CN110458090A - Working state of excavator detection method, device, equipment and storage medium - Google Patents
Working state of excavator detection method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN110458090A CN110458090A CN201910730377.5A CN201910730377A CN110458090A CN 110458090 A CN110458090 A CN 110458090A CN 201910730377 A CN201910730377 A CN 201910730377A CN 110458090 A CN110458090 A CN 110458090A
- Authority
- CN
- China
- Prior art keywords
- detection
- image
- excavator
- foreground
- processed
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/0008—Industrial image inspection checking presence/absence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
- G08B25/01—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium
- G08B25/08—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium using communication transmission lines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30242—Counting objects in image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of working state of excavator detection method, device, equipment and storage mediums, this method comprises: carrying out background modeling for the video frame in the video flowing of input to obtain the foreground image of image to be processed, and pre-process to foreground image；If the ratio that the quantity of pixel accounts for the quantity of pixel in entire image to be processed in foreground image is greater than the first preset ratio threshold value, the quantity for the detection model statistic mixed-state target that application constructs in advance；Wherein, detection target includes excavator；If the quantity for detecting target is greater than zero, the location information of detection block where exporting detection target, and determine the quantity of detection block；The number summation of the foreground pixel point in each detection block is counted, if summation is greater than the second preset threshold, it is determined that excavator is in running order, and sends warning information to the terminal device bound in advance.Real-time detection working state of excavator, and warning information is sent, realize the protection to communication cable.
Description
Technical field
The present invention relates to computer assisted image processing technical fields, and in particular to a kind of working state of excavator detection method,
Device, equipment and storage medium.
Background technique
With the development of science and technology the use of excavator improves production efficiency, at the same time, in some special scenes
In, the operation of excavator brings threat to the normal use of communications optical cable route.
It in the related technology, usually can be using traditional machine learning method or using the server of deep learning method
The detection pattern at end detects the working condition of excavator.But in the above method, the former defect is excavator institute
The outdoor environment at place brings huge challenge to detection, detection effect is unsatisfactory with the variation of weather；The defect of the latter
Be, it is high to the performance requirement of server, when needing the scene detected to increase, then cannot in real time to the situation in scene into
Row judgement.Therefore, method in the related technology cannot effectively detect the working condition of excavator.
Summary of the invention
In view of this, a kind of working state of excavator detection method, device, equipment and storage medium are provided, to solve phase
The problem of excavator in the technology of pass is easy to cause the communications optical cable route of surrounding to be destroyed in use.
The present invention adopts the following technical scheme:
In a first aspect, the embodiment of the present application provides a kind of working state of excavator detection, this method comprises:
Background modeling is carried out to obtain the foreground image of image to be processed for the video frame in the video flowing of input, and right
The foreground image is pre-processed；The video flowing is to obtain to setting regions shooting around excavator；
If the ratio that the quantity of pixel accounts for the quantity of pixel in entire image to be processed in the foreground image is greater than
First preset ratio threshold value, the then quantity for the detection model statistic mixed-state target that application constructs in advance；Wherein, the detection target
Including excavator；
If the quantity of the detection target is greater than zero, the location information of detection block where exporting the detection target, and
Determine the quantity of the detection block；
The number summation of the foreground pixel point in each detection block is counted, if the summation is greater than the second preset threshold,
It determines that the excavator is in running order, and sends warning information to the terminal device bound in advance.
Further, background modeling is carried out to obtain the prospect of image to be processed for the video frame in the video flowing of input
Image, comprising:
Background modeling is carried out for the video frame in the video flowing of input, using default foreground detection algorithm by described wait locate
The foreground image and background image for managing image separate, to obtain the foreground image of the image to be processed.
Further, it is described to the foreground image carry out pretreatment include:
Opening operation processing is carried out to the foreground image.
Further, the detection model constructed in advance includes the lightweight using more classification single pole detection algorithm buildings
Convolutional neural networks model.
Further, the default foreground detection algorithm includes Vive algorithm.
Further, the detection model constructed in advance includes the lightweight using more classification single pole detection algorithm buildings
Convolutional neural networks model.
Further, the default foreground detection algorithm includes Vive algorithm.
Second aspect, the embodiment of the present application provide a kind of working state of excavator detection device, which includes:
Preprocessing module carries out background modeling for the video frame in the video flowing for input to obtain image to be processed
Foreground image, and the foreground image is pre-processed；The video flowing is to obtain to setting regions shooting around excavator
；
Destination number detection module, the quantity used in the pixel in the foreground image account for picture in entire image to be processed
When the ratio of the quantity of vegetarian refreshments is greater than the first preset ratio threshold value, using the number of the detection model statistic mixed-state target constructed in advance
Amount；Wherein, the detection target includes excavator；
Detection block quantity determining module, for exporting the detection target when the quantity of the detection target is greater than zero
The location information of place detection block, and determine the quantity of the detection block；
Warning information sending module, for counting the number summation of the foreground pixel point in each detection block, if described total
Be greater than the second preset threshold, it is determined that the excavator is in running order, and sends to the terminal device bound in advance pre-
Alert information.
