Summary of the invention
In view of above-mentioned, present disclose provides a kind of method and devices of wake-up device.Using this method and device, work as detection
Around to equipment there are people and detected people close to equipment when, the interactive operation of wake-up device, thus, it is possible to accurate
Ground wakes up interactive operation.
According to one aspect of the disclosure, a kind of method of wake-up device is provided, comprising: based on the environment map around equipment
Picture identifies and whether there is people around equipment;There are when people around the equipment, obtain between the people and the equipment extremely
Few two range informations;Based at least two acquired range informations, determine the people whether close to the equipment;With
And when determining the people close to the equipment, wake up the equipment.
Optionally, in one example, it is obtained between the people and the equipment around the equipment there are when people
At least two range informations may include: that the people is obtained using distance sensing device there are when people around the equipment
At least two range informations between the equipment.
Optionally, in one example, the ambient image may include at least two frame ambient images, obtain the people with
At least two range informations between the equipment may include: based on at least two frame ambient images, determine the people with
At least two range informations between the equipment.
Optionally, in one example, the ambient image can be the 3D rendering obtained using 3D photographic device, be based on
At least two frame ambient images, determine that at least two range informations between the people and the equipment may include: to be based on
At least two frame 3D renderings determine at least two range informations between the people and the equipment.
Optionally, in one example, the ambient image can be the 2D image obtained using 2D photographic device, be based on
At least two frame ambient images, determine that at least two range informations between the people and the equipment may include: to be based on
At least two frame ambient images carry out spatial modeling, to obtain at least two spatial models;And it is based on described at least two
Spatial model obtains at least two space coordinates of the people, using as at least two between the people and the equipment away from
From information.
Optionally, in one example, based on the ambient image around equipment, identifying can be with the presence or absence of people around equipment
It include: that characteristics of human body's identification is executed to the ambient image, to identify around the equipment with the presence or absence of people.
Optionally, in one example, the characteristics of human body may include face.
According to another aspect of the disclosure, a kind of method of wake-up device is also provided, comprising: based on the ring around equipment
Border image identifies and whether there is target object around equipment;There are when target object around the equipment, it is based at least two frames
Whether ambient image determines the target object close to the equipment using target tracking algorism;And when the determining mesh
Mark object close to the equipment when, wake up the equipment.
According to another aspect of the present disclosure, a kind of device for wake-up device is also provided, comprising: human bioequivalence unit,
The ambient image being configured as around based on equipment identifies and whether there is people around equipment;Distance acquiring unit is configured as
There are at least two range informations when people, obtained between the people and equipment around the equipment;Human body close to determination unit,
It is configured as determining the people whether close to the equipment based at least two acquired range informations;And equipment
Wakeup unit is configured as waking up the equipment when determining the people close to the equipment.
Optionally, in one example, the distance acquiring unit may include distance sensing device.
Optionally, in one example, the ambient image may include at least two frame ambient images, and the distance obtains
Unit is configured as: based on at least two frame ambient images, determining at least two distances between the people and the equipment
Information.
Optionally, in one example, the ambient image can be the 3D rendering obtained using 3D photographic device, described
Distance acquiring unit is configured as: be based at least two frame 3D renderings, determine between the people and the equipment at least two away from
From information.
Optionally, in one example, the ambient image is the 2D image obtained using 2D photographic device, the distance
Acquiring unit includes: spatial modeling module, is configured as carrying out spatial modeling based on at least two frame ambient images, to obtain
At least two spatial models;And apart from module is obtained, it is configured as determining the people based at least two spatial model
At least two space coordinates, using as at least two range informations between the determination people and the equipment.
Optionally, in one example, the human bioequivalence unit can be configured as: to the ambient image executor
Body characteristics identification, to identify around the equipment with the presence or absence of people.
