Embodiment
Below, the example embodiment according to the application will be described in detail by referring to the drawings.Obviously, described embodiment is only
Only be a part of embodiment of the application, rather than the application whole embodiments, it should be appreciated that the application is not by described herein
The limitation of example embodiment.
Application general introduction
As described above, safety monitoring algorithm on the market is only detected using characteristic portion (such as, face/human body) at present,
The influence of the problems such as due to wrong report, can reduce overall Consumer's Experience.
Found by further analysis, the safety monitoring scheme of existing feature based location detection does not distinguish monitoring field
In scape diverse location region may have different invasion probability, and only in algorithm characteristic portion recognize result very
Sensitivity, so as to produce the testing result of high wrong report, reduces the experience of user.
For the technical problem, the basic conception of the application be propose a kind of security-protecting and monitoring method, device, electronic equipment,
Computer program product and computer-readable recording medium, it can be by the alarm in diverse location region in analysis monitoring scene
Priority, and the different alarm strategy of correspondence, so as to be effectively reduced false alarm rate, lift Consumer's Experience.Specifically, exist
When analyzing diverse location region, more complicated model, the environmental characteristics of analysis monitoring scene can be used, and generate
Different band of position importance information, in the band of position with different importances, is alarmed using different strategies.
It is thereby achieved that more efficient and accurate safety monitoring.
It should be noted that the above-mentioned basic conception of the application can be applied not only to the application scenario of intrusion detection, also
It can apply to the various application scenarios such as household care, Traffic monitoring.
After the general principle of the application is described, carry out specifically to introduce the various non-limits of the application below with reference to the accompanying drawings
Property embodiment processed.
Example system
Fig. 1 illustrates the schematic diagram of the application scenarios operated according to the safety monitoring of the embodiment of the present application.
As shown in figure 1, including safety monitoring equipment 100 and target object 200 for the application scenarios that safety monitoring is operated.
The target object 200 can may pay close attention to its any kind of object whether occurred in monitoring scene, and it can
So that including characteristic portion, this feature position has certain characteristic information, for example, color, texture, shape, layout etc., thus,
It can be identified in the picture by special algorithm.For example, under the scene that family monitors, the target object 200 can be with
People, its can as intrusion detection, household care etc. object, correspondingly, this feature position can be the face of user, shape
Each body part such as body, trunk, hand, head, foot.And for example, under the scene of traffic monitoring, the target object 200
Can be the traffic entity of motor vehicle, bicycle, pedestrian etc., it can be supervised as vehicle Flow Detection, traffic offence etc.
Object, correspondingly, this feature position can be the global feature (for example, shape) of each traffic entity, local feature (example
Such as, number plate) etc..Alternatively, under other scenes, the target object 200 can also be any other object, such as robot,
Unmanned plane etc..
The safety monitoring equipment 100 can be used for carrying out target object detect and track, position determination, area type knowledge
It Deng not operate.For example, the safety monitoring equipment 100 can include camera 110 and safety monitoring module 120.
For example, the camera (image device) 110 can be used for the view data for catching monitoring scene, it can include one
Individual or multiple cameras.For example, the view data that camera 110 is collected can be consecutive image frame sequence (that is, video
Stream) or discrete picture frame sequence (that is, the image data set arrived in predetermined sampling time point sampling) etc..For example, the camera 110
It can be such as monocular camera, binocular camera, many mesh cameras, in addition, it can be used for catching gray-scale map, can also catch and carry
The cromogram of colouring information.Certainly, the camera of any other type as known in the art and be likely to occur in the future all may be used
So that applied to the application, the mode that the application catches image to it is not particularly limited, as long as resulting in the ash of input picture
Degree or colouring information.In order to reduce the amount of calculation in subsequent operation, in one embodiment, it can analyzed and located
Before reason, cromogram is subjected to gray processing processing.Certainly, in another embodiment, can also in order to retain bigger information content
Directly cromogram is analyzed and handled.
