can be obtained and be stored in semantic layer.Movable information and identity information are easy to
The relevant personnel understand the concrete condition of the vehicle that there is the condition of a fire, and such as license plate number, vehicle, travel direction and speed etc., thus do
Go out to deal carefully with.
To condition of a fire parameter and Treatment Analysis, fire analysis result, the classification of the such as condition of a fire or rank etc. can be obtained, can embody
The order of severity of the condition of a fire or urgency level.
Transfer condition of a fire classification or rank from semantic layer, early warning or advisory information can be produced according to condition of a fire classification or rank.Can
It is presented on Traffic monitoring end 100a, so that related management personnel know the condition of a fire and counte-rplan.
Can be to retain or delete according to the information that the analysis result in later stage determines each hierarchical storage.For example, by car
Each layer analysis of area image 310, find to have no the condition of a fire, can delete the relevant information of each hierarchical storage, or only retain ring
The Back ground Information of border sensing layer.If confirming, the condition of a fire in vehicle, can retain the relevant information of each level, to facilitate after treatment situation
The relevant personnel can transfer examination the later stage to investigate fire alarm reason, condition of a fire responsibility etc..So, effective information can be retained, reduce redundancy
Information.
Refer to Fig. 5, the image collection module 110 of road monitoring apparatus 100 may include the image acquisition being arranged at road
Device 111, such as images first-class, can be used for obtaining monitoring image 300 in real time, such as road monitoring video recording.Road monitoring apparatus 100
May also include the relevant device of Traffic monitoring end 100a.Traffic monitoring end 100a can be the Surveillance center of vehicle supervision department,
Equipped with related monitoring personnel, can be used for monitor in real time condition of road surface.In some embodiments, S6 is at Traffic monitoring end
100a produces early warning or advisory information, to facilitate monitoring personnel to understand the condition of a fire and the situation of periphery traffic in time.Some embodiment party
The decision-making module 160 of formula can be used for producing early warning or advisory information in Traffic monitoring end 100a.Advisory information can by voice or
The modes such as text prompt present.
Additionally, fully understanding the condition of a fire for convenience of Traffic monitoring end 100a, the more information of acquisition can be analyzed and be presented on friendship
Logical monitoring side 100a.
For example, Fig. 6-7 are referred to, in some embodiments, road monitoring method may include：S8, at Traffic monitoring end
100a produces information and is stored in semantic layer；Information may include condition of a fire classification or rank, spot for photography and/or shooting
Time, shooting time is the shooting time of the corresponding monitoring image 300 of vehicle region image 310 that there is the condition of a fire.S8 can be by certain
The reminding module 180 of the road monitoring apparatus 100 of a little embodiments is realized, and that is, reminding module 180 can be used at Traffic monitoring end
100a produces information and is stored in semantic layer.
Advisory information can be presented by modes such as voice or text prompt.For example, prompting is " in T time, S section, in appearance
Degree rank fire alarm, with relatively large dense smoke, no flame ".Thus helping relevant monitoring personnel to understand the condition of a fire.
, all to there being shooting time, the vehicle region image 310 of therefore storage fire condition is corresponding for the every frame of monitoring image 300
The monitoring image 300 of frame shooting time, for more accurate fire condition time of origin.By by time, place, condition of a fire class
And the information such as rank is presented on Traffic monitoring end 100a, associated monitoring personnel can not facilitated to fully understand information, more had with making
The process decision-making of effect, thus the prevention generation of more major break down or the loss of minimizing accident.
Further, the information being presented on Traffic monitoring end 100a may also include the identity information of vehicle.
For example, Fig. 8-9 are referred to, in some embodiments, road monitoring method may include：S4a, processes vehicle region
Image 310 is to obtain the identity information of vehicle；Information may include identity information.S4a can be by the monitoring of some embodiments
Second processing module 140a of device is realized, and that is, Second processing module 140a can be used for processing vehicle region image 310 to obtain
The identity information of vehicle.
Wherein identity information can be the license plate number of vehicle, brand, vehicle etc..Advisory information can be carried by voice or word
The mode such as show presents.For example, " in T time, S section, license plate number is 123456, the jubilee wagen of YY brand occurs for prompting
Intermediate-grade fire alarm, with relatively large dense smoke, no flame ".Thus helping relevant monitoring personnel to understand the condition of a fire and the condition of a fire occurs
Vehicle, to take effective process measure to relevant vehicle as early as possible.