Further, the preprocessing module includes foreground image acquisition submodule, the foreground image acquisition submodule
It is specifically used for:
Background modeling is carried out for the video frame in the video flowing of input, using default foreground detection algorithm by described wait locate
The foreground image and background image for managing image separate, to obtain the foreground image of the image to be processed.
Further, the preprocessing module is specifically used for: carrying out opening operation processing to the foreground image.
The third aspect, the embodiment of the present application provide a kind of equipment, which includes:
Processor, and the memory being connected with the processor；
For the memory for storing computer program, the computer program is at least used to execute the embodiment of the present application the
Working state of excavator detection method described in one side；
The processor is for calling and executing the computer program in the memory.
Fourth aspect, the embodiment of the present application provide a kind of storage medium, and the storage medium is stored with computer program,
When the computer program is executed by processor, realize each in working state of excavator detection method as described in relation to the first aspect
Step.
The invention adopts the above technical scheme, carries out background modeling by the video frame in the video flowing for input to obtain
The foreground image of image to be processed is taken, and foreground image is pre-processed；In this way by the method for foreground detection, can exclude
The identification of picture still state, and then reduce power consumption；If the quantity of pixel accounts for picture in entire image to be processed in foreground image
The ratio of the quantity of vegetarian refreshments is greater than the first preset ratio threshold value, then the number for the detection model statistic mixed-state target that application constructs in advance
Amount；In this way, accuracy of identification is high, analysis speed is fast；Wherein, detection target includes excavator；If the quantity for detecting target is greater than zero,
The location information of detection block where then exporting detection target, and determine the quantity of detection block；Count the prospect in each detection block
The number summation of pixel, if summation is greater than the second preset threshold, it is determined that excavator is in running order, and binds to preparatory
Terminal device send warning information.In addition, sending warning information in time after judging working state of excavator, excavation is protected
Communication cable around in machine use process.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of flow chart of excavator condition detection method provided in an embodiment of the present invention；
Fig. 2 is the flow chart of another excavator condition detection method provided in an embodiment of the present invention；
Fig. 3 is a kind of structural schematic diagram of excavator condition checkout gear provided in an embodiment of the present invention；
Fig. 4 is a kind of structural schematic diagram of equipment provided in an embodiment of the present invention.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, technical solution of the present invention will be carried out below
Detailed description.Obviously, described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Base
Embodiment in the present invention, those of ordinary skill in the art are obtained all without making creative work
Other embodiment belongs to the range that the present invention is protected.
Embodiment
Fig. 1 is a kind of flow chart of excavator condition detection method provided in an embodiment of the present invention, and this method can be by this
The excavator condition checkout gear that inventive embodiments provide executes, and the mode which can be used software and/or hardware realizes.
With reference to Fig. 1, this method can specifically include following steps:
S101, background modeling is carried out for the video frame in the video flowing of input to obtain the foreground picture of image to be processed
Picture, and the foreground image is pre-processed；The video flowing is to obtain to setting regions shooting around excavator.
Specifically, using video camera, such as can be rotating camera and the setting regions around excavator is shot,
The maximum magnitude that the setting regions comprehensively considers the demand of user and camera can be shot determines jointly.For example, in certain time,
Excavator only carries out operation in region A, then region A can be identified as the week of the excavator in this working state of excavator detection method
Enclose setting regions.In addition, may include the location information etc. of communication cable in user demand, the location information of communication cable can be with
It gets in advance, and in actual application, setting regions can be determined according to the location information, and then obtain the setting area
The video flowing in domain.
It is shot using photographing device, obtains corresponding video stream data, frame acquisition is carried out to the video flowing of input, is led to
It crosses and background modeling is carried out to video frame, obtain the foreground image of image to be processed.It then, can in order to which the foreground image made is more stable
To pre-process to the foreground image, and pretreated mode is interfered here without limiting for example, by using that can exclude noise
Pretreatment mode.
If the quantity of pixel accounts for the ratio of the quantity of pixel in entire image to be processed in S102, the foreground image
Greater than the first preset ratio threshold value, then the quantity for the detection model statistic mixed-state target that application constructs in advance；Wherein, the detection
Target includes excavator.
Specifically, the quantity of pixel is indicated with count (pixel_frt) in foreground image, in entire image to be processed
The quantity of pixel is height*width, and height indicates the pixel number of image to be processed in the height direction,
Width indicates the pixel quantity of image to be processed in the direction of the width, and height*width indicates entire image to be processed
In pixel quantity.In this manner it is possible to which the quantity for calculating pixel in foreground image accounts for pixel in entire image to be processed
Quantity ratio a, the first preset ratio threshold value indicates with threshold0, and the first preset threshold be it is adjustable, specifically
It can be arranged according to the distance of video camera distance detection scene.
