CN110597077A - Method and system for realizing intelligent scene switching based on indoor positioning - Google Patents
Method and system for realizing intelligent scene switching based on indoor positioning Download PDFInfo
- Publication number
- CN110597077A CN110597077A CN201910912256.2A CN201910912256A CN110597077A CN 110597077 A CN110597077 A CN 110597077A CN 201910912256 A CN201910912256 A CN 201910912256A CN 110597077 A CN110597077 A CN 110597077A
- Authority
- CN
- China
- Prior art keywords
- positioning
- scene
- module
- indoor
- moving object
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000003491 array Methods 0.000 claims abstract description 13
- 230000008569 process Effects 0.000 claims abstract description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 23
- 238000001514 detection method Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 7
- 238000012795 verification Methods 0.000 claims description 7
- 238000011084 recovery Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 230000005236 sound signal Effects 0.000 claims description 3
- 230000000644 propagated effect Effects 0.000 claims description 2
- 230000009471 action Effects 0.000 abstract description 5
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 230000036760 body temperature Effects 0.000 abstract description 2
- 238000012790 confirmation Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 6
- 230000004927 fusion Effects 0.000 description 5
- 230000006399 behavior Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 3
- 230000004807 localization Effects 0.000 description 3
- 238000000926 separation method Methods 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000037237 body shape Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B15/00—Systems controlled by a computer
- G05B15/02—Systems controlled by a computer electric
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/26—Pc applications
- G05B2219/2642—Domotique, domestic, home control, automation, smart house
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a method and a system for realizing scene intelligent switching based on indoor positioning, which are used for determining the range of an area to be positioned in an indoor space; respectively and correspondingly installing infrared sensing receiving equipment and four microphone arrays; the infrared sensing receiving equipment determines the only small-range positioning area; accurately positioning with the four microphone arrays; the auxiliary positioning module carries out identity judgment on the movable object; and the scene switching module completes the scene switching operation. The invention has the beneficial effects that: firstly, the safety and the concealment are better; secondly, comprehensive positioning can be carried out according to the sound and the body temperature of the action of the active person or the multiple dimensions of being captured to the image in a certain range in the action process; and thirdly, the accurate positioning of the moving person in the moving process can be well assisted and detected in the indoor environment, and the confirmation degree for distinguishing the specific identity of the moving person is obviously improved.
Description
Technical Field
The invention relates to the technical field of intelligent home furnishing, in particular to a method for realizing intelligent scene switching based on indoor positioning and a system for realizing intelligent scene switching based on indoor positioning.
Background
In recent years, when satellite positioning cannot be used in an indoor environment, an indoor positioning technology is used as auxiliary positioning of satellite positioning, and the problems that a satellite signal is weak when reaching the ground and cannot penetrate through a building are solved. And finally, positioning the current position of the object. The indoor positioning means that position positioning is realized in an indoor environment, and a set of indoor position positioning system is formed by mainly integrating multiple technologies such as wireless communication, base station positioning or inertial navigation positioning and the like, so that position monitoring of personnel, objects and the like in an indoor space is realized. The relatively mature target positioning technology mainly adopts radar and sonar technologies, is usually used in the military field, mainly aims at active positioning of a radiation source, and has poor concealment and safety; the current microphone array is mainly used for sound source separation and positioning, is a passive target positioning and has good safety and concealment. The prior art has poor positioning precision and poor safety and concealment, and a better solution is urgently needed to realize reliable positioning.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. In this section, as well as in the abstract and the title of the invention of this application, simplifications or omissions may be made to avoid obscuring the purpose of the section, the abstract and the title, and such simplifications or omissions are not intended to limit the scope of the invention.
The present invention has been made in view of the above-mentioned conventional problems.
Therefore, one technical problem solved by the present invention is: the method is used for realizing intelligent scene switching by accurately positioning the indoor moving object.
In order to solve the technical problems, the invention provides the following technical scheme: a method for realizing scene intelligent switching based on indoor positioning determines the range of an area to be positioned in an indoor space and divides the area to be positioned into a plurality of small-range positioning areas; correspondingly installing infrared sensing receiving equipment and a group of four microphone arrays positioned on four different positions in space in each small-range positioning area respectively; the infrared sensing receiving equipment detects the body surface temperature of the moving object in real time and determines the only small-range positioning area where the moving object is located; according to the determined only small-range positioning area, accurately positioning the position of the moving object by using the four corresponding microphone arrays in the current area; the auxiliary positioning module is used for carrying out identity judgment on the movable object by combining with accurate positioning; and the scene switching module accurately completes the scene switching operation for each moving object according to the identity of the moving object.
As a preferred scheme of the method for realizing intelligent scene switching based on indoor positioning, the method comprises the following steps: each small-range positioning area is a detection range corresponding to the infrared sensing receiving equipment in each area, and the detection range of each small-range positioning area covers the range of the area to be positioned.