The safety monitoring module 120 can be used for detecting target object in the image sequence of the monitoring scene gathered;
In response to detecting target object in the particular image frame among described image sequence, determine the target object in the spy
Determine the location of pixels in picture frame;The area of the specific location area residing for the target object is determined according to the location of pixels
Field type;And scheduled operation is performed according to the area type of the specific location area.It is thereby achieved that more efficient
And accurate safety monitoring.
Understand spirit herein and principle it should be noted that above-mentioned application scenarios are for only for ease of and show, this
The embodiment not limited to this of application.On the contrary, embodiments herein can apply to any scene that may be applicable.For example, should
Target object 200 can be one or more, and similarly, the safety monitoring equipment 100 can also be one or more.
Illustrative methods
Security-protecting and monitoring method according to the embodiment of the present application is described with reference to Fig. 1 application scenarios.
Fig. 2 illustrates the flow chart of the security-protecting and monitoring method according to the embodiment of the present application.
As shown in Fig. 2 can be included according to the security-protecting and monitoring method of the embodiment of the present application:
In the step s 120, target object is detected in the image sequence of the monitoring scene gathered.
For example, the view data of monitoring scene, to generate image sequence, the image sequence can constantly be obtained by camera
It is classified as a series of continuous or discrete picture frame generated sequentially in time.It is then possible in each two field picture not
Target object is detected disconnectedly.
Fig. 3 illustrates the flow chart of the target object detecting step according to the embodiment of the present application.
As shown in figure 3, step S120 can include:
In sub-step S121, the characteristic portion of target object is detected in each picture frame of described image sequence;With
And
In sub-step S122, in response to detecting the characteristic portion, determine and detect target object.
For convenience, below, it will be described in detail under the application scenario of intrusion detection.
For example, camera can be arranged in the specific location in the space to be monitored (for example, room) in advance, to realize
The purpose of safety monitoring.The imaging angle of the camera can be reasonably set, to cause it is photographed as completely as possible whole
Individual room, thus when invader invades the room, can be captured at once by camera.
It is then possible to the view data acquired from camera, carry out feature recognition, such as face/human body is detected
Characteristic information.
Here, under the application scenario of intrusion detection, as detected object be invader, its for example can be people,
Animal, robot etc., behind gone on to say taking human as example.Thus, for example, can be detected in each picture frame the face of people/
The characteristic portions such as human body.
For example, this feature detection can be using simple aspect ratio to (for example, detecting the shape and cloth of face on face
Office etc.) mode, it would however also be possible to employ realized based on the mode of machine learning (for example, deep neural network).
Once the characteristic portions such as potential face/human body are detected in some particular image frame in image sequence, then
Think to detect the people as target object in the particular image frame.
In step S140, in response to detecting target object in the particular image frame among described image sequence, really
Fixed location of pixels of the target object in the particular image frame.
Once target object is detected in particular image frame, it may be determined that the location of pixels of the target object.
Fig. 4 illustrates the flow chart that step is determined according to the location of pixels of the embodiment of the present application.
As shown in figure 4, step S140 can include:
In sub-step S141, location of pixels of the characteristic portion in the particular image frame is determined;And
In sub-step S142, the location of pixels of the target object is determined according to the location of pixels.
For example, it may be determined that location of pixels of the characteristic portion such as face/human body in picture frame, that is, judge the face/people
Body is in abscissa and ordinate in picture frame.
Due to when carrying out face/human testing, (for example, frame choosing) can be labeled to them in picture frame, so
Here the frame favored area of callout box can directly be used as the location of pixels of characteristic portion.For example, in the feelings of rectangle callout box
Under condition, the upper left corner of the callout box and the coordinate in the lower right corner can be selected, the position coordinates of characteristic portion is used as.
Next, the location of pixels at this feature position simply can be determined directly as to the location of pixels of target object.
For example, when the characteristic portion detected is characteristics of human body, can be by the location of pixels of the characteristics of human body directly as object
The location of pixels of body.
Alternatively, whole object come further frame can also be selected according to the location of pixels for the characteristic portion determined
Body, and determine its location of pixels., can be according to the position of face characteristic for example, when the characteristic portion detected is face characteristic
Put further estimation human body position, and using the position of human body estimated as target object location of pixels.