In addition, showing to show current with the presence of the excavator of movement, at this moment at this time if a is greater than threshold0
Frame needs to carry out the identification of working state of excavator, at this point, using the quantity of the detection model statistic mixed-state target constructed in advance,
Carry out the identification of working state of excavator；Wherein, the detection target includes excavator.Otherwise, continue to calculate in foreground image
The quantity of pixel accounts for the ratio of the quantity of pixel in entire image to be processed, until the ratio is greater than the first preset ratio threshold
When value, start the detection of working state of excavator.The calculation formula of a is as follows:
Optionally, the detection model constructed in advance includes the lightweight volume using more classification single pole detection algorithm buildings
Product neural network model.In actual application process, since outdoor illumination condition stability is not good and excavator enough
Shape itself is non-rigid, both factors bring difficulty to excavator identification.The method of deep learning is due to arriving at its end at present
The processing mode at end, and, feature automatically extracts, under such a scenario, for traditional object detection algorithms,
With great robustness.Therefore, the detection model constructed in advance used in the application includes the more classification single pole detections of application
The lightweight convolutional neural networks model of algorithm building, for example, the lightweight network model of great operation advantage can be used
Mobilenet0.25, and combine object detection algorithms SSD (the Single Shot MultiBox of Analysis On Multi-scale Features detection
Detector, single pole detectors of classifying more) algorithm, realize the detection to excavator.
If the quantity of S103, the detection target are greater than zero, the position letter of detection block where exporting the detection target
Breath, and determine the quantity of the detection block.
Specifically, the quantity of detection target can be indicated with num_detect, it is defeated if the quantity of detection target is greater than zero
Target is detected out in the location information of detection block, and location information for example can be detection block on four direction up and down
Maximum abscissa, minimum abscissa, maximum ordinate and minimum ordinate, coordinate here can refer to pixel coordinate.In addition,
After output detects the location information of detection block where target, the quantity of detection block can also be determined, the quantity of detection block can be with
It is indicated with num_process.It should be noted that the quantity of detection block and the quantity of excavator do not contact directly.
The number summation of S104, foreground pixel point in each detection block of statistics, if the summation is greater than the second default threshold
Value, it is determined that the excavator is in running order, and sends warning information to the terminal device bound in advance.
Specifically, counting the foreground pixel in each detection block after the location information of above-mentioned determining detection block and quantity
The number summation of point indicates that determining excavator processing working condition, generates early warning when the summation is greater than the second preset threshold
Information, and warning information is sent to the terminal device bound in advance.The warning information can be text information, can also be voice
It is timely to can contribute to administrative staff in addition, can also carry the identification information etc. of detection block in the warning information in this way for information
Determine the position etc. of in running order excavator.Illustratively, the terminal device bound in advance can be administrative staff's
Mobile phone, alternatively, being the computer etc. of centralized control room where administrative staff.
Above-mentioned analytic process is that the analytical judgment carried out to a detection zone will be directed in actual application process
Each detection zone does analysis as above, until all detection is completed for whole detection zone and detection block.Here detection zone
Domain can be a part of image to be processed, and the division of each detection zone can be research staff according to the need of administrative staff
It asks, alternatively, being set according to the Historical Jobs situation of excavator record.
The invention adopts the above technical scheme, carries out background modeling by the video frame in the video flowing for input to obtain
The foreground image of image to be processed is taken, and foreground image is pre-processed；In this way by the method for foreground detection, can exclude
The identification of picture still state, and then reduce power consumption；If the quantity of pixel accounts for picture in entire image to be processed in foreground image
The ratio of the quantity of vegetarian refreshments is greater than the first preset ratio threshold value, then the number for the detection model statistic mixed-state target that application constructs in advance
Amount；In this way, accuracy of identification is high, analysis speed is fast；Wherein, detection target includes excavator；If the quantity for detecting target is greater than zero,
The location information of detection block where then exporting detection target, and determine the quantity of detection block；Count the prospect in each detection block
The number summation of pixel, if summation is greater than the second preset threshold, it is determined that excavator is in running order, and binds to preparatory
Terminal device send warning information.In addition, judging around communication cable after the working state of excavator of operation in time
Warning information is sent, the communication cable around in excavator use process is protected.
Fig. 2 is a kind of flow chart for working state of excavator detection method that further embodiment of this invention provides, this implementation
Example is realized on the basis of the above embodiments.With reference to Fig. 2, this method can specifically include following steps:
S201, background modeling is carried out for the video frame in the video flowing of input, using default foreground detection algorithm by institute
The foreground image and background image for stating image to be processed separate, to obtain the foreground image of the image to be processed.
Optionally, the default foreground detection algorithm includes Vive algorithm.Wherein, Vive algorithm is that one kind is based on background more
New foreground detection algorithm, principle are that the pixel value and pervious pixel value by extracting pixel (x, y) surrounding establish picture
Then pixel value at another frame (x, y) is compared by the sample set of vegetarian refreshments with the pixel value in sample set again, if its with
If the big Mr. Yu's threshold value of the distance of pixel value in sample set, then it is assumed that the pixel is foreground pixel point, is otherwise background picture
Vegetarian refreshments.In the embodiment of the present application, Vive algorithm can in video moving object and background distinguish, at excavator
When stationary state, it will not threaten to the cable machinery of surrounding.Therefore it need to only pay close attention to and occur the feelings changed in scene
When condition, judge that the part of movement is wanted with the presence or absence of excavator, while compared to continuous detection, the operand of foreground detection always
It is small, help to reduce power consumption of the whole system when using in equipment.