The relevant image of identity information, such as image of car plate, logo etc. can be obtained first from vehicle region image 310
And be stored in characteristic layer, then these images are processed to obtain the identity informations such as license plate number, brand, vehicle and to be stored in language
Adopted layer.
Further, the information being presented on Traffic monitoring end 100a may also include the movable information of vehicle.For example, please
Refering to Figure 10-11, in some embodiments, road monitoring method may include：S4b, processes vehicle region image 310 to obtain
The kinematic parameter of vehicle；Information may include kinematic parameter.S4b can be by the road monitoring apparatus 100 of some embodiments
3rd processing module 140b is realized, and that is, the 3rd processing module 140b can be used for processing vehicle region image 310 to obtain vehicle
Kinematic parameter.
Wherein kinematic parameter may include the direction of motion of vehicle, movement velocity etc..Advisory information can pass through voice or word
The modes such as prompting present.For example, " in T time, S section, license plate number is that the jubilee wagen of 123456, YY brand goes out for prompting
Existing intermediate-grade fire alarm, with relatively large dense smoke, no flame, this vehicle is just with the speed of AA towards ZZ direction running ".Thus helping
Relevant monitoring personnel understands the condition of a fire, the vehicle of the condition of a fire and the kinestate of vehicle, to take to relevant vehicle as early as possible
Effective process measure.
Can obtain the relevant image of kinematic parameter first from vehicle region image 310, such as predetermined time interval many
The image that comprises this vehicle is simultaneously stored in characteristic layer, then these images are processed travel speed to obtain this vehicle and
The kinematic parameters such as direction are simultaneously stored in semantic layer.
In some embodiments that may include S4a, road monitoring method may also include：S9, sends early warning or recommendation letter
Cease vehicle corresponding to identity information.Wherein identity information can be license plate number of vehicle etc..
The networked system of vehicle and road monitoring apparatus 100 or Traffic monitoring end 100a can be set up, detecting, fire occurs
During feelings, send early warning or advisory information to the corresponding vehicle of identity information to remind the driver of this vehicle.So, driver can be helped
Understand that the condition of a fire is simultaneously adopted an effective measure, to avoid the generation of more major accident, prevent or minimizing personnel and property loss.
To sum up, embodiment of the present invention can be analyzed to the condition of a fire on road, and by related important information with Information Level
The structure of level is stored, and necessary information or early warning information are presented to the relevant personnel.Related personnel can be helped to fully understand
The condition of a fire, to make appropriate process.May also aid in relevant personnel's later stage gathering information to be checked, to seek cause of accident or to look for
Seek the accident responsibility of associated vehicle or personnel.
The road monitoring method of embodiment of the present invention and device can be used for road, such as highway, especially preferably
Apply in the section that fire hazards easily occur.
" " center ", " longitudinal ", " horizontal ", " long it is to be understood that term in the description of embodiments of the present invention
Degree ", " width ", " thickness ", " on ", D score, "front", "rear", "left", "right", " vertical ", " level ", " top ", " bottom ", " interior ",
" outward ", the orientation of instruction such as " clockwise ", " counterclockwise " or position relationship are based on orientation shown in the drawings or position relationship, only
It is to describe for the ease of describing embodiments of the present invention and simplification, rather than indicate or imply that the device of indication or element are necessary
There is specific orientation, with specific azimuth configuration and operation, therefore it is not intended that restriction to embodiments of the present invention.
Additionally, term " first ", " second " are only used for describing purpose, and it is not intended that indicating or imply relative importance or implying
Indicate the quantity of indicated technical characteristic.Thus, define " first ", the feature of " second " can be expressed or impliedly wrap
Include one or more described feature.In the description of embodiments of the present invention, " multiple " are meant that two or two
More than, unless otherwise expressly limited specifically.
