CN107423864A - The analysis method and device of crewman's behavior - Google Patents
The analysis method and device of crewman's behavior Download PDFInfo
- Publication number
- CN107423864A CN107423864A CN201610343948.6A CN201610343948A CN107423864A CN 107423864 A CN107423864 A CN 107423864A CN 201610343948 A CN201610343948 A CN 201610343948A CN 107423864 A CN107423864 A CN 107423864A
- Authority
- CN
- China
- Prior art keywords
- crewman
- behavioral data
- image
- video
- static images
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 72
- 230000003542 behavioural effect Effects 0.000 claims abstract description 189
- 230000003068 static effect Effects 0.000 claims abstract description 75
- 238000000034 method Methods 0.000 claims abstract description 18
- 230000006399 behavior Effects 0.000 claims description 69
- 238000012545 processing Methods 0.000 claims description 29
- 238000006243 chemical reaction Methods 0.000 claims description 19
- 238000000605 extraction Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 12
- 238000001914 filtration Methods 0.000 claims description 7
- 239000000284 extract Substances 0.000 claims description 6
- 230000009467 reduction Effects 0.000 claims description 3
- 238000011161 development Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000011946 reduction process Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000005260 corrosion Methods 0.000 description 2
- 230000007797 corrosion Effects 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 210000001747 pupil Anatomy 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/82—Energy audits or management systems therefor
Abstract
The invention discloses a kind of analysis method and device of crewman's behavior, wherein, analysis method includes:The video image of crewman is gathered by video capture device;Video image is pre-processed, video image is converted into multiple static images;The behavioral data of crewman is obtained from multiple static images;The behavioral data of crewman is analyzed, to generate the assessment result of the behavioural norm of crewman.This method generates the assessment result of the behavioural norm of crewman, reference frame is provided for the safety management of ship-handling by analyzing the behavioral data of crewman.
Description
Technical field
The present invention relates to shipping safety technical field, more particularly to a kind of analysis method and device of crewman's behavior.
Background technology
In recent years, China's shipping industry is fast-developing, and its comprehensive strength has been significantly improved on the whole, has had
For safety, the reach of science condition.But during shipping enterprise's fast development between production and operation and safety management still
Many problems so be present.Particularly after financial crisis, shipping enterprise is in the development for focusing on interests, and safety problem is more
Prominent, in the case where major safety risks can not be effectively controlled, security incident happens occasionally, the lives and properties of crewman
Safety is by great threat.
To allow shipping business to obtain benign development, it is necessary to enough attention safety, production and operation are improved by Strengthening Safety Management
Development.However, at present for ship-handling safety management research, only qualitatively theory analysis, without clear and definite
Calculate the mode with assessing.
The content of the invention
The purpose of the present invention is intended at least solve one of above-mentioned technical problem to a certain extent.
Therefore, first purpose of the present invention is to propose a kind of analysis method of crewman's behavior, this method is by analyzing crewman
Behavioral data, generate the assessment result of the behavioural norm of crewman, reference frame provided for the safety management of ship-handling.
Second object of the present invention is to propose a kind of analytical equipment of crewman's behavior.
For the above-mentioned purpose, the analysis method of crewman's behavior of first aspect present invention embodiment, comprises the following steps:Pass through
Video capture device gathers the video image of crewman;The video image is pre-processed, the video image is changed
For multiple static images;The behavioral data of the crewman is obtained from the multiple static images;Behavior number to the crewman
According to being analyzed, to generate the assessment result of the behavioural norm of the crewman.
The analysis method of crewman's behavior according to embodiments of the present invention, extracts the Haar features in multiple static images, and according to
The Haar features of multiple static images position to the target image in multiple static images, and then carry out two to target image
Value is handled, and the behavioral data of crewman is extracted from the target image after binary conversion treatment.It ensure that the row of the crewman of extraction
For the accuracy of data, the accuracy for the assessment result that the behavioural norm of crewman is generated according to crewman's behavioral data has been ensured.
In addition, in one embodiment of the invention, being pre-processed to the video image, the video image is turned
Multiple static images are changed to, including:The video image is scanned frame by frame, generated multiple corresponding to the video image
Video frame image;The multiple video frame image is pre-processed according to predetermined manner, it is corresponding to generate the video image
Multiple static images.
In one embodiment of the invention, the predetermined manner includes gray proces, noise reduction process, at histogram equalization
One or more in reason, filtering process.
In one embodiment of the invention, before being pre-processed to the multiple video frame image according to predetermined manner,
Also include:The human face region image in the multiple picture frame is obtained, and the pretreatment is carried out to the human face region image.
In one embodiment of the invention, the behavioral data of the crewman is obtained from the multiple static images, including:
Extract the Haar features in the multiple static images, and according to the Haar features of the multiple static images to the multiple
Target image in static images is positioned;Binary conversion treatment is carried out to the target image, and from the binary conversion treatment
The behavioral data of the crewman is extracted in target image afterwards.
In one embodiment of the invention, the behavioral data of the crewman is analyzed, including:According to the crewman's
Behavioral data determines the current location information and motion track of the crewman;And/or institute is identified according to the behavioral data of the crewman
State the current fatigue state of crewman;And/or the identity information of crewman is identified according to the behavioral data of the crewman;And/or according to institute
The behavioral data for stating crewman determines the rudder for ship direction information of the crewman;And/or according to the identification of the behavioral data of the crewman
Crewman's lookout behavioural informations.