As a preferred scheme of the method for realizing intelligent scene switching based on indoor positioning, the method comprises the following steps: the four-microphone array is an array formed by arranging a group of omnidirectional microphones positioned at four different positions in space of the small-range positioning area according to a certain shape rule, and is used for accurately positioning according to sound data generated by the moving object in the moving process.
As a preferred scheme of the method for realizing intelligent scene switching based on indoor positioning, the method comprises the following steps: the four microphone arrays are devices for carrying out space sampling on space propagation sound signals, and further comprise near field models and far field models which are used for dividing the arrays into a linear array, a planar array or a volume array according to the distance between a sound source emitted by the moving object and the microphone arrays, and the linear array, the planar array or the volume array can be divided according to the topological structure of the microphone arrays.
As a preferred scheme of the method for realizing intelligent scene switching based on indoor positioning, the method comprises the following steps: the auxiliary positioning module comprises a step of identifying that the four-microphone array accurately positions the moving object; the acquisition module clearly captures the image or video single-frame picture information of the moving object according to the positioning; and comparing the similarity of the captured images to determine the real identity of the moving object.
As a preferred scheme of the method for realizing intelligent scene switching based on indoor positioning, the method comprises the following steps: the auxiliary positioning module also comprises the following processing steps of collecting a plurality of pieces of multi-state picture data of various family members as a training set, a test set and a verification set of the algorithm model; training the algorithm model; the acquisition module takes a live picture or video to extract the characteristic data of the moving object and inputs the trained algorithm model; the judging module judges whether the snap-shot person is a member of a family or not according to the output result of the algorithm model and the collected historical data and determines the similarity and reliability of specific identities; and finishing the identification of the specific real identity of the moving object.
As a preferred scheme of the method for realizing intelligent scene switching based on indoor positioning, the method comprises the following steps: the scene switching module comprises the following steps of obtaining the behavior state of the moving object in the current moving space; and recovering the recovery of the behavior state of the active object in the previous space scene in the next active space, thereby realizing seamless scene switching.
As a preferred scheme of the method for realizing intelligent scene switching based on indoor positioning, the method comprises the following steps: the scene switching module comprises a network controller, a device controller and a function module, and comprises the following switching steps that the network controller establishes seamless interconnection of indoor devices through a ZigBee wireless sensor network, and the indoor devices are added into the same gateway after verification; the device controller stores state parameters and historical records of devices in different scenes; the function module starts and initializes the indoor equipment, and switches and synchronizes state parameters of corresponding equipment to complete scene switching according to a trigger event causing scene switching.
As a preferred scheme of the method for realizing intelligent scene switching based on indoor positioning, the method comprises the following steps: the function module comprises an event trigger module, a scene switching control module and a scene execution module; the event triggering module generates triggering event information according to the position change or scene change after the auxiliary positioning module is combined with the accurate positioning module to perform identity judgment on the movable object; the scene switching control module receives the event information input by the event trigger module or the state parameters actively input by other equipment, correspondingly generates scene control information after receiving the event information or the state parameters and transmits the scene control information to the scene execution module; and the scene execution module executes the control information, synchronizes the state parameter setting of the corresponding equipment and completes scene switching.
The invention solves another technical problem that: the method is realized by depending on the system.
In order to solve the technical problems, the invention provides the following technical scheme: a system for realizing scene intelligent switching based on indoor positioning comprises an infrared sensing receiving device, a four-microphone array, an auxiliary positioning module and a scene switching module; the infrared sensing receiving equipment and the four-microphone array are used for positioning a moving object in an indoor space; the auxiliary positioning module is used for judging the identity of the positioned movable object; the scene switching module is used for switching the device state parameters of the active object in the current scene to the devices in the next scene and synchronizing the state parameters.
The invention has the beneficial effects that: firstly, the safety and the concealment are better; secondly, comprehensive positioning can be carried out according to the sound and the body temperature of the action of the active person or the multiple dimensions of being captured to the image in a certain range in the action process; the accurate positioning of the moving person in the moving process can be well assisted and detected in the indoor environment, and the confirmation degree for distinguishing the specific identity of the moving person is obviously improved; fourthly, based on the solution, a more effective and feasible technical method can be provided for switching the solutions such as the smart home between specific scenes.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise. Wherein:
fig. 1 is a schematic overall flowchart structure diagram of a method for implementing scene intelligent switching based on indoor positioning according to a first embodiment of the present invention;
fig. 2 is a schematic structural diagram of a region to be located and a small-range location region according to a first embodiment of the present invention;
fig. 3 is a schematic view of a flow structure of scene switching according to a first embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating a comparison of the performance of various positioning modes according to the first embodiment of the present invention;
fig. 5 is a schematic overall structural diagram of a system for implementing intelligent scene switching based on indoor positioning according to a second embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, specific embodiments accompanied with figures are described in detail below, and it is apparent that the described embodiments are a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present invention, shall fall within the protection scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those specifically described and will be readily apparent to those of ordinary skill in the art without departing from the spirit of the present invention, and therefore the present invention is not limited to the specific embodiments disclosed below.