S202, opening operation processing is carried out to the foreground image.
Wherein, in mathematical morphology, opening operation is defined as first corroding to be expanded afterwards, and mathematical morphology is one and establishes
Image analysis subject on lattice theory and topology basis, is the basic theories of morphological image processing.Its basic fortune
Calculation include: corrosion and expansion, opening operation and closed operation, skeleton extract, limit burn into hit or miss transform, Morphological Gradient,
Top-hat transformation, grading analysis, Watershed Transformation etc..Therefore, in the embodiment of the present application, foreground image is carried out at opening operation
Reason, can be obtained by the noise removed in foreground image in this way, obtains stable foreground image.
If the quantity of pixel accounts for the ratio of the quantity of pixel in entire image to be processed in S203, the foreground image
Greater than the first preset ratio threshold value, then the quantity for the detection model statistic mixed-state target that application constructs in advance；Wherein, the detection
Target includes excavator.
If the quantity of S204, the detection target are greater than zero, the position letter of detection block where exporting the detection target
Breath, and determine the quantity of the detection block.
The number summation of S205, foreground pixel point in each detection block of statistics, if the summation is greater than the second default threshold
Value, it is determined that the excavator is in running order, and sends warning information to the terminal device bound in advance.
In the embodiment of the present application, background modeling is carried out by the video frame in the video flowing for input, before default
Scape detection algorithm separates foreground image and the background image of the image to be processed, to obtain the prospect of the image to be processed
Image, the operand that foreground detection is utilized is small, helps to reduce power consumption of the whole system in equipment；And to foreground image into
The processing of row opening operation, eliminates the noise in foreground image, has obtained stable foreground image.In this way, there is accurate determine to excavate
The working condition of machine and in time early warning provide technical foundation.
To sum up, in the embodiment of the present application, by the excavator detection system based on prospect judgement and depth light weight network, lead to
The identification that the method for crossing foreground detection excludes picture still state calculates, and then reduces the power consumption of equipment；By using lightweight
Deep learning model identify excavator, and then determine working state of excavator, it is higher than existing machine learning method precision, together
When compared to server end deep learning method detection scheme analysis speed faster, and then realize that real-time warning information pushes away
It send；The working condition of excavator is analyzed, the analysis of prospect is passed through and can effectively judge excavator in conjunction with identification technology
Working condition, warning information can accurately be pushed in this way.
Fig. 3 is the structural schematic diagram that the present invention is a kind of working state of excavator detection device that embodiment provides, the dress
It sets and is adapted for carrying out a kind of working state of excavator detection method that the embodiment of the present invention is supplied to.As shown in figure 3, the device has
Body may include: preprocessing module 301, destination number detection module 302, detection block quantity determining module 303 and warning information
Sending module 304.
Wherein, preprocessing module 301, for for input video flowing in video frame carry out background modeling with obtain to
The foreground image of image is handled, and the foreground image is pre-processed；The video flowing is to setting area around excavator
Domain shooting obtains；Destination number detection module 302 accounts for entire figure to be processed used in the quantity of the pixel in the foreground image
When the ratio of the quantity of pixel is greater than the first preset ratio threshold value as in, using the detection model statistic mixed-state mesh constructed in advance
Target quantity；Wherein, the detection target includes excavator；Detection block quantity determining module 303, in the detection target
Quantity when being greater than zero, the location information of detection block where exporting the detection target, and determine the quantity of the detection block；In advance
Alert information sending module 304, for counting the number summation of the foreground pixel point in each detection block, if the summation is greater than the
Two preset thresholds, it is determined that the excavator is in running order, and sends warning information to the terminal device bound in advance.
The invention adopts the above technical scheme, carries out background modeling by the video frame in the video flowing for input to obtain
The foreground image of image to be processed is taken, and foreground image is pre-processed；In this way by the method for foreground detection, can exclude
The identification of picture still state, and then reduce power consumption；If the quantity of pixel accounts for picture in entire image to be processed in foreground image
The ratio of the quantity of vegetarian refreshments is greater than the first preset ratio threshold value, then the number for the detection model statistic mixed-state target that application constructs in advance
Amount；In this way, accuracy of identification is high, analysis speed is fast；Wherein, detection target includes excavator；If the quantity for detecting target is greater than zero,
The location information of detection block where then exporting detection target, and determine the quantity of detection block；Count the prospect in each detection block
The number summation of pixel, if summation is greater than the second preset threshold, it is determined that excavator is in running order, and binds to preparatory
Terminal device send warning information.In addition, sending warning information in time after judging working state of excavator, excavation is protected
Communication cable around in machine use process.
Further, preprocessing module 301 includes foreground image acquisition submodule, the foreground image acquisition submodule tool
Body is used for: background modeling is carried out for the video frame in the video flowing of input, using default foreground detection algorithm by described wait locate
The foreground image and background image for managing image separate, to obtain the foreground image of the image to be processed.
