CN109360362A - A kind of railway video monitoring recognition methods, system and computer-readable medium - Google Patents
A kind of railway video monitoring recognition methods, system and computer-readable medium Download PDFInfo
- Publication number
- CN109360362A CN109360362A CN201811253116.0A CN201811253116A CN109360362A CN 109360362 A CN109360362 A CN 109360362A CN 201811253116 A CN201811253116 A CN 201811253116A CN 109360362 A CN109360362 A CN 109360362A
- Authority
- CN
- China
- Prior art keywords
- image
- foreign bodies
- detection result
- bodies detection
- video
- 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
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19639—Details of the system layout
- G08B13/19645—Multiple cameras, each having view on one of a plurality of scenes, e.g. multiple cameras for multi-room surveillance or for tracking an object by view hand-over
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19654—Details concerning communication with a camera
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/22—Electrical actuation
- G08B13/24—Electrical actuation by interference with electromagnetic field distribution
- G08B13/2491—Intrusion detection systems, i.e. where the body of an intruder causes the interference with the electromagnetic field
Abstract
The present invention provides a kind of railway video monitoring recognition methods, system and computer-readable mediums, it is related to the technical field of image procossing, it include: the target video image after data prediction that the target road section of railway of front-end video acquisition device acquisition is obtained by multiple images processing server, and foreign bodies detection is carried out to video image, obtain foreign bodies detection result, wherein, foreign bodies detection result is the video image comprising foreign matter;Classified by intelligent recognition server to foreign bodies detection result, obtain classification results, wherein classification results are used to characterize the alarm level information of foreign bodies detection result;Handled by management server foreign bodies detection result and alarm level information, wherein processing includes at least one of: storage, publication and displaying, the present invention alleviate the existing higher technical problem of video intrusion detection algorithm false detection rate.
Description
Technical field
The present invention relates to the technical fields of image procossing and pattern-recognition, monitor and identify more particularly, to a kind of railway video
Method, system and computer-readable medium.
Background technique
With the fast development of China express railway, railway is used as national important infrastructure and the popular vehicles,
Play an important roll in Chinese society development.Therefore high-speed railway operation security and disaster prevention are met in railway construction in China
The major issue arrived, through investigating, China express railway in face of disaster mainly have natural calamity (flood, earthquake etc.), fire,
The several aspects of burst accident, foreign body intrusion.In contrast, foreign body intrusion occurrence frequency is higher, while endangering caused by it also simultaneously
No less than the former.Existing high-speed railway route all has comprehensive video monitoring subsystem, which can real time inspection Railway Site
Video, and history video can be saved, understand field condition for each department and provide platform.But existing integrated video monitoring system
System, although having preliminary video analysis and recognition capability, the accuracy rate of identification is not high, the case where there are a large amount of wrong reports,
It can only be used in the simple occasion such as unattended computer room, it can not be in complex scene and night use.It is therefore desirable to study energy
Enough adapt to various scenes, and railway video intelligent recognition (invasion of high-speed rail circumference) system with higher recognition accuracy.
Summary of the invention
It can in view of this, the purpose of the present invention is to provide a kind of railway video monitoring recognition methods, system and computers
Medium is read, to alleviate the existing higher technical problem of video intrusion detection algorithm false detection rate.
In a first aspect, the embodiment of the invention provides a kind of railway videos to monitor identifying system, comprising: multiple images processing
Server, intelligent recognition server and management server;Described multiple images processing server, the intelligent recognition server and
The management server is connected with front-end video acquisition device respectively;Described multiple images processing server is described for obtaining
The target video image after data prediction of the target road section of the railway of front-end video acquisition device acquisition, and to institute
It states target video image and carries out foreign bodies detection, obtain foreign bodies detection result, wherein the foreign bodies detection result is to include foreign matter
Video image;The intelligent recognition server obtains classification results for classifying to the foreign bodies detection result, wherein
The classification results are used to characterize the alarm level information of the foreign bodies detection result;The management server is used for described different
Analyte detection result and the alarm level information are handled, wherein the processing includes at least one of: storage, publication
And displaying.
Further, the system also includes interchanger, described multiple images processing servers, the intelligent recognition clothes
Business device and the management server are connected by the interchanger with front-end video acquisition device respectively.
Further, the system also includes image pre-processing modules, wherein described image preprocessing module includes institute
State front-end video acquisition device and multiple cameras, wherein each camera is connected with the front-end video acquisition device respectively;Institute
Front-end video acquisition device is stated for acquiring the raw video image in target railway section;And the raw video image is carried out
Processing, obtains the target video image.
Second aspect, the embodiment of the invention also provides a kind of railway videos to monitor recognition methods, is applied to above-mentioned first
Railway video described in any one of aspect monitors identifying system, comprising: obtains the railway of front-end video acquisition device acquisition
The target video image after data prediction of target road section, and foreign bodies detection is carried out to the target video image,
Obtain foreign bodies detection result, wherein the foreign bodies detection result is the video image comprising foreign matter;To the foreign bodies detection result
Classify, obtain classification results, wherein the classification results are used to characterize the alarm level letter of the foreign bodies detection result
Breath;The foreign bodies detection result and the alarm level information are handled, wherein it is described processing include it is following at least it
One: storage, publication and displaying.
Further, the method also includes: acquisition target railway section raw video image;To the original video
Image is handled, and the target video image is obtained.
