Methods, systems, and self-moving devices for multi-sensor clock synchronization

Abstract

This invention discloses a method, system, and self-moving device for multi-sensor clock synchronization. The method is applied to a self-moving device including a first sensor and a second sensor. The method includes generating a first rotational speed-time curve for the first sensor and a second rotational speed-time curve for the second sensor during the rotation of the self-moving device; determining the phase difference between the first and second rotational speed-time curves; and adjusting the clocks of the first and second sensors to be synchronized based on the phase difference. This method and system for multi-sensor clock synchronization more intelligently and effectively improves the efficiency of multi-sensor clock synchronization.

Description

Technical Field

[0001] This invention belongs to the technical field of robotics, specifically relating to a method, system, and self-moving device for multi-sensor clock synchronization. Background Technology

[0002] Self-moving devices are those that use artificial intelligence to automatically complete preset tasks within a designated area, such as cleaning robots and smart lawnmowers. To acquire various information within the fixed area, self-moving devices are typically equipped with numerous sensors. Each sensor has its own clock to record the time of the sensing data.

[0003] To ensure the proper functioning of the controller during the operation of the self-moving device, the clocks of all sensors must be synchronized. Therefore, before the self-moving device leaves the factory, the multiple sensors configured on it need to be synchronized, a process collectively known as multi-sensor clock synchronization.

[0004] Currently, clock synchronization methods for multiple sensors include hardware-based methods, which synchronize the time of multiple sensors by using the same clock. However, since sensors are becoming increasingly modular, each sensor integrates its own clock. Using the same clock for multiple sensors introduces other hardware matching problems, making implementation cumbersome and costly. Another method involves experimentally measuring the clock times of multiple sensors and then calibrating them via software. This method relies on manual measurement, is not easily scalable, and is time-consuming and inefficient.

[0005] Therefore, it is necessary to improve the existing technology to overcome the aforementioned defects. Summary of the Invention

[0006] Therefore, the technical problem to be solved by the present invention is to provide a clock synchronization method for different types of sensors that can reduce operational complexity and improve efficiency.

[0007] To address the aforementioned technical problems, this invention provides a multi-sensor clock synchronization method applied to a self-moving device, wherein the self-moving device includes at least a first sensor and a second sensor, and the method includes:

[0008] During the rotation of the self-moving device, a first rotational speed-time curve of the first sensor and a second rotational speed-time curve of the second sensor are generated.

[0009] Determine the phase difference between the first rotational speed-time curve and the second rotational speed-time curve;

[0010] Based on the phase difference, the clocks of the first sensor and the second sensor are adjusted to be consistent.

[0011] In one embodiment, generating the first rotational speed curve of the first sensor includes:

[0012] The rotational speed of the first sensor is obtained using an inertial sensor, and a first rotational speed-time curve is generated based on the rotational speed and the clock of the first sensor; wherein the inertial sensor is disposed on the self-moving device.

[0013] In one embodiment, the first sensor is an odometer.

[0014] In one embodiment, the second sensor is a camera, and the generation of the second rotational speed-time curve of the second sensor includes:

[0015] As the camera rotates following the self-moving device, it captures multiple target images corresponding to the calibration board.

[0016] Based on multiple target images, a second rotation speed-time curve is generated using feature point recognition.

[0017] In one embodiment, the step of capturing multiple target images of the calibration board by the camera during the rotation of the self-moving device includes:

[0018] As the camera follows the rotation of the self-moving device, it takes pictures of the calibration board at a preset frequency to obtain images of the calibration board at different positions and rotation angles relative to the camera.

[0019] In one embodiment, the calibration board is a checkerboard pattern.

[0020] In one embodiment, generating the second rotation speed curve based on multiple target images using a feature point recognition method includes:

[0021] Mark a feature point on the chessboard grid;

[0022] The location of the feature point is identified in each target image, the position change of the feature point in adjacent target images is calculated, and a second rotation speed curve is generated by combining the shooting frequency of the camera.