In one embodiment of the invention, in addition to:The behavioral data of the crewman and crewman's Analysis model of network behaviors are carried out
Matching, to generate the metewand of the behavioural norm of the crewman.
In one embodiment of the invention, the behavioral data of each crewman has the corresponding time in the metewand
Stamp, the analysis method also include:The video image is played back, and the behavior number of the crewman is determined according to the timestamp
The behavioral data of each crewman is verified according to corresponding video frame image, and according to the video frame image.
For the above-mentioned purpose, the analytical equipment of crewman's behavior of second aspect of the present invention embodiment, including:Acquisition module, use
In the video image that crewman is gathered by video capture device;Processing module, for being pre-processed to the video image,
So that the video image is converted into multiple static images;First acquisition module, for being obtained from the multiple static images
The behavioral data of the crewman;Analysis module, for analyzing the behavioral data of the crewman, to generate the crewman
Behavioural norm assessment result.
The analytical equipment of crewman's behavior according to embodiments of the present invention, extracts the Haar features in multiple static images, and according to
The Haar features of multiple static images position to the target image in multiple static images, and then carry out two to target image
Value is handled, and the behavioral data of crewman is extracted from the target image after binary conversion treatment.It ensure that the row of the crewman of extraction
For the accuracy of data, the accuracy for the assessment result that the behavioural norm of crewman is generated according to crewman's behavioral data has been ensured.
In addition, in one embodiment of the invention, the processing module, including:Scanning element, for the video
Image is scanned frame by frame, generates multiple video frame images corresponding to the video image;Processing unit, for described more
Individual video frame image is pre-processed according to predetermined manner, to generate multiple static images corresponding to the video image.
In one embodiment of the invention, the predetermined manner includes gray proces, noise reduction process, at histogram equalization
One or more in reason, filtering process.
In one embodiment of the invention, in addition to:Second acquisition module, for obtaining the people in the multiple picture frame
Face area image;The processing module is additionally operable to carry out the pretreatment to the human face region image.
In one embodiment of the invention, the first acquisition module includes:First extraction unit, it is the multiple quiet for extracting
Haar features in state picture;Positioning unit, for according to the Haar features of the multiple static images to the multiple quiet
Target image in state picture is positioned;Second extraction unit, for carrying out binary conversion treatment to the target image, and
The behavioral data of the crewman is extracted from the target image after the binary conversion treatment.
In one embodiment of the invention, the analysis module is used for:The ship is identified according to the behavioral data of the crewman
The current fatigue state of member;And/or the identity information of crewman is identified according to the behavioral data of the crewman;And/or according to the ship
The behavioral data of member determines the rudder for ship direction information of the crewman;And/or the crewman is identified according to the behavioral data of the crewman
Lookout behavioural informations.
In one embodiment of the invention, in addition to:Matching module, for by the behavioral data of the crewman and crewman's row
Matched for analysis model, to generate the metewand of the behavioural norm of the crewman.
In one embodiment of the invention, the behavioral data of each crewman has the corresponding time in the metewand
Stamp, the analytical equipment also include:Authentication module, for playing back the video image, according to determining the timestamp
Video frame image corresponding to the behavioral data of crewman, and the behavior number according to the video frame image to each crewman
According to being verified.
The additional aspect of the present invention and advantage will be set forth in part in the description, and partly will become bright from the following description
It is aobvious, or recognized by the practice of the present invention.
Brief description of the drawings
Of the invention above-mentioned and/or additional aspect and advantage will be apparent from the following description of the accompanying drawings of embodiments
Be readily appreciated that, wherein:
Fig. 1 is the flow chart of the analysis method of crewman's behavior according to an embodiment of the invention;
Fig. 2 is the flow chart according to the analysis method of crewman's behavior of a specific embodiment of the invention;
Fig. 3 is the flow chart of the analysis method of crewman's behavior in accordance with another embodiment of the present invention;
Fig. 4 is the flow chart according to the analysis method of crewman's behavior of another embodiment of the invention;
Fig. 5 is the structural representation of the analytical equipment of crewman's behavior according to an embodiment of the invention;
Fig. 6 is the structural representation according to the analytical equipment of crewman's behavior of a specific embodiment of the invention;
Fig. 7 is the structural representation of the analytical equipment of crewman's behavior in accordance with another embodiment of the present invention;
Fig. 8 is the structural representation according to the analytical equipment of crewman's behavior of another embodiment of the invention;
Fig. 9 is the structural representation according to the analytical equipment of crewman's behavior of further embodiment of the present invention;And
Figure 10 is the structural representation according to the analytical equipment of crewman's behavior of a still further embodiment of the present invention.
Embodiment
Embodiments of the invention are described below in detail, the example of the embodiment is shown in the drawings, wherein identical from beginning to end
Or similar label represents same or similar element or the element with same or like function.Retouched below with reference to accompanying drawing
The embodiment stated is exemplary, it is intended to for explaining the present invention, and is not considered as limiting the invention.
The analysis method and device of crewman's behavior of the embodiment of the present invention are specifically described below in conjunction with the accompanying drawings.
Fig. 1 is the flow chart of the analysis method of crewman's behavior according to an embodiment of the invention.As shown in figure 1, the ship
The analysis method of member's behavior includes:
S110, the video image of crewman is gathered by video capture device.
It is appreciated that the safe driving of behavior and ship of the crewman on ship is closely bound up.Such as in tired shape
The crewman of state, may be when driving ship, because reaction causes ship to hit a submerged reef not in time.Therefore can be according to analysis
The behavioural information of crewman, the safety management that ships drive.