In the description of embodiments of the present invention, it should be noted that unless otherwise clearly defined and limited, term
" installation ", " being connected ", " connection " should be interpreted broadly, for example, it may be being fixedly connected or being detachably connected, or one
Body ground connects；Can be to be mechanically connected or electrically connect or can mutually communicate；Can be to be joined directly together it is also possible to lead to
Cross intermediary to be indirectly connected to, can be the connection of two element internals or the interaction relationship of two elements.For ability
For the those of ordinary skill in domain, above-mentioned term specifically containing in embodiments of the present invention can be understood as the case may be
Justice.
In embodiments of the present invention, unless otherwise clearly defined and limited, fisrt feature second feature it
" on " or D score can include the first and second feature directly contacts it is also possible to include the first and second features be not directly to connect
Touch but by the other characterisation contact between them.And, fisrt feature second feature " on ", " top " and " on
Face " includes fisrt feature directly over second feature and oblique upper, or to be merely representative of fisrt feature level height be higher than second special
Levy.Fisrt feature second feature " under ", " lower section " and " below " include fisrt feature directly over second feature and tiltedly on
Side, or it is merely representative of fisrt feature level height less than second feature.
Following disclosure provides many different embodiments or example for realizing embodiments of the present invention not
Same structure.In order to simplify the disclosure of embodiments of the present invention, hereinafter the part and setting of specific examples is described.When
So, they are only merely illustrative, and purpose does not lie in the restriction present invention.Additionally, embodiments of the present invention can be in different examples
Son in repeat reference numerals and/or reference letter, this repeat to be for purposes of simplicity and clarity, itself does not indicate and is begged for
By the relation between various embodiments and/or setting.Additionally, the various specific technique that embodiments of the present invention provide
With the example of material, but those of ordinary skill in the art can be appreciated that the application of other techniques and/or making of other materials
With.
In the description of this specification, reference term " embodiment ", " some embodiments ", " schematically enforcement
The description of mode ", " example ", " specific example " or " some examples " etc. means the tool with reference to described embodiment or example description
Body characteristicses, structure, material or feature are contained at least one embodiment or the example of the present invention.In this manual,
Identical embodiment or example are not necessarily referring to the schematic representation of above-mentioned term.And, the specific features of description, knot
Structure, material or feature can combine in any one or more embodiments or example in an appropriate manner.
In flow chart or here any process described otherwise above or method description are construed as, represent and include
The module of the code of executable instruction of one or more steps for realizing specific logical function or process, fragment or portion
Point, and the scope of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discuss suitable
Sequence, including according to involved function by substantially simultaneously in the way of or in the opposite order, carry out perform function, this should be by the present invention
Embodiment person of ordinary skill in the field understood.
Represent in flow charts or here logic described otherwise above and/or step, for example, it is possible to be considered as to use
In the order list of the executable instruction realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (system as computer based system, including processor or other can hold from instruction
Row system, device or equipment instruction fetch the system of execute instruction) use, or with reference to these instruction execution systems, device or set
Standby and use.For the purpose of this specification, " computer-readable medium " can any can be comprised, store, communicate, propagate or pass
Defeated program is for instruction execution system, device or equipment or the dress using with reference to these instruction execution systems, device or equipment
Put.The more specifically example (non-exhaustive list) of computer-readable medium includes following：There is the electricity of one or more wirings
Connecting portion (electronic installation), portable computer diskette box (magnetic device), random access memory (RAM), read only memory
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device, and portable optic disk is read-only deposits
Reservoir (CDROM).In addition, computer-readable medium can even is that the paper that can print described program thereon or other are suitable
Medium, because edlin, interpretation or if necessary with it can then be entered for example by carrying out optical scanning to paper or other media
His suitable method is processed to electronically obtain described program, is then stored in computer storage.
It should be appreciated that each several part of embodiments of the present invention can be with hardware, software, firmware or combinations thereof Lai real
Existing.In the above-described embodiment, multiple steps or method can be with storage in memory and by suitable instruction execution systems
The software of execution or firmware are realizing.For example, if realized with hardware, with the same in another embodiment, available ability
Any one of following technology known to domain or their combination are realizing：Have for logic function is realized to data signal
The discrete logic of logic gates, has the special IC of suitable combinational logic gate circuit, programmable gate array
(PGA), field programmable gate array (FPGA) etc..