Further, the video image is RGB image, handles the raw video image, obtains the mesh
Mark video image includes: to carry out image de-jittering processing to the RGB image, and scheme to the RGB after image de-jittering processing
As carrying out image equalization processing and image enhancement processing, the target video image is obtained.
Further, the video image is multispectral image, is handled the raw video image, is obtained described
Target video image includes: to carry out image registration to the multispectral image, obtains the multispectral image after image registration;It is right
Multispectral image after described image registration carries out image co-registration, obtains subject fusion image, and by the subject fusion figure
As being used as the target video image.
Further, classify to the foreign bodies detection result, obtaining classification results includes: by depth convolutional Neural
Network carries out classification processing to the foreign bodies detection result, with institute in each video image in the determination foreign bodies detection result
Type information comprising foreign matter;Classified based on type information determination to the foreign bodies detection result, obtains described point
Class result.
Further, the method also includes: based on report corresponding to each video image in the foreign bodies detection result
Alert class information determines alarm signal, and executes actuation of an alarm according to the alarm signal.
The third aspect, the embodiment of the invention also provides a kind of non-volatile program codes that can be performed with processor
Computer-readable medium, said program code make the processor execute any the method in above-mentioned first aspect.
In embodiments of the present invention, the railway of front-end video acquisition device acquisition is obtained by multiple images processing server
Target road section the target video image after data prediction, and to video image carry out foreign bodies detection, obtain different
Analyte detection result, wherein foreign bodies detection result is the video image comprising foreign matter;By intelligent recognition server to foreign bodies detection
As a result classify, obtain classification results, wherein classification results are used to characterize the alarm level information of foreign bodies detection result;It is logical
It crosses management server to handle foreign bodies detection result and alarm level information, wherein processing includes at least one of: being deposited
Storage, publication and displaying.In the present embodiment, using distribution-centralized processing method, by low-cost processes equipment in each camera
Video acquisition front end image is handled, by the doubtful abnormal conditions image tentatively identified be sent to railway video intelligence
Identifying system is focused on, and realizes the accurate detection and intelligent recognition invaded railway foreign body, and then alleviate existing view
The higher technical problem of frequency intrusion detection algorithm false detection rate.
Other features and advantages of the present invention will illustrate in the following description, also, partly become from specification
It obtains it is clear that understand through the implementation of the invention.The objectives and other advantages of the invention are in specification, claims
And specifically noted structure is achieved and obtained in attached drawing.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
It, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution in the prior art
Embodiment or attached drawing needed to be used in the description of the prior art be briefly described, it should be apparent that, it is described below
Attached drawing is some embodiments of the present invention, for those of ordinary skill in the art, before not making the creative labor
It puts, is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of schematic diagram of railway video monitoring identifying system according to an embodiment of the present invention;
Fig. 2 is a kind of flow chart of railway video monitoring recognition methods according to an embodiment of the present invention;
Fig. 3 be it is according to an embodiment of the present invention the first optionally railway video monitoring recognition methods flow chart;
Fig. 4 be second according to an embodiment of the present invention optionally railway video monitoring recognition methods flow chart;
Fig. 5 is the schematic diagram of a kind of electronic equipment according to an embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with attached drawing to the present invention
Technical solution be clearly and completely described, it is clear that described embodiments are some of the embodiments of the present invention, rather than
Whole embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not making creative work premise
Under every other embodiment obtained, shall fall within the protection scope of the present invention.
Embodiment one:
According to embodiments of the present invention, a kind of railway video monitoring identifying system embodiment is provided.
Fig. 1 is a kind of schematic diagram of railway video monitoring identifying system according to an embodiment of the present invention, as shown in Figure 1, should
System includes: multiple images processing server 10, intelligent recognition server 20 and management server 30;Described multiple images processing
Server 10, the intelligent recognition server 20 and the management server 30 are connected with front-end video acquisition device 40 respectively
It connects.
Specifically, described multiple images processing server 10 is used to obtain the railway of the front-end video acquisition device acquisition
Target road section the target video image after data prediction, and and to the target video image carry out foreign matter inspection
It surveys, obtains foreign bodies detection result, wherein the foreign bodies detection result is the video image comprising foreign matter;
The intelligent recognition server 20 obtains classification results for classifying to the foreign bodies detection result, wherein
The classification results are used to characterize the alarm level information of the foreign bodies detection result;
The management server 30 is used to handle the foreign bodies detection result and the alarm level information,
In, the processing includes at least one of: storage, publication and displaying.
In embodiments of the present invention, the railway of front-end video acquisition device acquisition is obtained by multiple images processing server
Target road section the target video image after data prediction, and to video image carry out foreign bodies detection, obtain different
Analyte detection result, wherein foreign bodies detection result is the video image comprising foreign matter;By intelligent recognition server to foreign bodies detection
As a result classify, obtain classification results, wherein classification results are used to characterize the alarm level information of foreign bodies detection result;It is logical
It crosses management server to handle foreign bodies detection result and alarm level information, wherein processing includes at least one of: being deposited
Storage, publication and displaying.In the present embodiment, using distribution-centralized processing method, by low-cost processes equipment in each camera
Video acquisition front end image is handled, by the doubtful abnormal conditions image tentatively identified be sent to railway video intelligence
Identifying system is focused on, and realizes the accurate detection and intelligent recognition invaded railway foreign body, and then alleviate existing view
The higher technical problem of frequency intrusion detection algorithm false detection rate.
