CN107679518A - A kind of detecting system - Google Patents
A kind of detecting system Download PDFInfo
- Publication number
- CN107679518A CN107679518A CN201711024866.6A CN201711024866A CN107679518A CN 107679518 A CN107679518 A CN 107679518A CN 201711024866 A CN201711024866 A CN 201711024866A CN 107679518 A CN107679518 A CN 107679518A
- Authority
- CN
- China
- Prior art keywords
- area
- region
- color
- processor
- image
- 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
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/162—Detection; Localisation; Normalisation using pixel segmentation or colour matching
-
- 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
-
- 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
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
-
- 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
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
Abstract
The embodiment of the invention discloses a kind of detecting system, for determining that the corresponding dress ornament of staff wears situation, to find the abnormal conditions of staff and the effectively safety management of specification power plant in time.The system includes：Image collecting device and processor, image collecting device connect with processor communication；Wherein, image collecting device, it is used for：Gather the first image for detection；Processor, it is used for：If there is area of skin color in the first image of image acquisition device, default processing is then carried out to area of skin color, at least one candidate region is obtained, if the first candidate region at least one candidate region includes human face region, determines corresponding dress ornament region in the first image according to human face region.
Description
Technical field
The present invention relates to technical field of image processing, more particularly to a kind of detecting system.
Background technology
Power plant be by it is some form of it is original can be converted into electric energy for fixation means or transport the dynamics factory of electricity consumption, can be with
Including firepower, waterpower, steam, diesel oil or nuclear plant etc..
During the production and operation of power plant, different types of power plant is possible to that uncontrollable harm can occur, such as non-
The illegal operation of staff, staff dress protection not in place for causing safety measure etc. due to work clothes.Therefore, for
The standardized administration of power plant and the control of security are particularly important.Wherein, must to the disengaging authority of the personnel in each region in power plant
Strict control must be carried out, to ensure the security of the equipment in each region of power plant and personnel.
However, power plant's operating area quantity is more, disengaging personnel are complicated, and staff's work post of power plant is more, relies on people
Power inspection can not discover the abnormal conditions of staff in time, and be difficult to specification power plant and support personnel's safety.
The content of the invention
The embodiments of the invention provide a kind of detecting system, for determining that the corresponding dress ornament of staff wears situation, with
The abnormal conditions of staff and the effectively safety management of specification power plant are found in time.
In view of this, first aspect present invention provides a kind of detecting system, it may include：
Image collecting device and processor；
Image collecting device connects with processor communication；
Wherein, image collecting device, it is used for：
Gather the first image for detection；
Processor, it is used for：
If the first image of image acquisition device has area of skin color, default processing is carried out to area of skin color, is obtained
To at least one candidate region；
If the first candidate region at least one candidate region includes human face region, according to human face region in the first figure
Corresponding dress ornament region is determined as in.
Further, system is applied to power industry.
Further, processor, it is specifically used for：
The area of skin color that neighbor distance is less than pre-determined distance is connected, obtains at least one first area；
If at least one target area for meeting default outline proportion at least one first area be present, at least one
The intersection of outline carries out fusion treatment in individual target area, obtains at least one candidate region.
Further, processor, it is specifically used for：
Area of skin color is subjected to divergence process according to preset multiple, to connect the colour of skin area that neighbor distance is less than pre-determined distance
Domain, obtain at least one first area.
Further, processor, it is additionally operable to：
Area of skin color is identified in the first image.
Further, processor, it is additionally operable to：
The color characteristic in dress ornament region is detected；
If color characteristic meets pre-set color feature, it is determined that the first image passes through detection.
Further, color characteristic includes color attribute and/or distribution of color area.
Further, system also includes：Output device, output device are connected with processor communication；
Output device, it is used for：
If processor detection color characteristic is unsatisfactory for pre-set color feature, alarm sounds are exported.
Further, dress ornament region includes work clothes region and/or work hat region and/or work footwear region.
Further, processor, it is additionally operable to：
According to default operational model, carry out Face datection at least one candidate region, and according to testing result determine to
The first candidate region in a few candidate region whether there is human face region.
As can be seen from the above technical solutions, the embodiment of the present invention has advantages below：
The embodiment of the present application provides a kind of detecting system, the first figure for being used to detect by image acquisition device
Picture, when there can be area of skin color in the first image, default processing is carried out to area of skin color using processor, to obtain at least
One candidate region, when human face region be present so as to the first candidate region at least one candidate region, pass through people
The relative wearing position of face and dress ornament, corresponding clothes can be accurately determined at least one candidate region according to human face region
Region is adornd, it is possible thereby to which the wearing situation for the dress ornament region decision such as staff for passing through determination, then can not only realize all
Such as the dressing standardized administration of power plant, dress ornament wearing can also be based on and found the abnormal situation in time, to prevent staff due to clothes
Decorations wearing does not meet safety problem caused by work requirements, so as to be advantageous to strengthen the safety management of such as power plant.