Further, preprocessing module 301 is specifically used for: carrying out opening operation processing to the foreground image.
Further, the detection model constructed in advance includes the lightweight using more classification single pole detection algorithm buildings
Convolutional neural networks model.
Further, the default foreground detection algorithm includes Vive algorithm.
Working state of excavator detection device provided in an embodiment of the present invention can be performed what any embodiment of that present invention provided
Working state of excavator detection method has the corresponding functional module of execution method and beneficial effect.
The embodiment of the present invention also provides a kind of equipment, referring to Fig. 4, Fig. 4 is a kind of structural schematic diagram of equipment, such as Fig. 4
Shown, which includes: processor 410, and the memory 420 being connected with processor 410；Memory 420 is for storing
Computer program, the computer program are at least used to execute the working state of excavator detection method in the embodiment of the present invention；
Processor 410 is for calling and executing the computer program in the memory, above-mentioned working state of excavator detection side
Method includes at least following steps: before carrying out background modeling for the video frame in the video flowing of input to obtain image to be processed
Scape image, and foreground image is pre-processed；If the quantity of pixel accounts for pixel in entire image to be processed in foreground image
The ratio of the quantity of point is greater than the first preset ratio threshold value, then the number for the detection model statistic mixed-state target that application constructs in advance
Amount；Wherein, detection target includes excavator；If the quantity for detecting target is greater than zero, detection block where exporting detection target
Location information, and determine the quantity of detection block；The number summation for counting the foreground pixel point in each detection block, if summation is greater than
Second preset threshold, it is determined that excavator is in running order, and sends warning information to the terminal device bound in advance.
The embodiment of the present invention also provides a kind of storage medium, and the storage medium is stored with computer program, the calculating
When machine program is executed by processor, realize such as each step in the working state of excavator detection method in the embodiment of the present invention:
Background modeling is carried out to obtain the foreground image of image to be processed for the video frame in the video flowing of input, and to foreground image
It is pre-processed；If the ratio that the quantity of pixel accounts for the quantity of pixel in entire image to be processed in foreground image is greater than the
One preset ratio threshold value, the then quantity for the detection model statistic mixed-state target that application constructs in advance；Wherein, detection target includes digging
Pick machine；If the quantity for detecting target is greater than zero, the location information of detection block where exporting detection target, and determine detection block
Quantity；The number summation of the foreground pixel point in each detection block is counted, if summation is greater than the second preset threshold, it is determined that excavate
Machine is in running order, and sends warning information to the terminal device bound in advance.
It is understood that same or similar part can mutually refer in the various embodiments described above, in some embodiments
Unspecified content may refer to the same or similar content in other embodiments.
It should be noted that in the description of the present invention, term " first ", " second " etc. are used for description purposes only, without
It can be interpreted as indication or suggestion relative importance.In addition, in the description of the present invention, unless otherwise indicated, the meaning of " multiple "
Refer at least two.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes
It is one or more for realizing specific logical function or process the step of executable instruction code module, segment or portion
Point, and the range of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discussed suitable
Sequence, including according to related function by it is basic simultaneously in the way of or in the opposite order, Lai Zhihang function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
It should be appreciated that each section of the invention can be realized with hardware, software, firmware or their combination.Above-mentioned
In embodiment, software that multiple steps or method can be executed in memory and by suitable instruction execution system with storage
Or firmware is realized.It, and in another embodiment, can be under well known in the art for example, if realized with hardware
Any one of column technology or their combination are realized: having a logic gates for realizing logic function to data-signal
Discrete logic, with suitable combinational logic gate circuit specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
Those skilled in the art are understood that realize all or part of step that above-described embodiment method carries
It suddenly is that relevant hardware can be instructed to complete by program, the program can store in a kind of computer-readable storage medium
In matter, which when being executed, includes the steps that one or a combination set of embodiment of the method.
It, can also be in addition, each functional unit in each embodiment of the present invention can integrate in a processing module
It is that each unit physically exists alone, can also be integrated in two or more units in a module.Above-mentioned integrated mould
Block both can take the form of hardware realization, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized and when sold or used as an independent product in the form of software function module, also can store in a computer
In read/write memory medium.
Storage medium mentioned above can be read-only memory, disk or CD etc..
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.In the present specification, schematic expression of the above terms are not
Centainly refer to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be any
One or more embodiment or examples in can be combined in any suitable manner.
Although the embodiments of the present invention has been shown and described above, it is to be understood that above-described embodiment is example
Property, it is not considered as limiting the invention, those skilled in the art within the scope of the invention can be to above-mentioned
Embodiment is changed, modifies, replacement and variant.
Claims (10)
1. a kind of working state of excavator detection method characterized by comprising
Background modeling is carried out to obtain the foreground image of image to be processed for the video frame in the video flowing of input, and to described
Foreground image is pre-processed；The video flowing is to obtain to setting regions shooting around excavator；
If the ratio that the quantity of pixel accounts for the quantity of pixel in entire image to be processed in the foreground image is greater than first
Preset ratio threshold value, the then quantity for the detection model statistic mixed-state target that application constructs in advance；Wherein, the detection target includes
Excavator；
If the quantity of the detection target is greater than zero, the location information of detection block where exporting the detection target, and determine
The quantity of the detection block；
The number summation of the foreground pixel point in each detection block is counted, if the summation is greater than the second preset threshold, it is determined that
The excavator is in running order, and sends warning information to the terminal device bound in advance.