Optionally, in the present embodiment, system further include: interchanger, described multiple images processing server, the intelligence
It can identify that server and the management server are connected by the interchanger with front-end video acquisition device respectively.
Optionally, in the present embodiment, the system also includes image pre-processing modules, wherein described image pretreatment
Module includes the front-end video acquisition device and multiple cameras, wherein each camera is set with head end video acquisition respectively
It is standby to be connected.
In the present embodiment, front-end video acquisition device is used to obtain the railway of the front-end video acquisition device acquisition
The raw video image of target road section;And the raw video image is handled, obtain the target video image.
Specifically, as shown in Figure 1, in the present embodiment, including several image processing servers, it is respectively as follows: at image
Manage server 11, image processing server 12 ..., image processing server 1N;1 intelligent recognition server;1 management service
Device.Several image processing servers, 1 intelligent recognition server and 1 management server are pre- by interchanger incoming image
Processing module.The I class or II class video access node of above-mentioned server and image pre-processing module carry out interface and obtain video figure
Picture.
It should be noted that in the present embodiment, can be according to the number of videos adjustable figure picture that different nodes access at
The quantity of server is managed, and configures 1 intelligent recognition server and 1 management server, video is accessed a fairly large number of
Node can configure more set systems.
Embodiment two:
According to embodiments of the present invention, a kind of embodiment of railway video monitoring recognition methods is provided, it should be noted that
Step shown in the flowchart of the accompanying drawings can execute in a computer system such as a set of computer executable instructions, and
It, in some cases, can be to be different from sequence execution institute herein and although logical order is shown in flow charts
The step of showing or describing.
Fig. 2 is a kind of flow chart of railway video monitoring recognition methods according to an embodiment of the present invention, as shown in Fig. 2, should
Method includes the following steps:
Step S202 obtains passing through after data prediction for the target road section of the railway of front-end video acquisition device acquisition
Target video image, and to the target video image carry out foreign bodies detection, obtain foreign bodies detection result, wherein described different
Analyte detection result is the video image comprising foreign matter;
Specifically, in the present embodiment, head end video acquisition is obtained by front-end video acquisition device shown in Fig. 1 to set
The raw video image of the target road section of the railway of standby acquisition;And the raw video image is handled, obtain target view
Frequency image.Foreign bodies detection is carried out to target video image by image processing server, obtains foreign bodies detection result.
Step S204 classifies to the foreign bodies detection result, obtains classification results, wherein the classification results are used
In the alarm level information for characterizing the foreign bodies detection result;
In the present embodiment, classified by intelligent recognition server shown in Fig. 1 to foreign bodies detection result, obtained
Classification results.
Step S206 handles the foreign bodies detection result and the alarm level information, wherein the processing packet
Include at least one of: storage, publication and displaying.
In the present embodiment, foreign bodies detection result and alarm level information are carried out by management server shown in FIG. 1
Processing.
In the present embodiment, using distribution-centralized processing method, by low-cost processes equipment each camera video
Acquisition front end handles image, and the doubtful abnormal conditions image tentatively identified is sent to railway video intelligent recognition system
System is focused on, and realizes the accurate detection and intelligent recognition invaded railway foreign body, and then alleviate existing video invasion
The higher technical problem of detection algorithm false detection rate.
As can be seen from the above description, in the present embodiment, in the target for the railway for obtaining front-end video acquisition device acquisition
Further include following steps before the target video image after data prediction in section:
Step S2011 acquires the raw video image in target railway section;
Step S2012 handles the raw video image, the target video image is obtained then, by preceding
End video capture device handles the raw video image, obtains target video image.
In image preprocessing as a result, it is desirable to use different preprocess methods for different image sources.Work as video image
When for RGB image, the raw video image is handled, the target video image is obtained and includes the following steps:
Image de-jittering processing is carried out to the RGB image, and figure is carried out to the RGB image after image de-jittering processing
As equilibrium treatment and image enhancement processing, the target video image is obtained.
It should be noted that RGB image herein can be SD, high definition or the starlight grade figure of existing comprehensive video image
Picture.As shown in figure 3, in the present embodiment, carrying out image de-jittering processing to RGB image first, (also referred to as camera shake picks
Except), then, is handled using image equalization and image enhancement processing successively carries out the RGB image after image de-jittering processing
Processing, obtains target video image.
After obtaining target video image in the manner described above, image processing server can be using based on background subtraction
The foreign matter occurred in the detection method Preliminary detection target video image divided.But it is influenced by light and weather condition, the inspection
There may be a certain number of false alarms for the testing result of survey method, while can only identify foreign matter but can not divide foreign matter
Class identification.
When video image is multispectral image, the raw video image is handled, the target video is obtained
Image includes the following steps:
Image registration is carried out to the multispectral image, obtains the multispectral image after image registration;
Image co-registration is carried out to the multispectral image after described image registration, obtains subject fusion image, and will be described
Subject fusion image is as the target video image.
Under normal circumstances, multispectral image can be acquired in the emphasis section of railway, for example, infrared image, visible light
Image and laser image.As shown in figure 4, in the present embodiment, after obtaining multispectral image, so that it may to infrared image,
Visible images and laser image carry out image registration processing, obtain the multispectral image after image registration.Image registration is just
It is to obtain (weather, illumination, camera position and angle etc.) under different time, different sensors (imaging device) or different condition
Two width or the multiple image process that is matched, be superimposed.Later, so that it may which the multispectral image after image registration is carried out
Image co-registration obtains subject fusion image, and using the subject fusion image as the target video image.