Those skilled in the art are appreciated that to realize all or part step that above-described embodiment method carries
Suddenly the program that can be by completes come the hardware to instruct correlation, and described program can be stored in a kind of computer-readable storage medium
In matter, this program upon execution, including one or a combination set of the step of embodiment of the method.
Additionally, each functional unit in various embodiments of the present invention can integrated in a processor it is also possible to
It is that unit is individually physically present it is also possible to two or more units are integrated in a module.Above-mentioned integrated mould
Block both can be to be realized in the form of hardware, it would however also be possible to employ the form of software function module is realized.Described integrated module is such as
Fruit using in the form of software function module realize and as independent production marketing or use when it is also possible to be stored in a computer
In read/write memory medium.Storage medium mentioned above can be read only memory, disk or CD etc..
Although embodiments of the invention have been shown and described above it is to be understood that above-described embodiment is example
Property it is impossible to be interpreted as limitation of the present invention, those of ordinary skill in the art within the scope of the invention can be to above-mentioned
Embodiment is changed, changes, replacing and modification.
Claims (12)
1. a kind of road monitoring method is it is characterised in that described road monitoring method adopts the realization of information level structural model, institute
State information level structural model and include environment sensing layer, object layer, characteristic layer, semantic layer and decision-making level, described road monitoring side
Method includes：
Obtain monitoring image and spot for photography and be stored in described environment sensing layer；
Determine whether that vehicle has abnormal reflective situation according to monitoring image；
If abnormal reflective with the presence of vehicle, extract from monitoring image and there is abnormal reflective vehicle region image and be stored in described
Object layer；
The magazine neural-network processing unit of site of deployment processes vehicle region image to recognize whether the condition of a fire, if depositing
Then obtaining condition of a fire parametric image and be related to the information of vehicle and be stored in characteristic layer；
Condition of a fire classification or rank are judged according to condition of a fire parameter and is stored in semantic layer；And
Produce early warning or advisory information and be stored in decision-making level according to spot for photography and condition of a fire classification or rank.
2. road monitoring method as claimed in claim 1 it is characterised in that described according to spot for photography and condition of a fire classification or level
Chan Sheng not early warning or advisory information be stored in the step of decision-making level and produce described early warning or advisory information at Traffic monitoring end.
3. road monitoring method as claimed in claim 1 is it is characterised in that described road monitoring method includes：
Produce information at Traffic monitoring end and be stored in described semantic layer；Described information includes condition of a fire classification or level
Not, described spot for photography and/or shooting time, described shooting time is the corresponding institute of described vehicle region image that there is the condition of a fire
State the shooting time of monitoring image.
4. road monitoring method as claimed in claim 3 is it is characterised in that described road monitoring method includes：
Process the identity information to obtain described vehicle for the described vehicle region image；Described information includes described identity letter
Breath.
5. road monitoring method as claimed in claim 4 is it is characterised in that described road monitoring method includes：
Process the kinematic parameter to obtain described vehicle for the described vehicle region image；Described information also includes described motion ginseng
Number.
6. road monitoring method as claimed in claim 4 it is characterised in that
Described road monitoring method also includes：
Send described early warning or advisory information to the corresponding described vehicle of described identity information.
7. road monitoring method as claimed in claim 1 is it is characterised in that at the magazine neutral net of described site of deployment
Whether reason cell processing vehicle region image passes through to detect in described vehicle region image with the step recognizing whether the condition of a fire
There is flame or smog judges whether the condition of a fire.
8. a kind of road monitoring apparatus are it is characterised in that described road monitoring apparatus adopt the realization of information level structural model, institute
State information level structural model and include environment sensing layer, object layer, characteristic layer, semantic layer and decision-making level, described road monitoring dress
Put including：
Image collection module, for obtaining monitoring image and spot for photography and being stored in described environment sensing layer；
According to monitoring image, image judge module, for determining whether that vehicle has abnormal reflective situation；
Extraction module, for the presence of vehicle abnormal reflective when extract from monitoring image and there is abnormal reflective vehicle region figure
Picture is simultaneously stored in described object layer；
First processing module, processing vehicle region image for the magazine neural-network processing unit of site of deployment to identify is
No have the condition of a fire and obtain condition of a fire parametric image in the presence of judging and be related to the information of vehicle and be stored in characteristic layer；
Parameter judge module, for judging condition of a fire classification or rank according to condition of a fire parameter and being stored in semantic layer；And
Decision-making module, produces early warning or advisory information and is stored in decision-making level according to spot for photography and condition of a fire classification or rank.
