WO2019127287A1

WO2019127287A1 - First smart device and connection method therefor and apparatus having storage function

Info

Publication number: WO2019127287A1
Application number: PCT/CN2017/119598
Authority: WO
Inventors: 阳光
Original assignee: 深圳配天智能技术研究院有限公司
Priority date: 2017-12-28
Filing date: 2017-12-28
Publication date: 2019-07-04
Also published as: CN109644263A; CN109644263B

Abstract

Disclosed is a first smart device and a connection method therefor, and an apparatus having a storage function, wherein the connection method comprises: the first smart device acquiring an image of a second smart device that comprising an identification code of the second smart device, identifying the identification code, and after establishing a connection with the second smart device according to the identification code, acquiring photographing parameters of the second smart device; acquiring the pixel size and shape of the identification code in the image, and calculating and determining a relative position between the first smart device and the second smart device according to photographing parameters of the first smart device, the pixel size and shape of the identification code in the image, and the actual size and shape of the identification code; establishing a binocular camera photographing mode with the second smart device according to the photographing parameters of the first smart device, the photographing parameters of the second smart device, and the relative position. By means of the described method, the first smart device may adaptively and flexibly establish the binocular camera photographing mode with other smart devices according to an actual scene.

Description

First smart device and connection method thereof, and device having storage function

【技术领域】[Technical Field]

The present invention relates to the field of smart devices, and in particular, to a first smart device, a connection method thereof, and a device having a storage function.

【背景技术】【Background technique】

With the development of electronic technology, more and more smart devices are applied to daily life or work, and the functions of smart devices tend to be diversified.

For example, a smart device with a camera function has been widely applied to the visual field, and the smart device performs related operations according to the acquired image. However, because the angle of view of the image that can be collected by the smart device is limited, the image information acquired by the single smart device is not comprehensive enough, which may affect the operation of the smart device.

【发明内容】 [Summary of the Invention]

The technical problem to be solved by the present invention is to provide a first smart device, a connection method thereof, and a device having a storage function. The smart device can adaptively and flexibly establish a connection with other smart devices according to an actual scenario, and establish a binocular camera mode. To obtain image information of the target object at different viewing angles.

In order to solve the above technical problem, the first technical solution adopted by the present invention is to provide a connection method of a smart device, where the connection method includes acquiring, by the first smart device, a flag code of the second smart device including the second smart device. a picture, the identifier code is identified, and after the connection is established with the second smart device, the shooting parameter of the second smart device is acquired; the first smart device acquires the flag in the image a pixel size and a shape of the code, determining, according to a shooting parameter of the first smart device, a pixel size and a shape of the flag code in the picture, and an actual size and shape of the identifier code, determining the first smart device and the Determining a relative pose relationship between the second smart devices; the first smart device according to the shooting parameters of the first smart device, the shooting parameters of the second smart device, and the relative pose relationship and the first The second smart device establishes a binocular camera mode.

In order to solve the above technical problem, the second technical solution adopted by the present invention is to provide a first smart device, where the first smart device includes an image capturing device and a processor, and the image capturing device is coupled to the processor; The image capture device is configured to acquire a picture of the second smart device that includes the identifier code of the second smart device; the processor is configured to identify the identifier code, and establish, according to the identifier code, the second smart device After the connection, acquiring the shooting parameters of the second smart device; and acquiring the pixel size and shape of the logo code in the image, according to the shooting parameters of the first smart device, the pixel size of the logo code in the image And determining a relative pose relationship between the first smart device and the second smart device according to a shape and an actual size and a shape of the identifier; the processor is further configured to be used according to the first smart device The shooting parameters, the shooting parameters of the second smart device, and the relative pose relationship establish a binocular imaging mode with the second smart device.

In order to solve the above technical problem, the third technical solution adopted by the present invention is to provide a device having a storage function, wherein the device having the storage function stores program data, and when the program data is executed, the present invention is implemented. The steps in any of the described methods of attachment.