In step S160, the area of the specific location area residing for the target object is determined according to the location of pixels
Field type.
In step S180, scheduled operation is performed according to the area type of the specific location area.
Once the location of pixels of target object is obtained, in above-mentioned two step, it is possible to determine that the target object is in
Where monitoring scene region and the area type for determining the band of position.It is then possible to according to area type come
Follow-up operation is performed, for example, selection is alarmed, do not alarmed or other possible operations.
For example, the area type of the band of position can be combine stablize graphical analysis and divide in advance, with difference
The band of position of alarm priority.For example, each band of position can include:Once detecting the sensitive position that target object is alarmed
Even if putting region, detecting target object and to meet non-sensitive positions region that predetermined condition just alarms, detect object
Wrong report band of position that body is not also alarmed etc..For example, the predetermined condition can detect target object to stablize motionless and continue
Situation, detect the situation of target object mass motion, detect target object and postpone situation of a period of time etc..Specifically
Band of position partiting step will the step of below in S110 be described in detail.
For example, the location of pixels scope of each the predefined band of position can be obtained, and by the pixel of target object
Position is compared with above-mentioned location of pixels scope, to determine the specific location area residing for target object, and determines its region
Type.
Determine after area type, follow-up behaviour can be performed according to the alarm priority associated with the band of position
Make.
Fig. 5 illustrates the flow chart that step is determined according to the area type of the embodiment of the present application.
As shown in figure 5, step S160 can include:
In sub-step S161, judge the location of pixels whether in easily wrong report pixel region;And
In sub-step S162, the easy wrong report pixel region is in response to the location of pixels, is determined described specific
The area type of the band of position belongs to the easily wrong report band of position, and the easy wrong report band of position is that wherein there may be the general of wrong report
Rate is more than or equal to the band of position of first threshold.
Correspondingly, step S180 can include:Belong to described easy in response to the area type of the specific location area
Report the band of position by mistake, do not perform alarm operation.
For example, after the location of pixels of invader is determined, can be according to the location of pixels and each predefined position
The coordinate range in region is put, the easy wrong report the pixel region whether invader is located in image is judged, so that it is determined that the invader
Whether the easy wrong report band of position in monitoring scene has been appeared in.For example, the easy wrong report band of position can be misinformation probability compared with
The band of position of high (for example, more than or equal to 70%).
Fig. 6 illustrates the schematic diagram of the monitoring scene of a specific example according to the embodiment of the present application.
As shown in fig. 6, multiple bands of position can have been divided in advance in monitoring scene.For example, this band of position
Division can be previously-completed based on the stable image of the monitoring scene.Different pixel regions corresponds in monitoring scene
The band of position with different alarm priorities.
For example, potentially including the easily wrong report band of position (region 1) in the monitoring scene.For example, situation about being monitored in family
Under, this easily report by mistake region can be television set, projection screen, DPF etc. may wherein occur continuously or once in a while face/
The region that human body is shown.Due to the above-mentioned characteristic in the region, it can be set as to the region of easily triggering false-alarm in advance, and will
Alarm strategy setting is accordingly:If detecting face/human body in zone 1, do not alarm.
With continued reference to Fig. 5, step S160 can also include:
In sub-step S163, it is not in the easy wrong report pixel region in response to the location of pixels but is in
Pixel region may be reported by mistake, the target object is tracked in the subsequent image frames of the particular image frame;
In sub-step S164, in response to tracing into the target object, determine whether the target object position occurs
It is mobile;And
In sub-step S165, there is not position movement in response to the target object, determine the specific location area
The area type in domain, which belongs to, may report the band of position by mistake, and the band of position that may report by mistake is that wherein there may be the probability of wrong report
Less than the first threshold but it is greater than or equal to the band of position of Second Threshold.
Correspondingly, step S180 can include:In response to the specific location area area type belong to it is described can
The band of position can be reported by mistake, alarm operation is not performed.