Brief description of the drawings
Fig. 1 is detecting system one embodiment schematic diagram in the embodiment of the present invention；
Fig. 2 is the fusion treatment schematic diagram of processor in detecting system in the embodiment of the present invention；
Fig. 3 is another embodiment schematic diagram of detecting system in the embodiment of the present invention.
Embodiment
The embodiments of the invention provide a kind of detecting system, for determining that the corresponding dress ornament of staff wears situation, with
The abnormal conditions of staff and the effectively safety management of specification power plant are found in time.
In order that those skilled in the art more fully understand the present invention program, below to the technology in the embodiment of the present invention
Scheme is clearly and completely described, it is clear that and described embodiment is only the embodiment of a present invention part, rather than
Whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not making creative work premise
Lower obtained every other embodiment, should all belong to the scope of protection of the invention.
Term " first ", " second ", " the 3rd " in description and claims of this specification and above-mentioned accompanying drawing, "
The (if present)s such as four " are for distinguishing similar object, without for describing specific order or precedence.It should manage
The data that solution so uses can exchange in the appropriate case, so that the embodiments described herein can be with except illustrating herein
Or the order beyond the content of description is implemented.In addition, term " comprising " and " having " and their any deformation, it is intended that
Cover it is non-exclusive include, be not necessarily limited to clearly for example, containing the process of series of steps or unit, method, product or equipment
Those steps or unit listed to Chu, but may include not list clearly or for these processes, method, product or
The intrinsic other steps of equipment or unit.
Detection method provided by the invention, it can be used for the dressing situation that user is detected in different dressing occasions, example
Such as, the doctor of hospital or nurse are respectively necessary for unified work clothes, and and for example, in some sterilizing laboratories, experimenter needs
Unified lab-gown.And in power plant, staff's work post of power plant is more, and power plant's operating area quantity is more, disengaging people
Member is complicated, thus for the staff of different work posts, it is necessary to unify and distinguishes other work posts progress dressings, with being capable of area
Divide the staff of different work posts, and can be made a distinction with Migrant women, to strengthen the management to power plant, simultaneously as electric
The particularity of factory's environment, the correct dressing of the staff of different work posts, can improve safety guarantee to a certain extent, thus
How the dressing situation of accurate judgement staff is particularly important.
Based on described above, the embodiment of the present invention by by the power plant in power industry this answer scene exemplified by illustrate.
For ease of understanding, the detecting system of the present invention is described in detail below by embodiment：
Referring to Fig. 1, detecting system one embodiment includes in the embodiment of the present invention：
Image collecting device 101 and processor 102；
Image collecting device 101 and processor 102 communicate to connect；
Wherein, image collecting device 101, it is used for：
Gather the first image for detection；
Processor 102, is used for：
If the first image that image collecting device 101 gathers has area of skin color, default processing is carried out to area of skin color,
Obtain at least one candidate region；
If the first candidate region at least one candidate region includes human face region, according to human face region in the first figure
Corresponding dress ornament region is determined as in.
In the present embodiment, image collecting device 101 can be such as camera, and image collecting device 101 can be installed on
In corresponding detection environment, the corresponding user detected in environment can be uptaked into, and the first figure for detection can be gathered
Picture.
Exemplary, the corresponding image collecting device 101 detected in environment can be monitored in real time, be monitored when detecting
When user in video be present, the current frame image including user, i.e. the first image can be gathered.Wherein, the identity of the user is not
It is defined, can is staff or non-working person.
It is understood that in the present embodiment, when image collecting device 101 is monitored in real time, can also gather every
One two field picture is the first image, i.e., is not done herein specific to currently carrying out Preliminary detection with the presence or absence of user in monitor video
Limit.
It should be noted that in the present embodiment, the setting angle of image collecting device 101 should meet following condition：
When being monitored in real time in corresponding detection environment, the whole body images of user can be collected to greatest extent.
Wired communication mode or communication can be used between image collecting device 101 and processor 102, such as with
Too net (RJ45 lines, optical fiber), industrial series bus (RS485, RS232, CAN), wired ethernet major advantage is data
Transmission is reliable, network capacity is big.Industrial series bus (RS485, RS232, CAN) advantage is that data transfer is reliable, design
Simply.Wireless mode mainly uses mobile operator mobile data access service, such as：GSM、GRPS、EVDO、CDMA、WCDMA
Deng.After image collecting device 101 gathers the first image for detection, processor 102 can obtain at image collecting device 101
The first image is taken, and carry out Face Detection can be carried out to first image, when the first image has area of skin color, to handle
Device 102 can carry out default processing to area of skin color, obtain at least one candidate region.