According to another aspect of the present disclosure, a kind of device of wake-up device is also provided, comprising: recongnition of objects device,
The ambient image being configured as around based on equipment identifies and whether there is target object around equipment;Target object tracking cell,
It is configured as around the equipment being based at least two frame ambient images there are when target object, it is true using target tracking algorism
Whether the fixed target object is close to the equipment;And equipment wakeup unit, it is configured as leaning on as the determining people
When the nearly equipment, the equipment is waken up.
According to another aspect of the present disclosure, a kind of calculating equipment is also provided, comprising: at least one processor;And storage
Device, the memory store instruction, when described instruction is executed by least one described processor, so that described at least one
Reason device executes method described in first aspect as above.
According to another aspect of the present disclosure, a kind of machine readable storage medium is also provided, executable instruction is stored with, institute
State instruction makes the machine execute method described in first aspect as above upon being performed.
According to another aspect of the present disclosure, a kind of calculating equipment is also provided, comprising: at least one processor;And storage
Device, the memory store instruction, when described instruction is executed by least one described processor, so that described at least one
Reason device executes method described in the second aspect as above.
According to another aspect of the present disclosure, a kind of non-transitory machinable medium is also provided, being stored with can hold
Row instruction, described instruction make the machine execute method described in the second aspect as above upon being performed.
Using disclosed method and device, when identifying around equipment there are when people, based on the people identified with set
It is the distance between standby determine identified people whether close to equipment, when the people identified close to equipment when wake-up
Equipment, to interact operation.The user that thereby, it is possible to just will be identified as having equipment using wish close to the people of equipment, with
Accurately wake-up device.
Using disclosed method and device, identifying that there are people around equipment based on the ambient image around equipment
When, identified people is obtained at a distance from equipment room based on the ambient image, so as to avoid acquired distance practical
On be not between identified people and equipment apart from the case where, to improve the accuracy of acquired range information, Jin Erti
The accuracy of high wake-up device.
Using disclosed method and device, by obtaining ambient image using 3D photographic device, and based on acquired
3D rendering data determine that identified people at a distance from equipment room, can be improved apart from recognition efficiency.
Using disclosed method and device, by obtaining ambient image using 2D photographic device, and based on acquired
2D image obtains identified the distance between people and equipment after carrying out three-dimensional modeling, can reduce hardware cost.
Using disclosed method and device, by executing characteristics of human body's identification to ambient image, to identify around equipment
It whether there is people in environment, can be improved the accuracy of the people in identification equipment ambient enviroment.
Specific embodiment
Theme described herein is discussed below with reference to example embodiment.It should be understood that discussing these embodiments only
It is in order to enable those skilled in the art can better understand that being not to claim to realize theme described herein
Protection scope, applicability or the exemplary limitation illustrated in book.It can be in the protection scope for not departing from present disclosure
In the case of, the function and arrangement of the element discussed are changed.Each example can according to need, omit, substitute or
Add various processes or component.In addition, feature described in relatively some examples can also be combined in other examples.
As used in this article, term " includes " and its modification indicate open term, are meant that " including but not limited to ".
Term "based" indicates " being based at least partially on ".Term " one embodiment " and " embodiment " expression " at least one implementation
Example ".Term " another embodiment " expression " at least one other embodiment ".Unless clearly indicated in context, otherwise one
The definition of a term is consistent throughout the specification.
The method and device of the wake-up device of the disclosure is described presently in connection with attached drawing.
Fig. 1 is the flow chart according to the method for the wake-up device of one embodiment of the disclosure.
As shown in Figure 1, based on the ambient image around equipment, identifying in block 102 to 104 and whether there is people around equipment.
People can be recognized whether by the characteristics of human body in environment-identification image.It in one example, can be using by instruction
Experienced human body contour outline identification model is come in environment-identification image with the presence or absence of people.In one example, can also be known using face
Other algorithm whether there is people in a manner of through recognition of face in environment-identification.