Furthermore, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
The present invention will be described in detail with reference to the drawings, wherein the cross-sectional views illustrating the structure of the device are not enlarged partially in general scale for convenience of illustration, and the drawings are only exemplary and should not be construed as limiting the scope of the present invention. In addition, the three-dimensional dimensions of length, width and depth should be included in the actual fabrication.
Meanwhile, in the description of the present invention, it should be noted that the terms "upper, lower, inner and outer" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation and operate, and thus, cannot be construed as limiting the present invention. Furthermore, the terms first, second, or third are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected and connected" in the present invention are to be understood broadly, unless otherwise explicitly specified or limited, for example: can be fixedly connected, detachably connected or integrally connected; they may be mechanically, electrically, or directly connected, or indirectly connected through intervening media, or may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Example 1
Referring to the schematic diagram of fig. 1, the schematic diagram is an overall flow structure diagram of a method for implementing scene intelligent switching based on indoor positioning in this embodiment, and is to solve the problems in the prior art that a microphone array is mainly used to implement sound source separation positioning, positioning accuracy is poor due to differences in used scenes, safety and concealment are not good, and a better solution is urgently needed to implement reliable positioning. The embodiment provides that the microphone array and the infrared sensor or the camera are combined to realize the accurate positioning of the position of the moving person and the judgment of the specific identity, so that the moving person can be positioned better and more accurately, and the function of distinguishing the specific identity of the moving person in a small-range moving place can be better realized; the method can accurately position the position and identity of the moving person, and simultaneously realize seamless switching of intelligent switching scenes in different moving spaces under scenes such as intelligent home and the like.
More specifically, the method for implementing intelligent scene switching based on indoor positioning in the embodiment includes the following steps:
s1: determining the range of a region 100 to be positioned in an indoor space, and dividing the region 100 to be positioned into a plurality of small-range positioning regions 101;
s2: an infrared sensing receiving device 200 and a group of four microphone arrays 300 which are positioned at four different positions in space are respectively and correspondingly arranged in each small-range positioning area 101. In this step, each small-range positioning area 101 is a detection range corresponding to the infrared sensing reception device 200 in each area, and the detection range of each small-range positioning area 101 covers the range of the area to be positioned 100, that is, each small-range positioning area 101 is actually determined by the detection range of the infrared sensing reception device 200, and in a popular way, the small-range positioning area 101 coincides with the detection range of the infrared sensing reception device 200. The area to be positioned 100 is formed by a plurality of small-range positioning areas 101, that is, the small-range positioning areas 101 cover the area to be positioned 100 together.
S3: the infrared sensing receiving equipment 200 detects the body surface temperature of the moving object in real time and determines the only small-range positioning area 101 where the moving object is located; the specific implementation in this step is that the infrared sensing reception device 200 is used as the center, the center of the infrared sensing reception device is used to radiate the detection range outwards, and when a detected moving object is located within the detection range of a certain infrared sensing reception device 200, the object is considered to be located in the small-range positioning area 101 at the center of the infrared sensing reception device 200, and the object is determined to be the only small-range positioning area 101.
S4: according to the determined unique small-range positioning region 101, the position of the moving object is accurately positioned by using the corresponding four-microphone array 300 in the current region; the four-microphone array 300 performs accurate positioning according to sound data generated by a moving object during movement based on an array formed by arranging a group of omnidirectional microphones located at four different positions in space of the small-range positioning region 101 according to a certain shape rule. The detection range of the same four-microphone array 300 covers the small-range localization area 101.
The four-microphone array 300 is a device for spatially sampling a spatially propagated sound signal, and further includes a near-field model and a far-field model which are divided according to the distance between a sound source emitted by the movement of a moving object and the microphone array, and may be a linear array, a planar array or a volume array according to the topological structure of the microphone array.
S5: the auxiliary positioning module 400 performs identity determination on the moving object in combination with the accurate positioning; the assisted positioning module 400 includes the steps of identifying,
the four-microphone array 300 accurately locates the moving object;
the acquisition module 401 clearly captures the image or video single-frame picture information of the moving object according to the positioning;
and comparing the similarity of the captured images to determine the real identity of the moving object.
Further, the assisted positioning module 400 further includes the following more specific processing steps:
collecting a plurality of multi-state picture data of various family members as a training set, a test set and a verification set of the algorithm model 402;
training the algorithm model 402;
the acquisition module 401 captures a live body picture or video to extract characteristic data of a moving object, and inputs the characteristic data into the trained algorithm model 402;
the judging module 403 judges whether the snap-shot person is a member of the family or not according to the output result of the algorithm model 402 and the collected historical data and determines the similarity and reliability of specific identities;
and finishing the identification of the specific real identity of the moving object.