It is exemplary, can carry out colour of skin statistics in advance, and can according to corresponding to being set the colour of skin of people colour of skin threshold value model
Enclose, for each skin tone value in colour of skin threshold range, corresponding pixel value can be provided with, it is hereby achieved that presetted pixel
Scope, and the corresponding relation of skin tone value and pixel value can be stored.Processor 102 obtains first at image collecting device 101
After image, it may be determined that the pixel value of each pixel in the first image, and can by the pixel value of each pixel with
Contrasted with presetted pixel scope, if the pixel value of pixel, in the range of presetted pixel, processor 102 can determine this
Pixel is area of skin color, conversely, the pixel is non-area of skin color.Thus, when it is determined that the first image has area of skin color,
Processor 102 can carry out default processing to area of skin color, obtain at least one candidate region.Wherein, each candidate region
One or more area of skin color can be included, so that concentration analysis can be carried out to the area of skin color of the user detected.
Exemplary, pixel value can be by HSV (Hue, Saturation, Value, the brightness of tone saturation degree) color space
It is indicated, hsv color space is a kind of color space created according to the intuitive nature of color, by H (Hue, tone), S
(Saturation, saturation degree) and V (Value, brightness) these three components are formed, and the spans of H components can be 0 °~
360 °, the span of S components can be 0.0~1.0, and the span of V component is 0 (black)~1 (white).
It is understood that in the present embodiment, area of skin color can not also be meet presetted pixel threshold range one
Pixel, in actual applications, it can also be other, such as include two pixels, be not specifically limited herein.
Further, processor 102 carries out default processing to the area of skin color in the first image, obtains at least one candidate
Behind region, Face datection can also be carried out at least one candidate region, with the first candidate at least one candidate region
When region includes human face region, corresponding dress ornament region can be determined in the first image according to human face region.
Specifically, in general, the dress code based on workplace, image collecting device 101 be able to may collect
Area of skin color in addition to face, such as the back of the hand, then processor 102 be likely to be obtained not by carrying out default processing to area of skin color
There is the candidate region of facial feature information, thus processor 102 also needs to carry out Face datection at least one candidate region, with
Determine human face region.
In actual applications, after it is determined that the first candidate region includes human face region, processor 102 can be according to face area
Domain determines corresponding dress ornament region in the first image.Specifically, when power plant carries out related operation, it is necessary to dress suitable work
Clothing, work hat, or even work footwear, wherein, work clothes, work hat (safety cap), the wearing position of work footwear are conventional, if work hat is in face area
The surface in domain, work clothes, work hat are successively in the underface of human face region.Thus, in actual applications, processor 102 can root
According to the default geometrical relationship of dress ornament and human face region, and dress ornament pre-set dimension scope (such as power plant staff and
Speech, work hat have the size design determined), it is watershed area the using human face region in the first image including human face region
Corresponding dress ornament region is determined in one image, e.g., in the surface of human face region, determines work hat region, in human face region just
Lower section, determine work clothes region and/or work footwear region.Wherein, work footwear region can be combined with other supplementary means and be determined, with
Accurate work footwear region is obtained, specific means does not limit herein.
In the present embodiment, the first image for detection is gathered by image collecting device 101, can be in the first image
When area of skin color be present, default processing is carried out to area of skin color using processor 102, to obtain at least one candidate region, from
And when can have human face region in the first candidate region at least one candidate region, worn by face and the relative of dress ornament
Position is worn, corresponding dress ornament region can be accurately determined at least one candidate region according to human face region, it is possible thereby to
By the wearing situation of the dress ornament region decision such as staff of determination, then the dressing specification of such as power plant can be not only realized
Management, dress ornament wearing can also be based on and found the abnormal situation in time, to prevent staff from not meeting work due to dress ornament wearing
Safety problem caused by demand, so as to be advantageous to strengthen the safety management of such as power plant.
Optionally, in some embodiments of the invention, processor 102, can be specifically used for：
According to default operational model, carry out Face datection at least one candidate region, and according to testing result determine to
The first candidate region in a few candidate region whether there is human face region.
Specifically, human face region is determined, it is necessary to can believe first the face feature of people in order to accurately carry out Face datection
Breath is counted, and default operational model is trained using the facial feature information of statistics, and the default operational model can be with
For neutral net, grader etc..After the training for completing default operational model, processor 102 can utilize pre- after training
If operational model carries out Face datection to candidate region one by one, and can be determined according to testing result at least one candidate region
The first candidate region whether include human face region.