In another example, can identify around equipment there are when people, obtained using distance sensing device people with
At least two range informations between equipment.For example, infrared acquisition, the side of tellurometer survey, radar sensor ranging can be passed through
Formula is come around awareness apparatus with the presence or absence of people.Such mode can be improved the efficiency for obtaining range information, and reduce calculation resources,
But the barriers such as animal, vehicle Jing Guo equipment may be erroneously identified as people by such identification method.By being based on being obtained
The ambient image taken carries out human bioequivalence, can be avoided when the barriers such as animal, vehicle are close to equipment, mistakenly wakes up and sets
Standby interactive operation.
There are when people in equipment ambient enviroment, in block 106, at least two range informations between people and equipment are obtained.
At least two range informations are two range informations that time series has sequencing.For example, can be by sending out around equipment
Microwave is penetrated, and receives the range information for being reflected back toward the microwave acquisition of equipment at least two moment.In another example, may be used also
To obtain the range information at least two moment by setting radar sensor etc..
In one example, it can be obtained between people and equipment at least based on acquired at least two frame ambient images
Two range informations.It can be by determining from identifying around equipment and identifying characteristics of human body in ambient image there are when people
The distance between the human body identified and equipment.It in one example, can the part or complete based on the human body identified
Size of the portion at least two frame ambient images, to obtain range information.In this example, acquired range information can not
It is the distance value of quantization, but the qualitatively information such as remote or close.
In one example, it can use the 3D rendering around the equipment of 3D photographic device acquisition, as around equipment
Ambient image.In this example, can based on the 3D rendering data at least two frame 3D renderings, obtain identified people with
At least two range informations between equipment.3D rendering itself has depth information, therefore can be based on the depth in 3D rendering
Information obtains range information.For example, the reflected depth of 3D rendering can be based in at least two frame ambient images of shooting
Degree information determines that identified people relative to the 3D rendering shot before is farther or closer from equipment.It can also be based on
Depth information is extracted from captured 3D rendering to obtain specific distance value.
Although can also get the distance between people and equipment information using microwave, laser radar etc., if
It recognizes there are having vehicle, animal etc. when people by equipment around equipment, acquired range information is likely to be vehicle, animal
Information between equal barriers and equipment.Thus there may be mistakes for the range information obtained.And it is obtained based on ambient image
When the distance between people and equipment information, it can be ensured that acquired range information is the distance between people and equipment information, and
It is not the distance between barriers and the equipment information such as animal, vehicle by equipment, so as to ensure acquired distance
The accuracy of information.
After getting range information, people is determined based at least two acquired range informations in block 108 to 110
Whether close to equipment.It, can be with when range information posterior in time series is more closer from equipment than preceding range information
Determine identified people close to equipment.
In one example, when ambient image is 3D rendering, at least two frame 3D renderings in time sequencing can be compared
Depth information between middle people and equipment, to identify identified people whether close to equipment.It in another example, can be with
2D image is obtained as ambient image using 2D photographic device, and is compared at least two frame 2D images, part or all of human body
Size, to judge identified people whether close to equipment.For example, when after the moment ambient image in identify
When face is bigger than the facial size in the ambient image at preceding moment, identified people can be determined close to equipment.
In another example, it can use the modes such as laser radar range or tellurometer survey to obtain at least two moment people
Determine identified people close to equipment when posterior distance is smaller than preceding distance with the range information of equipment.
When determining identified people close to equipment, in block 112, wake-up device.If identified around equipment
There are people and the people that is identified is close to equipment, then can determine the use for existing around equipment and having to equipment using wish
Family.For example, when someone close to Vending Machine when, can determine the people be have to Vending Machine consumption wish use
Family, thus can wake-up device in time, to trade with user.
Thereby, it is possible to avoid in someone being only to pass through equipment and mistakenly wake-up device when there is no using wish.
In one example, can in people close to equipment, and between the people and equipment away from predetermined threshold with
When interior, wake-up device.Thereby, it is possible to further increase the accuracy for waking up control, to improve user experience.