After obtaining target video image in the manner described above, image processing server can be calculated using target detection
The foreign matter occurred in method detection target video image.
As can be seen from the above description, after obtaining target video image, image processing server is to target video image
Foreign bodies detection is carried out, obtains foreign bodies detection as a result, obtaining foreign matter inspection to tentatively be identified to invasion and other abnormal conditions
Survey result, wherein stating foreign bodies detection result is the video image comprising foreign matter.
In the present embodiment, after obtaining foreign bodies detection result, so that it may be examined by intelligent recognition server to foreign matter
It surveys result to classify, obtains classification results.
Optionally, classify to the foreign bodies detection result, obtaining classification results includes:
Classification processing is carried out to the foreign bodies detection result by depth convolutional neural networks, with the determination foreign bodies detection
As a result the type information of foreign matter included in each video image in;
Classified based on type information determination to the foreign bodies detection result, obtains the classification results.
Specifically, in the present embodiment, the foreign bodies detection result that intelligent recognition server sends image processing server
Further intelligent recognition and classification are carried out with target video image.Intelligent recognition server by utilizing artificial intelligence, especially depth
The newest fruits of learning algorithm after being trained and optimize for railway scene, can significantly improve railway video image intelligent
The accuracy of identification.Intelligent recognition server can also classify to the result of identification, and realize to different situations setting not
With urgency level (alternatively, alarm level information) realize grading forewarning system, and by final foreign bodies detection result and classification results
It is sent to management server to be stored, issues and show.
It should be noted that in the present embodiment, being regarded by intelligent recognition server to foreign bodies detection result and target
Before frequency image is identified and classified, need to be trained the depth convolutional neural networks in intelligent recognition server.
When training, the railway scene image of multiple cameras is obtained (that is, original video first with front-end video acquisition device
Image), and different classes of image is labeled and image preprocessing building railway scene data set;Planned network structure,
Adjust network structure hyper parameter such as network layer (convolution, Chi Hua, Dropout, BN etc.), parameter selection (convolution kernel size, step-length
Deng).The convolution kernel and the number of plies of general networking increase, and the learning ability of network is stronger, but can have network mould in practical applications
Type committed memory greatly and the longer problem of detection time, while designing convolutional neural networks structure to network progress model pressure
Contracting can reduce network redundancy and amount of ram, increases detection speed, meets the requirement of railway scene real-time monitoring.Pass through iron
Road contextual data collection is trained the depth convolutional neural networks.
Above-mentioned intelligent recognition server can use high-performance GPU calculation server, but since it only handles front end figure
As the image after processing server preliminary treatment, 1 intelligent recognition server can handle greater number of video image, and total
Body cost does not dramatically increase.
In addition to this, management server is also based on alarm corresponding to each video image etc. in foreign bodies detection result
Grade information determines alarm signal, and executes actuation of an alarm according to the alarm signal.
It should be noted that management server user oriented provides the access interface of system, it can be achieved that authentication logs in, automatically
Detection saves and the functions such as export, equipment management, user management with alarm, the inquiry of history warning message, alarm video.
As can be seen from the above description, in the present embodiment, using distribution-centralization video image processing mode, each
Camera video acquisition front end pre-processes image, and the doubtful abnormal conditions image tentatively identified is sent to image procossing
Server, intelligent recognition server and management server are focused on, although distributed treatment number of devices is more,
For low-cost processes equipment, totle drilling cost declines instead.In the present embodiment, in order to guarantee Detection accuracy, reduction rate of false alarm will
Preliminary recognition result is sent to image processing server and intelligent recognition server is focused on, firstly, image procossing takes
Business device tentatively identifies target video image, and intelligent recognition server is recycled to confirm and divide foreign bodies detection result
Class.The accuracy rate of identification not only can be improved in this way but also algorithm can be reduced to the effect of hardware resource, to reduce system entirety
Cost.Multispectral camera can suitably be increased in key sections and complex ground simultaneously, and known for multispectral image Intelligent Optimal
Other algorithm improves the accuracy rate of night video intelligent identification and the ability of intrusion detection.
In conclusion using method provided by the invention for having following excellent in the identification of railway video monitoring image
Point:
A large amount of network bandwidth concerns are occupied when 1. being able to solve centralized processing using distributed approach, although processing is set
It is standby more, but due to using low-cost equipment, so that overall cost is declined instead.
2. there are the data of abnormal conditions to be transmitted to centralized processing system preliminary identification, there are abnormal feelings to doubtful
The method of condition two stage recognition, it may be assumed that firstly, image processing server tentatively identifies target video image, recycle intelligence
Identification server is confirmed and is classified to foreign bodies detection result.
3. the present invention do not need to be modified existing railway Synthetic Visual System and can guarantee high-accuracy and
In the case where meeting real-time monitoring requirement, system overall cost is reduced.
Embodiment three:
Present embodiments provide a kind of electronic equipment, the structural schematic diagram of a kind of electronic equipment shown in Figure 5, the electricity
Sub- equipment includes: processor 50, memory 51, bus 52 and communication interface 55, the processor 50, communication interface 55 and storage
Device 51 is connected by bus 52;Processor 50 is for executing the executable module stored in memory 51, such as computer program.