Exemplary, in obtained at least one candidate region, processor 102 can utilize sliding window and image gold
The method that word tower combines is scanned, and image block corresponding to each window is put into infundibulate cascade classifier, so as to
With obtain each window whether be face classification results, can finally be obtained to doing non-maxima suppression for the window of face
Human face region, and then can determine that at least one candidate region includes the first candidate region of human face region.
It is understood that processor 102 carries out the method for Face datection except the content of described above in the present embodiment,
In actual applications, other manner can also be used, as long as processor 102 can determine first at least one candidate region
Whether candidate region includes human face region, is not specifically limited herein.
Optionally, in some embodiments of the invention, processor 102, can be specifically used for：
The area of skin color that neighbor distance is less than pre-determined distance is connected, obtains at least one first area；
If at least one target area for meeting default outline proportion at least one first area be present, at least one
The intersection of the outline of each in individual target area carries out fusion treatment, obtains at least one candidate region.
Specifically, assume that processor 102 meets a pixel of presetted pixel threshold range as a skin using pixel value
Color region, then when processor 102 determines that the first image has area of skin color, area of skin color can be one or more, and by
In these area of skin color be single scattered pixel, so as to need processor 102 to be attached corresponding area of skin color, with
Carry out Face datection.However, in actual applications, in addition to the area of skin color of face may be shown in the first image, may be used also
It is shown in other area of skin color for meeting presetted pixel threshold range be present in the first image, such as the back of the hand, then in order to avoid
The error detection of human face region caused by the area of skin color connection of the area of skin color and the back of the hand of such as face, processor 102 can be only
The area of skin color that neighbor distance is less than pre-determined distance is connected, at least one first area is obtained, so as to be advantageous to such as face
It is attached respectively between area of skin color and the area of skin color of the back of the hand.
Further, after at least one first area is obtained, in order to improve detection efficiency, processor 102 can reject
Fall the first area for not meeting opposite site in human body, i.e., by being united in advance to the outline proportion of opposite site in human body
Meter, the ratio of width to height of such as face, head body ratio, and after setting a default outline proportion according to statistics, processor 102 can be with
Using default outline proportion as judging whether first area meets the standard of the ratio of opposite site in human body, so as to as much as possible
Exclusion is not belonging to the first area of a part for human body.It is understood that the default outline proportion in the present embodiment not only may be used
Think a threshold value, or two threshold values, the both ends point value of as one outline proportion scope, profile is not met to reject
The first area of proportion, it can specifically be configured according to being actually needed, be not specifically limited herein.
Further, processor 102 determines to meet at least one of default outline proportion at least one first area
Behind target area, fusion treatment can also be carried out to the intersection of the outline of each at least one target area, with
Obtain at least one candidate region.Exemplary, area of skin color after at least one first area is by expanding is attached
When obtaining, each at least one target area there may be partially overlapping for the area of skin color after expansion, for specification
The outline of each at least one target area, preferably to realize Face datection, processor 102 can be at least one
The outline of each in individual target area is modified accordingly, to cause the foreign steamer of each at least one target area
Wide comparatively regular, thus, processor 102 can be to the intersection of the outline of each at least one target area
Carry out fusion treatment, as illustrated in fig. 2, it is assumed that square 1 with the part outline that square 2 be target area, square 1 with it is square
2 partially overlap, then after square shaped 1 is merged with square 2, can obtain one include square 1 with square 2 square 3, side
Shape 3 will rebuild the outline of corresponding target area, thus the outline of each at least one target area
After intersection carries out fusion treatment, at least one candidate region can be obtained, after each candidate region is fusion treatment
A target area.
It should be noted that the above-mentioned content that fusion treatment is carried out on processor 102 is only for example in the present embodiment
Bright, in actual applications, processor 102 can also use other methods, and the shape after the fusion of target area can also be according to reality
Border needs to be configured, as square 1 and the shape that is obtained after square 2 fusion treatment can also be to be other beyond square, herein
It is not specifically limited.
Optionally, in some embodiments of the invention, processor 102, can be specifically used for：
Area of skin color is subjected to divergence process according to preset multiple, to connect the colour of skin area that neighbor distance is less than pre-determined distance
Domain, obtain at least one first area.