When using 2D photographic device to obtain ambient image, hardware cost can reduce.At this point, in order to more accurately
Determine that identified people whether close to equipment, can use acquired 2D image to carry out three-dimensional modeling.Fig. 2 is root
According to the exemplary flow chart apart from acquisition process in the method for the wake-up device of another embodiment of the present disclosure.
As shown in Fig. 2, spatial modeling is carried out based at least two frame ambient images, in block 202 to obtain at least two spaces
Model.Each spatial model corresponds to a frame ambient image.For example, at the first moment, it can be based on the environment map at the first moment
Picture carries out spatial modeling at least frame ambient image before the ambient image, to obtain the environment for being directed to for the first moment
The spatial model of image.It similarly, can be before ambient image and the ambient image based on the second moment at the second moment
An at least frame ambient image carries out spatial modeling, to obtain the spatial model for corresponding to the ambient image at the second moment.By
This, can obtain at least two spatial models corresponding at least two frame ambient images.
In this example, at least two 2D photographic devices be can use and obtain ambient image from different perspectives.At least two
A 2D photographic device for example can be binocular camera shooting head etc..It in one example, can be using SLAM method based on acquired
At least two frame ambient images carry out spatial modeling.At least two frame ambient images are the environment maps for having sequencing in time series for this
Picture can be successive frame, can also with interval predetermined frame discontinuous frame.It can be raw based on the image data in ambient image
At point cloud data, and then the most parcel convex surface enveloping solid that cloud is put between at least two frame ambient images is calculated, to generate spatial model.
When getting at least two spatial models, in block 204, at least two spatial models is based on, obtain people at least
Two spaces coordinate, using as at least two range informations between people and equipment.Ambient image is obtained with the visual angle of equipment
, thus ambient image is equivalent to the visual field of equipment.At this point, the space coordinate of the people obtained based on spatial model, can be seen
Make coordinate of the people relative to equipment.Therefore, the space coordinate of the people thus obtained can be regarded the distance between as people and equipment.
There are when people around equipment, based on people will be present in spatial model acquired in ambient image.At this point it is possible to logical
The space coordinate that the characteristics of human body crossed in identification spatial model comes, to obtain the space coordinate of people.Characteristics of human body for example can be
Face characteristic, can be using the face coordinate in spatial model as the space coordinate of people.
Fig. 3 is the flow chart of the method for wake-up device according to another embodiment of the present disclosure.
It identifies based on the ambient image around equipment in block 302 and block 304 and whether there is target object around equipment.Mesh
Mark object can be people, can be by carrying out the modes such as human body contour outline identification or recognition of face to ambient image come environment-identification figure
It whether there is people as in.
In block 306 and block 308, there are when target object around equipment, at least two frame ambient images is based on, target is utilized
Whether track algorithm determines the target object close to equipment.For example, at least two frame ambient images can be based on, TLD is utilized
(Tracking-by-Detection) algorithm, MDP track (MDP Tracking) algorithm, KCF target tracking algorism, OpenCV
Target tracking algorism etc. is come people's progress target following to identifying from ambient image.By target following, mesh can be obtained
It is opposite away from variation between mark object and equipment, when the relative distance tails off at any time, it may be determined that target object is close
Equipment.
When determining target object close to equipment, in block 310, wake-up device.
Fig. 4 is according to the structural block diagram of the device of the wake-up device of one embodiment of the disclosure.As shown in figure 4, equipment is called out
Device 400 of waking up includes human bioequivalence unit 410, distance acquiring unit 420, human body close to determination unit 430 and equipment wake-up
Unit 440.
Human bioequivalence unit 410 is configured as based on the ambient image around acquired equipment, and identifying around equipment is
It is no that there are people.In one example, human bioequivalence unit 410 is configured as executing ambient image characteristics of human body's identification, to know
It whether there is people around other equipment.