The invention has the beneficial effects that the smart device of the present invention can obtain the picture of the other smart device including its identification code in real time, and automatically establish a connection with the corresponding smart device according to the identifier code, and the flag in the picture is different from the prior art. After the code and the actual logo code are processed and analyzed, the relative pose relationship between the smart devices is determined, and the binocular camera mode is established according to the relative pose relationship and the shooting parameters corresponding to the smart device. The smart device of the present invention can adaptively and flexibly establish a binocular camera mode with other smart devices according to an actual scene, to obtain images of different perspectives, and can determine a three-dimensional size of a target object in a common field of view and a three-dimensional feature point of a space object. Coordinates to facilitate three-dimensional modeling of objects.

【附图说明】 [Description of the Drawings]

1 is a schematic flow chart of an embodiment of a method for connecting a smart device according to the present invention;

2 is a schematic structural diagram of an embodiment of a first smart device according to the present invention;

3 is a schematic structural view of an embodiment of a device having a storage function according to the present invention.

【具体实施方式】【Detailed ways】

The technical solutions in the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings in order to make the technical solutions, the technical solutions, and the technical effects achieved by the present invention.

The method for connecting the smart device of the present embodiment includes: the first smart device acquiring a picture of the second smart device that includes the identifier of the second smart device, identifying the identifier code, and establishing a connection with the second smart device according to the identifier code, Obtain the shooting parameters of the second smart device.

The first smart device acquires the pixel size and shape of the logo code in the picture, and determines, according to the shooting parameter of the first smart device, the pixel size of the logo code in the picture, and the actual size and shape of the logo code, the first smart device and the a relative pose relationship between the second smart devices; and establishing a binocular camera mode with the second smart device according to the shooting parameters of the first smart device, the shooting parameters of the second smart device, and the relative pose relationship.

In one embodiment, the actual size and shape of the identification code of the first smart device and the second smart device are consistent, and the actual size and shape of the identification code are pre-set in the first smart device.

In another embodiment, the information included in the identifier of the second smart device is pre-set with the actual size and shape of the identifier, and the first smart device can identify the identifier to obtain the actual size and shape of the identifier. .

For a clear description of the connection method of the above embodiment, please refer to FIG. 1. FIG. 1 is a schematic flowchart diagram of an embodiment of a connection method of a smart device according to the present invention.

101: The first smart device acquires a picture of the second smart device that includes the identifier code of the second smart device, identifies the identifier code, and obtains a shooting parameter of the second smart device after establishing a connection with the second smart device according to the identifier code.

The first smart device and the second smart device have a camera function, for example, the first smart device and the second smart device are robots; or may be smart cameras.

The first smart device and the second smart device are in the same working environment. That is, the second smart device is within the effective range of the first smart device imaging.

In this implementation manner, the first smart device acquires a picture of the second smart device that includes the identifier code of the second smart device, identifies the identifier code, and establishes a connection with the second smart device according to the identifier code, and acquires the second intelligence. Shooting parameters of the device.

The capturing parameter of the second smart device includes an internal parameter of the second smart device, the internal parameter includes an image magnification of the second smart device, and further includes a pixel size of the second smart device.

The identifier code is one of a two-dimensional code or a barcode, and the identifier includes a plurality of information, specifically including an identifier of the second smart device and a connection manner. Optionally, the identification code further includes the actual size and shape of the two-dimensional code or the barcode of the second smart device.

Specifically, the first smart device performs photographing or photographing on the second smart device to obtain a picture of the second smart device that includes the identifier code of the second smart device. The first smart device scans the identifier code, obtains the identification code of the second smart device from the identifier code, and establishes a connection manner, and establishes a connection with the second smart device according to the connection manner. The identification code is pre-set by the smart device when it leaves the factory, and the unique identity verification for each smart device may be a device number or a serial number.

In addition, the connection method may be a wired connection or a wireless connection. Specifically, the wireless connection mode may be a wifi connection or a Bluetooth connection or a zigbee connection. The specific connection mode may be selected according to the usage scenario of the smart device, and is not specifically limited herein.

Step 102: The first smart device acquires a pixel size and a shape of the identifier code in the picture, and determines the first smart according to the shooting parameter of the first smart device, the pixel size of the identifier code in the image, and the actual size and shape of the shape code. The relative pose relationship between the device and the second smart device.

In this embodiment, the first smart device acquires the pixel size and shape of the logo code in the picture, and according to the shooting parameters of the first smart device, the pixel size and shape of the logo code in the picture, and the actual size and shape of the identification code. The calculation determines a pose relationship between the first smart device and the second smart device.

Wherein, the pixel size is the number of pixels of the logo code in the picture. The relative pose relationship is specifically a relative position relationship and a relative posture relationship. Specifically, the relative positional relationship includes a relative distance relationship, and the relative attitude relationship includes a relative angular relationship.

The shooting parameters of the first smart device include internal parameters of the first smart device. Specifically, the internal parameters include an image magnification factor and a pixel size of the first smart device.

Specifically, the first smart device establishes an imaging geometric model according to a shooting algorithm according to a shooting parameter of the first smart device, a pixel size of the flag code in the picture, and an actual size and shape of the identifier code to determine the first smart device and the first The relative pose relationship between the two smart devices. In one of the embodiments, the imaging geometry model can be established by a linear calibration algorithm to determine a relative pose relationship between the first smart device and the second smart device.

In order to improve the accuracy, in another embodiment, the imaging geometric model may also be established by a nonlinear calibration algorithm to determine a relative pose relationship between the first smart device and the second smart device. At the same time, establishing an imaging geometric model according to the nonlinear calibration algorithm can avoid distortion caused by the distance of the first smart device relative to the second smart device and the angle of the shooting.

Here, the principle of the calibration algorithm and the calculation process are explained. In the vision system, geometric information such as the position and shape of an object in a three-dimensional environment is calculated from the image information acquired by the camera, and objects in the environment are identified. The position of each point in the image is related to the geometric position of the corresponding point on the surface of the space object. The relationship between these locations is determined by the imaging geometry model, which is typically calculated by a calibration algorithm. It may be assumed that there is a simple linear relationship between the image captured by the camera and the object in three-dimensional space: [image] = M [object], where matrix M can be regarded as a geometric model of camera imaging. The parameters in M are camera parameters. This process of solving parameters is called camera calibration. In the present embodiment, the first smart device unit converts the pixel size of the logo code in the picture according to its image enlargement factor and image resolution to be unified with the unit of the actual size of the logo code. Then, the relative pose relationship between the first smart device and the second smart device is determined according to the size relationship and the shape relationship of the two.

In a practical application scenario, the identification code of the second smart device is disposed on the side of the body thereof, for example, directly above the lens of the second smart device. The shape of the identification code is a quadrilateral, and the size of the quadrilateral is fixed, for example, one of a square or a rectangle; the shape of the identification code may also be a circular shape or an elliptical shape, which may be designed according to actual conditions, and is convenient for scanning and identification.

When the first smart device is shooting the side where the second smart device is provided with the identification code, the shape of the obtained identification code is not deformed and the shape of the actual identification code is the same, that is, the obtained identification code size is relatively The actual dimensions are linear and scale up or down. Specifically, a geometric model may be established using a linear calibration method to determine a relative pose relationship between the first smart device and the second smart device.

When the first smart device is photographed at a certain tilt angle with respect to the side on which the second smart device is provided with the identification code, the shape of the obtained identification code may be deformed accordingly. For example, the square identification code may be deformed in parallel. a quadrilateral or an irregular quadrilateral, that is, the size of the obtained logo code is nonlinearly changed with respect to the actual size, and the nonlinear relationship can be determined according to the size of the obtained logo code and the actual size of the logo code, thereby determining the The tilt angle of a side of the smart device relative to the second smart device with the identification code. That is, the relative angle between the first smart device and the second smart device is determined. Specifically, a geometric model may be established using a non-linear calibration method to determine a relative pose relationship between the first smart device and the second smart device.

In order to obtain the identifier code of the second smart device more quickly and conveniently, the identifier code may be set in a plurality of different locations of the second smart device, and the specific orientation information is set in the identification code of each location to make the first smart The device may determine an orientation between the first smart device and the second smart device according to the orientation of the identification code.

103: The first smart device establishes a binocular camera mode with the second smart device according to the shooting parameters of the first smart device, the shooting parameters of the second smart device, and the relative pose relationship.

In this embodiment, the first smart device establishes a binocular imaging mode with the second smart device according to the shooting parameters of the first smart device, the shooting parameters of the second smart device, and the relative pose relationship.

Among them, the binocular camera mode simulates the principle of human vision, observes an object from two or more points, acquires images at different viewing angles, and determines the correspondence between each pair of images according to the matching relationship of pixels between the images, through the triangle The measurement principle yields a disparity map. After the disparity information is obtained, the depth information and the three-dimensional information of the original image can be obtained according to the projection model, to calculate the actual distance between the object and the camera, and the three-dimensional size of the object, thereby reconstructing the three-dimensional shape and position of the target object.

In a specific application scenario, when the shooting directions of the first smart device and the second smart device are opposite or the shooting angle is large (for example, 90°), the first smart device and the second smart device establish the binocular camera mode. The first smart device can acquire an image acquired by the second smart device.

In another specific application scenario, when the shooting directions of the first smart device and the second smart device are the same, and the shooting angle is between 0° and 90°, the first smart device and the second smart device establish binoculars. After the image capturing mode, the three-dimensional image can be synthesized by the image captured by the first smart device itself and the image acquired from the second smart device.

Specifically, in the set coordinate system, by the relative pose between the first smart device and the second smart device, the distance between the first smart device and the second smart device projection center and the respective projection centers may be determined. Coordinates to determine the projection model.

The first smart device and the second smart device capture the target object at the same time, respectively obtaining corresponding captured images. When the image acquired by the first smart device and the second smart device is on the same plane, the first smart device and the first smart device The height of the target object in the different images acquired by the second smart device is the same, but there is parallax in the horizontal direction.

According to the projection model of the binocular camera, according to the disparity information of the first smart device and the second smart, the depth information and the three-dimensional information of the original image can be obtained to calculate the actual distance between the object and the smart device, and the three-dimensional size of the object. Thereby reconstructing the three-dimensional shape and position of the target object. Here, it should be noted that the first smart device and the second smart device can acquire and scan each other's identification code to automatically establish a binocular imaging mode. In order to obtain more image information, it is also possible that a plurality of smart devices acquire each other and scan the other party's identification code to automatically establish a multi-vision mode. For example, three smart devices acquire and scan each other's identification codes to automatically establish a tri-image mode.

Different from the prior art, the smart device of the present embodiment can obtain a picture of another smart device including its identification code in real time, and automatically establish a connection with the corresponding smart device according to the identifier code, and the flag code and the actual logo code in the picture. After the processing analysis, the relative pose relationship between the smart devices is determined, and the binocular camera mode is established according to the relative pose relationship and the shooting parameters corresponding to the smart device. The smart device of the present embodiment can adaptively and flexibly establish a binocular camera mode with other smart devices according to an actual scenario, to acquire images of different views, and can determine the three-dimensional size of the target object in the common field of view and the feature points of the space object. Three-dimensional coordinates to facilitate three-dimensional modeling of objects.

In this embodiment, a method for connecting a smart device is also provided, by which the first smart device can optimize the travel route by using the second smart device to improve the problem that the first smart device has a limited field of view on the travel route.

Different from the connection method in the foregoing embodiment, the connection method of the present embodiment establishes binocular with the second smart device according to the shooting parameters of the first smart device, the shooting parameters of the second smart device, and the relative pose relationship. The step of the camera mode further includes: after the first smart device and the second smart device establish the binocular camera mode, the first smart device acquires an image acquired by the second smart device; the image captured by the first smart device according to the camera and the slave device The step of planning the path of the first smart device by the image acquired by the second smart device.

In this embodiment, after the first smart device and the second smart device establish a binocular camera mode, the first smart device acquires an image acquired by the second smart device. The image acquired by the second smart device includes environment information. Specifically, the environment information includes an object size and a display condition, a motion situation, and the like in a visual range of the second smart device. Determining, by the first smart device, whether there is an obstacle on the current travel path of the first smart device according to the image captured by itself and the image acquired from the second smart device; if there is an obstacle, determining the travel path of the first smart device according to the location of the obstacle .

In a specific application scenario, when the first smart device is traveling, it is limited by its route of travel and its own cause, and the field of view of the first smart device is limited. The first smart device can acquire image information of other smart devices to re-plan the travel path.

The following is an example of a sweeping robot. In the course of the sweeping robot, due to its short stature, only a small area of environmental information can be captured. The planned route may become a “dead end” due to obstacles on the route, so that the sweeping robot has to return to the original road, reducing work efficiency. At this time, the cleaning robot can first establish a connection with the second smart device in the visual range by using the first smart device to obtain the environmental information acquired by the second smart device. In other cases, a connection may be established with the third smart device to obtain the environment information acquired by the third smart device, and the selection is made according to the relative location of the smart device, which is not limited herein.

The cleaning robot determines whether there is an obstacle on the current travel path of the cleaning robot based on the environmental information obtained from the second smart device and the image taken by itself. If there is an obstacle, the travel path of the sweeping robot is determined according to the position of the obstacle.

Optionally, in other application scenarios, the binocular intelligent device can be used for monitoring, which not only can make the monitoring picture clearer, but also can calculate the passenger flow, real-time monitoring of the vehicle speed, and vehicle unmanned driving.

Different from the foregoing implementation manner, the first smart device of the present embodiment further acquires image information acquired by the second smart device, so as to comprehensively grasp the environment in the travel path of the first smart device, thereby intelligently planning the travel path to avoid the first smart device. The device is blocked by obstacles during travel.

Since the planning path requires more hardware resources and requires higher processing data by the processor, in order to save hardware resources and improve data processing capability, in another embodiment, the first smart device can also input data information. Sending to the external controller, the external controller plans the path of the first smart device according to the received data information, and the first smart device acquires the path of the path from the external controller and travels according to the path.

The external controller may be a computer or a server, and is not specifically limited herein.

Specifically, the first smart device acquires an image acquired by the second smart device, and images the image captured by itself, the image acquired from the second smart device, the shooting parameters of the first smart device, and the shooting parameters of the second smart device. Sending to the external controller, so that the external controller plans the travel path of the first smart device according to the image captured by the first smart device, the image of the second smart device, the shooting parameters of the first smart device, and the shooting parameters of the second smart device. .

Because the image information acquired by the first smart device and the second smart device is limited, all the environmental information in the path of the first smart device cannot be fully reflected, so that the path planned by the external controller is not perfect. In order to avoid the occurrence of the foregoing situation, in another embodiment, the external controller is connected to a plurality of smart devices, and the external controller has a large amount of data information. The first smart device also sends its own physical location information to the external controller, and the external controller matches the physical location information and the picture information sent by the first smart device to determine whether the first intelligence exists in the database. The physical location information of the device and the image information matched by the picture information sent by the first smart device, if any, are combined with all relevant image information for path planning.

Different from the foregoing embodiment, the first smart device of the embodiment can plan the travel path of the external controller, thereby saving hardware resources and improving the speed of the path planning.

Referring to FIG. 2, FIG. 2 is a schematic structural diagram of an embodiment of a first smart device according to the present invention. The first smart device includes an image capture device 201 and a processor 202. The processor 202 is coupled to the image capture device 201.

The smart device device is a robot or a smart camera, and is not specifically limited herein.

In the present embodiment, the image capture device 201 is configured to acquire a picture of the second smart device that includes the second smart device, and specifically, the image capture device 201 takes a photo or video to the second smart device to obtain the second image. A picture of the smart device including the identification code of the second smart device.

The processor 202 identifies the identifier code, and after establishing a connection with the second smart device according to the identifier code, acquires the shooting parameters of the second smart device.

The shooting parameters of the second smart device include internal parameters of the second smart device and external parameters. The external parameters include the optical core coordinates of the second smart device, the internal parameters include the image magnification of the second smart device, and the pixel size of the second smart device.

The processor 202 scans the identifier code, obtains the identification code of the second smart device and the connection manner from the identifier code, and establishes a connection with the second smart device according to the connection manner. The identification code is pre-set by the smart device when it leaves the factory, and the unique identity verification for each smart device may be a device number or a serial number.

In this embodiment, the processor 202 acquires the pixel size and shape of the logo code in the picture, and calculates according to the shooting parameters of the first smart device, the pixel size and shape of the logo code in the picture, and the actual size and shape of the identification code. Determining a pose relationship between the first smart device and the second smart device.

The shooting parameters of the first smart device include external parameters and internal parameters of the first smart device. Specifically, the external parameters include the optical core coordinates of the first smart device, and the internal parameters include the image magnification of the first smart device.

Specifically, the processor 202 establishes an imaging geometric model according to a calibration algorithm according to a shooting parameter of the first smart device, a pixel size of the flag code in the picture, and an actual size and shape of the identifier code to determine the first smart device and the second The relative pose relationship between smart devices. In one of the embodiments, the imaging geometry model can be established by a linear calibration algorithm to determine a relative pose relationship between the first smart device and the second smart device.

Here, the principle of the calibration algorithm and the calculation process are explained. In the vision system, geometric information such as the position and shape of an object in a three-dimensional environment is calculated from the image information acquired by the camera, and objects in the environment are identified. The position of each point in the image is related to the geometric position of the corresponding point on the surface of the space object. The relationship between these locations is determined by the imaging geometry model, which is typically calculated by a calibration algorithm. It may be assumed that there is a simple linear relationship between the image captured by the camera and the object in three-dimensional space: [image] = M [object], where matrix M can be regarded as a geometric model of camera imaging. The parameters in M are camera parameters. This process of solving parameters is called camera calibration.

In the present embodiment, the processor 202 unit converts the pixel size of the flag code in the picture according to the image enlargement factor and the image resolution of the first smart device to be unified with the unit of the actual size of the flag code. Then, the relative pose relationship between the first smart device and the second smart device is determined according to the size relationship and the shape relationship of the two.

In this embodiment, the processor 202 establishes a binocular imaging mode with the second smart device according to the shooting parameters of the first smart device, the shooting parameters of the second smart device, and the relative pose relationship.

According to the projection model of the binocular camera, according to the disparity information of the first smart device and the second smart, the depth information and the three-dimensional information of the original image can be obtained to calculate the actual distance between the object and the smart device, and the three-dimensional size of the object. Thereby reconstructing the three-dimensional shape and position of the target object.

Here, it should be noted that the first smart device and the second smart device can acquire and scan each other's identification code to automatically establish a binocular imaging mode. In order to obtain more image information, it is also possible that a plurality of smart devices acquire each other and scan the other party's identification code to automatically establish a multi-vision mode. For example, three smart devices acquire and scan each other's identification codes to automatically establish a tri-image mode.

The processor 202 can also utilize the second smart device to optimize the travel route to improve the problem that the first smart device has a limited field of view on the travel route.

In this embodiment, after the first smart device and the second smart device establish a binocular camera mode, the processor 202 acquires an image acquired by the second smart device. The image acquired by the second smart device includes environment information. Specifically, the environment information includes an object size and a display condition, a motion situation, and the like in a visual range of the second smart device. The processor 202 determines, according to the image captured by the first smart device and the image acquired by the second smart device, whether there is an obstacle on the current travel path of the first smart device; if there is an obstacle, determining the travel of the first smart device according to the position re-planning of the obstacle path.

Since the planning path requires more hardware resources and requires higher processing data by the processor 20, in order to save hardware resources and improve data processing capability, in another embodiment, the processor 202 can also perform data information. The controller sends the path to the external smart device according to the received data information, and the processor 202 obtains the path of the path from the external controller, and the first smart device travels according to the path.

Specifically, the processor 202 acquires an image acquired by the second smart device, and sends an image captured by itself, an image acquired from the second smart device, a shooting parameter of the first smart device, and a shooting parameter of the second smart device. The external controller is configured to cause the external controller to plan the travel path of the first smart device according to the image captured by the first smart device, the image of the second smart device, the shooting parameters of the first smart device, and the shooting parameters of the second smart device.

Because the image information acquired by the first smart device and the second smart device is limited, all the environmental information in the path of the first smart device cannot be fully reflected, so that the path planned by the external controller is not perfect. In order to avoid the occurrence of the foregoing situation, in another embodiment, the external controller is connected to a plurality of smart devices, and the external controller has a large amount of data information. The processor 202 also sends its own physical location information to the external controller, and the external controller performs matching according to the physical location information and the picture information sent by the first smart device, and determines whether the first smart device exists in the database. The physical location information and the image information matched by the picture information sent by the first smart device, if any, are combined with all relevant image information for path planning.

The first smart device further acquires the image information acquired by the second smart device to comprehensively grasp the environment in the travel path of the first smart device, thereby intelligently planning the travel path to prevent the first smart device from being blocked by the obstacle during the traveling.

3 is a schematic structural view of an embodiment of a device having a storage function according to the present invention. In the present embodiment, at least one program data 301 is stored in the device 30 having the storage function. The program data 301 is used to perform the marker-based positioning method in any of the above embodiments.

The device 30 having the storage function may be a storage chip in the smart device, a hard disk, or a portable hard disk or other readable and writable storage tool such as a USB flash drive or an optical disk, and may be a server or the like, which is not specifically limited herein. In the several embodiments provided by the present application, it should be understood that the disclosed methods and apparatus may be implemented in other manners. The device implementations described above are merely illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be another division manner. For example, multiple units or components may be combined or integrated. Go to another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in an electrical, mechanical or other form.

The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. An integrated unit, if implemented in the form of a software functional unit and sold or used as a standalone product, can be stored in a computer readable storage medium.

Based on such understanding, the technical solution of the present application, in essence or the contribution to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium. A number of instructions are included to cause a computer device (which may be a personal computer, server, or network device, etc.) or a processor to perform all or part of the steps of the various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read only memory (ROM, Read-Only) Memory, random access memory (RAM), disk or optical disk, and other media that can store program code.

The above is only the embodiment of the present application, and thus does not limit the scope of patents of the present application, and the equivalent structure or equivalent process transformation made by using the specification and the contents of the drawings, or directly or indirectly applied to other related technical fields, The same is included in the scope of patent protection of this application.

Claims

A method for connecting a smart device, characterized in that the connection method comprises:

Obtaining, by the first smart device, a picture of the second intelligent device that includes the identifier code of the second smart device, identifying the identifier code, and establishing a connection with the second smart device according to the identifier code, acquiring the second Shooting parameters of the smart device;

Obtaining, by the first smart device, a pixel size and a shape of the flag code in the picture, according to a shooting parameter of the first smart device, a pixel size and a shape of the flag code in the picture, and an actual The size and shape calculation determines a relative pose relationship between the first smart device and the second smart device;

The first smart device establishes a binocular imaging mode with the second smart device according to the shooting parameters of the first smart device, the shooting parameters of the second smart device, and the relative pose relationship.
The method for connecting a smart device according to claim 1, wherein the shooting parameter according to the first smart device, the pixel size and shape of the logo code in the picture, and the actual size of the logo code And the step of determining, by the shape calculation, the relative pose relationship between the first smart device and the second smart device, specifically:

Forming an imaging geometric model according to a calibration algorithm according to a shooting parameter of the first smart device, a pixel size and a shape of the flag code in the picture, and an actual size and shape of the identification code to determine the first smart device and A relative pose relationship between the second smart devices.
The method for connecting a smart device according to claim 2, wherein the calibration algorithm is a linear calibration algorithm or a nonlinear calibration algorithm.
The method for connecting a smart device according to claim 1, wherein the connection method further comprises:

After the first smart device and the second smart device establish a binocular camera mode, the first smart device acquires an image acquired by the second smart device;

The first smart device plans a path of the first smart device according to an image captured by itself and an image acquired from the second smart device.
The method for connecting a smart device according to claim 4, wherein the first smart device plans the first smart device according to an image taken by itself and an image acquired from the second smart device The steps of the path path specifically include:

Determining, by the first smart device, whether there is an obstacle on its current travel path according to an image taken by itself and an image acquired from the second smart device; if there is an obstacle, re-planning according to the position of the obstacle The travel path of the first smart device.
The method for connecting a smart device according to claim 1, wherein the connection method further comprises:

Obtaining, by the first smart device, an image acquired by the second smart device;

Sending, by the first smart device, an image captured by itself, an image acquired from the second smart device, a shooting parameter of the first smart device, and a shooting parameter of the second smart device to an external controller, Taking the external controller according to the image captured by the first smart device, the image of the second smart device, the shooting parameters of the first smart device, and the shooting parameters of the second smart device. The path of travel of a smart device.
The method for connecting a smart device according to claim 1, wherein the step of the first smart device acquiring a picture of the second smart device that includes the second smart device comprises:

The first smart device captures the second smart device to obtain a picture of the second smart device that includes the identifier code of the second smart device.
The method for connecting a smart device according to claim 1, wherein the photographing parameter of the first smart device includes the first smart device internal parameter, wherein the internal parameter comprises the first smart device Image magnification and cell size.
The method for connecting a smart device according to claim 1, wherein the shooting parameter of the second smart device includes an internal parameter of the second smart device, wherein the internal parameter includes the second smart device Image magnification and cell size.
The method of connecting a smart device according to claim 1, wherein the logo code is one of a two-dimensional code or a barcode.
The method for connecting a smart device according to claim 1, wherein the identification code comprises actual size and shape of the identification code and connection mode information.
a first smart device, wherein the first smart device includes an image capture device and a processor, and the image capture device is coupled to the processor;

The image collection device is configured to acquire a picture of the second smart device that includes the identifier code of the second smart device;

The processor is configured to identify the identifier code, obtain a connection parameter of the second smart device after establishing a connection with the second smart device according to the identifier code, and acquire a flag code in the image. Determining, by the pixel size and the shape, the first smart device and the first according to a shooting parameter of the first smart device, a pixel size and a shape of the logo code in the image, and an actual size and shape of the logo code The relative pose relationship between the two smart devices;

The processor is further configured to establish a binocular imaging mode with the second smart device according to the shooting parameters of the first smart device, the shooting parameters of the second smart device, and the relative pose relationship.
The first smart device according to claim 12, wherein the processor is specifically configured to: according to a shooting parameter of the first smart device, a pixel size and a shape of a flag code in the picture, and the flag The actual size and shape of the code establishes an imaging geometric model in accordance with a calibration algorithm to determine a relative pose relationship between the first smart device and the second smart device.
The first smart device according to claim 13, wherein the calibration algorithm is a linear calibration algorithm or a non-linear calibration algorithm.
The first smart device according to claim 12, wherein the processor is further configured to acquire the second smart after the first smart device and the second smart device establish a binocular camera mode An image obtained by the device; and planning a path of the first smart device according to the image captured by the first smart device and the image acquired from the second smart device.
The first smart device according to claim 12, wherein the processor is further configured to acquire an image acquired by the second smart device;

And transmitting, by the image captured by the first smart device, the image acquired by the second smart device, the shooting parameter of the first smart device, and the shooting parameter of the second smart device to an external controller, And causing the external controller to plan the first according to an image captured by the first smart device, an image of the second smart device, a shooting parameter of the first smart device, and a shooting parameter of the second smart device. The path of travel of the smart device.
The first smart device according to claim 12, wherein the shooting parameters of the first smart device comprise internal parameters of the first smart device, wherein the internal parameters comprise the first smart device Image magnification and cell size.
The first smart device according to claim 12, wherein the shooting parameters of the second smart device comprise internal parameters of the second smart device, wherein the internal parameters comprise the second smart device Image magnification and cell size.
The first smart device according to claim 12, wherein the identification code comprises actual size and shape of the identification code and connection mode information.
A device having a storage function, wherein the device having a storage function stores program data, and when the program data is executed, the steps in the connection method according to any one of claims 1 to 11 are implemented.