9. road monitoring apparatus as claimed in claim 8 are it is characterised in that described decision-making module is used for producing at Traffic monitoring end
Raw described early warning or advisory information.
10. road monitoring apparatus as claimed in claim 8 are it is characterised in that described road monitoring apparatus include：
Reminding module, for producing information at Traffic monitoring end and being stored in described semantic layer；Described information includes
Condition of a fire classification or rank, described spot for photography and/or shooting time, described shooting time is the described vehicle region that there is the condition of a fire
The shooting time of the corresponding described monitoring image of image.
11. road monitoring apparatus as claimed in claim 10 are it is characterised in that described road monitoring apparatus include：
Second processing module, for processing the identity information to obtain described vehicle for the described vehicle region image；Described prompting letter
Breath also includes described identity information.
12. road monitoring apparatus as claimed in claim 11 are it is characterised in that described road monitoring apparatus include：
3rd processing module, for processing the kinematic parameter to obtain described vehicle for the described vehicle region image；Described prompting letter
Breath also includes described kinematic parameter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610875518.9A CN106448161A (en) | 2016-09-30 | 2016-09-30 | Road monitoring method and road monitoring device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610875518.9A CN106448161A (en) | 2016-09-30 | 2016-09-30 | Road monitoring method and road monitoring device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106448161A true CN106448161A (en) | 2017-02-22 |
Family
ID=58171735
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610875518.9A Pending CN106448161A (en) | 2016-09-30 | 2016-09-30 | Road monitoring method and road monitoring device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106448161A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111932889A (en) * | 2020-08-18 | 2020-11-13 | 湖南汽车工程职业学院 | Traffic dispersion system based on vehicle-road cooperation |
| CN113257024A (en) * | 2021-04-29 | 2021-08-13 | 中汽研汽车检验中心(广州)有限公司 | Expressway rear-end collision prevention early warning method and system based on V2I |
| CN113838022A (en) * | 2021-09-22 | 2021-12-24 | 清华珠三角研究院 | Method, system and device for identifying abnormal working conditions of automobile and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1852428A (en) * | 2006-05-25 | 2006-10-25 | 浙江工业大学 | Intelligent tunnel safety monitoring apparatus based on omnibearing computer vision |
| CN102625083A (en) * | 2012-03-07 | 2012-08-01 | 深圳市信义科技有限公司 | Method for constructing video monitoring network |
| KR101229945B1 (en) * | 2012-04-06 | 2013-02-06 | 김명호 | System for alarm and detection accident of tunnel |
| CN103150549A (en) * | 2013-02-05 | 2013-06-12 | 长安大学 | Highway tunnel fire detecting method based on smog early-stage motion features |
| CN105678946A (en) * | 2016-02-22 | 2016-06-15 | 吴正明 | Fire remote detection system and method based on unmanned plane |
| CN105788142A (en) * | 2016-05-11 | 2016-07-20 | 中国计量大学 | Video image processing-based fire detection system and detection method |
| CN105869408A (en) * | 2016-04-27 | 2016-08-17 | 长安大学 | Hub temperature anomaly detection and early warning method and system |
-
2016
- 2016-09-30 CN CN201610875518.9A patent/CN106448161A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1852428A (en) * | 2006-05-25 | 2006-10-25 | 浙江工业大学 | Intelligent tunnel safety monitoring apparatus based on omnibearing computer vision |
| CN102625083A (en) * | 2012-03-07 | 2012-08-01 | 深圳市信义科技有限公司 | Method for constructing video monitoring network |
| KR101229945B1 (en) * | 2012-04-06 | 2013-02-06 | 김명호 | System for alarm and detection accident of tunnel |
| CN103150549A (en) * | 2013-02-05 | 2013-06-12 | 长安大学 | Highway tunnel fire detecting method based on smog early-stage motion features |
| CN105678946A (en) * | 2016-02-22 | 2016-06-15 | 吴正明 | Fire remote detection system and method based on unmanned plane |