Wherein, memory 51 may include high-speed random access memory (RAM, Random Access Memory),
It may further include non-labile memory (non-volatile memory), for example, at least a magnetic disk storage.By extremely
A few communication interface 55 (can be wired or wireless) is realized logical between the system network element and at least one other network element
Letter connection, can be used internet, wide area network, local network, Metropolitan Area Network (MAN) etc..
Bus 52 can be isa bus, pci bus or eisa bus etc..The bus can be divided into address bus, data
Bus, control bus etc..Only to be indicated with a four-headed arrow convenient for indicating, in Fig. 5, it is not intended that an only bus or
A type of bus.
Wherein, memory 51 is for storing program, and the processor 50 executes the journey after receiving and executing instruction
Sequence, method performed by the device that the stream process that aforementioned the present embodiment any embodiment discloses defines can be applied to processor 50
In, or realized by processor 50.
Processor 50 may be a kind of IC chip, the processing capacity with signal.During realization, above-mentioned side
Each step of method can be completed by the integrated logic circuit of the hardware in processor 50 or the instruction of software form.Above-mentioned
Processor 50 can be general processor, including central processing unit (Central Processing Unit, abbreviation CPU), network
Processor (Network Processor, abbreviation NP) etc.;It can also be digital signal processor (Digital Signal
Processor, abbreviation DSP), specific integrated circuit (Application Specific Integrated Circuit, referred to as
ASIC), field programmable gate array (Field-Programmable Gate Array, abbreviation FPGA) or other are programmable
Logical device, discrete gate or transistor logic, discrete hardware components.It may be implemented or execute the public affairs in the present embodiment
Each method, step and the logic diagram opened.General processor can be microprocessor or the processor be also possible to it is any often
The processor etc. of rule.The step of method in conjunction with disclosed in the present embodiment, can be embodied directly in hardware decoding processor and execute
At, or in decoding processor hardware and software module combination execute completion.Software module can be located at random access memory,
This fields such as flash memory, read-only memory, programmable read only memory or electrically erasable programmable memory, register maturation
In storage medium.The storage medium is located at memory 51, and processor 50 reads the information in memory 51, completes in conjunction with its hardware
The step of above method.
Above-mentioned electronic equipment can be used for executing grading forewarning system method provided in this embodiment, or is installed on the present embodiment and mentions
The grading forewarning system device of confession.
Further, the present embodiment additionally provides a kind of machine readable storage medium, and machine readable storage medium is stored with place
The executable program code of device is managed, program code is configured to that processor is made to execute aforementioned attack early warning method.
The technical effect and preceding method embodiment phase of device provided by the embodiment of the present invention, realization principle and generation
Together, to briefly describe, Installation practice part does not refer to place, can refer to corresponding contents in preceding method embodiment.
In addition, in the description of the embodiment of the present invention unless specifically defined or limited otherwise, term " installation ", " phase
Even ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or be integrally connected;It can
To be mechanical connection, it is also possible to be electrically connected;It can be directly connected, can also can be indirectly connected through an intermediary
Connection inside two elements.For the ordinary skill in the art, above-mentioned term can be understood at this with concrete condition
Concrete meaning in invention.
In the description of the present invention, it should be noted that term " center ", "upper", "lower", "left", "right", "vertical",
The orientation or positional relationship of the instructions such as "horizontal", "inner", "outside" be based on the orientation or positional relationship shown in the drawings, merely to
Convenient for description the present invention and simplify description, rather than the device or element of indication or suggestion meaning must have a particular orientation,
It is constructed and operated in a specific orientation, therefore is not considered as limiting the invention.In addition, term " first ", " second ",
" third " is used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In several embodiments provided herein, it should be understood that disclosed systems, devices and methods, it can be with
It realizes by another way.The apparatus embodiments described above are merely exemplary, for example, the division of the unit,
Only a kind of logical function partition, there may be another division manner in actual implementation, in another example, multiple units or components can
To combine or be desirably integrated into another system, or some features can be ignored or not executed.Another point, it is shown or beg for
The mutual coupling, direct-coupling or communication connection of opinion can be through some communication interfaces, device or unit it is indirect
Coupling or communication connection can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in the executable non-volatile computer-readable storage medium of a processor.Based on this understanding, of the invention
Technical solution substantially the part of the part that contributes to existing technology or the technical solution can be with software in other words
The form of product embodies, which is stored in a storage medium, including some instructions use so that
One computer equipment (can be personal computer, server or the network equipment etc.) executes each embodiment institute of the present invention
State all or part of the steps of method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-
Only Memory), random access memory (RAM, Random Access Memory), magnetic or disk etc. are various can be with
Store the medium of program code.