[0023] In one embodiment, adjusting the clocks of the first sensor and the second sensor to be consistent includes:

[0024] Adjust the phase difference by moving the clock of the first sensor forward or backward; or...

[0025] Adjust the phase difference by moving the clock of the second sensor forward or backward.

[0026] Furthermore, the present invention also provides a multi-sensor clock synchronization system applied to a self-moving device, the self-moving device including at least a first sensor and a second sensor, wherein the type of the first sensor is different from the type of the second sensor, and the system includes:

[0027] The rotation speed-time curve generation module is used to generate a first rotation speed-time curve of the first sensor and a second rotation speed-time curve of the second sensor during the rotation of the self-moving device.

[0028] The determining module is used to determine the phase difference between the first rotational speed-time curve and the second rotational speed-time curve;

[0029] An adjustment module is used to adjust the clock of the first sensor and the clock of the second sensor to be consistent based on the phase difference.

[0030] Furthermore, the present invention also provides a self-moving device, comprising:

[0031] Self-moving device body,

[0032] The first sensor is disposed on the main body of the self-moving device;

[0033] A second sensor is disposed on the main body of the self-moving device; wherein the type of the first sensor is different from the type of the second sensor.

[0034] The clocks of the first sensor and the second sensor are synchronized using the multi-sensor clock synchronization method described in any of the above embodiments.

[0035] The technical solution provided by this invention has the following advantages:

[0036] The multi-sensor clock synchronization method, system, and self-moving device provided by the present invention generate a first rotation speed time curve of a first sensor and a second rotation speed time curve of a second sensor during the rotation of the self-moving device, further obtain the phase difference between the first rotation speed time curve and the second rotation speed time curve of the second sensor, and adjust the clock of the first sensor and the clock of the second sensor to be consistent according to the phase difference, thereby improving the efficiency of multi-sensor clock synchronization more intelligently and effectively. Attached Figure Description

[0037] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0038] Figure 1 This is a schematic flowchart of a multi-sensor clock synchronization method provided in Embodiment 1 of the present invention;

[0039] Figure 2 This is a schematic diagram of the module structure of a multi-sensor clock synchronization system provided in Embodiment 2 of the present invention. Detailed Implementation

[0040] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The present invention will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0041] It should be noted that the terms "first," "second," etc., in the specification, claims, and drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0042] In this invention, unless otherwise stated, directional terms such as "upper," "lower," "top," and "bottom" are generally used in relation to the direction shown in the accompanying drawings, or in relation to the vertical, perpendicular, or gravitational direction of the component itself; similarly, for ease of understanding and description, "inner" and "outer" refer to the inner and outer contours of each component itself, but the above directional terms are not intended to limit this invention.

[0043] In this invention, unless otherwise stated, the examples described below are merely specific examples and are not intended to limit the embodiments of the invention to the specific steps, values, conditions, data, order, etc. Those skilled in the art can utilize the concept of this invention to construct more embodiments not mentioned herein by reading this specification.

[0044] Self-moving devices are those that utilize artificial intelligence to automatically complete pre-set tasks within a designated area, such as cleaning robots and intelligent lawnmowers. To acquire various information within this fixed area, self-moving devices are typically equipped with numerous sensors, such as image sensors, odometers, and laser sensors. Each sensor has its own clock to record the time of the sensing data. To ensure the self-moving device's controller functions correctly during operation, the times displayed by all the sensors must be synchronized. Therefore, before the self-moving device leaves the factory, the multiple sensors configured on it need to be synchronized, a process collectively known as multi-sensor clock synchronization. Existing clock hardware methods and manual measurement and adjustment methods suffer from high costs or low efficiency.

[0045] To address the aforementioned problems, this embodiment provides a method for multi-sensor clock synchronization. This multi-sensor clock synchronization method is applied to a self-moving device, wherein the self-moving device includes at least a first sensor and a second sensor. Figure 1 As shown, the method, in its specific implementation, includes the following steps:

[0046] S100. During the rotation of the self-moving device, a first rotation speed-time curve of the first sensor and a second rotation speed-time curve of the second sensor are generated.