If for example, invader is not at the easy wrong report pixel region in image, determining whether that the invader is
The no possibility wrong report pixel region being located in image, so that it is determined that the possibility whether invader has been appeared in monitoring scene is missed
Report the band of position.For example, it can be that misinformation probability is medium (for example, being less than 70% but being more than or equal to that this, which may report the band of position by mistake,
40%) the band of position.
As shown in fig. 6, the band of position (region 2) may be reported by mistake by being also possible that in the monitoring scene.For example, in family's prison
In the case of control, it can be that sofa, tea table, photo frame etc. are people including that may be misidentified by algorithm that this, which may report region by mistake,
Some patterns or texture of face/human body but invader, which tend not to be located at the region at its place, (for example, being based on for general knowledge, to be entered
The person of invading will not generally be sitting on sofa, stand near tea table or rely on metope after intrusion room for a long time, keep not
It is dynamic).Due to the above-mentioned characteristic in the region, it can be set as in advance may to trigger the region of false-alarm, and will alarm accordingly
Strategy setting is:If detecting face/human body in region 2, need to continue the people that arrives of tracing detection, and if its
Follow-up many frame ins never have appearance motion (motion), then do not alarm.
With continued reference to Fig. 5, step S160 can also include:
In sub-step S166, there is position movement in response to the target object, determine the pixel of the characteristic portion
Size;
In sub-step S167, the Pixel Dimensions and intended pixel size of relatively more described characteristic portion;And
In sub-step S168, it is equal to the intended pixel size in response to the Pixel Dimensions of the characteristic portion, it is determined that
The area type of the specific location area, which belongs to described, may report the band of position by mistake.
Correspondingly, step S180 can include:In response to the specific location area area type belong to it is described can
The band of position can be reported by mistake, alarm operation is not performed.
As shown in fig. 6, in addition to region 2, the monitoring scene is also possible that others may report region (region by mistake
3).For example, in the case where family monitors, this may report region by mistake and can also be that owner is likely located at it on sofa, still
Invader tends not to be located at the region at it (for example, being based on for general knowledge, invader usual not president after intrusion room
Time is movable on sofa).Due to the above-mentioned characteristic in the region, it can be set as in advance may to trigger the region of false-alarm,
And the strategy setting that will alarm accordingly is:If detecting face/human body in region 3, need to continue the people that tracing detection is arrived,
And if it is moved in follow-up many frame ins, then the size of face/human body is determined whether, if face/human body
Size is identical with face/human dimension that personnel are sitting on the sofa, then it is probably the owner in room to illustrate the personnel, is not entered
The person of invading, then do not alarm.
With continued reference to Fig. 5, step S160 can also include:
In sub-step S169, in response to the specific location area be not belonging to the easy wrong report band of position or it is described can
The band of position can be reported by mistake, determine that the area type of the specific location area belongs to alarm sensitive position region, the alarm is quick
The sense band of position is that wherein there may be the band of position that the probability of wrong report is less than the Second Threshold.
Correspondingly, step S180 can include:Belong to the report in response to the area type of the specific location area
Alert sensitive position region, is immediately performed alarm operation.
If for example, invader is also not at the easy wrong report pixel region in image, then it is assumed that the invader is located at figure
Alarm sensitive pixel regions as in, so that it is determined that the invader has appeared in the alarm sensitive position region in monitoring scene.
For example, the alarm sensitive position region can be the band of position of misinformation probability relatively low (for example, less than 40%).
As shown in fig. 6, the monitoring scene is also possible that the region in addition to the 1-3 of region, that is, sensitizing range of alarming.Cause
This, can be by strategy setting of alarming accordingly:If detecting face/human body in this position, alarm immediately.For example,
If detecting face/human body in region 3, need to continue the people that tracing detection is arrived, and if it is in follow-up many frame ins
Move, then determine whether the size of face/human body, if the size at this feature position is sitting in this more than or less than personnel
Face/human dimension on sofa is identical, then illustrate the personnel may actually stand before sofa (that is, sofa and camera lens it
Between) or sofa behind, then, it is probably invader, then alarms at once.For example, the alarm sensitizing range can also be gate,
Corridor, important financial storing place (for example, safety cabinet) etc..