2. being built the method according to claim 1, wherein carrying out background for the video frame in the video flowing of input
Mould is to obtain the foreground image of image to be processed, comprising:
Background modeling is carried out for the video frame in the video flowing of input, using default foreground detection algorithm by the figure to be processed
The foreground image and background image of picture separate, to obtain the foreground image of the image to be processed.
3. the method according to claim 1, wherein it is described to the foreground image carry out pretreatment include:
Opening operation processing is carried out to the foreground image.
4. the method according to claim 1, wherein the detection model constructed in advance includes the more classification of application
The lightweight convolutional neural networks model of single pole detection algorithm building.
5. according to the method described in claim 2, it is characterized in that, the default foreground detection algorithm includes Vive algorithm.
6. a kind of working state of excavator detection device characterized by comprising
Preprocessing module, before carrying out background modeling for the video frame in the video flowing for input to obtain image to be processed
Scape image, and the foreground image is pre-processed；The video flowing is to obtain to setting regions shooting around excavator；
Destination number detection module, the quantity used in the pixel in the foreground image account for pixel in entire image to be processed
Quantity ratio be greater than the first preset ratio threshold value when, using the quantity of the detection model statistic mixed-state target constructed in advance；
Wherein, the detection target includes excavator；
Detection block quantity determining module, for exporting the detection target place when the quantity of the detection target is greater than zero
The location information of detection block, and determine the quantity of the detection block；
Warning information sending module, for counting the number summation of the foreground pixel point in each detection block, if the summation is big
In the second preset threshold, it is determined that the excavator is in running order, and sends early warning letter to the terminal device bound in advance
Breath.
7. device according to claim 6, which is characterized in that the preprocessing module includes that foreground image obtains submodule
Block, the foreground image acquisition submodule are specifically used for:
Background modeling is carried out for the video frame in the video flowing of input, using default foreground detection algorithm by the figure to be processed
The foreground image and background image of picture separate, to obtain the foreground image of the image to be processed.
8. device according to claim 6, which is characterized in that the preprocessing module is specifically used for:
Opening operation processing is carried out to the foreground image.
9. a kind of equipment characterized by comprising
Processor, and the memory being connected with the processor；
The memory is at least used for perform claim and requires any one of 1-5 for storing computer program, the computer program
The working state of excavator detection method；
The processor is for calling and executing the computer program in the memory.
10. a kind of storage medium, which is characterized in that the storage medium is stored with computer program, the computer program quilt
When processor executes, each step in working state of excavator detection method as described in any one in claim 1-5 is realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910730377.5A CN110458090A (en) | 2019-08-08 | 2019-08-08 | Working state of excavator detection method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910730377.5A CN110458090A (en) | 2019-08-08 | 2019-08-08 | Working state of excavator detection method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110458090A true CN110458090A (en) | 2019-11-15 |
Family
ID=68485452
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910730377.5A Pending CN110458090A (en) | 2019-08-08 | 2019-08-08 | Working state of excavator detection method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110458090A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111401269A (en) * | 2020-03-19 | 2020-07-10 | 成都云盯科技有限公司 | Commodity hotspot detection method, device and equipment based on monitoring video |
| CN112836268A (en) * | 2019-11-25 | 2021-05-25 | 深圳云天励飞技术有限公司 | Pipeline excavating method and related product |
| CN112862817A (en) * | 2021-03-16 | 2021-05-28 | 精英数智科技股份有限公司 | Roller rope disorder detection method and device based on machine vision |
| CN112947180A (en) * | 2021-02-04 | 2021-06-11 | 中国地质大学（武汉） | Heavy machinery operation state identification and prediction method, device, equipment and storage medium |
| CN113808154A (en) * | 2021-08-02 | 2021-12-17 | 惠州Tcl移动通信有限公司 | Video image processing method and device, terminal equipment and storage medium |
| CN115439511A (en) * | 2022-11-09 | 2022-12-06 | 广东电网有限责任公司珠海供电局 | Excavator motion monitoring method, system and equipment |