There are when people around equipment, distance acquiring unit 420 obtains at least two between identified people and equipment
A range information.In one example, distance acquiring unit 420 may include distance sensing device.Distance sensing device is for example
It can be infrared spy device, radar sensing device, microwave distance measuring device etc..
When getting range information, human body close to determination unit 430 be configured as based on acquired at least two away from
From information, determine people whether close to equipment.When determining people close to equipment, 440 wake-up device of equipment wakeup unit.
In one example, equipment wakeup unit 440, which can be configured as, is determining people close to equipment and and equipment
The distance between be less than predetermined distance threshold when, wake-up device.
In one example, image includes at least two frame ambient images around equipment.At this point, distance acquiring unit 420 can
To be configured as obtaining at least two range informations between identified people and equipment based on ambient image.
In one example, ambient image can be the 3D rendering obtained using 3D photographic device.In this example, distance
Acquiring unit 420 can be configured as based at least two frame 3D renderings, obtain at least two between identified people and equipment
A range information.
Fig. 5 is an exemplary structural block diagram of the distance acquiring unit 420 in equipment Rouser 400 shown in Fig. 4.
As shown in figure 5, distance acquiring unit 420 is including spatial modeling module 421 and apart from acquisition module.In this example, equipment week
Enclosing ambient image is the 2D image obtained using 2D photographic device.
Spatial modeling module 421 is configured as carrying out spatial modeling based at least two frame ambient images, to obtain at least two
A spatial model.Distance is obtained module 422 and is configured as being obtained at least two spaces seat of people based at least two spatial models
Mark, using as at least two range informations between people and equipment.
The structural block diagram of the device of the wake-up device of Fig. 6 according to another embodiment of the present disclosure.As shown in fig. 6, equipment is called out
Device 600 of waking up includes recongnition of objects device 610, target object tracking cell 620 and equipment wakeup unit 630.
Recongnition of objects device 610 is configured as the ambient image around based on equipment, identifies whether deposit around equipment
In target object.Target object tracking cell 620 is configured as around the equipment being based at least two there are when target object
Whether frame ambient image determines the target object close to the equipment using target tracking algorism.When determining target object
When close to equipment, equipment wakeup unit 630 wakes up the equipment.
Above by reference to Fig. 1 to Fig. 6, the embodiment of the method and device according to the wake-up device of the disclosure is retouched
It states.To the details mentioned in the description of embodiment of the method, it is being equally applicable to the embodiment of the device of the disclosure above.
The device of the wake-up device of the disclosure can use hardware realization, can also be using software or hardware and software
Combination is to realize.To the details mentioned in the description of embodiment of the method, it is being equally applicable to the reality of the device of the disclosure above
Apply example.All the embodiments in this specification are described in a progressive manner, same and similar part between each embodiment
It refers to each other.
The device of the wake-up device of the disclosure can use hardware realization, can also be using software or hardware and software
Combination is to realize.Taking software implementation as an example, as the device on a logical meaning, being will by the processor of equipment where it
Corresponding computer program instructions are read into memory what operation was formed in memory.In the disclosure, the device of wake-up device
Such as it can use and calculate equipment realization.
Fig. 7 is the structural frames according to the calculating equipment of the method for realizing wake-up device of one embodiment of the disclosure
Figure.As shown in fig. 7, calculating equipment 700 includes processor 710, memory 720, memory 730, communication interface 740 and internal bus
750, and processor 710, memory 720, memory 730, communication interface 740 link together via bus 750.According to one
Embodiment, calculating equipment 700 may include at least one processor 710, which executes can in computer
It reads to store in storage medium (that is, memory 720) or at least one computer-readable instruction of coding is (that is, above-mentioned with software shape
The element that formula is realized).
In one embodiment, computer executable instructions are stored in memory 720, make at least one when implemented
A processor 710: it based on the ambient image around equipment, identifies and whether there is people around equipment;Exist around the equipment
When people, at least two range informations between people and the equipment are obtained;Based at least two acquired range informations, determine
Whether the people is close to the equipment;And when determining the people close to the equipment, wake up the equipment.