For example, certainly, among above-mentioned steps before alarm operation is performed, detecting face/human body in other words
Whether after characteristic information, it is the owner's characteristic information pre-set in feature database that can also first judge it, with prevent by
The owner of family is mistakenly considered invader, and produces false-alarm.
For example, above-mentioned alarm operation can by such as sound, illumination, vibration, push and disappear immediately to the mobile phone of user
One or more of the various modes such as cease, dial the police emergency number to realize, with reach warning invader, report law enfrocement official,
Remind the purpose of owner user.
In one embodiment, further, in order to realize the band of position of each in monitoring scene area type draw
Point, as shown in figure 1, before step S120, can also be included according to the security-protecting and monitoring method of the embodiment of the present application:
In step s 110, area type division is carried out to each band of position of the monitoring scene.
As described above, before above-mentioned step S120 to S180 is performed, can be carried out to the stable image of monitoring scene
Analysis, to mark off the band of position with different alarm priorities in advance.Certainly, the application not limited to this, for example, the region
Type division result can also be that system is preset according to intrinsic monitoring scene.
For example, this area type division operation can be performed in local side, but in order to obtain the meter of reduction local side
It is counted as this and improves arithmetic accuracy, the division operation can also be realized in server end (high in the clouds).
Fig. 7 illustrates the flow chart of the area type partiting step according to the embodiment of the present application.
As shown in fig. 7, step S110 can include:
In sub-step S111, the stable picture frame of the monitoring scene is obtained, the stable picture frame is to exist therebetween
Mobile target object number be less than predetermined threshold picture frame;
In sub-step S112, pattern analysis is carried out to the monitoring scene according to the stable picture frame, to determine
The probability that the band of position and its appearance for being wherein likely to occur wrong report are reported by mistake;And
In sub-step S113, band of position division is carried out to the monitoring scene according to the result of the pattern analysis
And determine the area type of each band of position.
For example, before the safety monitoring equipment 100 is formally enabled, it is necessary first to which it is initialized.
To this end it is possible to use, camera 200 shoots the image of monitoring scene, and the region analysis for newly adding
Part obtains stable image.
It is not to run each time to obtain stable image, but on camera, one is carried out when just unlatching
The judgement of series, the pattern analysis of interval time long progress;If in target location movement this period target seldom, i.e.,
Varying less for image, then can be understood as the substantially stable environment of family, image can be uploaded to high in the clouds and started
Carry out image analysis, with determine various ranks wrong report sensitizing range (e.g., including rate of false alarm very high television area, by mistake
The higher metope of report rate, texture are complicated, sofa region, and other regions).
For example, image scene can be parsed, the attribute of specific each part is obtained.For example, after taking image, Ke Yifen
Analysis draws following type area:The region such as gate, corridor, important financial storing place (for example, safety cabinet) can be set
Sensitizing range is set to, is needed if invasion is detected than faster alarm;The image such as television set viewing area can be set
For the region of easily triggering alarm, do not alarmed if information is detected in this position;Can be by sofa, tea table, metope etc.
Region is set to the region for needing to judge that the information such as motion can just alarm.For example, the function of this part can beyond the clouds and/or this
Ground is identified using machine learning (for example, deep neural network).
In addition, after except above-mentioned zone analysis, can also be in graphical analysis, further addition personnel analysis, with same
When obtain some personal information carry out each section type of alarm confirmation.
For example, with reference to the specifying information of user, it is actually that user often lives that can count as region 3 in Fig. 6
Dynamic region, but be not typically the position that the people invaded often occurs, with reference to the analysis of this part, it can get specific
Position, and computing is carried out beyond the clouds and/or locally, so as to update the sensitive face/human body of overall regional needs and right
The statistical information for the size that the camera answered is shown, to update corresponding alarm strategy.
Above, by the way of being handled using high in the clouds, the information in binding site and region enters the extension of row information, can cause each
This custom data of individual user can unite beyond the clouds, can also reduce the local of safety monitoring equipment 100 well
Operand and amount of storage.