Finally, it should be noted that embodiment described above, only a specific embodiment of the invention, to illustrate the present invention
Technical solution, rather than its limitations, scope of protection of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair
It is bright to be described in detail, those skilled in the art should understand that: anyone skilled in the art
In the technical scope disclosed by the present invention, it can still modify to technical solution documented by previous embodiment or can be light
It is readily conceivable that variation or equivalent replacement of some of the technical features;And these modifications, variation or replacement, do not make
The essence of corresponding technical solution is detached from the spirit and scope of technical solution of the embodiment of the present invention, should all cover in protection of the invention
Within the scope of.Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. a kind of railway video monitors identifying system characterized by comprising multiple images processing server, intelligent recognition clothes
Business device and management server;Described multiple images processing server, the intelligent recognition server and the management server point
It is not connected with front-end video acquisition device;
Described multiple images processing server is used to obtain the target road section of the railway of the front-end video acquisition device acquisition
Target video image after data prediction, and foreign bodies detection is carried out to the target video image, obtain foreign matter inspection
Survey result, wherein the foreign bodies detection result is the video image comprising foreign matter;
The intelligent recognition server obtains classification results, wherein described point for classifying to the foreign bodies detection result
Class result is used to characterize the alarm level information of the foreign bodies detection result;
The management server is for handling the foreign bodies detection result and the alarm level information, wherein described
Processing includes at least one of: storage, publication and displaying.
2. system according to claim 1, which is characterized in that the system also includes interchanger, at described multiple images
Server is managed, the intelligent recognition server and the management server pass through the interchanger respectively and set with head end video acquisition
It is standby to be connected.
3. system according to claim 1, which is characterized in that the system also includes: image pre-processing module, wherein
Described image preprocessing module includes the front-end video acquisition device and multiple cameras, wherein each camera respectively with it is described
Front-end video acquisition device is connected;
The front-end video acquisition device is used to acquire the raw video image in target railway section;And to the original video figure
As being handled, the target video image is obtained.
4. a kind of railway video monitors recognition methods, supervised applied to railway video described in any one of the claims 1 to 3
Control identifying system characterized by comprising
Obtain the target video figure after data prediction of the target road section of the railway of front-end video acquisition device acquisition
Picture, and foreign bodies detection is carried out to the target video image, obtain foreign bodies detection result, wherein the foreign bodies detection result is
Video image comprising foreign matter;
Classify to the foreign bodies detection result, obtain classification results, wherein the classification results are for characterizing the foreign matter
The alarm level information of testing result;
The foreign bodies detection result and the alarm level information are handled, wherein it is described processing include it is following at least it
One: storage, publication and displaying.
5. according to the method described in claim 4, it is characterized in that, the method also includes:
Acquire the raw video image in target railway section;
The raw video image is handled, the target video image is obtained.
6. according to the method described in claim 5, it is characterized in that, the video image is RGB image, to the original video
Image is handled, and is obtained the target video image and is included:
Image de-jittering processing is carried out to the RGB image, and it is equal to carry out image to the RGB image after image de-jittering processing
Weighing apparatus processing and image enhancement processing, obtain the target video image.
7. according to the method described in claim 5, it is characterized in that, the video image is multispectral image, to described original
Video image is handled, and is obtained the target video image and is included:
Image registration is carried out to the multispectral image, obtains the multispectral image after image registration;
Image co-registration is carried out to the multispectral image after described image registration, obtains subject fusion image, and by the target
Blending image is as the target video image.
8. according to the method described in claim 4, being classified it is characterized in that, classify to the foreign bodies detection result
Result includes:
Classification processing is carried out to the foreign bodies detection result by depth convolutional neural networks, with the determination foreign bodies detection result
In each video image included in foreign matter type information;
Classified based on type information determination to the foreign bodies detection result, obtains the classification results.
9. according to the method described in claim 4, it is characterized in that, the method also includes:
Alarm signal is determined based on alarm level information corresponding to each video image in the foreign bodies detection result, and according to
The alarm signal executes actuation of an alarm.
10. a kind of computer-readable medium for the non-volatile program code that can be performed with processor, which is characterized in that described