Specifically, the video image of crewman by the video capture device on ship, can be gathered, in order to be regarded according to this
Frequency image obtains the behavioural information of crewman.
Wherein, the video image quality of collection and the configuration of video capture device are related.
In one embodiment of the invention, in order to ensure the video image quality of collection, video capture device can be with
Raspberry Pi are terminal platform, and Raspberry Pi carry the core processors of ARM Cortex-A7 tetra-, 1GB LPDDR2
The hardware modules such as SDRAM and VideoCore IV double-cores GPU, while GPU offer OpenGLs ES 2.0,
The hardware-accelerated high-end decoding of OpenVG and 1080p30H.264.
Due in the application of reality, the video quality of collection can by the environment where ship, crewman's scope of activities,
There is fuzzy situation etc. in the influence of the factors such as crewman's driving habit, such as the video image that the rainy day may result in collection,
Therefore in order to be further ensured that the quality of video image, when gathering the video image of crewman, it is also necessary to consider ship
Environmental factor etc..
In one embodiment of the invention, video capture device is taken the photograph using camera module using RPi Camera are infrared
As module, the module can realize zoom function, can be by effectively being avoided because of crewman's scope of activities not according to environment zoom
The image caused by difference such as same, different crewman's driving habits and different ship environments obscures.
The image gathered by infrared photography module, by the simple pre- place such as noise reduction, setting contrast, histogram equalization
Reason, and can be sent image to back-end analysis system in a manner of video flowing by way of Real-time Transport Protocol, can be effective
Capacity volume variance of the reflection collection target with ship-handling cabin background to external radiation, while there is stronger anti-interference, energy
Analysis and processing enough for successive image provide gray average it is relative stablize, the good video image of spatial coherence.
S120, video image is pre-processed, video image is converted into multiple static images.
Specifically, after video image is collected, for the ease of analyzing the behavioural information of the crewman in the video image,
Need to pre-process video image, by video image be converted into multiple picture qualities preferably, be easy to subsequent analysis
Static images.
, wherein it is desired to it is noted that image processing techniques means are varied, can not had to according to application scenarios, using not
Video image is converted to multiple static images by same technological means.
As a kind of example, video image can be scanned frame by frame, generate multiple video frame images corresponding to video image.
And multiple video frame images are pre-processed according to predetermined manner, to generate multiple static images corresponding to video image,
Wherein, predetermined manner includes a kind of or more in gray proces, noise reduction process, histogram equalization processing, filtering process
Kind.
S130, the behavioral data of crewman is obtained from multiple static images.
Specifically, the behavioral data of crewman can by the respective handling to the target image in static images, be obtained.Wherein,
Target image is the image for the physiological site that can react the behavioural information of crewman, for example can react crewman's notice collection
Eye image of middle situation and degree of fatigue etc..
It is emphasized that the behavioral data of crewman, the existing equipment of different behavioural norms and different ships has from crewman's
Close, the behavioral data of user can have a variety of.Such as the behavioral data of crewman can include crewman eyes behavioral data,
The facial image of crewman, the real-time position information of crewman and real-time limb action of crewman etc..
Specifically, the target image in multiple static images can be positioned first, and after target image is oriented,
According to concrete application demand, associated picture treatment technology means are taken, target image are handled to obtain the behavior of crewman
Data.
In addition, in one embodiment of the invention, in the above-mentioned target image in static images calculate the mistake of processing
Cheng Zhong, in order to reduce the waste of computing resource, improve the efficiency of calculating, can also to multiple video frame images according to default
Before mode is pre-processed, the face region in multiple images frame is positioned, and intercepts human face region image, to obtaining
Multiple images frame in human face region image pre-processed according to predetermined manner.
S140, the behavioral data of crewman is analyzed, to generate the assessment result of the behavioural norm of crewman.
Specifically, for the behavioural information of more intuitive understanding crewman, the behavioral data of crewman can be analyzed, with life
Into the behavioural norm assessment result of crewman.
, wherein it is desired to explanation, by assessment result can be determined that out the behavior of crewman meet right behavioural norm, whether
With danger etc..The assessment result can have many forms, for example can be showed in a manner of metewand, you can make
The degree of the behavioural norm of crewman is represented with metewand, metewand is higher, the behavior of crewman more specification, safer.
In order to more strengthen the analysis method of clearly crewman's behavior of the description embodiment of the present invention, below in conjunction with the accompanying drawings 2 couples of crewman
The analysis process of behavior is illustrated, and is described as follows:As shown in Fig. 2 crewman's behavioural analysis flow can be divided into image
Obtain four (S210), image procossing (S220), graphical analysis (S230) and image understanding (S240) steps.
Specifically, in step S210, video image can be obtained by the video capture device of correlation.
And then in step S220, image procossing can be divided into two steps of data processing (S221) and pretreatment (S222)
Suddenly, after video image is got, after the data processing operation such as be adjusted correspondingly, compress and deposit to video image,
Video image is pre-processed by technological means such as transducer calibration, filtering, enhancing and recoveries, video image is turned
It is changed to multiple static images.
Further, in step S230, multiple static images are analyzed, positioned by Target Segmentation, target image,
The image analysis technology means such as target image tracking and feature extraction obtain the behavioral data of crewman from multiple static images.
Further, in step S240, the behavioral data of crewman is analyzed, by target identification, behavior understanding,
The assessment result of the behavioural norm of the technological means decision making crewman such as threat estimating.