As can be seen here, can be in the monitoring scene gathered using the security-protecting and monitoring method according to the embodiment of the present application
Target object is detected in image sequence;In response to detecting target object in the particular image frame among described image sequence,
Determine location of pixels of the target object in the particular image frame;The object is determined according to the location of pixels
The area type of specific location area residing for body;And predetermined behaviour is performed according to the area type of the specific location area
Make.It is thereby achieved that more efficient and accurate safety monitoring.It is thereby achieved that more efficient and accurate security protection prison
Control.
More specifically, the advantage after employing the security-protecting and monitoring method according to the embodiment of the present application is:
1st, by detection/parsing (Parsing) method, the alarm level of each band of position in monitoring scene is obtained,
So as to safeguard the alarm weight distribution figure of a set of different alarming logics;
2nd, as a result of finer scene analysis, so as to effectively reduce the generation of false-alarm, user's body is lifted
Test;
3rd, due to using based drive characteristic portion (for example, face/human body) posture analysis, it can avoid missing in theory
The generation of report, cost is only the introduction of a small amount of calculation process.
Exemplary means
Below, it is described with reference to Figure 8 the security monitoring device according to the embodiment of the present application.
Fig. 8 illustrates the block diagram of the security monitoring device according to the embodiment of the present application.
As shown in figure 8, can be included according to the security monitoring device 300 of the embodiment of the present application:Target object detection unit
320, for detecting target object in the image sequence of the monitoring scene gathered;Location of pixels determining unit 340, for ringing
Ying Yu detects target object in the particular image frame among described image sequence, determines the target object described specific
Location of pixels in picture frame;Area type determining unit 360, for determining the target object according to the location of pixels
The area type of residing specific location area;And scheduled operation execution unit 380, for according to the specific location area
Area type perform scheduled operation.
In one example, the target object detection unit 320 can be in each picture frame of described image sequence
Detect the characteristic portion of target object;And in response to detecting the characteristic portion, determine and detect target object.
In one example, the location of pixels determining unit 340 can determine the characteristic portion in the specific pattern
As the location of pixels in frame;And the location of pixels of the target object is determined according to the location of pixels.
In one example, whether the area type determining unit 360 may determine that the location of pixels in easily by mistake
Report pixel region;And the easy wrong report pixel region is in response to the location of pixels, the specific location area is determined
Area type belong to easily wrong report the band of position, the easy wrong report band of position be wherein be more than there may be the probability of wrong report or
Equal to the band of position of first threshold.
In one example, the scheduled operation execution unit 380 can in response to the specific location area region
Type belongs to the easy wrong report band of position, does not perform alarm operation.
In one example, the area type determining unit 360 may also respond to the location of pixels and be not in
The easy wrong report pixel region but in pixel region may be reported by mistake, in the subsequent image frames of the particular image frame with
Target object described in track;In response to tracing into the target object, determine whether the target object position movement occurs;And
There is not position movement in response to the target object, determine that the area type of the specific location area belongs to possible wrong report
The band of position, the band of position that may report by mistake is wherein to be less than the first threshold there may be the probability of wrong report but big
In or equal to Second Threshold the band of position.
In one example, the scheduled operation execution unit 380 can in response to the specific location area region
Type, which belongs to described, may report the band of position by mistake, and alarm operation is not performed.
In one example, the area type determining unit 360 may also respond to the target object and position occurs
It is mobile, determine the Pixel Dimensions of the characteristic portion;Compare the Pixel Dimensions and intended pixel size of the characteristic portion;And
It is equal to the intended pixel size in response to the Pixel Dimensions of the characteristic portion, determines the region class of the specific location area
Type, which belongs to described, may report the band of position by mistake.
In one example, the scheduled operation execution unit 380 can in response to the specific location area region
Type, which belongs to described, may report the band of position by mistake, and alarm operation is not performed.