Program code makes the processor execute described any the method for claim 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811253116.0A CN109360362A (en) | 2018-10-25 | 2018-10-25 | A kind of railway video monitoring recognition methods, system and computer-readable medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811253116.0A CN109360362A (en) | 2018-10-25 | 2018-10-25 | A kind of railway video monitoring recognition methods, system and computer-readable medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109360362A true CN109360362A (en) | 2019-02-19 |
Family
ID=65346738
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811253116.0A Pending CN109360362A (en) | 2018-10-25 | 2018-10-25 | A kind of railway video monitoring recognition methods, system and computer-readable medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109360362A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110084987A (en) * | 2019-04-29 | 2019-08-02 | 复钧智能科技(苏州)有限公司 | A kind of foreign matter inspecting system and method towards rail traffic |
CN110992327A (en) * | 2019-11-27 | 2020-04-10 | 北京达佳互联信息技术有限公司 | Lens contamination state detection method and device, terminal and storage medium |
CN111488866A (en) * | 2020-06-29 | 2020-08-04 | 北京大成国测科技有限公司 | Invading object identification method and device based on deep learning and electronic equipment |
CN111507282A (en) * | 2020-04-21 | 2020-08-07 | 名创优品(横琴)企业管理有限公司 | Target detection early warning analysis system, method, equipment and medium |
CN111768372A (en) * | 2020-06-12 | 2020-10-13 | 国网智能科技股份有限公司 | Method and system for detecting foreign matters in GIS equipment cavity |
CN111862535A (en) * | 2020-06-26 | 2020-10-30 | 武汉北斗星度科技有限公司 | Railway peripheral collapse and rockfall monitoring and early warning system |
CN111915848A (en) * | 2020-08-18 | 2020-11-10 | 成都森川科技股份有限公司 | Flood control and disaster reduction monitoring and alarming device for railway engineering |
CN112528791A (en) * | 2020-12-03 | 2021-03-19 | 山东星宏电讯有限责任公司 | Anti-intrusion system and method for railway station yard |
CN114913654A (en) * | 2022-05-16 | 2022-08-16 | 北京京航安机场工程有限公司 | Airport enclosure intrusion pre-alarm processing equipment and method based on edge calculation |
CN116960814A (en) * | 2022-10-28 | 2023-10-27 | 中国铁建电气化局集团有限公司 | Foreign matter removing method, device, equipment and medium for overhead contact system |
Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080211668A1 (en) * | 2007-03-02 | 2008-09-04 | Dixon Walter V | Method and system to detect humans or animals within confined spaces with a low rate of false alarms |
CN101582963A (en) * | 2008-04-22 | 2009-11-18 | 索尼株式会社 | Offloading processing of images from a portable digital camera |
CN101726498A (en) * | 2009-12-04 | 2010-06-09 | 河海大学常州校区 | Intelligent detector and method of copper strip surface quality on basis of vision bionics |
CN201570108U (en) * | 2009-11-11 | 2010-09-01 | 四川格致科技发展有限公司 | System for monitoring intrusion of foreign bodies |
WO2011036661A1 (en) * | 2009-09-24 | 2011-03-31 | Elbit Systems Ltd. | System and method for long-range surveillance of a scene and alerting of predetermined unusual activity |
CN201867937U (en) * | 2010-10-18 | 2011-06-15 | 成都智胜通科技有限责任公司 | Forecast system for railway geologic hazard |
CN103356293A (en) * | 2013-08-05 | 2013-10-23 | 南京工业大学 | Surgery navigation system and method based on multispectral image fusion of reflecting mirror faces with adjustable angles and adjustable positions |
CN103632486A (en) * | 2013-11-26 | 2014-03-12 | 北京交通大学 | Processing and displaying alarm system for high-speed rail disaster prevention information |
CN104616003A (en) * | 2015-03-06 | 2015-05-13 | 侯苏 | System for identifying type of foreign matters on power line |
CN104787084A (en) * | 2015-04-16 | 2015-07-22 | 北京交通大学 | Railway foreign matter clearance intrusion detection system and method |
CN106056821A (en) * | 2016-08-13 | 2016-10-26 | 哈尔滨理工大学 | Power-transmission-line foreign-matter-invasion intelligent-video on-line monitoring evaluation system |
CN205862497U (en) * | 2016-08-13 | 2017-01-04 | 哈尔滨理工大学 | Electric line foreign matter intrusion intelligent video on-line monitoring assessment system |
CN106485718A (en) * | 2016-09-30 | 2017-03-08 | 北京通航信息科技有限公司 | One kind overdoes slash recognition methodss and device |
CN106741008A (en) * | 2016-12-29 | 2017-05-31 | 北京交通大学 | Rail track method for recognizing impurities and system |
CN107770631A (en) * | 2017-10-31 | 2018-03-06 | 长光卫星技术有限公司 | Suitable for the video image intelligent processing system of large area array meter level high-resolution satellite |
CN108055347A (en) * | 2017-12-27 | 2018-05-18 | 河南辉煌软件有限公司 | Railway disaster prevention safety monitoring system based on wireless sensor network |
CN108550174A (en) * | 2018-03-08 | 2018-09-18 | 中国地质大学(武汉) | A kind of coastline Super-resolution Mapping and system based on half global optimization |
-
2018
- 2018-10-25 CN CN201811253116.0A patent/CN109360362A/en active Pending
Patent Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080211668A1 (en) * | 2007-03-02 | 2008-09-04 | Dixon Walter V | Method and system to detect humans or animals within confined spaces with a low rate of false alarms |
CN101582963A (en) * | 2008-04-22 | 2009-11-18 | 索尼株式会社 | Offloading processing of images from a portable digital camera |
WO2011036661A1 (en) * | 2009-09-24 | 2011-03-31 | Elbit Systems Ltd. | System and method for long-range surveillance of a scene and alerting of predetermined unusual activity |
CN201570108U (en) * | 2009-11-11 | 2010-09-01 | 四川格致科技发展有限公司 | System for monitoring intrusion of foreign bodies |
CN101726498A (en) * | 2009-12-04 | 2010-06-09 | 河海大学常州校区 | Intelligent detector and method of copper strip surface quality on basis of vision bionics |
CN201867937U (en) * | 2010-10-18 | 2011-06-15 | 成都智胜通科技有限责任公司 | Forecast system for railway geologic hazard |
CN103356293A (en) * | 2013-08-05 | 2013-10-23 | 南京工业大学 | Surgery navigation system and method based on multispectral image fusion of reflecting mirror faces with adjustable angles and adjustable positions |
CN103632486A (en) * | 2013-11-26 | 2014-03-12 | 北京交通大学 | Processing and displaying alarm system for high-speed rail disaster prevention information |
CN104616003A (en) * | 2015-03-06 | 2015-05-13 | 侯苏 | System for identifying type of foreign matters on power line |
CN104787084A (en) * | 2015-04-16 | 2015-07-22 | 北京交通大学 | Railway foreign matter clearance intrusion detection system and method |
CN106056821A (en) * | 2016-08-13 | 2016-10-26 | 哈尔滨理工大学 | Power-transmission-line foreign-matter-invasion intelligent-video on-line monitoring evaluation system |
CN205862497U (en) * | 2016-08-13 | 2017-01-04 | 哈尔滨理工大学 | Electric line foreign matter intrusion intelligent video on-line monitoring assessment system |
CN106485718A (en) * | 2016-09-30 | 2017-03-08 | 北京通航信息科技有限公司 | One kind overdoes slash recognition methodss and device |
CN106741008A (en) * | 2016-12-29 | 2017-05-31 | 北京交通大学 | Rail track method for recognizing impurities and system |
CN107770631A (en) * | 2017-10-31 | 2018-03-06 | 长光卫星技术有限公司 | Suitable for the video image intelligent processing system of large area array meter level high-resolution satellite |
CN108055347A (en) * | 2017-12-27 | 2018-05-18 | 河南辉煌软件有限公司 | Railway disaster prevention safety monitoring system based on wireless sensor network |
CN108550174A (en) * | 2018-03-08 | 2018-09-18 | 中国地质大学(武汉) | A kind of coastline Super-resolution Mapping and system based on half global optimization |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110084987A (en) * | 2019-04-29 | 2019-08-02 | 复钧智能科技(苏州)有限公司 | A kind of foreign matter inspecting system and method towards rail traffic |
CN110992327A (en) * | 2019-11-27 | 2020-04-10 | 北京达佳互联信息技术有限公司 | Lens contamination state detection method and device, terminal and storage medium |
CN111507282A (en) * | 2020-04-21 | 2020-08-07 | 名创优品(横琴)企业管理有限公司 | Target detection early warning analysis system, method, equipment and medium |
CN111507282B (en) * | 2020-04-21 | 2023-06-30 | 创优数字科技(广东)有限公司 | Target detection early warning analysis system, method, equipment and medium |
CN111768372A (en) * | 2020-06-12 | 2020-10-13 | 国网智能科技股份有限公司 | Method and system for detecting foreign matters in GIS equipment cavity |
CN111768372B (en) * | 2020-06-12 | 2024-03-12 | 国网智能科技股份有限公司 | Method and system for detecting foreign matters in cavity of GIS (gas insulated switchgear) |
CN111862535A (en) * | 2020-06-26 | 2020-10-30 | 武汉北斗星度科技有限公司 | Railway peripheral collapse and rockfall monitoring and early warning system |
CN111488866A (en) * | 2020-06-29 | 2020-08-04 | 北京大成国测科技有限公司 | Invading object identification method and device based on deep learning and electronic equipment |
CN111915848A (en) * | 2020-08-18 | 2020-11-10 | 成都森川科技股份有限公司 | Flood control and disaster reduction monitoring and alarming device for railway engineering |
CN112528791A (en) * | 2020-12-03 | 2021-03-19 | 山东星宏电讯有限责任公司 | Anti-intrusion system and method for railway station yard |
CN114913654A (en) * | 2022-05-16 | 2022-08-16 | 北京京航安机场工程有限公司 | Airport enclosure intrusion pre-alarm processing equipment and method based on edge calculation |
CN116960814A (en) * | 2022-10-28 | 2023-10-27 | 中国铁建电气化局集团有限公司 | Foreign matter removing method, device, equipment and medium for overhead contact system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109360362A (en) | A kind of railway video monitoring recognition methods, system and computer-readable medium | |
WO2022105243A1 (en) | Event detection method, apparatus, electronic device, and storage medium | |
CN110390262B (en) | Video analysis method, device, server and storage medium | |
Aboah | A vision-based system for traffic anomaly detection using deep learning and decision trees | |
JP6905850B2 (en) | Image processing system, imaging device, learning model creation method, information processing device | |
WO2019179024A1 (en) | Method for intelligent monitoring of airport runway, application server and computer storage medium | |
KR102197946B1 (en) | object recognition and counting method using deep learning artificial intelligence technology | |
US9122932B2 (en) | Method and system for automatically detecting multi-object anomalies utilizing joint sparse reconstruction model | |
KR102122859B1 (en) | Method for tracking multi target in traffic image-monitoring-system | |
CN110826429A (en) | Scenic spot video-based method and system for automatically monitoring travel emergency | |
CN104966304A (en) | Kalman filtering and nonparametric background model-based multi-target detection tracking method | |
KR102122850B1 (en) | Solution for analysis road and recognition vehicle license plate employing deep-learning | |
CN112071084A (en) | Method and system for judging illegal parking by utilizing deep learning | |
Kumar et al. | Automatic multiclass instance segmentation of concrete damage using deep learning model | |
CN108229256A (en) | A kind of road construction detection method and device | |
Yang et al. | Traffic flow estimation and vehicle‐type classification using vision‐based spatial–temporal profile analysis | |
KR20220146670A (en) | Traffic anomaly detection methods, devices, devices, storage media and programs | |
Atzori et al. | HEIMDALL: an AI-based infrastructure for traffic monitoring and anomalies detection | |
CN113673311A (en) | Traffic abnormal event detection method, equipment and computer storage medium | |
CN115546742A (en) | Rail foreign matter identification method and system based on monocular thermal infrared camera | |
US11532158B2 (en) | Methods and systems for customized image and video analysis | |
CN109583396A (en) | A kind of region prevention method, system and terminal based on CNN two stages human testing | |
Wang et al. | Vision-based highway traffic accident detection | |
CN115471872A (en) | Behavior detection method and device for distributing advertisement, electronic equipment and storage medium | |
TWI706381B (en) | Method and system for detecting image object |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190219 |