CN112244705B - Intelligent cleaning device, control method and computer storage medium - Google Patents

Abstract

The invention discloses an equipment control method for intelligent cleaning equipment, intelligent cleaning equipment and computer storage media. The method includes: obtaining the video of the space scene captured by the camera on the intelligent cleaning device in real time, decomposing the video containing the moving target to be triggered into multiple frames of video images according to the preset time interval; dividing the first sense of the video image A region of interest ROI1 and a second region of interest ROI2; if within the preset time interval, the movement index of the moving target to be triggered within the first region of interest ROI1 in the multiple frames of video images reaches the first If the threshold is controlled, a first control signal is sent, and if the motion index of the moving object to be triggered within the second region of interest ROI2 in the multiple frames of video images reaches a second control threshold, a second control signal is sent. The present invention adopts the camera to recognize the user's body movements to realize the control of starting and stopping the equipment.

Description

Intelligent cleaning device, control method, computer storage medium

technical field

The present invention relates to the technical field of cooking appliances, in particular to a method for controlling the cooking appliance and the cooking appliance.

Background technique

At present, more and more households use smart cleaning equipment such as sweeping robots to replace part of housework, but there is still room for improvement in reducing the burden of housework. The current physical buttons of the sweeping robot are all on the body of the sweeping robot, which is relatively close to the ground. For the elderly who are not good at using smartphones and have inconvenient waists and legs, it is particularly inconvenient to start and shut down the sweeping robot.

Therefore, it is necessary to provide a cooking appliance control method and the cooking appliance, so as to at least partly solve the above problems.

Contents of the invention

A series of concepts in simplified form are introduced in the Summary of the Invention, which will be further detailed in the Detailed Description. The summary of the invention in the present invention does not mean to limit the key features and essential technical features of the claimed technical solution, nor does it mean to try to determine the protection scope of the claimed technical solution.

One aspect of the present invention provides an equipment control method for intelligent cleaning equipment, the control method includes: acquiring the video of the space scene captured by the camera on the intelligent cleaning equipment in real time, and converting the video containing the moving object to be triggered according to The preset time interval is decomposed into multiple frames of video images; the first region of interest ROI1 and the second region of interest ROI2 of the video image are divided; if within the preset time interval, the multiple frames of video images fall into When the motion index of the moving object to be triggered in the first region of interest ROI1 reaches the first control threshold, a first control signal is sent, and if the multiple frames of video images fall into the second region of interest ROI2 When the exercise index of the exercise target to be triggered reaches the second control threshold, a second control signal is sent.

According to the control method of the present invention, it is possible to realize the control such as starting and stopping of the device by using the camera to recognize the user's body movements, and the user does not need to personally operate the buttons on the body of the intelligent cleaning device, which brings great convenience to the user.

Preferably, the first region of interest ROI1 and the second region of interest ROI2 are planar regions perpendicular to the axis of the camera.

Thus, the first and second regions of interest can be divided simply and accurately, which provides guarantee for the subsequent motion decomposition of the moving object to be triggered.

Preferably, the first region of interest ROI1 is in a plane region perpendicular to the axis of the camera, and the long side is a rectangle in the x-axis direction; the second region of interest ROI2 is perpendicular to the axis of the camera In the plane area, the long side is a rectangle in the y-axis direction.

Thus, the first region of interest ROI1 and the second region of interest ROI2 can be accurately divided.

Preferably, the first region of interest ROI1 is: corresponding to the moving target to be triggered at a position higher than the first predetermined distance of the camera, taking the axis of the camera as a reference, moving horizontally at a constant speed for a second predetermined distance at the position The mapping range formed by the imaging plane of the above camera.

Therefore, there must be a moving object to be triggered in the first region of interest ROI1, which is beneficial for the smart cleaning device to perform corresponding actions according to the movement of the moving object to be triggered.

Preferably, the second region of interest ROI2 is: corresponding to the moving target to be triggered at a position higher than the first predetermined distance from the camera, and taking the axis of the camera as a base point, perform a horizontal uniform movement at a third predetermined distance. The distance is a mapping range formed by the imaging plane of the camera, and the third predetermined distance is different from the second predetermined distance.

Therefore, there must be a moving object to be triggered in the second region of interest ROI2, which is beneficial for the smart cleaning device to perform corresponding actions according to the movement of the moving object to be triggered.

