CN109214293A - A kind of oil field operation region personnel wearing behavioral value method and system - Google Patents
A kind of oil field operation region personnel wearing behavioral value method and system Download PDFInfo
- Publication number
- CN109214293A CN109214293A CN201810889649.1A CN201810889649A CN109214293A CN 109214293 A CN109214293 A CN 109214293A CN 201810889649 A CN201810889649 A CN 201810889649A CN 109214293 A CN109214293 A CN 109214293A
- Authority
- CN
- China
- Prior art keywords
- personnel
- region
- dress
- image
- oil field
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Alarm Systems (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of oil field operation region personnel to dress behavioral value method and system, wherein detection method is comprising steps of S1, acquisition monitoring image;Area-of-interest in S2, interception monitoring image;Foreground image in S3, extraction area-of-interest;It whether there is specific connected region in S4, detection foreground image;S5, the specific connected region is analyzed and processed, judges whether personnel dress tooling, if it is, the detection of next frame image is carried out, otherwise triggering alarm.Wearing behavioral value method and system of the invention can be realized the accurately and efficiently detection that oil field operation region personnel are dressed with behavior, and be capable of high degree eliminates influence of the nature shade for the Stability and veracity of wearing behavioral value.
Description
Technical field
The present invention relates to technical field of image detection, specifically a kind of oil field operation region personnel dress behavioral value
Method and system.
Background technique
Due to the particularity of Oilfield Operation District, due to safety concerns, usually there is certain wearing requirement to staff,
The personnel for entering oil field operation region need to dress specific tooling.Currently, for the inspection for entering oil field operation region personnel
Survey is generally limited to identification detection, is then usually to be detected by artificially identification for wearing behavior, is difficult to realize automatic
The monitoring of change.Further, Oilfield Operation District is usually open, that is, is exposed in the environment of sun light direct beam, as a result, work
Large effect will be generated to existing image analysis processing by making cast shadow caused by personnel itself, be seriously affected to personnel
The accuracy for dressing detection, to the case where error detection and false alarm often occur.Currently, lacking one kind can be realized height
Effect, accurately automatic detection oil field operation region personnel dress the detection method and system of behavior
Summary of the invention
The purpose of the present invention is to solve the above problem, and behavior reality can be dressed to oil field operation region personnel by providing one kind
Apply efficient, accurate and stable detection method and system.
Present invention technical solution used for the above purpose is: a kind of oil field operation region personnel wearing behavior inspection
Survey method, comprising the following steps:
S1, monitoring image is obtained;
Area-of-interest in S2, interception monitoring image;
Foreground image in S3, extraction area-of-interest;
It whether there is specific connected region in S4, detection foreground image;
S5, the specific connected region is analyzed and processed, judges whether personnel dress tooling, if it is, carrying out
The detection of next frame image, otherwise triggering alarm.
Preferably, the specific connected region refers to the connected region in image comprising portrait.
Preferably, judge that the method whether testing staff dresses tooling includes: by the specific connection in the step S5
Region carries out region division, judges whether the specific pixel accounting in divided region is more than setting value, is more than setting value, then sentences
It is set to personnel and has dressed tooling, negative is determined as that personnel do not dress tooling.
Preferably, the specific connected region is divided into head, trunk and lower limb portion according to average person's ratio.
Preferably, the specific pixel refers to the pixel for the tooling color dressed needed for personnel.
Preferably, the lower half portion in monitoring image is chosen as area-of-interest, alternatively, with the frequent movable area of personnel
Domain is as the area-of-interest.
Preferably, further include that current weather conditions are determined, determine current weather be fine day or cloudy day, according to really
Fixed weather condition selects corresponding specific connected component analysis processing strategie.
Preferably, when being determined as fine day, the analysis processing strategie to the specific connected region includes: to establish to be monitored
Shadow model of personnel under the conditions of natural lighting in region, and removed out of specific connected region in conjunction with the shadow model
Be identified as be shade part, the specific connected region after dash area will be removed as judging whether personnel dress tooling
Target area.
Preferably, the shadow model includes the shade spy that the personnel in monitored region generate under the conditions of natural lighting
Levy the relationship that changes with time.
Preferably, the mode determined current weather includes: one fixed reference of selection in monitored region
Object, detection judge whether it generates shade, if generating shade, are determined as that fine day, no shade are then determined as the cloudy day.
Preferably, in the step S3, foreground image is extracted by the way of Gaussian Mixture background modeling.
The present invention also provides a kind of oil field operation region personnel to dress behavioral value system, comprising:
Image acquisition unit, for obtaining monitoring image;
Image processing unit judges institute for extracting foreground image from the area-of-interest of monitoring image, and detecting
It states in foreground image with the presence or absence of specific connected region;
Analysis and processing unit judges whether personnel dress tooling for being analyzed and processed to the specific connected region.
Compared with prior art, the present invention has at least the following advantages and the utility model has the advantages that
1, the solution of the present invention extracts area-of-interest from monitoring image, so that interference region to be omitted or go
Except processing, interference or wrong report are avoided the occurrence of;Using personnel activity region as region is predominantly detected, detection efficiency is improved.
2, personnel's wearing behavioral value method and system detection of the present invention is relatively simple, accurate, efficient, can have
It imitates and behavior realization automatic monitoring in real time is dressed to the personnel of Oilfield Operation District, improve security control efficiency.
3, detection method of the invention and system efficiently solve natural light shade to personnel dress detection accuracy and
Stability bring influences, and improves the Stability and veracity of detection.
Detailed description of the invention
Fig. 1 is the flow diagram of the wearing behavioral value method of the embodiment of the present invention;
Fig. 2 is the structural block diagram of the wearing behavioral value system of the embodiment of the present invention.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and embodiments, refering to shown in attached drawing 1-2, the present invention
Following examples are provided.
A kind of oil field operation region personnel wearing behavioral value method, comprising the following steps:
S1, monitoring image is obtained;
Area-of-interest in S2, interception monitoring image;
Foreground image in S3, extraction area-of-interest;
It whether there is specific connected region in S4, detection foreground image;
S5, the specific connected region is analyzed and processed, judges whether personnel dress tooling, if it is, carrying out
The detection of next frame image, otherwise triggering alarm.
Monitoring as one kind specifically, in the step S1, in monitoring area needed for being obtained by monitoring camera
Image, the oil field operation region that the monitoring area monitors needed for referring in the present embodiment.
Preferably, the step S3 includes being separated from area-of-interest by the way of Gaussian Mixture background modeling
Background and foreground image out.Gaussian Mixture background modeling is suitable for isolating from image sequence in the case where video camera is fixed
Background and prospect.In the case where video camera is fixed, the variation of background be slowly, can be by being modeled to background, to one
Width given image separates foreground and background, and in general, prospect is exactly moving object, to reach the mesh of moving object segmentation
's.
Preferably, the specific connected region in the step S4 refers to the connected region in image comprising portrait.It answers
The explanation detects specific connected region from foreground image and belongs to the prior art, is not elaborated herein.The step
Area-of-interest described in S2 refers to object detection area, as it is a kind of it is specific preferably, the area-of-interest is personnel
Frequent movable region.For the personnel in oil field operation region, often movable region is approximately fixed, therefore, with
The region helps accurately to detect from foreground image as area-of-interest judges the specific connected region.Meanwhile
The interference that the moving object except area-of-interest can also be excluded, that is, avoid other moving object erroneous judgement personnel, from
And improve the Stability and veracity of specific connected region detection judgement.It also contributes to reducing in step S5 simultaneously to specific company
The analysis computational processing in logical region, improves detection efficiency.As another preferred scheme, the lower half in monitoring image is chosen
Part is used as area-of-interest.This programme is such a based on solving the problems, such as: in the monitoring image in oil field operation region, figure
What the top half area monitoring as in was arrived is usually the picture of pumping unit, and pumping unit is at work, the fortune up and down of horse head
Dynamic and its shade can judge to interfere to the detection of the specific connected region in foreground image, or even the feelings of erroneous judgement occur
Condition.In consideration of it, the lower half portion chosen in monitoring image is arranged as area-of-interest, while by the top half in monitoring image
In addition in area-of-interest, the movement and its shade bring of the subregional pumping unit horsehead in the upper half in image can be eliminated
Interference, also, in general, the personnel of Oilfield Operation District also will not substantially enter the pumping of monitoring image top half
Below oil machine, that is to say, that the zone of action of personnel is also usually in the lower half portion region of monitoring image, therefore, also substantially
The case where being not in the leak detection to personnel.
Preferably, judging that the method whether personnel dress tooling includes: by the specific connection in the step S5
Region carries out region division, judges whether the specific pixel accounting in divided region is more than setting value, is more than setting value, then sentences
It is set to personnel and has dressed tooling, negative is determined as that personnel do not dress tooling.Specifically, can be according to average person's ratio by the spy
Determine connected region and be divided into head, trunk and lower limb portion, the specific pixel can be the tooling color of wearing needed for personnel
Pixel.For example, the color for the cap dressed needed for head is yellow, then it is referring to given threshold, to header area with the yellow
Domain carries out binary conversion treatment, is white by the processes pixel to match with yellow, and unmatched pixel is handled as black, by
This, calculates the ratio that white area accounts for head zone, when the ratio is more than setting value, is then determined as that the head of personnel has been dressed
Otherwise cap is judged to not dressing cap.Likewise, the color of wearing needed for trunk and lower limb portion is such as set as red
Color is then to carry out binary conversion treatment to head zone, and then judge the phase after binary conversion treatment referring to given threshold with the red
The accounting in region is answered, to judge whether trunk portion and/or lower limb portion dress the tooling for formulating color.As one kind specifically,
The setting value of above-mentioned specific pixel accounting can be set as any value between 70%-100%.
Preferably, further include determining current weather conditions, determine that current weather is fine day or cloudy day, according to
Identified weather condition selects corresponding specific connected component analysis processing strategie.One kind is specifically, can pass through network actively
Obtain weather forecast situation or input weather condition.
As one preferred, when being determined as fine day, the analysis processing strategie to the specific connected region includes: to build
Shadow model of personnel under the conditions of natural lighting in vertical monitored region, and in conjunction with the shadow model from specific connected region
In domain removal be identified as be shade part, the specific connected region after dash area will be removed as judging whether personnel wear
Wear the target area of tooling.It is further preferred that the shadow model includes personnel in monitored region in natural lighting item
The shadow character generated under part changes with time relationship.I.e. using average person as reference model, establishes average person and monitoring
In the correspondence changing rule data of generated shade at any time under the conditions of natural lighting in region.The practice processes of the program
It is, in the case where geographical location information (including latitude and longitude information) is certain, a certain certain objects in the geographical location
(i.e. metamorphosis is smaller, for example, by taking the average person in the present embodiment as an example, the personnel in oil field operation region are usually
Standing state, body shape changes are relatively small, therefore can be approximately fixed form) in natural lighting condition, generated yin
The form (including general shape, area and the relative positional relationship between the certain objects) of shadow and time (including season
Information and specific time point) there is certain corresponding relationship.That is, for specific to the present embodiment, oil field operation
The personnel in region generated shade form under the conditions of a certain specific moment, it was in natural lighting is foreseeable.This implementation
The technical problem that example scheme is solved is: when the personnel to oil field operation region carry out wearing detection, due in fine day
Solar irradiation under the conditions of, shade caused by human body (cast shadow) can be moved together with human body, and then to foreground image
When carrying out the detection of specific connected region and judging, the shade of human body and its generation can be determined as a specific connected region or
The erroneous judgement of human body shade is set to specific connected region, so that the accuracy for influencing wearing detection judgement even will lead to wrong report
It is alert.For example, having dressed the feelings of tooling in personnel so that the shade of human body and its generation is determined as a specific connected region as an example
Under condition, due to the presence of shade, the accounting of specific pixel (the corresponding pixel of tooling color) can be obviously reduced, consequently, it is possible to accidentally
It is determined as that personnel do not dress tooling, to generate false alarm.This programme is by removing shadow part in specific connected region as a result,
Point, to ensure that the accuracy of wearing detection judgement.
As one preferred, for the accuracy for improving detection, the mode determined current weather includes: in institute
It monitoring and chooses a fixed reference in region, detection judges whether it generates shade, if generating shade, it is determined as fine day,
There is no shade to be then determined as cloudy day or non-fine day.Specifically, detection judges whether the fixed reference generates the side of shade
Method can be with are as follows: establishing the fixed reference, generated shade is at any time under the conditions of monitoring in region in natural lighting
Corresponding changing rule data, that is to say, that fixed reference is in the determining time (including specific date and specific moment)
Shade caused by lower is predictable, and the form of shade and its positional relationship between fixed reference be also can
Prediction, therefore, only fine day need to can be determine whether by the detection of the shade to the object of reference.One kind is specifically, described
Fixed reference can be the object for being fixedly installed on the form in oil field operation region and fixing, for example, being erected in the straight-bar on ground.
The embodiment of the present invention also provides a kind of oil field operation region personnel wearing behavioral value system, comprising:
Image acquisition unit, for obtaining monitoring image;
Image processing unit judges institute for extracting foreground image from the area-of-interest of monitoring image, and detecting
It states in foreground image with the presence or absence of specific connected region;
Analysis and processing unit judges whether personnel dress tooling for being analyzed and processed to the specific connected region.
Wherein, the area-of-interest is that the specific connected region, which refers in image, includes as object detection area
The connected region of portrait.As it is a kind of it is specific preferably, the area-of-interest is personnel often movable region.It is further excellent
Choosing, the lower half portion in monitoring image is chosen as area-of-interest, helps accurately to detect judgement from foreground image
The specific connected region out.Meanwhile the interference of the moving object except area-of-interest can be also excluded, to improve
The Stability and veracity of specific connected region detection judgement.
Further, the analysis and processing unit judges that the method whether personnel dress tooling includes: by the specific company
Logical region carries out region division, judges whether the specific pixel accounting in divided region is more than setting value, is more than setting value, then
It is determined as that personnel have dressed tooling, negative is determined as that personnel do not dress tooling.Specifically, can will be described according to average person's ratio
Specific connected region is divided into head, trunk and lower limb portion, and the specific pixel can be the tooling face of wearing needed for personnel
The pixel of color.It is then referring to setting with the red for example, the color of wearing needed for trunk and lower limb portion is set as red
Threshold value carries out binary conversion treatment to head zone, and then judges the accounting of the corresponding region after binary conversion treatment, to judge body
Whether cadre and/or lower limb portion dress the tooling for formulating color.Specifically, it can setting above-mentioned specific pixel accounting as one kind
Definite value is set as any value between 70%-100%.
Preferably, it further includes nature shadow model data that the oil field operation region personnel, which dress behavioral value system,
Library.The shade that the personnel in monitoring section domain generate under the conditions of natural lighting is stored in the nature shadow model database
Feature changes with time relation data.I.e. using average person as reference model, establishes average person and be in monitoring region
The correspondence changing rule data of generated shade at any time under the conditions of natural lighting.The analysis and processing unit is also to working as the day before yesterday
Gas situation is determined, is determined that current weather is fine day or cloudy day, is selected corresponding specific company according to identified weather condition
Logical regional analysis processing strategie.Further, when being determined as fine day, the analysis and processing unit divides specific connected region
Analysis processing strategie includes: to transfer out from natural shadow model database pair according to obtaining the corresponding temporal information of monitoring image
The shadow character data answered remove from the specific connected region in conjunction with the shadow character data and are identified as being shade
Part will remove the specific connected region after dash area as judging whether personnel dress the target area of tooling.This programme
By removing dash area in specific connected region, to ensure that the accuracy of wearing detection judgement.
One kind is specifically, the analysis and processing unit can actively obtain weather forecast situation or input weather by network
Situation determines weather condition.
Preferred as another kind, described image processing unit also extracts fixed reference from acquired monitoring image
Object area, by the analysis and processing unit analyze and determine fixed reference region whether include fixed reference shade, packet
Containing shade, then it is determined as fine day, is otherwise determined as the cloudy day.Specifically, also being stored in the nature shadow model database
The shadow character that fixed reference generates under the conditions of natural lighting is stated to change with time relation data.Analysis and processing unit inspection
Survey in fixed reference region whether the pixel comprising characterization shade is determined as the cloudy day if not including, if comprising determining
For fine day.Further, analysis and processing unit can be by calling the fixed reference stored in nature shadow model database to exist
Shadow character data under the corresponding time (contain opposite between the morphological feature and shade and fixed reference of shade
Positional relationship), to determine the band of position for carrying out shadow Detection in fixed reference region.One kind is specifically, the fixation
Object of reference can be the object for being fixedly installed on the form in oil field operation region and fixing, for example, being erected in the straight-bar on ground.
It is further preferred that it further includes alarm unit that the oil field operation region personnel, which dress behavioral value system, when point
When analysis processing unit is determined as that personnel do not dress tooling, triggering alarm unit is alarmed, meanwhile, it will by wireless transmission unit
Monitoring image before and after the alarm of interception in 10-20 seconds is sent to remote monitoring terminal, provides remote monitoring terminal and carries out into one
The analytical judgment of step.
Preferably, network condition is poor since oil field operation region is often in relatively remote region, network bandwidth
Not enough, phenomena such as often will appear monitoring image Transmission, flower screen.Therefore, by image acquisition unit (including camera)
It is per second that frame per second is set as 8 frames, and resolution ratio is set as 1080*720 and reaches compromise, realizes that transmission is stablized, does not occur colored screen.
In the description of the embodiment of the present invention, particular features, structures, materials, or characteristics can at any one or
It can be combined in any suitable manner in multiple embodiment or examples.
In the description of the embodiment of the present invention, it is to be understood that "-" and "~" indicated is that two values are same
Range, and the range includes endpoint.Such as: " A-B " indicates to be greater than or equal to A, and is less than or equal to the range of B." A~B "
It indicates to be greater than or equal to A, and is less than or equal to the range of B.
In the description of the embodiment of the present invention, the terms "and/or", only it is a kind of describe affiliated partner pass
Connection relationship indicates may exist three kinds of relationships, for example, A and/or B, can indicate: individualism A exists simultaneously A and B, individually
There are these three situations of B.In addition, character "/" herein, typicallys represent the relationship that forward-backward correlation object is a kind of "or".
It although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
A variety of variations, modification, replacement can be carried out to these embodiments without departing from the principles and spirit of the present invention by understanding
And modification, the scope of the present invention is defined by the appended.
Claims (10)
1. a kind of oil field operation region personnel dress behavioral value method, which comprises the following steps:
S1, monitoring image is obtained;
Area-of-interest in S2, interception monitoring image;
Foreground image in S3, extraction area-of-interest;
It whether there is specific connected region in S4, detection foreground image;
S5, the specific connected region is analyzed and processed, judges whether personnel dress tooling, if it is, carrying out next
The detection of frame image, otherwise triggering alarm.
2. oil field operation region personnel according to claim 1 dress behavioral value method, which is characterized in that described specific
Connected region refers to the connected region in image comprising portrait.
3. oil field operation region personnel according to claim 2 dress behavioral value method, which is characterized in that the step
Judge that the method whether personnel dress tooling includes: that the specific connected region is carried out region division in S5, judges to be divided
Whether the specific pixel accounting in region is more than setting value, is more than setting value, then is determined as that personnel have dressed tooling, negative determines
Tooling is not dressed for personnel.
4. oil field operation region personnel according to claim 3 dress behavioral value method, which is characterized in that according to common
The specific connected region is divided into head, trunk and lower limb portion by human body proportion.
5. oil field operation region personnel according to claim 3 dress behavioral value method, which is characterized in that described specific
Pixel refers to the pixel for the tooling color dressed needed for personnel.
6. oil field operation region personnel according to claim 1 dress behavioral value method, which is characterized in that choose monitoring
Lower half portion in image is as area-of-interest.
7. oil field operation region personnel according to claim 1 dress behavioral value method, which is characterized in that further include pair
Current weather conditions are determined, are determined that current weather is fine day or cloudy day, are selected according to identified weather condition corresponding
Specific connected component analysis processing strategie.
8. oil field operation region personnel according to claim 7 dress behavioral value method, which is characterized in that when being determined as
When fine day, the analysis processing strategie to the specific connected region includes: the personnel that establish in monitored region in natural lighting
Under the conditions of shadow model, and removed out of specific connected region in conjunction with the shadow model be identified as be shade part,
The specific connected region after dash area will be removed as judging whether personnel dress the target area of tooling.
9. oil field operation region personnel according to claim 7 dress behavioral value method, which is characterized in that the shade
Model includes that the shadow character that generates under the conditions of natural lighting of the personnel in monitored region changes with time relationship.
10. a kind of oil field operation region personnel dress behavioral value system characterized by comprising
Image acquisition unit, for obtaining monitoring image;
Image processing unit, for extract foreground image from the area-of-interest of monitoring image, and detect judge it is described before
It whether there is specific connected region in scape image;
Analysis and processing unit judges whether personnel dress tooling for being analyzed and processed to the specific connected region.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810889649.1A CN109214293A (en) | 2018-08-07 | 2018-08-07 | A kind of oil field operation region personnel wearing behavioral value method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810889649.1A CN109214293A (en) | 2018-08-07 | 2018-08-07 | A kind of oil field operation region personnel wearing behavioral value method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109214293A true CN109214293A (en) | 2019-01-15 |
Family
ID=64988054
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810889649.1A Pending CN109214293A (en) | 2018-08-07 | 2018-08-07 | A kind of oil field operation region personnel wearing behavioral value method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109214293A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112395999A (en) * | 2020-11-19 | 2021-02-23 | 平安普惠企业管理有限公司 | Wearing standard judging method based on image recognition and related equipment |
CN115280395A (en) * | 2020-03-31 | 2022-11-01 | 株式会社小松制作所 | Detection system and detection method |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101364304A (en) * | 2008-09-25 | 2009-02-11 | 上海交通大学 | Shadow detection method based on color invariance and Gauss model |
CN101763646A (en) * | 2009-12-30 | 2010-06-30 | 深圳大学 | Shadow detection method and device and video image processing system |
CN102509073A (en) * | 2011-10-17 | 2012-06-20 | 上海交通大学 | Static target segmentation method based on Gauss background model |
CN102982558A (en) * | 2012-11-28 | 2013-03-20 | 无锡港湾网络科技有限公司 | Method and device for detecting moving target |
CN106295551A (en) * | 2016-08-05 | 2017-01-04 | 南京理工大学 | A kind of personal security cap wear condition real-time detection method based on video analysis |
US20180144207A1 (en) * | 2014-07-25 | 2018-05-24 | Denso Corporation | Pedestrian detection device and pedestrian detection method |
-
2018
- 2018-08-07 CN CN201810889649.1A patent/CN109214293A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101364304A (en) * | 2008-09-25 | 2009-02-11 | 上海交通大学 | Shadow detection method based on color invariance and Gauss model |
CN101763646A (en) * | 2009-12-30 | 2010-06-30 | 深圳大学 | Shadow detection method and device and video image processing system |
CN102509073A (en) * | 2011-10-17 | 2012-06-20 | 上海交通大学 | Static target segmentation method based on Gauss background model |
CN102982558A (en) * | 2012-11-28 | 2013-03-20 | 无锡港湾网络科技有限公司 | Method and device for detecting moving target |
US20180144207A1 (en) * | 2014-07-25 | 2018-05-24 | Denso Corporation | Pedestrian detection device and pedestrian detection method |
CN106295551A (en) * | 2016-08-05 | 2017-01-04 | 南京理工大学 | A kind of personal security cap wear condition real-time detection method based on video analysis |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115280395A (en) * | 2020-03-31 | 2022-11-01 | 株式会社小松制作所 | Detection system and detection method |
CN112395999A (en) * | 2020-11-19 | 2021-02-23 | 平安普惠企业管理有限公司 | Wearing standard judging method based on image recognition and related equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103069434B (en) | For the method and system of multi-mode video case index | |
CN106096577B (en) | A kind of target tracking method in camera distribution map | |
CN101493980B (en) | Rapid video flame detection method based on multi-characteristic fusion | |
CN109409256A (en) | A kind of forest rocket detection method based on 3D convolutional neural networks | |
CN105187785B (en) | A kind of across bayonet pedestrian's identifying system and method based on choice of dynamical notable feature | |
CN109377703A (en) | A kind of forest fireproofing early warning system and its method based on machine vision | |
CN106339657B (en) | Crop straw burning monitoring method based on monitor video, device | |
CN107256386A (en) | Human behavior analysis method based on deep learning | |
CN109241847A (en) | The Oilfield Operation District safety monitoring system of view-based access control model image | |
CN103679745B (en) | A kind of moving target detecting method and device | |
CN109377480A (en) | Arable land use change detection method based on deep learning | |
CN110110732B (en) | Intelligent inspection method for catering kitchen | |
CN102663362B (en) | Moving target detection method based on gray features | |
CN106096603A (en) | A kind of dynamic flame detection method merging multiple features and device | |
CN111126293A (en) | Flame and smoke abnormal condition detection method and system | |
CN104811586A (en) | Scene change video intelligent analyzing method, device, network camera and monitoring system | |
CN112183472A (en) | Method for detecting whether test field personnel wear work clothes or not based on improved RetinaNet | |
CN105469038A (en) | Safety cap video detection method for electric power switching station | |
CN114202646A (en) | Infrared image smoking detection method and system based on deep learning | |
CN101299274B (en) | Detecting method and system for moving fixed target | |
CN109214293A (en) | A kind of oil field operation region personnel wearing behavioral value method and system | |
CN113436229A (en) | Multi-target cross-camera pedestrian trajectory path generation method | |
CN112287823A (en) | Facial mask identification method based on video monitoring | |
CN107067595A (en) | State identification method, device and the electronic equipment of a kind of indicator lamp | |
CN105096305A (en) | Method and device for analyzing state of insulators |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190115 |