In summary, the analysis method of crewman's behavior of the embodiment of the present invention, the video of crewman is gathered by video capture device
Image, video image is pre-processed, video image is converted into multiple static images, and from multiple static images
The behavioral data of crewman is obtained, and then the behavioral data of crewman is analyzed, to generate the assessment knot of the behavioural norm of crewman
Fruit.This method generates the assessment result of the behavioural norm of crewman, is the peace of ship-handling by analyzing the behavioral data of crewman
Full management provides reference frame.
For more clear explanation, the behavioral data of crewman how is obtained from multiple static images, below in conjunction with the accompanying drawings 3
It is specifically described, in this example, positioning target image by way of the Haar features for extracting static images, and passes through
Binaryzation mode pre-processes to target image, to obtain the behavioral data of crewman.It is described as follows:
S310, the video image of crewman is gathered by video capture device.
S320, video image is pre-processed, video image is converted into multiple static images.
S330, extracts the Haar features in multiple static images, and according to the Haar features of multiple static images to multiple quiet
Target image in state picture is positioned.
S340, binary conversion treatment is carried out to target image, and the behavior of crewman is extracted from the target image after binary conversion treatment
Data.
The basic thought of Haar features is exactly first by rectangle frame piecemeal, then the gray-scale pixels of piecemeal is combined point with edge feature
A kind of characteristic analysis method of analysis.Haar features are divided into three classes:Edge feature, linear character, central feature and diagonal are special
Sign, these three combinations of features are into feature templates.There are white and two kinds of rectangles of black in feature templates, and define the spy of the template
Value indicative be white rectangle pixel and subtract black rectangle pixel and.
So as to which the rectangular image area of ad-hoc location can be abstracted as to Haar features, the spy of institute overlay area in the target image
Value indicative is that the grey scale pixel value of white portion, can be by mesh by this method with subtracting black region grey scale pixel value sum in image
Mark area image feature and carry out quantification treatment, target image is oriented by the grey scale change situation of the static images calculated.
As a kind of example, when target image is eye image, in image information human eye feature can be expressed as coordinate, away from
From information such as, color, brightness, shapes.Haar features belong to matrix character, thus can with eye image its be abstracted as with point,
The simple graph of the primitive geometric elements such as line, face composition.So as to the Haar features by extracting human eye region, orient
Eye image.
Further, after target image is positioned, binary conversion treatment is carried out to target image, and target image is carried out corresponding
The corrosion and expansion of number, after the target image is carried out into noise power, in the target image as far as possible after guarantee processing only
Target image information be present, consequently facilitating extracting the behavioral data of crewman in target image after treatment.
S350, the behavioral data of crewman is analyzed, the behavioral data of crewman is matched with crewman's Analysis model of network behaviors,
To generate the metewand of the behavioural norm of crewman.
Specifically, in order to more intuitive understanding crewman behavioural information, it is necessary to analyze the behavioral data of crewman, have
Body is as follows:
As a kind of example, the current location information and motion track of crewman are determined according to the behavioral data of crewman, such as can root
The current location information and motion track of crewman is determined according to the real time position data of crewman.
As a kind of example, the current fatigue state of crewman can be identified according to the behavioral data of crewman, such as can be according to crewman's
The behavioral data of eyes, such as the intensity of pupil, the frequency of blink etc., identify the current fatigue state of crewman.
As a kind of example, the identity information of crewman can be identified according to the behavioral data of crewman, such as can be according to the people to crewman
Face information data, identify the identity information of crewman.
As a kind of example, the rudder for ship direction information of crewman is determined according to the behavioral data of crewman, such as, it can be existed according to crewman
The concrete operations behavioral data of driver's cabin degree steering wheel either ship operation button, determine the rudder for ship direction information of crewman.
As a kind of example, crewman's lookout behavioural informations are identified according to the behavioral data of crewman, such as can be according to crewman in ship
The information datas such as the limb action on oceangoing ship, identify crewman's lookout behavioural informations.
Further, after analyzing the behavioral data of crewman, the assessment result of crewman's behavior is generated according to analysis result.
Specifically, assessment result can be represented by metewand.It is appreciated that prestored in crewman's Analysis model of network behaviors
There is the corresponding relation of crewman's behavioral data and crewman's behavioural norm metewand, so as to by the behavioral data of crewman and crewman's row
Matched for analysis model, to generate the metewand of the behavioural norm of crewman.
In summary, the analysis method of crewman's behavior of the embodiment of the present invention, the Haar features in multiple static images are extracted,
And the target image in multiple static images is positioned according to the Haar features of multiple static images, and then to target image
Binary conversion treatment is carried out, and the behavioral data of crewman is extracted from the target image after binary conversion treatment.It ensure that the ship of extraction
The accuracy of the behavioral data of member, the standard for the assessment result that the behavioural norm of crewman is generated according to crewman's behavioral data is ensured
True property.
In the application of reality, in order to ensure the accuracy of the obtained assessment result of the behavioural norm of crewman, ensure as ship
The reference frame provided safely of driving has reliability, it is necessary to the correlation of the obtained assessment result of the behavioural norm of crewman
Property is verified.
Specifically, Fig. 4 is according to the flow chart of the analysis method of crewman's behavior of another embodiment of the invention, such as Fig. 4 institutes
Show, the analysis method of crewman's behavior includes:
S410, the video image of crewman is gathered by video capture device.
S420, video image is pre-processed, video image is converted into multiple static images.
S430, the behavioral data of crewman is obtained from multiple static images.