S6: the scene switching module 500 precisely completes the scene switching operation for each moving object according to the identity of the moving object. The scene switching module 500 includes the following steps:
acquiring the behavior state of an active object in the current active space;
and recovering the recovery of the behavior state of the active object in the previous space scene in the next active space, thereby realizing seamless scene switching.
Further, the scene switching module 500 includes a network controller 501, a device controller 502, and a function module 503, and the scene switching module 500 further includes the following specific switching steps:
the network controller 501 establishes seamless interconnection of indoor devices through a ZigBee wireless sensor network, and adds the indoor devices into the same gateway after verification;
the device controller 502 stores state parameters and history of the device in different scenarios;
the function module 503 starts and initializes the indoor device, and switches and synchronizes the state parameters of the corresponding devices to complete scene switching according to the trigger event causing scene switching.
In this step, it should be noted that the functional module 503 includes an event triggering module 503a, a scene switching control module 503b, and a scene executing module 503 c; the event triggering module 503a generates triggering event information according to the position change or scene change after the auxiliary positioning module 400 performs identity determination on the moving object in combination with the accurate positioning; the scene switching control module 503b receives the event information input by the event triggering module 503a or the state parameters actively input by other devices, and correspondingly generates scene control information after receiving the event information or the state parameters, and transmits the scene control information to the scene execution module 503 c; the scene execution module 503c executes the control information, synchronizes the state parameter settings of the corresponding devices, and completes scene switching.
Referring to the schematic of fig. 2, the embodiment should be further explained, wherein the schematic of fig. 2 is only a division of a plane space and there is only one set of small-range positioning areas 101. It is understood that the region to be located 100 and the small-range locating region 101 are actually space concepts and include an indoor three-dimensional space, and the detection radiation ranges of the infrared sensing receiving device 200 and the four-microphone array 300 are also in a three-dimensional state, and the two regions can respectively cover the region to be located 100 and the small-range locating region 101, so that in the indoor space, the infrared sensing receiving device 200 can perform rough small-range detection first, and then the four-microphone array 300 can perform accurate locating.
Meanwhile, in this embodiment, the small-range positioning area 101 needs to cover the area to be positioned 100, and then the infrared sensing receiving device 200 is installed in a plurality of different positions, and the detection positions thereof necessarily have overlapped parts, for example, a part a in the figure, if the parts detected by the two small-range positioning areas 101 together are distinguished according to the strength of signal reception, and when the signal strengths of the two sides are equal, the auxiliary positioning module 400 can be directly skipped to directly complete accurate positioning according to the spatial position coordinates of the infrared sensing receiving device 200. If the signals are not equal, the four microphone arrays 300 in the small-range positioning area 101 with stronger signals are selected for accurate positioning. If the distance is separately located according to the strength of the signal, the algorithm is complex, and the accuracy requirement of the signal receiver is high, and this embodiment proposes to use the four-microphone array 300 to accurately locate in the small-range locating area 101.
Furthermore, many sound source positioning methods based on microphone arrays are available, for example, the method based on sound time difference is characterized in that the core of the algorithm is to accurately estimate the propagation delay and obtain the sound source position information by performing cross-correlation processing on signals among the microphones, and the method can further obtain the sound source position information by simple delay summation, geometric calculation, direct utilization of cross-correlation results to perform controllable power response search and the like. The improved phase transformation weighted controllable response power SRP-PHAT sound source positioning algorithm adopted by the embodiment has stronger robustness in a reverberation environment, improves the anti-noise and anti-reverberation capabilities, reduces the calculated amount, improves the real-time processing speed, can realize sound source positioning in a real environment, has no specific requirements on an array type, and is also suitable for a distributed array, so that the algorithm obtains better effect.
In this embodiment, the auxiliary positioning module 400 mainly uses the deep learning related technology of AI, the target detection and classification algorithm, and first collects multiple multi-state picture data of various family members as a training set, a testing set and a verification set of the algorithm, extracts feature data of an active person through a living picture or video captured by a camera, predicts and judges whether the captured person is a member of a family by combining a model trained by the algorithm, determines the similarity and reliability of a specific identity, and completes the identification of the specific real identity of the active person. Wherein the acquisition module 401 is a camera device, such as a video camera and a video camera, and the acquired data includes height, body shape and contour data of the subject, for example. The algorithm model 402 is an image recognition model, for example, a Python script is written using a convolutional neural network to classify images, a trained model is loaded, and an input image is classified, such as the latest deep learning image classification model in Keras: VGG16, VGG19, ResNet50, inclusion v3, and Xception, and then use these architectures to classify images. The method comprises the steps of acquiring information, acquiring image, preprocessing the image (such as binarization processing, reverse color processing and other processing methods) to obtain characteristic data, training the process (classifier reference and classification decision), and identifying. The identity recognition of the moving object by the determining module 403 is completed after matching and comparing with the collected comparison data.