[0047] S200. Determine the phase difference between the first rotational speed-time curve and the second rotational speed-time curve.

[0048] S300. Based on the phase difference, adjust the clock of the first sensor and the clock of the second sensor to be consistent.

[0049] The aforementioned self-moving devices can be understood as devices capable of moving autonomously and completing corresponding tasks. Specifically, these self-moving devices may include at least one of the following: cleaning robots, monitoring robots, etc. Cleaning robots include, for example, sweeping robots, mopping robots, or combined sweeping and mopping robots. It should be noted that the self-moving devices listed above are merely illustrative. In actual implementation, depending on the specific application scenario and processing requirements, the aforementioned self-moving devices may also include inspection robots, nanny robots, etc. This specification does not limit this. Corresponding to different self-moving devices,

[0050] In this system, both the first and second sensors are mounted on the self-moving device and are used to collect environmental parameters surrounding the self-moving device and / or parameters of the self-moving device itself. The first sensor may include at least one of the following: an image sensor (such as a camera, webcam, etc.), an infrared sensor, an odometer, an ultrasonic sensor, a laser sensor, etc. The second sensor may include at least one of the following: an image sensor (such as a camera, webcam, etc.), an infrared sensor, an odometer, an ultrasonic sensor, a laser sensor, etc. It should be noted that the first and second sensors listed above are merely illustrative.

[0051] In this embodiment, the first sensor and the second sensor can be of the same type or different types. As long as the clocks of the first sensor and the second sensor are different, the multi-sensor clock synchronization method provided in the above embodiments can be used. For example, if the first sensor and the second sensor are of the same type, such as both being laser rangefinders, and both the first and second sensors have their own clocks, the multi-sensor clock synchronization method provided in the above embodiments can be used for clock synchronization.

[0052] Implementing the above method requires configuring a rotating device for rotating the self-moving device. That is, the self-moving device can be rotated by the rotation of the rotating device. Specifically, the self-moving device is fixed to the rotating device, which rotates at a preset speed, thereby driving the self-moving device to rotate synchronously at the preset speed. The first sensor and the second sensor also rotate synchronously with the self-moving device, thus ensuring that the rotation speed of the first sensor and the rotation speed of the second sensor are consistent and synchronized in time.

[0053] In the first rotational speed-time curve, the horizontal axis parameter is time, and the vertical axis parameter is rotational speed or rotational angular velocity; in the second rotational speed-time curve, the horizontal axis parameter is time, and the vertical axis parameter is rotational speed or rotational angular velocity. The horizontal axis parameter type of the first rotational speed-time curve and the second rotational speed-time curve are the same, and the vertical axis parameter of the first rotational speed-time curve and the second rotational speed-time curve are the same.

[0054] The time parameters of the first rotational speed time curve are recorded by the clock of the first sensor, and the time parameters of the second rotational speed time curve are recorded by the clock of the second sensor. Since the rotation of the first and second sensors is synchronized, if the clock of the first sensor is synchronized with the clock of the second sensor, the phase difference between the first and second rotational speed time curves is zero; if the clock of the first sensor is not synchronized with the clock of the second sensor, there is a phase difference between the first and second rotational speed time curves.

[0055] The specific value of the phase difference reflects the difference in synchronization between the clocks of the first sensor and the second sensor. Based on this phase difference, the clocks of the first and second sensors can be synchronized.

[0056] In this embodiment, a first rotation speed-time curve corresponding to the first sensor and a second rotation speed-time curve corresponding to the second sensor are obtained during the rotation of the mobile device. By comparing the phase difference between the first and second rotation speed-time curves, the clocks of the first and second sensors can be synchronized based on the phase difference. This clock synchronization method is not only simple but also highly efficient.