In another embodiment, computer executable instructions are stored in memory 720, make at least one when implemented
A processor 710: it based on the ambient image around equipment, identifies and whether there is target object around equipment;In the equipment week
It encloses there are when target object, is based at least two frame ambient images, determines the target object whether using target tracking algorism
Close to the equipment;And when determining the target object close to the equipment, wake up the equipment.
It should be understood that the computer executable instructions stored in memory 720 make at least one processing when implemented
Device 710 carries out the above various operations and functions described in conjunction with Fig. 1-6 in each embodiment of the disclosure.
According to one embodiment, a kind of program product of such as non-transitory machine readable media is provided.Non-transitory
Machine readable media can have instruction (that is, above-mentioned element realized in a software form), which when executed by a machine, makes
It obtains machine and executes the above various operations and functions described in conjunction with Fig. 1-6 in each embodiment of the disclosure.
Specifically, system or device equipped with readable storage medium storing program for executing can be provided, stored on the readable storage medium storing program for executing
Realize above-described embodiment in any embodiment function software program code, and make the system or device computer or
Processor reads and executes the instruction being stored in the readable storage medium storing program for executing.
In this case, it is real that any one of above-described embodiment can be achieved in the program code itself read from readable medium
The function of example is applied, therefore the readable storage medium storing program for executing of machine readable code and storage machine readable code constitutes of the invention one
Point.
The embodiment of readable storage medium storing program for executing include floppy disk, hard disk, magneto-optic disk, CD (such as CD-ROM, CD-R, CD-RW,
DVD-ROM, DVD-RAM, DVD-RW, DVD-RW), tape, non-volatile memory card and ROM.It selectively, can be by communication network
Network download program code from server computer or on cloud.
It is above-mentioned that this specification specific embodiment is described.Other embodiments are in the scope of the appended claims
It is interior.In some cases, the movement recorded in detail in the claims or step can be come according to the sequence being different from embodiment
It executes and desired result still may be implemented.In addition, process depicted in the drawing not necessarily require show it is specific suitable
Sequence or consecutive order are just able to achieve desired result.In some embodiments, multitasking and parallel processing be also can
With or may be advantageous.
Not all step and unit are all necessary in above-mentioned each process and each system construction drawing, can be according to reality
Need to ignore certain step or units.Each step execution sequence be not it is fixed, can according to need and be determined.It is above-mentioned
Apparatus structure described in each embodiment can be physical structure, be also possible to logical construction, that is, some units may be by same
Physical entity is realized, is realized alternatively, some units may divide by multiple physical entities, alternatively, can be by multiple autonomous devices
Certain components realize jointly.
The term used in entire this specification " exemplary " means " being used as example, example or illustration ", and unexpectedly
Taste than other embodiments " preferably " or " have advantage ".For the purpose of the understanding to described technology is provided, it is embodied
Mode includes detail.However, it is possible to implement these technologies without these specific details.In some examples
In, in order to avoid the concept to described embodiment causes indigestion, well known construction and device is shown in block diagram form.
The optional embodiment of embodiment of the disclosure, still, the implementation of the disclosure is described in detail in conjunction with attached drawing above
Example be not limited to the above embodiment in detail, in the range of the technology design of embodiment of the disclosure, can to this
The technical solution of disclosed embodiment carries out a variety of simple variants, these simple variants belong to the protection of embodiment of the disclosure
Range.
The foregoing description of present disclosure is provided so that any those of ordinary skill in this field can be realized or make
Use present disclosure.To those skilled in the art, the various modifications carried out to present disclosure are apparent
, also, can also answer generic principles defined herein in the case where not departing from the protection scope of present disclosure
For other modifications.Therefore, present disclosure is not limited to examples described herein and design, but disclosed herein with meeting
Principle and novel features widest scope it is consistent.