Referring to fig. 3, it is further illustrated that the scene switching process of the scene switching module 500 in this embodiment is illustrated, and the main technologies and methods for assisting positioning and identity determination include: the infrared sensor (infrared sensing receiving equipment 200) is used for roughly positioning the detection of the body surface temperature according to the moving person or object; positioning by a four-microphone array according to sounds emitted by a moving person moving or the like; the camera collects the living body image or video information of the moving person nearby and predicts the probability of the family members by combining with a model trained by an AI deep learning algorithm so as to determine the real identity of the family members. It should be noted here that, the event triggering module 503a is triggered by a position change or a scene of the located moving object, for example, a scene deemed as an object changes when the position changes to a certain range, a corresponding scene description is defined based on a certain range, such as a scene in a living room in a certain range, a toilet scene in a certain range, or a bedroom in a certain range, and when the position detects that the moving object changes from the living room scene to the bedroom scene, the event triggering module 503a is triggered to generate corresponding control information, control and synchronize device status information from the living room to the bedroom, and finally complete scene switching.
Scene one:
in this embodiment, the actual areas of the family living room, the bedroom and the bathroom are taken as the test areas, that is, the space of the area to be positioned 100 in this embodiment is formed jointly, the infrared sensing receiving device 200 and the four-microphone array 300 are disposed in the space, the small-range positioning area 101 is radiated from the detection range of the infrared sensing receiving device 200 and covers the area to be positionedA domain 100. In this scenario, the positioning method in the embodiment and the prior art are applied to positioning, 24 reference monitoring points are uniformly set in the test to cover the space of the area 100 to be positioned, and the coordinate (a) is correspondingly definedn,bn) According to the method, the infrared sensing receiving equipment 200 is arranged on 24 reference monitoring points to radiate small-range positioning areas 101, and four microphone arrays 300 are arranged in each small-range positioning area 101 to complete installation of the method. Compared with the traditional method, the method adopts four groups of independent positioning experiments of infrared sensing, a microphone array, Bluetooth and geomagnetism, wherein the infrared sensing, the Bluetooth and the geomagnetism are all arranged on 24 reference monitoring points to carry out separate and independent tests; in addition, the microphone array is an independent test without 24 infrared sensing receiving devices 200 under the arrangement of the method.
The testing process is that each group of modes is positioned and tested for 5 times, error values of each time are calculated, and then 5 times of errors are averaged to obtain a final error value.
TABLE 1 orientation mode Performance comparison (unit: m)
And (3) carrying out simulation by utilizing Matlab to realize the positioning algorithm, and comparing infrared sensing positioning, microphone array positioning, two kinds of fusion positioning, Bluetooth positioning and geomagnetic positioning. The error accumulation distribution obtained according to the experimental simulation is shown in the following graph (a), wherein the abscissa is an error value, the ordinate is corresponding error accumulation probability, and the composite represents fusion positioning of the infrared sensing and the microphone array; MicArray represents microphone array positioning; BlueTooth denotes BlueTooth positioning; InfaredSensors represent infrared sensing positioning; geomagnetism denotes Geomagnetic localization. The advantages of the infrared sensing and microphone array fusion positioning scheme are verified through comparison of the 5 positioning modes. The single infrared sensing positioning average error is 2.496m, and when the error is 2.52m, the positioning precision can reach 80%; the positioning average error of the single microphone array is 1.06m, and when the error is 1.12m, the positioning precision can reach 80%; the single Bluetooth positioning average error is 1.18m, and when the error is 1.24m, the positioning precision can reach 80%; the single geomagnetic positioning average error is 4.35m, and when the error is 4.42m, the positioning precision can reach 80%; the average positioning error of the infrared sensing and microphone array fusion is 0.72m, and when the error is 0.82m, the positioning accuracy can reach 80%, and experiments show that the fusion positioning mode greatly improves the positioning accuracy by 67.5%, 22.7%, 30.5% and 81.15% compared with the single infrared sensing, microphone array, Bluetooth and geomagnetic positioning accuracy respectively. Therefore, in combination with the schematic diagram of fig. 4, the embodiment has higher precision improvement compared with the traditional positioning mode, so that more precision of intelligent scene switching is ensured, and great significance is achieved.
Example 2
Referring to the schematic diagram of fig. 4, in order to implement the method for implementing intelligent scene switching based on indoor positioning, a system for implementing intelligent scene switching based on indoor positioning is provided in this embodiment. Specifically, the system comprises an infrared sensing receiving device 200, a four-microphone array 300, an auxiliary positioning module 400 and a scene switching module 500; wherein the infrared sensing reception device 200 and the four-microphone array 300 are used for localization of a moving object of an indoor space; the auxiliary positioning module 400 is used for determining the identity of the positioned moving object; the scene switching module 500 is used for switching the device state parameters of the active object in the current scene to the next scene device and synchronizing the state parameters.