[0057] In an optional embodiment, the step of "generating the first rotational speed curve of the first sensor" in step S100 above specifically includes the following steps:

[0058] S110. Obtain the rotational speed of the first sensor using an inertial sensor;

[0059] S130. Generate a first rotation speed-time curve based on the rotation speed and the clock of the first sensor; wherein the inertial sensor is disposed on the self-moving device.

[0060] Inertial sensors typically include accelerometers and gyroscopes, as well as their single-axis, dual-axis, and triaxial inertial measurement units, allowing them to directly obtain rotational angular velocity. Since the inertial sensor, like the first sensor, is located on the self-moving device, the rotational angular velocity detected by the inertial sensor is equal to the rotational angular velocity of the first sensor.

[0061] In an alternative embodiment, the first sensor is an odometer. An odometer is used to detect the travel distance of a self-moving device and is one of the important sensors in a self-moving device.

[0062] In an optional embodiment, the second sensor is a camera, and the step of "generating the second rotational speed-time curve of the second sensor" in step S100 above specifically includes the following steps:

[0063] S120: During the process of the camera following the rotation of the self-moving robot, the camera captures multiple target images corresponding to the calibration plate;

[0064] S140. Based on multiple target images, a second rotation speed-time curve is generated using feature point recognition.

[0065] The calibration board is fixedly placed in front of the self-moving device. As the camera rotates with the self-moving device, it can capture (capture) multiple target images of the calibration board. The rotation of the self-moving device causes the position of the camera relative to the calibration board to change, so the multiple target images corresponding to the calibration board are not the same.

[0066] To better understand how the camera acquires multiple target images corresponding to the calibration board during the rotation of the self-moving device in step S120, optionally, it can be achieved through the following technical solution: In this embodiment, "capturing multiple target images corresponding to the calibration board by the camera during the rotation of the self-moving robot" includes: during the rotation of the self-moving robot, the camera captures images of the calibration board at a preset frequency to obtain images of the calibration board at different positions and rotation angles relative to the camera.

[0067] The preset frequency mentioned above refers to the camera's shooting frequency, meaning the camera takes multiple images of the calibration board at the preset frequency to obtain multiple target images. Preferably, the preset frequency is a fixed time interval, meaning the time difference between adjacent target images is the same.

[0068] In one optional embodiment, the calibration plate is a checkerboard pattern. The checkerboard pattern has a standard structure and regular dimensions, offering advantages such as simple calibration and high accuracy.

[0069] To better understand how the second rotational speed-time curve is generated using feature point recognition in step S140, it can optionally be implemented using the following technical solution: In this embodiment, "generating the second rotational speed curve based on multiple target images using feature point recognition" includes:

[0070] S141. Mark a feature point on the chessboard grid;

[0071] S143. Identify the position of the feature point in each target image, calculate the position change of the feature point in adjacent target images, and generate a second rotation speed curve by combining the shooting frequency of the camera.

[0072] The positional changes of the feature points in adjacent target images, combined with the camera's shooting frequency, can be used to obtain the camera's rotational angular velocity, which is then used as the vertical axis parameter of the second rotational velocity curve; and the camera's clock recording is then used as the horizontal axis parameter of the second rotational velocity curve.

[0073] In an optional embodiment, adjusting the clocks of the first sensor and the second sensor to be consistent includes: adjusting the phase difference of the clock of the first sensor forward or backward; or, adjusting the phase difference of the clock of the second sensor forward or backward.

[0074] The multi-sensor clock synchronization system provided in the above embodiments can synchronously calibrate the clocks of multiple sensors, improving the efficiency of multi-sensor clock calibration for self-moving devices and solving the problems of high cost of hardware synchronization and the trouble of manual testing synchronization in the prior art.

[0075] The various embodiments of the methods described in this specification are presented in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on its differences from other embodiments. Relevant details can be found in the descriptions of the method embodiments. Specifically, the technical solutions can be implemented based on the foregoing examples of related embodiments; therefore, a detailed description of each implementation scheme is not provided here.

[0076] It should be emphasized that the steps of the above embodiments can be combined with each other as long as there is no conflict.