| CN116055690A (en) * | 2023-04-03 | 2023-05-02 | 山东金宇信息科技集团有限公司 | Method and equipment for processing machine room monitoring video |
Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10105646A (en) * | 1996-09-25 | 1998-04-24 | Ricoh Co Ltd | Method and device for erasing ruled line and recording medium |
| CN103324158A (en) * | 2013-05-14 | 2013-09-25 | 浙江大学 | Engineering machinery onboard video monitoring system with face detection function |
| CN103425960A (en) * | 2012-05-25 | 2013-12-04 | 信帧电子技术（北京）有限公司 | Method for detecting fast-moving objects in video |
| CN103810498A (en) * | 2014-02-14 | 2014-05-21 | 广州供电局有限公司 | Method and system for monitoring excavator in construction scene |
| CN104244113A (en) * | 2014-10-08 | 2014-12-24 | 中国科学院自动化研究所 | Method for generating video abstract on basis of deep learning technology |
| CN104463904A (en) * | 2014-09-22 | 2015-03-25 | 国家电网公司 | High-voltage line foreign matter invasion target detection method |
| CN105868734A (en) * | 2016-04-22 | 2016-08-17 | 江苏电力信息技术有限公司 | Power transmission line large-scale construction vehicle recognition method based on BOW image representation model |
| CN105894701A (en) * | 2016-04-05 | 2016-08-24 | 江苏电力信息技术有限公司 | Large construction vehicle identification and alarm method for preventing external damage to transmission lines |
| CN106650622A (en) * | 2016-11-18 | 2017-05-10 | 华南农业大学 | Excavator working state identification method based on hybrid LBF shape regression model |
| CN106780549A (en) * | 2016-11-18 | 2017-05-31 | 天津大学 | Stabilization moving target detecting method based on Android platform |
| CN107679495A (en) * | 2017-10-09 | 2018-02-09 | 济南大学 | A kind of detection method of transmission line of electricity periphery activity engineering truck |
| CN107888887A (en) * | 2017-12-02 | 2018-04-06 | 深圳市燃气集团股份有限公司 | A kind of video monitoring method for early warning and system for monitoring gas pipeline damage from third-party |
| CN107992899A (en) * | 2017-12-15 | 2018-05-04 | 四川大学 | A kind of airdrome scene moving object detection recognition methods |
| CN108198207A (en) * | 2017-12-22 | 2018-06-22 | 湖南源信光电科技股份有限公司 | Multiple mobile object tracking based on improved Vibe models and BP neural network |
| CN108985169A (en) * | 2018-06-15 | 2018-12-11 | 浙江工业大学 | Across the door operation detection method in shop based on deep learning target detection and dynamic background modeling |
| CN109035292A (en) * | 2018-08-31 | 2018-12-18 | 北京智芯原动科技有限公司 | Moving target detecting method and device based on deep learning |
| CN109255335A (en) * | 2018-09-28 | 2019-01-22 | 广州希华通讯设备有限公司 | Identification monitoring system for construction site excavator |
| CN109343443A (en) * | 2018-09-28 | 2019-02-15 | 广州希华通讯设备有限公司 | Excavate machine monitoring recognition methods |
| CN109657564A (en) * | 2018-11-28 | 2019-04-19 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of personnel detection method, device, storage medium and terminal device on duty |
| CN109727275A (en) * | 2018-12-29 | 2019-05-07 | 北京沃东天骏信息技术有限公司 | Object detection method, device, system and computer readable storage medium |
-
2019
- 2019-08-08 CN CN201910730377.5A patent/CN110458090A/en active Pending
Patent Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10105646A (en) * | 1996-09-25 | 1998-04-24 | Ricoh Co Ltd | Method and device for erasing ruled line and recording medium |
| CN103425960A (en) * | 2012-05-25 | 2013-12-04 | 信帧电子技术（北京）有限公司 | Method for detecting fast-moving objects in video |
| CN103324158A (en) * | 2013-05-14 | 2013-09-25 | 浙江大学 | Engineering machinery onboard video monitoring system with face detection function |
| CN103810498A (en) * | 2014-02-14 | 2014-05-21 | 广州供电局有限公司 | Method and system for monitoring excavator in construction scene |
| CN104463904A (en) * | 2014-09-22 | 2015-03-25 | 国家电网公司 | High-voltage line foreign matter invasion target detection method |
| CN104244113A (en) * | 2014-10-08 | 2014-12-24 | 中国科学院自动化研究所 | Method for generating video abstract on basis of deep learning technology |
| CN105894701A (en) * | 2016-04-05 | 2016-08-24 | 江苏电力信息技术有限公司 | Large construction vehicle identification and alarm method for preventing external damage to transmission lines |
| CN105868734A (en) * | 2016-04-22 | 2016-08-17 | 江苏电力信息技术有限公司 | Power transmission line large-scale construction vehicle recognition method based on BOW image representation model |
| CN106650622A (en) * | 2016-11-18 | 2017-05-10 | 华南农业大学 | Excavator working state identification method based on hybrid LBF shape regression model |
| CN106780549A (en) * | 2016-11-18 | 2017-05-31 | 天津大学 | Stabilization moving target detecting method based on Android platform |
| CN107679495A (en) * | 2017-10-09 | 2018-02-09 | 济南大学 | A kind of detection method of transmission line of electricity periphery activity engineering truck |
| CN107888887A (en) * | 2017-12-02 | 2018-04-06 | 深圳市燃气集团股份有限公司 | A kind of video monitoring method for early warning and system for monitoring gas pipeline damage from third-party |
| CN107992899A (en) * | 2017-12-15 | 2018-05-04 | 四川大学 | A kind of airdrome scene moving object detection recognition methods |
| CN108198207A (en) * | 2017-12-22 | 2018-06-22 | 湖南源信光电科技股份有限公司 | Multiple mobile object tracking based on improved Vibe models and BP neural network |