Further, the infrared sensing receiving device 200 is an infrared sensing receiver which is arranged at different positions in space to cover the area 100 to be positioned, can receive infrared signals and independently complete receiving and outputting of infrared rays, is compatible with TTL level signals, has a size similar to that of a common plastic package triode, is suitable for various infrared remote controls and infrared data transmission, does not need to accurately detect data in the embodiment, and can determine the unique small-range positioning area 101 only by detecting the existence of signals. The so-called microphone array is a sound collection system, and the system collects sounds from different spatial directions by using a plurality of microphones, and the microphones are arranged according to specified requirements and then added with corresponding algorithms (arrangement + algorithm) to solve a plurality of room acoustic problems, such as sound source positioning, dereverberation, speech enhancement, blind source separation and the like, to realize positioning. The assistant positioning module 400 is a processing chip hardware embedded with an image recognition algorithm model, and is used for realizing image recognition of a moving object and confirming the identity of the moving object.
Wherein the scene switching module 500 comprises a network controller 501, a device controller 502 and a function module 503. The network controller 501 is also called a network card, network adapter or Network Interface Card (NIC), and if there is a computer without a network card in the network, the computer will not be able to communicate with other computers and will not get any service provided by the server. Of course, if the server does not have a network card, the server is not called, so the network card is a necessary device for the server, just like a common PC (personal computer) is provided with a processor. The network card on the PC is usually used to connect the PC to a LAN (local area network), and the server network card is generally used to connect the server to a network device such as a switch. The device controller 502 is an entity in a computer whose primary responsibility is to control one or more I/O devices to enable the exchange of data between the I/O devices and the computer. It is an interface between the CPU and the I/O device, it receives commands from the CPU and controls the I/O device to operate so as to free the processor from the cumbersome device control transactions, it is an addressable device that has only a unique device address when it controls only one device; if the control can connect with a plurality of devices, a plurality of device addresses are contained, and each device address corresponds to one device. The controller is used for controlling and coordinating the action control of the whole computer, and generally needs a Program Counter (PC), an Instruction Register (IR), an Instruction Decoder (ID), a timing and control circuit, a pulse source, an interrupt and the like to complete together.
The functional module 503 further includes a functional module 503 comprising an event triggering module 503a, a scene switching control module 503b, and a scene executing module 503c, wherein the functional module 503 is also a processing chip controlled by an implanted program, and is integrated with a chip of the auxiliary positioning module 400 into a hardware device, and the software portion provides operations through a computer interface. The function module 503 is a software control part of the scene switching module 500, and the network controller 501 and the device controller 502 are hardware implementation parts of the scene switching module 500. Correspondingly cooperates with the auxiliary positioning module 400.
As used in this application, the terms "component," "module," "system," and the like are intended to refer to a computer-related entity, either hardware, firmware, a combination of hardware and software, or software in execution. For example, a component may be, but is not limited to being: a process running on a processor, an object, an executable, a thread of execution, a program, and/or a computer. By way of example, both an application running on a computing device and the computing device can be a component. One or more components can reside within a process and/or thread of execution and a component can be localized on one computer and/or distributed between two or more computers. In addition, these components can execute from various computer readable media having various data structures thereon. The components may communicate by way of local and/or remote processes such as in accordance with a signal having one or more data packets (e.g., data from one component interacting with another component in a local system, distributed system, and/or across a network such as the internet with other systems by way of the signal).
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.
Claims (10)
1. A method for realizing scene intelligent switching based on indoor positioning is characterized in that: comprises the following steps of (a) carrying out,
determining the range of a region (100) to be positioned in indoor space, and dividing the region (100) to be positioned into a plurality of small-range positioning regions (101);
correspondingly installing infrared sensing receiving equipment (200) and a group of four microphone arrays (300) positioned at four different positions in space in each small-range positioning area (101);
the infrared sensing receiving equipment (200) detects the body surface temperature of the moving object in real time and determines the only small-range positioning area (101) where the moving object is located;
according to the determined unique small-range positioning area (101), accurately positioning the position of the moving object by using the corresponding four-microphone array (300) in the current area;
the auxiliary positioning module (400) performs identity judgment on the movable object in combination with accurate positioning;
and the scene switching module (500) accurately completes the scene switching operation for each moving object according to the identity of the moving object.
2. The method for implementing intelligent scene switching based on indoor positioning as claimed in claim 1, wherein: each small-range positioning area (101) is a detection range corresponding to the infrared sensing receiving equipment (200) in each area, and the detection range of each small-range positioning area (101) covers the range of the area to be positioned (100).
3. The method for realizing intelligent scene switching based on indoor positioning as claimed in claim 1 or 2, wherein: the four-microphone array (300) is formed by arranging a group of omnidirectional microphones positioned at four different positions in space of the small-range positioning area (101) according to a certain shape rule, and is used for carrying out accurate positioning according to sound data generated by the moving object in the moving process.