Preferably, the exercise index includes any one or a combination of the coverage range, range of motion, and size of the center of motion of the exercise target to be triggered.

Thus, the accuracy of triggering the action to be executed can be improved by setting the exercise index.

Preferably, a feature extraction algorithm is used to filter out high-altitude background information and stationary targets in each frame of the video image, so as to extract the moving target to be triggered.

Thus, a clear moving target to be triggered can be obtained.

Preferably, if the camera is distorted, the (k1, k2, p1, p2, k3) distortion model is used when extracting the moving target to be triggered, and the distortion correction is completed according to the pre-calibration result, and the distortion model is:

xc＝x(1+k ₁ r ² +k ₂ r ⁴ +k ₃ r ⁶ )+[2·p ₁ ·xy+p ₂ ·(r ² +2x ² )]

yc＝y(1+k ₁ r ² +k ₂ r ⁴ +k ₃ r ⁶ )+[2·p ₁ ·xy+p ₂ ·(r ² +2y ² )]

Wherein, (x, y) are the coordinates of the distorted moving object to be triggered on the imaging plane of the camera, and (xc, yc) are the corrected coordinates of the moving object to be triggered on the imaging plane of the camera.

In this way, through distortion correction, the inaccurate influence of the extracted moving target to be triggered caused by the distortion of the camera can be avoided.

Another aspect of the present invention provides an intelligent cleaning device, including a memory, a processor, and a computer program stored on the memory and running on the processor. When the processor executes the program, any of the above-mentioned Steps of the methods described in the examples.

The intelligent cleaning device according to the present invention can realize the control of starting and stopping of the device by using the camera to recognize the user's body movements, without the need for the user to personally operate the buttons on the body of the intelligent cleaning device, which brings great convenience to the user.

Another aspect of the present invention provides a computer storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the method described in any of the above-mentioned embodiments are implemented.

Description of drawings

The following drawings of the invention are hereby included as part of the invention for understanding the invention. The accompanying drawings illustrate embodiments of the invention and description thereof to explain principles of the invention.

In the attached picture:

Fig. 1 is a schematic diagram of an intelligent cleaning device in a working scene according to a preferred embodiment of the present invention;

FIG. 2 shows a first region of interest ROI1 and a second region of interest ROI2;

Fig. 3 is an embodiment, in the working process of the intelligent cleaning device, the movement track of the moving object to be triggered within a period of time in the first region of interest ROI1 and the second region of interest ROI2;

FIG. 4 is a detection result representing that the motion index of the moving object to be triggered reaches the first control threshold in the first region of interest ROI1;

Fig. 5 is another embodiment, the movement track of the moving object to be triggered in the first region of interest ROI1 and the second region of interest ROI2 within a period of time during the working process of the smart cleaning device;

FIG. 6 is a detection result representing that the movement index of the moving target to be triggered reaches the second control threshold in the second region of interest ROI2;

Fig. 7 is yet another embodiment, during the working process of the smart cleaning device, the movement track of the moving object to be triggered within a period of time in the first region of interest ROI1 and the second region of interest ROI2; and

FIG. 8 is a detection result indicating that the movement indicators of the moving target to be triggered in both the first region of interest ROI1 and the second region of interest ROI2 do not reach the control threshold.

Detailed ways

In the following description, numerous specific details are given in order to provide a more thorough understanding of the present invention. It will be apparent, however, to one skilled in the art that embodiments of the invention may be practiced without one or more of these details. In other examples, some technical features known in the art are not described in order to avoid confusion with the embodiments of the present invention.

It should be noted that the terms used herein are for the purpose of describing specific embodiments only, and are not intended to limit exemplary embodiments according to the present invention. As used herein, singular forms are intended to include plural forms unless the context clearly dictates otherwise. In addition, it should also be understood that when the terms "comprising" and/or "comprising" are used in this specification, it indicates the presence of the features, integers, steps, operations, elements and/or components, but does not exclude the presence or One or more other features, integers, steps, operations, elements, components and/or combinations thereof are added.

Now, exemplary embodiments according to the present invention will be described in more detail with reference to the accompanying drawings. These example embodiments may, however, be embodied in many different forms and should not be construed as limited to only the embodiments set forth herein. It should be understood that these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the concept of these exemplary embodiments to those of ordinary skill in the art. In the drawings, the thicknesses of layers and regions are exaggerated for clarity, and the same reference numerals are used to designate the same elements, and thus their descriptions will be omitted.

The intelligent cleaning equipment provided by this disclosure can be (but not limited to) a sweeping robot, a mopping robot, or a sweeping and dragging integrated robot. The intelligent cleaning equipment can include a machine body, a perception system, a control system, a drive system, a cleaning system, systems and human-computer interaction systems. Wherein: the main body of the machine includes a forward part and a rearward part, and has an approximately circular shape (both front and rear are circular), and may also have other shapes, including but not limited to an approximately D-shaped shape with a front and rear circle.

The perception system includes a position determination device located above the main body of the machine, a buffer located on the forward part of the main body of the machine, cliff sensors and ultrasonic sensors, infrared sensors, magnetometers, accelerometers, gyroscopes, odometers and other sensing devices, and direction control The system provides various position information and motion status information of the machine. Location determining devices include but are not limited to cameras and laser distance measuring devices (LDS). The following takes the laser distance measuring device of the triangulation distance measuring method as an example to illustrate how to determine the position. The basic principle of the triangular ranging method is based on the proportional relationship of similar triangles, and will not be described in detail here.

The laser distance measuring device includes a light-emitting unit and a light-receiving unit. The light emitting unit may include a light source emitting light, and the light source may include a light emitting element such as an infrared or visible light emitting diode (LED) emitting infrared light or visible light. Preferably, the light source may be a light emitting element emitting a laser beam. In this embodiment, a laser diode (LD) is taken as an example of a light source. In particular, light sources using laser beams can allow for more accurate measurements compared to other lights due to the monochromatic, directional, and collimated properties of laser beams. For example, infrared light or visible light emitted by a light-emitting diode (LED) is affected by surrounding environmental factors (such as the color or texture of an object) and may be less accurate in measurement compared to a laser beam. The laser diode (LD) can be a point laser, which measures the two-dimensional position information of the obstacle, or a line laser, which measures the three-dimensional position information of the obstacle within a certain range.

The light receiving unit may include an image sensor on which a light spot reflected or scattered by an obstacle is formed. An image sensor may be a collection of multiple unit pixels in a single row or in multiple rows. These light-receiving elements can convert light signals into electrical signals. The image sensor may be a complementary metal-oxide-semiconductor (CMOS) sensor or a charge-coupled device (CCD) sensor, and a complementary metal-oxide-semiconductor (CMOS) sensor is preferred due to cost advantages. Also, the light receiving unit may include a light receiving lens assembly. Light reflected or scattered by obstacles can travel through the light receiving lens assembly to form an image on the image sensor. The receiving lens assembly can include single or multiple lenses.

The base may support a light emitting unit and a light receiving unit which are arranged on the base and are spaced apart from each other by a certain distance. In order to measure obstacles in the 360-degree direction around the robot, the base can be rotatably arranged on the main body, or the base itself can be rotated by setting a rotating element to rotate the emitted light and received light without rotating. The rotational angular velocity of the rotating element can be obtained by setting the optocoupler element and the code disc. The optocoupler element senses the tooth gap on the code disc, and the instantaneous angular velocity can be obtained by dividing the sliding time of the tooth gap and the distance between the tooth gaps. The greater the density of tooth gaps on the code disc, the higher the accuracy and precision of measurement, but the more precise the structure, the higher the amount of calculation; on the contrary, the smaller the density of tooth gaps, the higher the accuracy and accuracy of measurement. The accuracy is correspondingly lower, but the structure can be relatively simple, and the amount of calculation can be reduced, which can reduce some costs.

The data processing device connected with the light-receiving unit, such as DSP, records and transmits the obstacle distance values at all angles relative to the robot 0 degree angle direction to the data processing unit in the control system, such as an application processor ( AP), the CPU runs the particle filter-based positioning algorithm to obtain the current position of the robot, and draws a map based on this position for navigation. The positioning algorithm preferably uses Simultaneous Localization and Mapping (SLAM).

Although the laser distance measuring device based on the triangulation method can measure the distance value at an infinite distance beyond a certain distance in principle, it is very difficult to realize long-distance measurement, such as more than 6 meters, mainly because It is limited by the size of the pixel unit on the sensor of the light unit, and is also affected by the photoelectric conversion speed of the sensor, the data transmission speed between the sensor and the connected DSP, and the calculation speed of the DSP. The measurement value of the laser distance measuring device affected by the temperature will also change intolerable to the system, mainly because the thermal expansion and deformation of the structure between the light-emitting unit and the light-receiving unit causes the angle between the incident light and the outgoing light to change, and the light-emitting unit And the light receiving unit itself will also have temperature drift problems. After the laser distance measuring device is used for a long time, the deformation caused by the accumulation of various factors such as temperature changes and vibrations will also seriously affect the measurement results. The accuracy of the measurement results directly determines the accuracy of the map drawing, which is the basis for the robot to further implement the strategy, and is especially important.

The forward portion of the machine body may carry a bumper that detects one or more events (or object), the robot can pass the event (or object) detected by the buffer, such as an obstacle, a wall, and control the driving wheel module to make the robot respond to the event (or object), such as moving away from the obstacle.

The control system is arranged on the circuit board in the main body of the machine, and includes a computing processor, such as a central processing unit, an application processor, and a non-transitory memory, such as a hard disk, a flash memory, and a random access memory, in communication, and the application processor is based on The obstacle information fed back by the laser ranging device uses positioning algorithms, such as SLAM, to draw an instant map of the environment in which the robot is located. And combine the distance information and speed information fed back by the buffer, cliff sensor, ultrasonic sensor, infrared sensor, magnetometer, accelerometer, gyroscope, odometer and other sensing devices to comprehensively judge the current working state of the sweeper, such as crossing the threshold , on the carpet, located on a cliff, stuck above or below, full of dust boxes, picked up, etc., will also give specific next-step action strategies for different situations, so that the robot’s work is more in line with the owner’s requirements. Better user experience. Furthermore, the control system can plan the most efficient and reasonable cleaning path and cleaning method based on the real-time map information drawn by SLAM, greatly improving the cleaning efficiency of the robot.

The drive system may steer the robot 100 across the ground based on drive commands having distance and angular information, such as x, y, and theta components. The driving system includes a driving wheel module, which can control the left wheel and the right wheel at the same time. In order to control the movement of the machine more accurately, preferably, the driving wheel module includes a left driving wheel module and a right driving wheel module. Left and right drive wheel modules are opposed along a transverse axis defined by the main body. In order for the robot to move more stably on the ground or have a stronger movement capability, the robot may include one or more driven wheels, and the driven wheels include but are not limited to universal wheels. The driving wheel module includes road wheels, a driving motor and a control circuit for controlling the driving motor. The driving wheel module can also be connected with a circuit for measuring driving current and an odometer. The drive wheel module can be detachably connected to the main body for easy disassembly and maintenance. The drive wheels may have a biased drop suspension system, movably secured, eg rotatably attached, to the robot body, and receive a spring bias biased downward and away from the robot body. The spring bias allows the drive wheels to maintain contact and traction with the ground with a certain amount of ground force, while the cleaning elements also contact the ground with a certain pressure.

The cleaning system can be a dry cleaning system and/or a wet cleaning system. As a dry cleaning system, the main cleaning function comes from the cleaning system composed of the roller brush structure, the dust box structure, the fan structure, the air outlet and the connecting parts between the four. The roller brush structure with a certain interference with the ground sweeps up the garbage on the ground and rolls it to the front of the dust suction port between the roller brush structure and the dust box structure, and then the suction gas is generated by the fan structure and passes through the dust box structure Suction dust box structure. The dust removal ability of the sweeper can be characterized by the cleaning efficiency DPU (Dust pick up efficiency) of the garbage. The cleaning efficiency DPU is affected by the structure and material of the roller brush, and is affected by the dust suction port, dust box structure, fan structure, air outlet and the four. The influence of the wind power utilization rate of the air duct formed by the connected parts is affected by the type and power of the fan, which is a complex system design problem. Compared with ordinary plug-in vacuum cleaners, the improvement of dust removal capacity is more meaningful for cleaning robots with limited energy. Because the improvement of dust removal ability directly and effectively reduces the energy requirements, that is to say, the original machine that can clean 80 square meters of ground with one charge can evolve to clean 180 square meters or more with one charge. And the service life of the battery with reduced charging times will also be greatly increased, so that the frequency of user replacement of the battery will also increase. More intuitively and importantly, the improvement of the dust removal ability is the most obvious and important user experience, and the user will directly draw the conclusion of whether the sweeping/wiping is clean. Dry cleaning systems may also include side brushes having a rotational axis that is angled relative to the floor for moving debris into the area of the roller brush of the cleaning system.

The energy system includes rechargeable batteries such as NiMH and Lithium batteries. The rechargeable battery can be connected with a charging control circuit, a battery pack charging temperature detection circuit and a battery undervoltage monitoring circuit, and the charging control circuit, a battery pack charging temperature detection circuit, and a battery undervoltage monitoring circuit are connected with the single-chip microcomputer control circuit. The main unit is charged by being connected to the charging pile through the charging electrodes arranged on the side or the bottom of the fuselage.

The human-computer interaction system includes buttons on the host panel for users to select functions; it can also include display screens and/or indicator lights and/or speakers, which display the current state or function of the machine to the user Optional; may also include mobile phone client programs. For path-guided cleaning equipment, the mobile phone client can show the user a map of the environment where the equipment is located, as well as the location of the machine, and can provide users with more abundant and humanized functional items.

The intelligent cleaning device provided in the present disclosure is configured with an image acquisition unit and a distance measurement unit; the image acquisition unit is used to collect image data, and the distance measurement unit is used to collect distance measurement data. Wherein, the image acquisition unit and the ranging unit may be included in the position determination device of the above-mentioned perception system. For example, the image acquisition unit may be a camera, and the distance measuring unit may be a laser distance measuring device. As another example, the image acquisition unit and the ranging unit can be integrated into the camera; for example, a depth-sensing camera with TOF (Time offlight, time of flight) function, or a camera using 3D structured light technology can be used. Of course, the present disclosure does not limit the specific hardware forms of the image acquisition unit and the distance measurement unit.

Based on the above structure of the intelligent cleaning equipment, the present invention provides a control method for the intelligent cleaning equipment. The method can include:

Obtain the video of the space scene captured by the camera on the smart cleaning device in real time, and decompose the video containing the moving target to be triggered into multiple frames of video images according to the preset time interval;

Divide the first region of interest ROI1 and the second region of interest ROI2 of the video image;

If within the preset time interval, the motion index of the moving object to be triggered that falls into the first region of interest ROI1 in the multi-frame video image reaches the first control threshold, the first control signal is sent, and if the multi-frame video image falls into If the movement index of the movement target to be triggered in the second region of interest ROI2 reaches the second control threshold, a second control signal different from the first control signal is sent.

Among them, the camera can use infrared technology or depth of field technology to acquire space scene video. The "preset time interval" can be understood as: the video captured by the camera may be unstable in the short period of time when the smart cleaning device is just turned on, so it does not belong to the video that needs to be analyzed, then this video can be cut off; the smart cleaning device The time period of stable operation can be regarded as a preset time interval. It can be understood that within the preset time interval, the video containing the moving target (for example, an arm) to be triggered is required by the smart cleaning device.

For the spatial scene captured by the camera, it is related to the angle at which the camera is installed on the smart cleaning device, and the installation angle of the camera will also affect the division of the first ROI1 and the second ROI2 of the video image in subsequent steps.

After acquiring the video in the preset time interval and decomposing it into multiple frames of video images, it is necessary to divide each frame of video images into regions of interest. Since multiple frames of video images all contain a moving target to be triggered, specifically, the first region of interest ROI1 may be: the corresponding arm is at a position higher than the first predetermined distance from the camera (refer to FIG. 1 ), and the axis of the camera is L is used as a reference, and the mapping range formed by the imaging plane S of the camera is moved horizontally (left and right) at a constant speed for a second predetermined distance. It can be understood that the first ROI1 is an area in the imaging plane S perpendicular to the axis L of the camera.

As shown in Fig. 1 and Fig. 2, the first predetermined distance may be set between 1 meter and 1.5 meters. The second predetermined distance refers to a distance translated leftward or rightward with the intersection point of the hand and the axis L of the camera as a reference point. The second predetermined distance may be 30 cm. Of course, the second predetermined distance can also be set to other values according to actual needs, such as 35cm, 40cm and so on.

Similarly, the second region of interest ROI2 may be: the corresponding arm is at a position higher than the first predetermined distance from the camera (refer to FIG. 1 ), taking the axis L of the camera as a reference, and moving horizontally (left and right) at a uniform speed for a third predetermined distance. The distance is the mapping range formed by the imaging plane S of the camera. It can be understood that the second region of interest ROI2 is an area in the imaging plane S perpendicular to the axis L of the camera.

Similarly, the third predetermined distance refers to a distance that is different from the second predetermined distance and translates to the left or right with the intersection point of the hand and the axis L of the camera as a reference point. The third predetermined distance may be 50 cm. Of course, the third predetermined distance can also be set to other values according to actual needs, such as 55cm, 60cm and so on.

The dotted box shown in FIG. 2 is a real spatial scene area, which corresponds to the first ROI1 and the second ROI2 in the imaging plane S of the camera. It can be understood from Fig. 2 that the first region of interest ROI1 is in the imaging plane S perpendicular to the axis L of the camera, and the long side is a rectangle in the x-axis direction; the second region of interest ROI2 is the imaging plane perpendicular to the axis L of the camera In S, the long side is a rectangle in the y-axis direction.

As mentioned above, after the region of interest of the video image containing the moving object to be triggered is divided, next, the relationship between the movement index of the moving object to be triggered and the control threshold needs to be judged. If within the preset time interval, the motion index of the moving object to be triggered that falls into the first region of interest ROI1 in the multi-frame video image reaches the first control threshold, then send the first control signal (such as an open signal), if more When the motion index of the moving object to be triggered within the second region of interest ROI2 in the frame video image reaches the second control threshold, a second control signal (such as a stop signal) different from the first control signal is sent. The first and second control signals can also be set as signals for switching between different working modes.

The first region of interest ROI1 can be understood as the area projected by decomposing the motion of the moving object to be triggered into motion in the X direction, and the second region of interest ROI2 can be understood as the projected area that decomposes the motion of the moving object to be triggered into motion in the Y direction area.

In conjunction with a specific example, it can be understood that if the movement target (hand) to be triggered moves in a relatively horizontal direction, it means that the movement index of the hand in the first region of interest ROI1 satisfies the first control threshold, the smart cleaning device is controlled to be turned on through the first control signal. If the movement target (hand) to be triggered during this period of time moves, the hand is more inclined to the vertical direction, which means that the movement index of the hand in the second region of interest ROI1 meets the second control threshold, and the second control threshold is passed. The signal controls the intelligent cleaning equipment to stop.

Specifically, the exercise index of the exercise target to be triggered may include any one or a combination of the coverage range, motion range, and motion center size of the exercise target to be triggered. Thus, the accuracy of triggering the action to be executed can be improved by setting the exercise index.

As for the threshold value of the sports index, it is an empirical value. The selected threshold should make the palm movement can be observed normally in the optical flow diagram.

It can be understood that if one wants to obtain the movement index of the moving object to be triggered, the coordinates of the moving object to be triggered in the region of interest must be obtained first. Then, when the image is collected by the camera, the feature extraction algorithm can be used to filter out the high-altitude background information and the stationary target in each frame of the video image, so as to extract the moving target to be triggered.

If the camera is distorted, the (k1, k2, p1, p2, k3) distortion model can be used when extracting the moving target to be triggered, and the distortion correction can be completed according to the pre-calibration result. The distortion model is:

xc＝x(1+k ₁ r ² +k ₂ r ⁴ +k ₃ r ⁶ )+[2·p ₁ ·xy+p ₂ ·(r ² +2x ² )]

yc＝y(1+k ₁ r ² +k ₂ r ⁴ +k ₃ r ⁶ )+[2·p ₁ ·xy+p ₂ ·(r ² +2y ² )]

Wherein, (x, y) are the coordinates of the distorted moving object to be triggered on the imaging plane of the camera, and (xc, yc) are the corrected coordinates of the moving object to be triggered on the imaging plane of the camera.

Next, with reference to Fig. 3-Fig. 8, the control principle of the intelligent cleaning device applying the control method of the present invention during the test process is described, so as to better understand the present invention.

As shown in FIG. 3 , the darker colored line represents the movement trajectory of the moving object to be triggered in the X direction, and the lighter colored line represents the movement trajectory of the moving object to be triggered in the Y direction. It can be seen that the motion trajectory in the X direction has a large amplitude, and its motion index meets the set first control threshold. Therefore, the detection result is shown in Figure 4, and the action of starting the smart cleaning device is triggered.

As shown in FIG. 5 , the darker colored line represents the movement trajectory of the moving object to be triggered in the X direction, and the lighter colored line represents the movement trajectory of the moving object to be triggered in the Y direction. It can be seen that the motion trajectory in the Y direction has a large amplitude, and its motion index meets the set second control threshold. Therefore, the detection result is shown in Figure 6, and the trigger is to stop the action of the smart cleaning device.

As shown in FIG. 7 , the darker colored line represents the movement trajectory of the moving object to be triggered in the X direction, and the lighter colored line represents the movement trajectory of the moving object to be triggered in the Y direction. Its motion index does not meet the set first and second control thresholds, so no action is triggered.

The present invention also provides an intelligent cleaning device, the specific structure of which has been described in detail above and will not be repeated here. In addition, the present invention also provides a computer storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the method described in any of the above-mentioned embodiments are implemented.

According to the control method of the present invention, it is possible to realize the control such as starting and stopping of the device by using the camera to recognize the user's body movements, and the user does not need to personally operate the buttons on the body of the intelligent cleaning device, which brings great convenience to the user.

The processes and steps described in all the above preferred embodiments are just examples. Unless adverse effects occur, various processing operations may be performed in an order different from that of the flow described above. The order of steps in the above process can also be added, combined or deleted according to actual needs.

In addition, the commands, command numbers, and data items described in all the above-mentioned preferred embodiments are just examples, so these commands, command numbers, and data items can be set in any manner as long as the same functions are realized. The units of the terminal in each preferred embodiment can also be integrated, further divided or deleted according to actual needs.

The present invention has been described through the above-mentioned embodiments, but it should be understood that the above-mentioned embodiments are only for the purpose of illustration and description, and are not intended to limit the present invention within the scope of the described embodiments. In addition, those skilled in the art can understand that the present invention is not limited to the above-mentioned embodiments, and more variations and modifications can be made according to the teachings of the present invention, and these variations and modifications all fall within the claimed scope of the present invention. within the range. The protection scope of the present invention is defined by the appended claims and their equivalent scope.

Claims (6)

1. A device control method for an intelligent cleaning device, the control method comprising:

acquiring a video of a space scene shot by a camera on the intelligent cleaning equipment in real time, and decomposing the video containing a moving target to be triggered into a plurality of frames of video images according to a preset time interval;

dividing a first region of interest (ROI 1) and a second region of interest (ROI 2) of the video image, wherein the first region of interest (ROI 1) is a rectangle with long sides in the x-axis direction, the second region of interest (ROI 2) is a rectangle with long sides in the y-axis direction, and the first region of interest (ROI 1) and the second region of interest (ROI 2) are imaging plane regions perpendicular to the axis of the camera;

and if the motion index of the to-be-triggered moving object in the multi-frame video image falling into the first region of interest ROI1 reaches a first control threshold value, a first control signal is sent, and if the motion index of the to-be-triggered moving object in the multi-frame video image falling into the second region of interest ROI2 reaches a second control threshold value, a second control signal different from the first control signal is sent.

2. The apparatus control method according to claim 1, wherein the movement index includes any one or a combination of a coverage range, an action amplitude, and a movement center size of the movement of the moving object to be triggered.

3. The apparatus control method according to claim 1, wherein background information in high air and stationary objects in the video image of each frame are filtered out using a feature extraction algorithm to extract the moving object to be triggered.

4. The apparatus control method according to claim 3, wherein if the camera is distorted, when the moving object to be triggered is extracted, a distortion model (k 1, k2, p1, p2, k 3) is used to perform distortion correction according to a pre-calibration result, the distortion model being:

xc=x(1+k ₁ r ² +k ₂ r ⁴ +k ₃ r ⁶ )+[2•p ₁ •xy+p ₂ •(r ² +2x ² )]

yc=y(1+k ₁ r ² +k ₂ r ⁴ +k ₃ r ⁶ )+[2•p ₁ •xy+p ₂ •(r ² +2y ² )]

wherein (x, y) is the coordinates of the distorted moving object to be triggered on the imaging plane of the camera, and (xc, yc) is the coordinates of the corrected moving object to be triggered on the imaging plane of the camera.

5. A smart cleaning device comprising a memory, a processor and a computer program stored on the memory and running on the processor, characterized in that the processor implements the steps of the method of any one of claims 1 to 4 when the program is executed by the processor.

6. A computer storage medium having stored thereon a computer program, characterized in that the program when executed by a processor realizes the steps of the method according to any of claims 1 to 4.

Images