| CN105869408A (en) * | 2016-04-27 | 2016-08-17 | 长安大学 | Hub temperature anomaly detection and early warning method and system |
| CN105788142A (en) * | 2016-05-11 | 2016-07-20 | 中国计量大学 | Video image processing-based fire detection system and detection method |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111932889A (en) * | 2020-08-18 | 2020-11-13 | 湖南汽车工程职业学院 | Traffic dispersion system based on vehicle-road cooperation |
| CN113257024A (en) * | 2021-04-29 | 2021-08-13 | 中汽研汽车检验中心(广州)有限公司 | Expressway rear-end collision prevention early warning method and system based on V2I |
| CN113257024B (en) * | 2021-04-29 | 2023-09-12 | 中汽研汽车检验中心(广州)有限公司 | V2I-based rear-end collision prevention early warning method and system for expressway rain and fog environment |
| CN113838022A (en) * | 2021-09-22 | 2021-12-24 | 清华珠三角研究院 | Method, system and device for identifying abnormal working conditions of automobile and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2758879B1 (en) | A computing platform for development and deployment of sensor-driven vehicle telemetry applications and services | |
| CN109345829B (en) | Unmanned vehicle monitoring method, device, equipment and storage medium | |
| CN104670155B (en) | Anti-theft alarm system for vehicles based on high in the clouds car networking | |
| US10423841B2 (en) | Abnormality detection device and abnormality detection method | |
| CN106340205A (en) | Traffic monitoring method and traffic monitoring apparatus | |
| CN110400478A (en) | A kind of road condition notification method and device | |
| US11361556B2 (en) | Deterioration diagnosis device, deterioration diagnosis system, deterioration diagnosis method, and storage medium for storing program | |
| CN110895662A (en) | Vehicle overload alarm method and device, electronic equipment and storage medium | |
| CN110619277A (en) | Multi-community intelligent deployment and control method and system | |
| CN111783530A (en) | Safety system and method for monitoring and identifying behaviors in restricted area | |
| CN112633057A (en) | Intelligent monitoring method for abnormal behaviors in bus | |
| CN112686090A (en) | Intelligent monitoring system for abnormal behaviors in bus | |
| CN106448161A (en) | Road monitoring method and road monitoring device | |
| CN110544312A (en) | Video display method and device in virtual scene, electronic equipment and storage device | |
| KR102043922B1 (en) | A cctv divided management system and method it | |
| CN112132048A (en) | Community patrol analysis method and system based on computer vision | |
| CN115797403A (en) | Traffic accident prediction method and device, storage medium and electronic device | |
| CN115527364A (en) | Traffic accident tracing method and system based on radar vision data fusion | |
| CN113870551B (en) | Road side monitoring system capable of identifying dangerous and non-dangerous driving behaviors | |
| CN112598908B (en) | Driver red light running recognition method and device, electronic equipment and storage medium | |
| CN106448162A (en) | Road monitoring method and road monitoring device | |
| Gowda et al. | Design and Implementation of a System for Vehicle Accident Reporting and Tracking | |
| CN112365740A (en) | Alarm display method and device | |
| KR101686851B1 (en) | Integrated control system using cctv camera | |
| KR102436111B1 (en) | AI based event detection system targeting unlawful vehicle by using mobility system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20171207 Address after: 519000 Guangdong city of Zhuhai province Hengqin Baohua Road No. 6, room 105, -23898 (central office) Applicant after: Zhongxing Technology Co., Ltd. Address before: 519031 Guangdong city of Zhuhai province Hengqin Baohua Road No. 6, room 105 -15070 Applicant before: Guangdong Vimicro Corp |
|
| CB02 | Change of applicant information |
Address after: 519031 Guangdong city of Zhuhai province Hengqin Baohua Road No. 6, room 105, -23898 (central office) Applicant after: Mid Star Technology Limited by Share Ltd Address before: 519000 Guangdong city of Zhuhai province Hengqin Baohua Road No. 6, room 105, -23898 (central office) Applicant before: Zhongxing Technology Co., Ltd. |
|
| CB02 | Change of applicant information | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170222 |
|
| RJ01 | Rejection of invention patent application after publication |