4. The method of claim 3 for implementing intelligent scene cut based on indoor positioning, wherein: the four-microphone array (300) is a device for spatially sampling a spatially propagated sound signal, and further comprises a near field model and a far field model which are used for dividing the array into a near field model and a far field model according to the distance between a sound source emitted by the moving object and the microphone array, and can be divided into a linear array, a planar array or a volume array according to the topological structure of the microphone array.
5. The method for implementing intelligent scene switching based on indoor positioning as claimed in any one of claims 1, 2 or 4, wherein: the auxiliary positioning module (400) comprises identifying the steps of,
the four-microphone array (300) precisely locates the moving object;
the acquisition module (401) clearly captures the image or video single-frame picture information of the moving object according to the positioning;
and comparing the similarity of the captured images to determine the real identity of the moving object.
6. The method of claim 5 for implementing intelligent scene cut based on indoor positioning, wherein: the auxiliary positioning module (400) further comprises the following processing steps,
collecting a plurality of pieces of multi-state picture data of various family members as a training set, a testing set and a verification set of an algorithm model (402);
training the algorithmic model (402);
the acquisition module (401) takes a live picture or a video to extract the characteristic data of the moving object and inputs the trained algorithm model (402);
the judging module (403) judges whether the snap-shot person is a member of the family or not according to the output result of the algorithm model (402) and the collected historical data and determines the similarity and reliability of specific identities;
and finishing the identification of the specific real identity of the moving object.
7. The method of claim 6 for implementing intelligent scene cut based on indoor positioning, wherein: the scene switching module (500) comprises the steps of,
acquiring the behavior state of the active object in the current active space;
and recovering the recovery of the behavior state of the active object in the previous space scene in the next active space, thereby realizing seamless scene switching.
8. The method of claim 7 for implementing intelligent scene cut based on indoor positioning, wherein: the scene switching module (500) comprises a network controller (501), a device controller (502) and a function module (503), comprising the following switching steps,
the network controller (501) establishes seamless interconnection of indoor equipment through a ZigBee wireless sensor network, and adds the indoor equipment into the same gateway after verification;
the device controller (502) stores state parameters and history of the device in different scenarios;
the function module (503) starts and initializes the indoor equipment, and switches and synchronizes the state parameters of the corresponding equipment to complete the scene switching according to the trigger event causing the scene switching.
9. The method of claim 8 for implementing intelligent scene cut based on indoor positioning, wherein: the functional module (503) comprises an event trigger module (503a), a scene switching control module (503b) and a scene execution module (503 c);
the event triggering module (503a) generates triggering event information according to the position change or scene change after the auxiliary positioning module (400) combines with accurate positioning to perform identity judgment on the moving object;
the scene switching control module (503b) receives the event information input by the event triggering module (503a) or the state parameters actively input by other devices, and correspondingly generates scene control information after receiving the event information or the state parameters, and transmits the scene control information to the scene execution module (503 c);
the scene execution module (503c) executes the control information, synchronizes the state parameter settings of the corresponding devices and completes scene switching.
10. The utility model provides a system for realize scene intelligence switching based on indoor location which characterized in that: the system comprises an infrared sensing receiving device (200), a four-microphone array (300), an auxiliary positioning module (400) and a scene switching module (500);
the infrared sensing reception device (200) and the four-microphone array (300) are used for positioning of moving objects of an indoor space;
the auxiliary positioning module (400) is used for judging the identity of the positioned movable object;
the scene switching module (500) is used for switching the device state parameters of the active object in the current scene to the devices of the next scene and synchronizing the state parameters.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910912256.2A CN110597077B (en) | 2019-09-25 | 2019-09-25 | Method and system for realizing intelligent scene switching based on indoor positioning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910912256.2A CN110597077B (en) | 2019-09-25 | 2019-09-25 | Method and system for realizing intelligent scene switching based on indoor positioning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110597077A true CN110597077A (en) | 2019-12-20 |
CN110597077B CN110597077B (en) | 2022-11-18 |
Family
ID=68863379