Specifically, being illustrated by taking face as an example, in actual applications, due to reasons such as illumination, processor 102 exists
When carrying out the detection of area of skin color to the first image, the possible skewness of the colour of skin of face, so as to cause part facial regions
Domain is too bright and exceedes the presetted pixel threshold range of setting so that the part face area error detection is non-skin by processor 102
Color region.Because in order to make up such as error detection the occurrence of, colour of skin area that processor 102 will can detect first
Domain carries out divergence process according to preset multiple, i.e., centered on each area of skin color that this is detected, to each colour of skin area
The periphery in domain carries out the expansion of preset multiple, for example, it is assumed that square size is 0.3 millimeter × 0.3 millimeter, then can be with
Expanded on the basis of square original center to square original periphery so that the square size can adjust
For such as 0.5 millimeter × 0.5 millimeter, thus make up as much as possible due to being originally used for area of skin color, but due to the shadow of external factor
Ring and cause the area of skin color that error detection is non-area of skin color.Therefore, area of skin color is carried out divergence process by processor 102 one by one
Afterwards, the area of skin color after expansion can be connected as an entirety between each other, so that neighbor distance is less than in advance before expansion
If the area of skin color of distance can be connected, and obtain at least one first area.
Optionally, in some embodiments of the invention, processor 102, can be also used for：
Area of skin color is identified in the first image.
In the present embodiment, when processor 102 detects to the first image with the presence or absence of area of skin color, processor 102
It pair area of skin color determined can be identified in the first image, thus complete the skin to each pixel of the first image
After the detection in color region, processor 102 can learn the area of skin color of all determinations in the first image by mark, without
When connection neighbor distance is less than the area of skin color of pre-determined distance, the detection of area of skin color is re-started, advantageously reduces processing
The amount of calculation of device 102, improve detection efficiency.Wherein, the mode being identified in the first image to area of skin color can be
Area of skin color set mask mode, so as to processor 102 can by mask distinguish the first image in area of skin color with it is non-
Area of skin color.
It is understood that in the present embodiment area of skin color identification means except using described above mask in addition to,
In actual applications, can also be used alone or in combination using other manner, as long as can be carried out to area of skin color corresponding
Mark, to distinguish non-area of skin color, be not specifically limited herein.
Optionally, in some embodiments of the invention, processor 102, can be also used for：
The color characteristic in dress ornament region is detected；
If color characteristic meets pre-set color feature, it is determined that the first image passes through detection.
Specifically, after processor 102 determines corresponding dress ornament region in the first image, it can count and be taken in the first image
The color characteristic in region is adornd, can be detected to the color characteristic in dress ornament region, and the can be judged according to testing result
The dressing situation of user in one image.Wherein, color characteristic can include but is not limited to color attribute (such as red, green, Huang
The different color such as color, blueness) and/or distribution of color area.Preferably, because common dressing can be to this key element of color attribute
Judgement interfere, then in order to improve the accuracy rate of detection, color characteristic can include color attribute and distribution of color area.
Exemplary, it is assumed that when power plant carries out related operation, staff can include the staff for being responsible for operation
With the staff of responsible maintenance, and the operating area of power plant is more, different according to operating area, is responsible for the staff of operation
It can be divided into again：The work post such as boiler, steam turbine, electric, chemical, defeated coal, ash disposal, being responsible for the staff of maintenance can be divided into again：
The work posts such as boiler, steam turbine, electric, thermal technology, then according to the difference of work post, such as work clothes, work of corresponding staff's wearing
Cap may be different, and can be made a distinction by work clothes, the dress of work hat and the Migrant women of power plant.Wherein, for power plant
For staff, its dressing can have certain feature relative to the common dressing with non-working person, and these features can
Embodied with the color characteristic of the dress ornament by staff, then, in actual applications, work that can in advance to power plant
The dress ornament information of personnel is counted, to establish the dress ornament information bank of the staff for power plant, and can be to each work post
All clothing types in corresponding dress ornament region carry out color attribute, the record of distribution of color area, with the color category of record
Property, distribution of color area are pre-set color feature, can also establish the pre-set color feature in corresponding dress ornament region with it is corresponding
Mapping relations between work post.For example, it is assumed that power plant includes three work posts, each work post has corresponding work clothes, work hat, work post
A work clothes are color 1, work hat is color 2, and work post B work clothes are color 3, work hat is color 4, work post C work clothes are color 5,
Work hat is color 6, then for work clothes, its pre-set color feature can include color 1, color 3, color 5, and be directed to work hat,
Its pre-set color feature can include color 2, color 4, color 6.Thus, processor 102 is it is determined that the color in dress ornament region is special
After sign, the color characteristic in corresponding dress ornament region can be detected using pre-set color feature, to judge corresponding dress ornament
The color characteristic in region whether with pre-set color characteristic matching.