| CN108985169A (en) * | 2018-06-15 | 2018-12-11 | 浙江工业大学 | Across the door operation detection method in shop based on deep learning target detection and dynamic background modeling |
| CN109035292A (en) * | 2018-08-31 | 2018-12-18 | 北京智芯原动科技有限公司 | Moving target detecting method and device based on deep learning |
| CN109255335A (en) * | 2018-09-28 | 2019-01-22 | 广州希华通讯设备有限公司 | Identification monitoring system for construction site excavator |
| CN109343443A (en) * | 2018-09-28 | 2019-02-15 | 广州希华通讯设备有限公司 | Excavate machine monitoring recognition methods |
| CN109657564A (en) * | 2018-11-28 | 2019-04-19 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of personnel detection method, device, storage medium and terminal device on duty |
| CN109727275A (en) * | 2018-12-29 | 2019-05-07 | 北京沃东天骏信息技术有限公司 | Object detection method, device, system and computer readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 毛亮 等: "一种基于视频图像的挖掘机工作状态识别方法", 《系统工程理论与实践》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112836268A (en) * | 2019-11-25 | 2021-05-25 | 深圳云天励飞技术有限公司 | Pipeline excavating method and related product |
| CN112836268B (en) * | 2019-11-25 | 2024-06-07 | 深圳云天励飞技术有限公司 | Pipeline excavation method and related products |
| CN111401269A (en) * | 2020-03-19 | 2020-07-10 | 成都云盯科技有限公司 | Commodity hotspot detection method, device and equipment based on monitoring video |
| CN112947180A (en) * | 2021-02-04 | 2021-06-11 | 中国地质大学（武汉） | Heavy machinery operation state identification and prediction method, device, equipment and storage medium |
| CN112947180B (en) * | 2021-02-04 | 2022-06-24 | 中国地质大学（武汉） | Heavy machinery operation state identification and prediction method, device, equipment and storage medium |
| CN112862817A (en) * | 2021-03-16 | 2021-05-28 | 精英数智科技股份有限公司 | Roller rope disorder detection method and device based on machine vision |
| CN113808154A (en) * | 2021-08-02 | 2021-12-17 | 惠州Tcl移动通信有限公司 | Video image processing method and device, terminal equipment and storage medium |
| CN115439511A (en) * | 2022-11-09 | 2022-12-06 | 广东电网有限责任公司珠海供电局 | Excavator motion monitoring method, system and equipment |
| CN115439511B (en) * | 2022-11-09 | 2023-03-10 | 广东电网有限责任公司珠海供电局 | Excavator motion monitoring method, system and equipment |
| CN116055690A (en) * | 2023-04-03 | 2023-05-02 | 山东金宇信息科技集团有限公司 | Method and equipment for processing machine room monitoring video |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110458090A (en) | Working state of excavator detection method, device, equipment and storage medium | |
| CN106096577B (en) | A kind of target tracking method in camera distribution map | |
| CN110147743A (en) | Real-time online pedestrian analysis and number system and method under a kind of complex scene | |
| CN103839308B (en) | Number acquisition methods, Apparatus and system | |
| Wang et al. | Object detection using clustering algorithm adaptive searching regions in aerial images | |
| CN104463117A (en) | Sample collection method and system used for face recognition and based on video | |
| CN103268480A (en) | System and method for visual tracking | |
| CN107123131A (en) | A kind of moving target detecting method based on deep learning | |
| CN110428449A (en) | Target detection tracking method, device, equipment and storage medium | |
| CN109446989A (en) | Crowd massing detection method, device and storage medium | |
| CN108012202A (en) | Video concentration method, equipment, computer-readable recording medium and computer installation | |
| CN103577875A (en) | CAD (computer-aided design) people counting method based on FAST (features from accelerated segment test) | |
| CN109086648A (en) | A kind of method for tracking target merging target detection and characteristic matching | |
| CN103646257A (en) | Video monitoring image-based pedestrian detecting and counting method | |
| WO2020114116A1 (en) | Pedestrian detection method based on dense crowds, and storage medium and processor | |
| CN108647587A (en) | Demographic method, device, terminal and storage medium | |
| CN111476160A (en) | Loss function optimization method, model training method, target detection method, and medium | |
| CN109376693A (en) | Method for detecting human face and system | |
| CN108256567A (en) | A kind of target identification method and system based on deep learning | |
| CN110008789A (en) | Multiclass object detection and knowledge method for distinguishing, equipment and computer readable storage medium | |
| CN104680145A (en) | Method and device for detecting door opening/closing state change | |
| CN105243354B (en) | A kind of vehicle checking method based on target feature point | |
| CN108021852A (en) | A kind of demographic method, passenger number statistical system and electronic equipment | |
| Liu et al. | Image edge recognition of virtual reality scene based on multi-operator dynamic weight detection | |
| CN105809108B (en) | Pedestrian's localization method and system based on distributed vision |
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 |
Application publication date: 20191115 |
|
| RJ01 | Rejection of invention patent application after publication |