[0077] like Figure 2 As shown, this embodiment of the invention also provides a multi-sensor clock synchronization system 100. The multi-sensor clock synchronization system 100 is applied to a self-moving device, which includes at least a first sensor and a second sensor, wherein the type of the first sensor is different from the type of the second sensor. The multi-sensor clock synchronization system 100 includes: a rotation speed curve acquisition module 120, a determination module 130, and an adjustment module 140.

[0078] The rotation speed-time curve generation module 120 is used to generate a first rotation speed-time curve of the first sensor and a second rotation speed-time curve of the second sensor during the rotation of the self-moving device.

[0079] The determination module 130 is used to determine the phase difference between the first rotational speed-time curve and the second rotational speed-time curve.

[0080] The adjustment module 140 is used to adjust the clock of the first sensor and the clock of the second sensor to be consistent according to the phase difference.

[0081] The multi-sensor clock synchronization system 100 provided in this embodiment of the invention generates a first rotational speed-time curve of a first sensor and a second rotational speed-time curve of a second sensor during the rotation of the self-moving device. It further obtains the phase difference between the first rotational speed-time curve and the second rotational speed-time curve of the second sensor, and adjusts the clocks of the first sensor and the second sensor to be consistent based on the phase difference. It eliminates the need for all sensors on the self-moving device to share a single clock, effectively reducing the complexity and cost of the self-moving device design. It also eliminates the need for excessive manual intervention in the clock synchronization of multiple sensors, thus improving the efficiency of multi-sensor clock synchronization more intelligently and effectively.

[0082] In one embodiment, the multi-sensor clock synchronization system 100 further includes a rotating device. Specifically, the rotating device rotates the self-moving device at a predetermined speed by fixing the self-moving device to the rotating device, which then rotates at a preset speed, thereby driving the self-moving device to rotate synchronously at the preset speed. The first sensor and the second sensor also rotate synchronously with the self-moving device, thereby ensuring that the rotation speed of the first sensor and the rotation speed of the second sensor are consistent and synchronized in time.

[0083] In one embodiment, the rotation speed-time curve generation module 120 can generate a first rotation speed-time curve of the first sensor in the following manner: obtaining the rotation speed of the first sensor using an inertial sensor, and generating a first rotation speed-time curve based on the rotation speed and the clock of the first sensor; wherein the inertial sensor is disposed on the self-moving device. In one embodiment, the first sensor is an odometer.

[0084] In one embodiment, the rotation speed-time curve generation module 120 can generate a second rotation speed-time curve for the second sensor in the following manner: wherein the second sensor is a camera, and the camera acquires multiple target images corresponding to the calibration board during the rotation of the self-moving device; based on the multiple target images, a feature point recognition method is used to generate the second rotation speed-time curve. The camera photographs the calibration board during the rotation of the self-moving device, acquiring images of the calibration board at different positions and rotation angles relative to the camera.

[0085] In one optional embodiment, the calibration board is a checkerboard. Based on multiple target images, a second rotation speed curve is obtained by using a feature point recognition method, including: marking a feature point on the checkerboard; identifying the position of the feature point in each target image; calculating the position change of the feature point in adjacent target images; and combining the shooting frequency of the camera to obtain the second rotation speed curve.

[0086] In one embodiment, the adjustment module 140 adjusts the clocks of the first sensor and the second sensor to be consistent by: adjusting the phase difference of the clock of the first sensor forward or backward; or, adjusting the phase difference of the clock of the second sensor forward or backward.

[0087] This invention also provides a self-moving device, comprising: a main body, a first sensor disposed on the main body, and a second sensor disposed on the main body; wherein the type of the first sensor is different from the type of the second sensor.

[0088] In this embodiment, the clocks of the first sensor and the second sensor can be synchronized using any of the multi-sensor clock synchronization methods described above.

[0089] In this embodiment, the self-moving device can use any of the multi-sensor clock synchronization systems 100 described above to synchronize the clocks of the first sensor and the second sensor.