For example, when it is determined that corresponding dress ornament region is work clothes region, processor 102 can be special by the color in work clothes region
The pre-set color feature (including color 1, color 3, color 5) for levying the work clothes region with recording is matched, if work clothes region is
Color 1, color 3,5 any color of color, then processor 102 it is corresponding pre- can to determine that the color characteristic in work clothes region meets
If color characteristic, conversely, then processor 102 can determine that the color characteristic in work clothes region and pre-set color feature mismatch.
In the present embodiment, when establishing the dress ornament information bank for the staff of power plant, because work post is different and work
The difference of the title and rank of kind, then for different work posts or same work post, the different positions of different work posts or same work post
The dress ornament of rank can have certain difference, as work hat color is different, then can also establish work post, work post for the difference
The mapping relations of title and rank and the pre-set color feature in corresponding dress ornament region, with the record for the dress ornament information bank that becomes more meticulous.
Further, when color characteristic and the pre-set color characteristic matching in corresponding dress ornament region, processor 102 can be with
The first image is determined by detection, that is, it is staff to give tacit consent to the user in the first image.Thus, in actual applications, if
The detection environment that user in one image enters has disengaging management of the priority assignation with the specification detection environment, then only ought the
When one image passes through detection, the user that processor 102 can be just defaulted as in the first image has disengaging authority, and the user just may be used
To be allowed to pass in and out the detection environment freely.
Optionally, in some embodiments of the invention, as shown in figure 3, system can also include：Output device 103, it is defeated
Go out device 103 to communicate to connect with processor 102；
Output device 103, is used for：
If processor 102 detects color characteristic and is unsatisfactory for pre-set color feature, alarm sounds are exported.
Specifically, wired communication mode or side wireless communication can also be used between output device 103 and processor 102
Formula.When the color characteristic in corresponding dress ornament region mismatches with pre-set color feature, processor 102 can also determine the first figure
As by detection, that is, it is not non-working person to give tacit consent to the user in the first image.Thus, in actual applications, if the first image
In user enter detection environment there is disengaging management of the priority assignation with the specification detection environment, then when the first image does not lead to
When crossing detection, the user that can be defaulted as in the first image is non-working person, does not pass in and out the authority of the detection environment, then
Processor 102 can send the testing result to output device 103, can be with after output device 103 receives the testing result
The corresponding warning of output, such as alarm, to prevent authority forbidden area that non-working person is broken in power plant, and reach protection power plant
Safe effect, meanwhile, the user be originally used for staff but not work dress ornament when, output device can also be passed through
The alarm of 103 outputs carries out the prompting of correct dressing to the user, so as to be advantageous to the management of specification power plant.
It should be noted that output device 103 can be such as display in the present embodiment, there can also be sound to be other
Equipment of sound output etc., is not specifically limited herein.
It is understood that detecting system may include but be not limited only to image collection assembly 101, processor 102.This area
Technical staff is appreciated that Fig. 1, Fig. 3 schematic diagram are only the example of detecting system, does not form the restriction to detecting system,
It can include than illustrating more or less parts, either combine some parts or different parts, such as the detection system
System can also include input equipment, network access equipment etc..
It should be understood that in various embodiments of the present invention, the size of the sequence number of each element is not meant in said system
The priority of execution sequence, the execution sequence of each element should be determined with its function and internal logic, without tackling the embodiment of the present invention
Implementation process form any restriction.
Described above, the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although with reference to before
Embodiment is stated the present invention is described in detail, it will be understood by those within the art that：It still can be to preceding
State the technical scheme described in each embodiment to modify, or equivalent substitution is carried out to which part technical characteristic；And these
Modification is replaced, and the essence of appropriate technical solution is departed from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (10)
- A kind of 1. detecting system, it is characterised in that including：Image collecting device and processor；Described image harvester connects with the processor communication；Wherein, described image harvester, it is used for：Gather the first image for detection；The processor, is used for：If the first image of described image harvester collection has area of skin color, default place is carried out to the area of skin color Reason, obtains at least one candidate region；If the first candidate region at least one candidate region includes human face region, according to the human face region in institute State and corresponding dress ornament region is determined in the first image.
- 2. system according to claim 1, it is characterised in that the system is applied to power industry.
- 3. system according to claim 1 or 2, it is characterised in that the processor, be specifically used for：The area of skin color that neighbor distance is less than pre-determined distance is connected, obtains at least one first area；Meet at least one target area of default outline proportion if existing at least one first area, to it is described extremely The intersection of outline carries out fusion treatment in a few target area, obtains at least one candidate region.