S440, the behavioral data of crewman is analyzed, to generate the assessment result of the behavioural norm of crewman.
S450, playback video image, and the video frame image according to corresponding to timestamp determines the behavioral data of crewman, and according to
Video frame image is verified to the behavioral data of each crewman.
In one embodiment of the invention, the behavioral data of each crewman has corresponding timestamp in metewand, so as to
Can be by playing back video image, the video frame image according to corresponding to timestamp determines the behavioral data of crewman, and according to video figure
As frame is verified to the behavioral data of each crewman.
In summary, the analysis method of crewman's behavior in the embodiment of the present invention, can by playing back video image, and according to when
Between stamp determine video frame image corresponding to the behavioral data of crewman, and then the behavioral data according to video frame image to each crewman
Verified.The authenticity of the behavioral data of crewman is ensure that, has ensured the behavior that crewman is generated according to crewman's behavioral data
The accuracy of the assessment result of specification.
In order to realize above-described embodiment, the invention also provides a kind of analytical equipment of crewman's behavior, Fig. 5 is according to the present invention
The structural representation of the analytical equipment of crewman's behavior of one embodiment, as shown in figure 5, the analytical equipment bag of crewman's behavior
Include:Acquisition module 510, processing module 520, the first acquisition module 530 and analysis module 540.
Wherein, acquisition module 510, for gathering the video image of crewman by video capture device.
Specifically, acquisition module 510 by the video capture device on ship, can gather the video image of crewman, so as to
In the behavioural information that crewman is obtained according to the video image.
Wherein, the video image quality that acquisition module 510 gathers is related to the configuration of video capture device.
Processing module 520, for being pre-processed to video image, video image is converted into multiple static images.
Specifically, after video image is collected, for the ease of analyzing the behavioural information of the crewman in the video image,
Need processing module 520 to pre-process video image, video image is converted into multiple picture qualities preferably, just
In the static images of subsequent analysis.
, wherein it is desired to it is noted that image processing techniques means are varied, processing module 520 can be according to application scenarios
Do not have to, video image is converted to by multiple static images using different technological means.
As a kind of example, Fig. 6 is the structural representation according to the analytical equipment of crewman's behavior of a specific embodiment of the invention
Figure, as shown in fig. 6, on the basis of as shown in Figure 5, processing module 520 may include scanning element 521 and processing unit
522.I.e. scanning element 521 can be scanned frame by frame to video image, generate multiple video frame images corresponding to video image.
It is more corresponding to video image to generate and processing unit 522 pre-processes to multiple video frame images according to predetermined manner
Individual static images, wherein, predetermined manner is included in gray proces, noise reduction process, histogram equalization processing, filtering process
One or more.
First acquisition module 530, for obtaining the behavioral data of crewman from multiple static images.
Specifically, the first acquisition module 530 can obtain crewman's by the respective handling to the target image in static images
Behavioral data.Wherein, target image is the image for the physiological site that can react the behavioural information of crewman, for example can be energy
React crewman's notice and concentrate eye image of situation and degree of fatigue etc..
Specifically, the first acquisition module 530 can position to the target image in multiple static images first, and fixed
After position goes out target image, according to concrete application demand, associated picture treatment technology means are taken, target image is handled
To obtain the behavioral data of crewman.
In addition, Fig. 7 is the structural representation of the analytical equipment of crewman's behavior in accordance with another embodiment of the present invention, such as Fig. 7
Shown, on the basis of as shown in Figure 5, the device also includes the second acquisition module 550.I.e. in the implementation of the present invention
In example, during the above-mentioned target image in static images carries out calculating processing, in order to reduce the waste of computing resource,
The efficiency calculated is improved, the second acquisition module 550 can also pre-process to multiple video frame images according to predetermined manner
Before, the face region in multiple images frame is positioned, and intercepts human face region image, so as to which processing module 520 is to obtaining
Human face region image in the multiple images frame taken is pre-processed according to predetermined manner.
Analysis module 540, for analyzing the behavioral data of crewman, to generate the assessment result of the behavioural norm of crewman.
Specifically, for the behavioural information of more intuitive understanding crewman, behavior number of the analysis module 540 to crewman can be passed through
According to being analyzed, to generate the behavioural norm assessment result of crewman.
In summary, the analytical equipment of crewman's behavior of the embodiment of the present invention, the video of crewman is gathered by video capture device
Image, video image is pre-processed, video image is converted into multiple static images, and from multiple static images
The behavioral data of crewman is obtained, and then the behavioral data of crewman is analyzed, to generate the assessment knot of the behavioural norm of crewman
Fruit.The device generates the assessment result of the behavioural norm of crewman, is the peace of ship-handling by analyzing the behavioral data of crewman
Full management provides reference frame.
In order to more clearly illustrate, the behavioral data of crewman how is obtained from multiple static images, below in conjunction with the accompanying drawings 8-9
It is specifically described, in this example, the first acquisition module 530 by way of the Haar features for extracting static images positioning
Target image, and target image is pre-processed by binaryzation mode, to obtain the behavioral data of crewman.It is described as follows:
Fig. 8 be according to the structural representation of the analytical equipment of crewman's behavior of another of the invention embodiment, as shown in figure 8,
On the basis of as shown in Figure 5, the first acquisition module 530 includes:First extraction unit 531, positioning unit 532 and
Two extraction units 533.
Specifically, the first extraction unit 531 extracts the Haar features in multiple static images, and positioning unit 532 is according to multiple
The Haar features of static images position to the target image in multiple static images.
Further, after target image is positioned, the second extraction unit 533 carries out binary conversion treatment to target image, and right
Target image carries out the corrosion and expansion of corresponding number, and after the target image is carried out into noise power, guarantee as far as possible is handled
Target image information is only existed in target image afterwards, consequently facilitating extracting the behavior of crewman in target image after treatment
Data.
And then analysis module 540 is analyzed the behavioral data of crewman, by the behavioral data of crewman and crewman's behavioural analysis
Model is matched, to generate the metewand of the behavioural norm of crewman.
Specifically, in order to which the behavioural information of more intuitive understanding crewman, analysis module 540 need the behavioral data to crewman
Analyzed, it is specific as follows:
As a kind of example, analysis module 540 determines the current location information and moving rail of crewman according to the behavioral data of crewman
Mark, for example the current location information and motion track of crewman can be determined according to the real time position data of crewman.
As a kind of example, analysis module 540 can identify the current fatigue state of crewman according to the behavioral data of crewman, such as
It can identify that crewman's is current tired according to the intensity of the behavioral data of the eyes of crewman, such as pupil, the frequency of blink etc.
Labor state.
As a kind of example, analysis module 540 can identify the identity information of crewman according to the behavioral data of crewman, such as can root
According to the face information data to crewman, the identity information of crewman is identified.
As a kind of example, analysis module 540 determines the rudder for ship direction information of crewman according to the behavioral data of crewman, such as,
The rudder for ship of crewman can be determined according to crewman in the concrete operations behavioral data of driver's cabin degree steering wheel either ship operation button
Direction information.
As a kind of example, analysis module 540 identifies crewman's lookout behavioural informations according to the behavioral data of crewman, such as can
According to information datas such as limb action of the crewman on ship, crewman's lookout behavioural informations are identified.
Further, after analysis module 540 is analyzed the behavioral data of crewman, crewman's behavior is generated according to analysis result
Assessment result.
Specifically, assessment result can be represented by metewand.Fig. 9 is crewman's row according to further embodiment of the present invention
For analytical equipment structural representation, as shown in figure 9, on the basis of as shown in Figure 5, the analysis of crewman's behavior dress
Put and may also include:Matching module 560.It is appreciated that be previously stored with crewman's Analysis model of network behaviors crewman's behavioral data with
The corresponding relation of crewman's behavioural norm metewand, so as to which matching module 560 can be by the behavioral data of crewman and crewman's behavior point
Analysis model is matched, to generate the metewand of the behavioural norm of crewman.
In summary, the analytical equipment of crewman's behavior of the embodiment of the present invention, the Haar features in multiple static images are extracted,
And the target image in multiple static images is positioned according to the Haar features of multiple static images, and then to target image
Binary conversion treatment is carried out, and the behavioral data of crewman is extracted from the target image after binary conversion treatment.It ensure that the ship of extraction
The accuracy of the behavioral data of member, the standard for the assessment result that the behavioural norm of crewman is generated according to crewman's behavioral data is ensured
True property.
In the application of reality, in order to ensure the accuracy of the obtained assessment result of the behavioural norm of crewman, ensure as ship
The reference frame provided safely of driving has reliability, it is necessary to the correlation of the obtained assessment result of the behavioural norm of crewman
Property is verified.
Figure 10 be according to the structural representation of the analytical equipment of crewman's behavior of a still further embodiment of the present invention, as shown in Figure 10,
On the basis of as shown in Figure 5, the analytical equipment of crewman's behavior also includes authentication module 570.
Specifically, authentication module 570 is used to play back video image, and according to corresponding to timestamp determines the behavioral data of crewman
Video frame image, and the behavioral data of each crewman is verified according to video frame image.
In one embodiment of the invention, the behavioral data of each crewman has corresponding timestamp in metewand, so as to
Authentication module 570 can be by playing back video image, the video frame image according to corresponding to timestamp determines the behavioral data of crewman,
And the behavioral data of each crewman is verified according to video frame image.
, wherein it is desired to which explanation is the analytical equipment embodiment of crewman's behavior of the present invention, and combine the crewman of Fig. 1-Fig. 4 descriptions
The analysis method embodiment of behavior is corresponding, for the details not disclosed in the analytical equipment embodiment of crewman's behavior of the present invention,
The description of the analysis method embodiment of reference pair crewman's behavior, will not be repeated here.
In summary, the analytical equipment of crewman's behavior in the embodiment of the present invention, can by playing back video image, and according to when
Between stamp determine video frame image corresponding to the behavioral data of crewman, and then the behavioral data according to video frame image to each crewman
Verified.The authenticity of the behavioral data of crewman is ensure that, has ensured the behavior that crewman is generated according to crewman's behavioral data
The accuracy of the assessment result of specification.
In addition, term " first ", " second " are only used for describing purpose, and it is not intended that indicating or implying relatively important
Property or the implicit quantity for indicating indicated technical characteristic.Thus, define " first ", the feature of " second " can be with
Express or implicitly include at least one this feature.In the description of the invention, " multiple " are meant that at least two,
Such as two, three etc., unless otherwise specifically defined.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " tool
The description of body example " or " some examples " etc. means to combine specific features, structure, material that the embodiment or example describe
Material or feature are contained at least one embodiment or example of the present invention.In this manual, to the signal of above-mentioned term
Property statement be necessarily directed to identical embodiment or example.Moreover, specific features, structure, material or the spy of description
Point can combine in an appropriate manner in any one or more embodiments or example.In addition, in the case of not conflicting,
Those skilled in the art can be by the different embodiments or example described in this specification and the spy of different embodiments or example
Sign is combined and combined.
Although embodiments of the invention have been shown and described above, it is to be understood that above-described embodiment be it is exemplary,
It is not considered as limiting the invention, one of ordinary skill in the art within the scope of the invention can be to above-described embodiment
It is changed, changes, replacing and modification.
Claims (16)
1. a kind of analysis method of crewman's behavior, it is characterised in that comprise the following steps:
The video image of crewman is gathered by video capture device;
The video image is pre-processed, the video image is converted into multiple static images;
The behavioral data of the crewman is obtained from the multiple static images;
The behavioral data of the crewman is analyzed, to generate the assessment result of the behavioural norm of the crewman.
2. analysis method as claimed in claim 1, it is characterised in that pre-processed to the video image, by institute
State video image and be converted to multiple static images, including:
The video image is scanned frame by frame, generates multiple video frame images corresponding to the video image;
The multiple video frame image is pre-processed according to predetermined manner, it is multiple quiet corresponding to the video image to generate
State picture.
3. analysis method as claimed in claim 2, it is characterised in that the predetermined manner includes gray proces, at noise reduction
One or more in reason, histogram equalization processing, filtering process.
4. analysis method as claimed in claim 2 or claim 3, it is characterised in that to the multiple video frame image according to pre-
Before if mode is pre-processed, in addition to:
The human face region image in the multiple picture frame is obtained, and the pretreatment is carried out to the human face region image.
5. analysis method as claimed in claim 1, it is characterised in that the crewman is obtained from the multiple static images
Behavioral data, including:
Extract the Haar features in the multiple static images, and according to the Haar features of the multiple static images to described
Target image in multiple static images is positioned;
Binary conversion treatment is carried out to the target image, and the crewman is extracted from the target image after the binary conversion treatment
Behavioral data.
6. analysis method as claimed in claim 1, it is characterised in that analyze the behavioral data of the crewman, wrap
Include:
The current location information and motion track of the crewman is determined according to the behavioral data of the crewman;And/or
The current fatigue state of the crewman is identified according to the behavioral data of the crewman;And/or
The identity information of crewman is identified according to the behavioral data of the crewman;And/or
The rudder for ship direction information of the crewman is determined according to the behavioral data of the crewman;And/or
The crewman lookout behavioural informations are identified according to the behavioral data of the crewman.
7. analysis method as claimed in claim 6, it is characterised in that also include:
The behavioral data of the crewman is matched with crewman's Analysis model of network behaviors, to generate the behavioural norm of the crewman
Metewand.
8. analysis method as claimed in claim 7, it is characterised in that the behavior of each crewman in the metewand
Data have corresponding timestamp, and the analysis method also includes:
The video image, and the video frame image according to corresponding to the behavioral data that the timestamp determines the crewman are played back,
And the behavioral data of each crewman is verified according to the video frame image.
A kind of 9. analytical equipment of crewman's behavior, it is characterised in that including:
Acquisition module, for gathering the video image of crewman by video capture device;
Processing module, for being pre-processed to the video image, the video image is converted into multiple static images;
First acquisition module, for obtaining the behavioral data of the crewman from the multiple static images;
Analysis module, for analyzing the behavioral data of the crewman, to generate the assessment of the behavioural norm of the crewman
As a result.
10. analytical equipment as claimed in claim 9, it is characterised in that the processing module, including:
Scanning element, for being scanned frame by frame to the video image, generate multiple video figures corresponding to the video image
As frame;
Processing unit, for being pre-processed to the multiple video frame image according to predetermined manner, to generate the video figure
Multiple static images as corresponding to.
11. analytical equipment as claimed in claim 10, it is characterised in that the predetermined manner includes gray proces, noise reduction
One or more in processing, histogram equalization processing, filtering process.
12. the analytical equipment as described in claim 10 or 11, it is characterised in that also include:
Second acquisition module, for obtaining the human face region image in the multiple picture frame;
The processing module is additionally operable to carry out the pretreatment to the human face region image.
13. analytical equipment as claimed in claim 9, it is characterised in that the first acquisition module includes:
First extraction unit, for extracting the Haar features in the multiple static images;
Positioning unit, for according to the Haar features of the multiple static images to the target image in the multiple static images
Positioned;
Second extraction unit, for carrying out binary conversion treatment to the target image, and from the target after the binary conversion treatment
The behavioral data of the crewman is extracted in image.
14. analytical equipment as claimed in claim 9, it is characterised in that the analysis module is used for:
The current fatigue state of the crewman is identified according to the behavioral data of the crewman;And/or
The identity information of crewman is identified according to the behavioral data of the crewman;And/or
The rudder for ship direction information of the crewman is determined according to the behavioral data of the crewman;And/or
The crewman lookout behavioural informations are identified according to the behavioral data of the crewman.
15. analytical equipment as claimed in claim 14, it is characterised in that also include:
Matching module, for the behavioral data of the crewman to be matched with crewman's Analysis model of network behaviors, to generate the ship
The metewand of the behavioural norm of member.
16. analytical equipment as claimed in claim 15, it is characterised in that the row of each crewman in the metewand
There is corresponding timestamp for data, the analytical equipment also includes:
Authentication module, for playing back the video image, corresponding to the behavioral data that determines the crewman according to the timestamp
Video frame image, and the behavioral data of each crewman is verified according to the video frame image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610343948.6A CN107423864A (en) | 2016-05-23 | 2016-05-23 | The analysis method and device of crewman's behavior |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610343948.6A CN107423864A (en) | 2016-05-23 | 2016-05-23 | The analysis method and device of crewman's behavior |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107423864A true CN107423864A (en) | 2017-12-01 |
Family
ID=60422264
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610343948.6A Pending CN107423864A (en) | 2016-05-23 | 2016-05-23 | The analysis method and device of crewman's behavior |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107423864A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110264059A (en) * | 2019-06-12 | 2019-09-20 | 浙江蓝城建筑设计有限公司 | A kind of small town land use index measuring method and system |
CN111311573A (en) * | 2020-02-12 | 2020-06-19 | 贵州理工学院 | Branch determination method and device and electronic equipment |
CN112950094A (en) * | 2021-04-21 | 2021-06-11 | 中国水产科学研究院南海水产研究所 | Management method for fisherman on fishing boat |
CN113220910A (en) * | 2021-05-20 | 2021-08-06 | 大连海事大学 | Method and system for constructing ship deck cable database |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102163287A (en) * | 2011-03-28 | 2011-08-24 | 北京邮电大学 | Method for recognizing characters of licence plate based on Haar-like feature and support vector machine |
CN102263937A (en) * | 2011-07-26 | 2011-11-30 | 华南理工大学 | Driver's driving behavior monitoring device and monitoring method based on video detection |
CN104598890A (en) * | 2015-01-30 | 2015-05-06 | 南京邮电大学 | Human body behavior recognizing method based on RGB-D video |
CN105225420A (en) * | 2015-09-30 | 2016-01-06 | 中国民用航空总局第二研究所 | Based on air traffic controller's fatigue detection method of principal component analysis (PCA), device and system |
-
2016
- 2016-05-23 CN CN201610343948.6A patent/CN107423864A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102163287A (en) * | 2011-03-28 | 2011-08-24 | 北京邮电大学 | Method for recognizing characters of licence plate based on Haar-like feature and support vector machine |
CN102263937A (en) * | 2011-07-26 | 2011-11-30 | 华南理工大学 | Driver's driving behavior monitoring device and monitoring method based on video detection |
CN104598890A (en) * | 2015-01-30 | 2015-05-06 | 南京邮电大学 | Human body behavior recognizing method based on RGB-D video |
CN105225420A (en) * | 2015-09-30 | 2016-01-06 | 中国民用航空总局第二研究所 | Based on air traffic controller's fatigue detection method of principal component analysis (PCA), device and system |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110264059A (en) * | 2019-06-12 | 2019-09-20 | 浙江蓝城建筑设计有限公司 | A kind of small town land use index measuring method and system |
CN111311573A (en) * | 2020-02-12 | 2020-06-19 | 贵州理工学院 | Branch determination method and device and electronic equipment |
CN111311573B (en) * | 2020-02-12 | 2024-01-30 | 贵州理工学院 | Branch determination method and device and electronic equipment |
CN112950094A (en) * | 2021-04-21 | 2021-06-11 | 中国水产科学研究院南海水产研究所 | Management method for fisherman on fishing boat |
CN113220910A (en) * | 2021-05-20 | 2021-08-06 | 大连海事大学 | Method and system for constructing ship deck cable database |
CN113220910B (en) * | 2021-05-20 | 2023-06-06 | 大连海事大学 | Construction method and system of ship deck cable database |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11482040B2 (en) | Face anti-counterfeiting detection methods and systems, electronic devices, programs and media | |
Fernandes et al. | Predicting heart rate variations of deepfake videos using neural ode | |
Zhou et al. | Semantic-supervised infrared and visible image fusion via a dual-discriminator generative adversarial network | |
Qiu et al. | Finger vein presentation attack detection using total variation decomposition | |
CN105160318A (en) | Facial expression based lie detection method and system | |
CN108229297A (en) | Face identification method and device, electronic equipment, computer storage media | |
CN107423864A (en) | The analysis method and device of crewman's behavior | |
CN111126366B (en) | Method, device, equipment and storage medium for distinguishing living human face | |
CN110008793A (en) | Face identification method, device and equipment | |
CN110287791B (en) | Screening method and system for face pictures | |
CN107172354A (en) | Method for processing video frequency, device, electronic equipment and storage medium | |
CN112396011B (en) | Face recognition system based on video image heart rate detection and living body detection | |
CN108875542A (en) | A kind of face identification method, device, system and computer storage medium | |
CN109801412B (en) | Door access unlocking method and related device | |
Le Meur et al. | A spatio-temporal model of the selective human visual attention | |
CN111967319A (en) | Infrared and visible light based in-vivo detection method, device, equipment and storage medium | |
CN112307937A (en) | Deep learning-based identity card quality inspection method and system | |
CN114140844A (en) | Face silence living body detection method and device, electronic equipment and storage medium | |
Sakthimohan et al. | Detection and Recognition of Face Using Deep Learning | |
CN114360073A (en) | Image identification method and related device | |
CN111597864A (en) | Micro-expression recognition method based on cumulative light stream weighting characteristics | |
Mandal et al. | Human visual system inspired object detection and recognition | |
CN203276305U (en) | Intelligent gait recognition device based on cloud vision | |
CN113343889A (en) | Face recognition system based on silence live body detection | |
Bajracharya | Real time pattern recognition in digital video with applications to safety in construction sites |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171201 |
|
RJ01 | Rejection of invention patent application after publication |