In one example, the area type determining unit 360 may also respond to the specific location area and not belong to
In the easy wrong report band of position or it is described may report the band of position by mistake, determine that the area type of the specific location area belongs to
Alarm sensitive position region, the alarm sensitive position region is wherein to be less than the Second Threshold there may be the probability of wrong report
The band of position.
In one example, the scheduled operation execution unit 380 can in response to the specific location area region
Type belongs to the alarm sensitive position region, is immediately performed alarm operation.
In one example, the security monitoring device 300 can also include:Area type division unit 310, for pair
Each band of position of the monitoring scene carries out area type division.
In one example, the area type division unit 310 can obtain the stable picture frame of the monitoring scene,
The stable picture frame is that the number of the mobile target object existed therebetween is less than the picture frame of predetermined threshold;According to the stabilization
Picture frame to carry out pattern analysis to the monitoring scene, to determine wherein to be likely to occur the band of position of wrong report and its miss
The probability of report;And band of position division is carried out to the monitoring scene according to the result of the pattern analysis and each is determined
The area type of the band of position.
Unit and the concrete function of module and operation in above-mentioned security monitoring device 300 are had been described above with reference to figure
It is discussed in detail in the security-protecting and monitoring method of 1 to Fig. 7 description, and therefore, its repeated description will be omitted.
Supervised as described above, can apply to security protection as shown in Figure 1 according to the security monitoring device 300 of the embodiment of the present application
Control in equipment 100, for carrying out the operations such as detect and track, position are determined, area type is recognized to target object.
In one example, according to the security monitoring device 300 of the embodiment of the present application can as a software module and/
Or hardware module and be integrated into the safety monitoring equipment 100 in Fig. 1.For example, the security monitoring device 300 can be implemented
For the safety monitoring module 120 in equipment 100.For example, the security monitoring device 300 can be the safety monitoring equipment 100
A software module in operating system, or can be directed to one that the safety monitoring equipment 100 developed to apply journey
Sequence;Certainly, the security monitoring device 300 equally can be one of numerous hardware modules of the safety monitoring equipment 100.
Alternatively, in another example, the security monitoring device 300 and the safety monitoring equipment 100 can also be discrete
Equipment, and the security monitoring device 300 can be connected to the safety monitoring equipment 100 by wired and or wireless network,
And transmit interactive information according to the data format of agreement.
Example electronic device
Below, it is described with reference to Figure 9 the electronic equipment according to the embodiment of the present application.The electronic equipment can be computer or
Server or other equipment.For example, in one example, can be right according to the electronic equipment of the target object of the embodiment of the present application
Safety monitoring equipment 100 that should be in Fig. 1.
Fig. 9 illustrates the block diagram of the electronic equipment according to the embodiment of the present application.
As shown in figure 9, electronic equipment 10 includes one or more processors 11 and memory 12.
Processor 11 can be CPU (CPU) or with data-handling capacity and/or instruction execution capability
Other forms processing unit, and desired function can be performed with the other assemblies in control electronics 10.
Memory 12 can include one or more computer program products, and the computer program product can include each
The computer-readable recording medium of the form of kind, such as volatile memory and/or nonvolatile memory.The volatile storage
Device is such as can include random access memory (RAM) and/or cache memory (cache).It is described non-volatile to deposit
Reservoir is such as can include read-only storage (ROM), hard disk, flash memory.It can be deposited on the computer-readable recording medium
One or more computer program instructions are stored up, processor 11 can run described program instruction, to realize this Shen described above
The security-protecting and monitoring method of each embodiment please and/or other desired functions.In the computer-readable recording medium
In can also to store the location of pixels of target object, the area type of specific location area residing for target object etc. various
Content.
In one example, electronic equipment 10 can also include:Input unit 13 and output device 14, these components pass through
Bindiny mechanism's (not shown) interconnection of bus system and/or other forms.
For example, the input unit 13 can be above-mentioned camera 110, the image sequence for catching monitoring scene.This
Outside, the input equipment 13 can also include such as keyboard, mouse and communication network and its remote input equipment connected
Deng.
The output device 14 can export various information, including target to outside (for example, user or machine learning model)
Area type, warning message of specific location area residing for the location of pixels of object, target object etc..The output equipment 14 can
With including such as display, loudspeaker, printer and communication network and its remote output devices connected etc..
Certainly, to put it more simply, illustrate only some in component relevant with the application in the electronic equipment 10 in Fig. 9,
Eliminate the component of such as bus, input/output interface etc..In addition, according to concrete application situation, electronic equipment 10 is also
Any other appropriate component can be included.
Illustrative computer program product and computer-readable recording medium
In addition to the above method and equipment, embodiments herein can also be computer program product, and it includes meter
Calculation machine programmed instruction, the computer program instructions by processor when being run so that described computing device this specification is above-mentioned
The step in the security-protecting and monitoring method according to the various embodiments of the application described in " illustrative methods " part.
The computer program product can be write with any combination of one or more programming languages for holding
The program code of row the embodiment of the present application operation, described program design language includes object oriented program language, such as
Java, C++ etc., in addition to conventional procedural programming language, such as " C " language or similar programming language.Journey
Sequence code can perform fully on the user computing device, partly perform on a user device, independent soft as one
Part bag is performed, part is performed or completely in remote computing device on a remote computing on the user computing device for part
Or performed on server.
In addition, embodiments herein can also be computer-readable recording medium, it is stored thereon with computer program and refers to
Order, the computer program instructions by processor when being run so that above-mentioned " the exemplary side of described computing device this specification
The step in the security-protecting and monitoring method according to the various embodiments of the application described in method " part.
The computer-readable recording medium can use any combination of one or more computer-readable recording mediums.Computer-readable recording medium can
To be readable signal medium or readable storage medium storing program for executing.Readable storage medium storing program for executing can for example include but is not limited to electricity, magnetic, light, electricity
Magnetic, the system of infrared ray or semiconductor, device or device, or any combination above.Readable storage medium storing program for executing is more specifically
Example (non exhaustive list) includes:Electrical connection, portable disc with one or more wires, hard disk, random access memory
Device (RAM), read-only storage (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc
Read-only storage (CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
The general principle of the application is described above in association with specific embodiment, however, it is desirable to, it is noted that in this application
Advantage, advantage, effect referred to etc. is only exemplary rather than limitation, it is impossible to which it is the application to think these advantages, advantage, effect etc.
Each embodiment is prerequisite.In addition, detail disclosed above is merely to the effect of example and the work readily appreciated
With, and it is unrestricted, above-mentioned details is not intended to limit the application to realize using above-mentioned concrete details.
The device that is related in the application, device, equipment, the block diagram of system only illustratively the example of property and are not intended to
It is required that or hint must be attached in the way of square frame is illustrated, arrange, configure.As it would be recognized by those skilled in the art that
, it can connect, arrange by any-mode, configuring these devices, device, equipment, system.Such as " comprising ", "comprising", " tool
Have " etc. word be open vocabulary, refer to " including but is not limited to ", and can be with its used interchangeably.Vocabulary used herein above
"or" and " and " refer to vocabulary "and/or", and can be with its used interchangeably, unless it is not such that context, which is explicitly indicated,.Here made
Vocabulary " such as " refers to phrase " such as, but not limited to ", and can be with its used interchangeably.
It may also be noted that in device, apparatus and method in the application, each part or each step are to decompose
And/or reconfigure.These decompose and/or reconfigured the equivalents that should be regarded as the application.
The above description of disclosed aspect is provided so that any person skilled in the art can make or use this
Application.Various modifications in terms of these are readily apparent to those skilled in the art, and defined herein
General Principle can apply to other aspect without departing from scope of the present application.Therefore, the application is not intended to be limited to
Aspect shown in this, but according to the widest range consistent with the feature of principle disclosed herein and novelty.
In order to which purpose of illustration and description has been presented for above description.In addition, this description is not intended to the reality of the application
Apply example and be restricted to form disclosed herein.Although already discussed above multiple exemplary aspects and embodiment, this area skill
Art personnel will be recognized that its some modifications, modification, change, addition and sub-portfolio.