[0090] The present invention can implement all or part of the processes in the above methods, or it can be accomplished by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0091] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, servers, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0092] Obviously, the embodiments described above are merely some, not all, embodiments of the present invention. Based on the embodiments of the present invention, those skilled in the art can make other variations or modifications without creative effort, and all such variations or modifications should fall within the scope of protection of the present invention.

Claims

1. A method for multi-sensor clock synchronization, characterized in that, Applied to a self-moving device, the self-moving device including at least a first sensor and a second sensor, the method is used to perform clock synchronization calibration on the self-moving device before it leaves the factory, the method comprising: The self-moving device is rotated by a rotating device, so that the first sensor and the second sensor rotate synchronously with the self-moving device. During the rotation of the self-moving device, a first rotational speed-time curve of the first sensor and a second rotational speed-time curve of the second sensor are generated. Determine the phase difference between the first rotational speed-time curve and the second rotational speed-time curve; Based on the phase difference, the clocks of the first sensor and the second sensor are adjusted to be consistent.

2. The method for multi-sensor clock synchronization according to claim 1, characterized in that, The generation of the first rotational speed curve of the first sensor includes: The rotational speed of the first sensor is obtained using an inertial sensor, and a first rotational speed-time curve is generated based on the rotational speed and the clock of the first sensor; wherein the inertial sensor is disposed on the self-moving device.

3. The method for multi-sensor clock synchronization according to claim 2, characterized in that, The first sensor is an odometer.

4. The method for multi-sensor clock synchronization according to claim 1, characterized in that, in, The second sensor is a camera, and the generation of the second rotational speed time curve of the second sensor includes: As the camera rotates following the self-moving device, it captures multiple target images of the calibration board. Based on multiple target images, a second rotation speed-time curve is generated using feature point recognition.

5. The method for multi-sensor clock synchronization according to claim 4, characterized in that, The step of capturing multiple target images of the calibration board by the camera during the rotation of the self-moving device includes: As the camera follows the rotation of the self-moving device, it takes pictures of the calibration board at a preset frequency to obtain images of the calibration board at different positions and rotation angles relative to the camera.

6. The method for multi-sensor clock synchronization according to claim 4, characterized in that, The calibration board is a checkerboard pattern.

7. The method for multi-sensor clock synchronization according to claim 6, characterized in that, The step of generating a second rotational velocity curve based on multiple target images using feature point recognition includes: Mark a feature point on the chessboard grid; The location of the feature point is identified in each target image, the position change of the feature point in adjacent target images is calculated, and a second rotation speed curve is generated by combining the shooting frequency of the camera.

8. The method for multi-sensor clock synchronization according to claim 1, characterized in that, The step of aligning the clocks of the first sensor and the second sensor includes: Adjust the phase difference by moving the clock of the first sensor forward or backward; or... Adjust the phase difference by moving the clock of the second sensor forward or backward.

9. A multi-sensor clock synchronization system, characterized in that, An application for self-moving devices, the self-moving devices including at least a first sensor and a second sensor, wherein the type of the first sensor is different from the type of the second sensor, is used to perform clock synchronization calibration on the self-moving devices before they leave the factory, the system comprising: The rotation speed-time curve generation module is used to generate a first rotation speed-time curve of the first sensor and a second rotation speed-time curve of the second sensor during the rotation of the self-moving device. The determining module is used to determine the phase difference between the first rotational speed-time curve and the second rotational speed-time curve; An adjustment module is used to adjust the clock of the first sensor and the clock of the second sensor to be consistent according to the phase difference; A rotating device is used to drive the self-moving device to rotate, so that the first sensor and the second sensor rotate synchronously with the self-moving device.

10. A self-moving device, characterized in that, include: main body, The first sensor is disposed on the main body; A second sensor is disposed on the main body; wherein the type of the first sensor is different from the type of the second sensor. Wherein, the clock of the first sensor and the clock of the second sensor are synchronized using the multi-sensor clock synchronization method described in any one of claims 1 to 8.

Images