- 4. system according to claim 3, it is characterised in that the processor, be specifically used for：The area of skin color is subjected to divergence process according to preset multiple, to connect the skin that neighbor distance is less than pre-determined distance Color region, obtain at least one first area.
- 5. system according to claim 1 or 2, it is characterised in that the processor, be additionally operable to：The area of skin color is identified in described first image.
- 6. system according to claim 1 or 2, it is characterised in that the processor, be additionally operable to：The color characteristic in the dress ornament region is detected；If the color characteristic meets pre-set color feature, it is determined that described first image passes through detection.
- 7. shampoo paste according to claim 6, it is characterised in that the color characteristic includes color attribute and/or described Distribution of color area.
- 8. system according to claim 6, it is characterised in that the system also includes：Output device, the output device It is connected with the processor communication；The output device, is used for：If the processor detects the color characteristic and is unsatisfactory for the pre-set color feature, alarm sounds are exported.
- 9. system according to claim 1 or 2, it is characterised in that the dress ornament region includes work clothes region and/or work hat Region and/or work footwear region.
- 10. system according to claim 1 or 2, it is characterised in that the processor, be additionally operable to：According to default operational model, Face datection is carried out at least one candidate region, and institute is determined according to testing result The first candidate region stated at least one candidate region whether there is human face region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711024866.6A CN107679518A (en) | 2017-10-27 | 2017-10-27 | A kind of detecting system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711024866.6A CN107679518A (en) | 2017-10-27 | 2017-10-27 | A kind of detecting system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107679518A true CN107679518A (en) | 2018-02-09 |
Family
ID=61143224
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711024866.6A Pending CN107679518A (en) | 2017-10-27 | 2017-10-27 | A kind of detecting system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107679518A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109446932A (en) * | 2018-10-11 | 2019-03-08 | 武汉微道云信息科技有限公司 | A kind of dressing inspection method, device, terminal device and computer storage medium |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101020104A (en) * | 2007-03-27 | 2007-08-22 | 南京大学 | Embedded forest fire early-warning system based on video detection |
| US20080025577A1 (en) * | 2006-07-28 | 2008-01-31 | Koichi Kugo | Photographic image distinction method and photographic image processing apparatus |
| CN101655975A (en) * | 2008-08-22 | 2010-02-24 | 精工爱普生株式会社 | Image processing apparatus, image processing method and image processing program |
| CN101694718A (en) * | 2009-10-13 | 2010-04-14 | 西安电子科技大学 | Method for detecting remote sensing image change based on interest areas |
| CN102542260A (en) * | 2011-12-30 | 2012-07-04 | 中南大学 | Method for recognizing road traffic sign for unmanned vehicle |
| CN102779270A (en) * | 2012-06-21 | 2012-11-14 | 西南交通大学 | Target clothing image extraction method aiming at shopping image search |
| CN102799901A (en) * | 2012-07-10 | 2012-11-28 | 辉路科技（北京）有限公司 | Method for multi-angle face detection |
| CN104684465A (en) * | 2012-07-12 | 2015-06-03 | 菲力尔系统公司 | Infant monitoring systems and methods using thermal imaging |
| CN105678213A (en) * | 2015-12-20 | 2016-06-15 | 华南理工大学 | Dual-mode masked man event automatic detection method based on video characteristic statistics |
| CN105718886A (en) * | 2016-01-20 | 2016-06-29 | 武汉日创科技有限公司 | Moving personnel safety abnormity tumbling detection method |
| CN105931244A (en) * | 2016-04-29 | 2016-09-07 | 中科院成都信息技术股份有限公司 | Supervision-free image matting method and apparatus |
| CN106296667A (en) * | 2016-08-01 | 2017-01-04 | 乐视控股（北京）有限公司 | Hand detection method and system |
| CN106503716A (en) * | 2016-09-13 | 2017-03-15 | 中国电力科学研究院 | A kind of safety cap recognition methods that is extracted based on color and contour feature and system |
| CN106599778A (en) * | 2016-11-03 | 2017-04-26 | 南京邮电大学 | Rapid accurate human face detection method |
| CN106778481A (en) * | 2016-11-15 | 2017-05-31 | 上海百芝龙网络科技有限公司 | A kind of body heath's monitoring method |
| CN107133654A (en) * | 2017-05-25 | 2017-09-05 | 大连理工大学 | A kind of method of monitor video accident detection |
-
2017
- 2017-10-27 CN CN201711024866.6A patent/CN107679518A/en active Pending
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080025577A1 (en) * | 2006-07-28 | 2008-01-31 | Koichi Kugo | Photographic image distinction method and photographic image processing apparatus |
| CN101020104A (en) * | 2007-03-27 | 2007-08-22 | 南京大学 | Embedded forest fire early-warning system based on video detection |
| CN101655975A (en) * | 2008-08-22 | 2010-02-24 | 精工爱普生株式会社 | Image processing apparatus, image processing method and image processing program |
| CN101694718A (en) * | 2009-10-13 | 2010-04-14 | 西安电子科技大学 | Method for detecting remote sensing image change based on interest areas |
| CN102542260A (en) * | 2011-12-30 | 2012-07-04 | 中南大学 | Method for recognizing road traffic sign for unmanned vehicle |
| CN102779270A (en) * | 2012-06-21 | 2012-11-14 | 西南交通大学 | Target clothing image extraction method aiming at shopping image search |
| CN102799901A (en) * | 2012-07-10 | 2012-11-28 | 辉路科技（北京）有限公司 | Method for multi-angle face detection |
| CN104684465A (en) * | 2012-07-12 | 2015-06-03 | 菲力尔系统公司 | Infant monitoring systems and methods using thermal imaging |
| CN105678213A (en) * | 2015-12-20 | 2016-06-15 | 华南理工大学 | Dual-mode masked man event automatic detection method based on video characteristic statistics |
| CN105718886A (en) * | 2016-01-20 | 2016-06-29 | 武汉日创科技有限公司 | Moving personnel safety abnormity tumbling detection method |
| CN105931244A (en) * | 2016-04-29 | 2016-09-07 | 中科院成都信息技术股份有限公司 | Supervision-free image matting method and apparatus |
| CN106296667A (en) * | 2016-08-01 | 2017-01-04 | 乐视控股（北京）有限公司 | Hand detection method and system |
| CN106503716A (en) * | 2016-09-13 | 2017-03-15 | 中国电力科学研究院 | A kind of safety cap recognition methods that is extracted based on color and contour feature and system |
| CN106599778A (en) * | 2016-11-03 | 2017-04-26 | 南京邮电大学 | Rapid accurate human face detection method |
| CN106778481A (en) * | 2016-11-15 | 2017-05-31 | 上海百芝龙网络科技有限公司 | A kind of body heath's monitoring method |
| CN107133654A (en) * | 2017-05-25 | 2017-09-05 | 大连理工大学 | A kind of method of monitor video accident detection |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109446932A (en) * | 2018-10-11 | 2019-03-08 | 武汉微道云信息科技有限公司 | A kind of dressing inspection method, device, terminal device and computer storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107578041A (en) | A kind of detecting system | |
| CN107609544A (en) | A kind of detection method and device | |
| CN204631867U (en) | A kind of frontier port entry personnel's information automatic acquisition system | |
| CN106295551B (en) | A kind of personnel safety cap wear condition real-time detection method based on video analysis | |
| CN107784287A (en) | A kind of detection method and device, computer installation, readable storage medium storing program for executing | |
| CN103108159B (en) | Electric power intelligent video analyzing and monitoring system and method | |
| CN108537154A (en) | Transmission line of electricity Bird's Nest recognition methods based on HOG features and machine learning | |
| CN104994334A (en) | Automatic substation monitoring method based on real-time video | |
| CN106845344A (en) | Demographics' method and device | |
| CN111666920B (en) | Target article wearing detection method and device, storage medium and electronic device | |
| Li et al. | Toward efficient safety helmet detection based on YoloV5 with hierarchical positive sample selection and box density filtering | |
| CN110033601A (en) | A kind of Internet of Things fire protection alarm system and method based on WF-IoT | |
| CN111539276A (en) | Method for detecting safety helmet in real time in power scene | |
| CN107403180A (en) | A kind of numeric type equipment detection recognition method and system | |
| CN115201211A (en) | Quality control method and system for intelligent visual textile product | |
| CN113222973B (en) | Image processing method and device, processor, electronic equipment and storage medium | |
| CN106407908A (en) | Training model generation method and human face detection method and device | |
| CN112287823A (en) | Facial mask identification method based on video monitoring | |
| CN109241847A (en) | The Oilfield Operation District safety monitoring system of view-based access control model image | |
| CN109784375A (en) | Adaptive transformer part detection recognition method based on Faster RCNN | |
| CN111476083A (en) | Automatic identification method for wearing of safety helmet of electric power staff | |
| CN107133592A (en) | Electricity substation is using infrared thermal imaging and the human body target feature detection algorithm of visual light imaging technological incorporation | |
| CN109308670A (en) | The substation safety management-control method of Behavior-based control prediction | |
| CN113239760A (en) | Power grid operation field violation identification system | |
| CN113111771A (en) | Method for identifying unsafe behaviors of power plant workers |
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: 20180209 |