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910912256.2A Active CN110597077B (en) | 2019-09-25 | 2019-09-25 | Method and system for realizing intelligent scene switching based on indoor positioning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110597077B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111245688A (en) * | 2019-12-26 | 2020-06-05 | 的卢技术有限公司 | Method and system for intelligently controlling electrical equipment based on indoor environment |
CN111615028A (en) * | 2020-06-19 | 2020-09-01 | 歌尔科技有限公司 | Temperature detection method and device, sound box equipment and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110013075A1 (en) * | 2009-07-17 | 2011-01-20 | Lg Electronics Inc. | Method for processing sound source in terminal and terminal using the same |
CN103777615A (en) * | 2014-01-28 | 2014-05-07 | 宇龙计算机通信科技(深圳)有限公司 | Control device and method of intelligent home appliance |
CN103902963A (en) * | 2012-12-28 | 2014-07-02 | 联想(北京)有限公司 | Method and electronic equipment for recognizing orientation and identification |
CN104896668A (en) * | 2015-05-29 | 2015-09-09 | 广东美的暖通设备有限公司 | Intelligent adjustment system of indoor air conditioner and adjustment method of same |
CN105137771A (en) * | 2015-07-27 | 2015-12-09 | 上海斐讯数据通信技术有限公司 | Intelligent household appliance control system and method based on mobile terminal |
US20180336687A1 (en) * | 2017-05-22 | 2018-11-22 | Creavision Technologies Ltd. | Systems and methods for user detection, identification, and localization within a defined space |
-
2019
- 2019-09-25 CN CN201910912256.2A patent/CN110597077B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110013075A1 (en) * | 2009-07-17 | 2011-01-20 | Lg Electronics Inc. | Method for processing sound source in terminal and terminal using the same |
CN103902963A (en) * | 2012-12-28 | 2014-07-02 | 联想(北京)有限公司 | Method and electronic equipment for recognizing orientation and identification |
CN103777615A (en) * | 2014-01-28 | 2014-05-07 | 宇龙计算机通信科技(深圳)有限公司 | Control device and method of intelligent home appliance |
CN104896668A (en) * | 2015-05-29 | 2015-09-09 | 广东美的暖通设备有限公司 | Intelligent adjustment system of indoor air conditioner and adjustment method of same |
CN105137771A (en) * | 2015-07-27 | 2015-12-09 | 上海斐讯数据通信技术有限公司 | Intelligent household appliance control system and method based on mobile terminal |
US20180336687A1 (en) * | 2017-05-22 | 2018-11-22 | Creavision Technologies Ltd. | Systems and methods for user detection, identification, and localization within a defined space |
Non-Patent Citations (1)
Title |
---|
杨毅 等: "基于NIST评测的说话人分类及定位技术研究", 《电子与信息学报》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111245688A (en) * | 2019-12-26 | 2020-06-05 | 的卢技术有限公司 | Method and system for intelligently controlling electrical equipment based on indoor environment |
CN111615028A (en) * | 2020-06-19 | 2020-09-01 | 歌尔科技有限公司 | Temperature detection method and device, sound box equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN110597077B (en) | 2022-11-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021093872A1 (en) | Crowdsensing-based multi-source information fusion indoor positioning method and system | |
Wang et al. | Accurate and real-time 3-D tracking for the following robots by fusing vision and ultrasonar information | |
Ngamakeur et al. | A survey on device-free indoor localization and tracking in the multi-resident environment | |
CN104394588B (en) | Indoor orientation method based on Wi Fi fingerprints and Multidimensional Scaling | |
CN110597077B (en) | Method and system for realizing intelligent scene switching based on indoor positioning | |
CN108828501B (en) | Method for real-time tracking and positioning of mobile sound source in indoor sound field environment | |
Xiao et al. | Abnormal behavior detection scheme of UAV using recurrent neural networks | |
CN109389641A (en) | Indoor map integrated data generation method and indoor method for relocating | |
CN105975967A (en) | Target positioning method and system | |
WO2021094766A1 (en) | Occupant detection systems | |
JP2018061114A (en) | Monitoring device and monitoring method | |
Wendeberg et al. | Robust tracking of a mobile beacon using time differences of arrival with simultaneous calibration of receiver positions | |
CN111610492A (en) | Multi-acoustic sensor array intelligent sensing method and system | |
Sasaki et al. | Map-generation and identification of multiple sound sources from robot in motion | |
US20240053464A1 (en) | Radar Detection and Tracking | |
CN112379330B (en) | Multi-robot cooperative 3D sound source identification and positioning method | |
Vashist et al. | KF-Loc: A Kalman filter and machine learning integrated localization system using consumer-grade millimeter-wave hardware | |
CN104243894A (en) | Audio and video fused monitoring method | |
CN109600711B (en) | Indoor positioning method based on channel response frequency domain and spatial domain combined processing | |
Martinson et al. | Robotic discovery of the auditory scene | |
Ding et al. | Microphone array acoustic source localization system based on deep learning | |
Zhu et al. | Speaker localization based on audio-visual bimodal fusion | |
Altaf Khattak | Fawad; Nasralla, MM; Esmail, MA; Mostafa, H.; Jia, M. WLAN RSS-Based Fingerprinting for Indoor Localization: A Machine Learning Inspired Bag-of-Features Approach | |
Jahromi Shirazi et al. | Eavesdropping like a bat: Towards fusing active and passive sonar for a case study in simultaneous localization and mapping | |
CN113613188A (en) | Fingerprint library updating method and device, computer equipment and storage medium |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |