Scene Parameter Adjustment Method, Device, Electronic Device and Storage Medium

Abstract

The present invention relates to the technical field of smart home, and provides a method, a device, an electronic device and a storage medium for adjusting scene parameters. The method for adjusting scene parameters includes: obtaining historical image information at a preset distance position; identifying the historical image information to determine a current scene recognition result of the current floor decoration scene; and performing power adjustment based on the current scene recognition result. By identifying the historical image information to determine the current scene recognition result, the present invention achieves the purpose of enabling the sweeping robot to determine whether it is currently in a dark-colored floor tile scene. And by adjusting the power when the sweeping robot determines that it is currently in a dark-colored floor tile scene, it ensures that the sweeping robot can generate enough point cloud data when obtaining image information again, thereby avoiding the problem of obstacle avoidance failure caused by misjudgment of obstacles, and improving the obstacle avoidance flexibility and functional diversity of the sweeping robot.

Description

Technical Field

[0001] The present invention relates to the technical field of smart home, and particularly to a method and device for adjusting scene parameters, an electronic device, and a storage medium. Background Art

[0002] With the continuous development and progress of technology, the use of floor-sweeping robots for house cleaning has become increasingly popular. Although the floor-sweeping robot can reasonably avoid obstacles based on the set obstacle avoidance strategy during the cleaning process, when the floor-sweeping robot enters a scene with dark-colored floor tiles (such as black floor tiles) for cleaning, the light emitted by the laser emitter is absorbed, resulting in less generated point cloud data. Based on the less point cloud data, it is misjudged that the distance to the obstacle ahead is relatively close. When the light is emitted again for detection, the same misjudgment result occurs and obstacle avoidance is performed, thus causing obstacle avoidance failure. Summary of the Invention

[0003] The present invention aims to at least solve one of the technical problems existing in the related art. For this purpose, the present invention proposes a method for adjusting scene parameters, achieving the purpose of power adjustment on the premise that the floor-sweeping robot recognizes the current scene recognition result of the current floor decoration scene, thereby ensuring that the floor-sweeping robot can also reasonably avoid obstacles when in a dark-colored floor tile scene, and solving the problem of obstacle avoidance failure.

[0004] The present invention also proposes a second scene parameter adjustment device.

[0005] According to the scene parameter adjustment method of the first aspect embodiment of the present invention, it includes:

[0006] Obtain historical image information at a preset distance position;

[0007] Identify the historical image information to determine the current scene recognition result of the current floor decoration scene;

[0008] Perform power adjustment based on the current scene recognition result.

[0009] According to the scene parameter adjustment method of the embodiment of the present invention, when the floor-sweeping robot obtains historical image information at a preset distance position, by identifying the historical image information, the current scene recognition result of the current floor decoration scene is determined, and power adjustment is performed based on the current scene recognition result. In this way, by identifying the historical image information to determine the current scene recognition result, the purpose of the floor-sweeping robot to judge whether it is currently in a dark-colored floor tile scene is achieved, and by the way that the floor-sweeping robot performs power adjustment when it is determined that it is currently in a dark-colored floor tile scene, it is ensured that the floor-sweeping robot can generate enough point cloud data when obtaining image information again, thereby avoiding the problem of obstacle avoidance failure caused by misjudgment of obstacles, and improving the obstacle avoidance flexibility and function diversity of the floor-sweeping robot.

[0010] According to an embodiment of the present invention, the recognition of the historical image information to determine the current scene recognition result of the current floor decoration scene includes:

[0011] Perform grayscale recognition on the historical image information to determine the target grayscale value of the historical image information;

[0012] Based on the target grayscale value and a preset grayscale threshold, determine the current scene recognition result of the current floor decoration scene.

[0013] According to the scene parameter adjustment method of the embodiment of the present invention, the sweeping robot determines the current scene recognition result of the current floor decoration scene based on the target grayscale value obtained from the grayscale analysis of the historical image information and the preset grayscale threshold. By combining the image grayscale characteristics and the pre-set grayscale threshold to determine the current scene recognition result, the accuracy and reliability of the sweeping robot to determine the current scene are realized.

[0014] According to an embodiment of the present invention, after determining the current scene recognition result of the current floor decoration scene, the method further includes:

[0015] Adjust the moving speed based on the current scene recognition result.

[0016] According to the scene parameter adjustment method provided by the embodiment of the present invention, the sweeping robot adjusts the moving speed based on the current scene recognition result of the current floor decoration scene, so as to ensure that when the sweeping robot is currently on dark-colored floor tiles, it can avoid colliding with obstacles by adjusting the moving speed, improving the flexibility and reliability of the sweeping robot to adjust parameters.

[0017] According to an embodiment of the present invention, the recognition of the historical image information to determine the current scene recognition result of the current floor decoration scene includes:

[0018] Perform point cloud recognition on the historical image information to determine the current point cloud data distributed in the current floor decoration scene;

[0019] Based on the current point cloud data and a preset point cloud data threshold, determine the current scene recognition result of the current floor decoration scene.

[0020] According to the scene parameter adjustment method of the embodiment of the present invention, the sweeping robot determines the current scene recognition result of the current floor decoration scene based on the current point cloud data obtained from the point cloud recognition of the historical image information and the preset point cloud data threshold. By combining the point cloud data characteristics and the pre-set point cloud data threshold to determine the current scene recognition result, the flexibility and reliability of the sweeping robot to determine the current scene are realized.

[0021] According to an embodiment of the present invention, after determining the current point cloud data distributed in the current floor decoration scene, the method further includes:

[0022] Based on the current point cloud data, perform obstacle detection for the preset distance position.

[0023] According to the scene parameter adjustment method of the embodiment of the present invention, the floor sweeping robot performs obstacle detection for the preset distance position for the current point cloud data obtained by identifying the historical image information, so as to achieve the purpose of judging whether there is an obstacle in front based on the distribution characteristics of the point cloud data characteristics, and improve the reliability and accuracy of obstacle avoidance.

[0024] According to an embodiment of the present invention, after performing obstacle detection for the preset distance position, the method further includes:

[0025] Based on the detection success result of the obstacle and the current point cloud data, determine a moving direction strategy;

[0026] Move based on the moving direction strategy.

[0027] According to the scene parameter adjustment method provided by the embodiment of the present invention, when the floor sweeping robot detects an obstacle at the preset distance position, first determine a moving direction strategy based on the current point cloud data distributed in the current floor decoration scene, and then move based on the moving direction strategy, which improves the flexibility of the floor sweeping robot when avoiding obstacles.

[0028] According to an embodiment of the present invention, the determining a moving direction strategy based on the detection success result of the obstacle and the current point cloud data includes:

[0029] Based on the detection success result of the obstacle, determine the detected target obstacle;

[0030] Based on the current point cloud data, determine the height data of the target obstacle;

[0031] Based on the height data and a preset height data threshold, determine a moving direction strategy, where the moving direction strategy includes one of adjusting the current moving direction and maintaining the current moving direction.

[0032] According to the scene parameter adjustment method provided by the embodiment of the present invention, when the floor sweeping robot detects an obstacle at the preset distance position, by determining whether the height data of the target obstacle determined by the current point cloud data reaches the height data threshold, it is determined whether the floor sweeping robot maintains the current moving direction to press over the target obstacle and continue to move forward, or changes the moving direction to avoid the obstacle, thereby improving the obstacle avoidance flexibility and moving intelligence of the floor sweeping robot.

[0033] According to an embodiment of the present invention, after detecting obstacles at the preset distance position, the method further includes:

[0034] Based on the detection failure result of the obstacle, continue to move based on the current moving direction.

[0035] According to the scene parameter adjustment method provided by the present invention, when the sweeping robot determines that there is no obstacle at the preset distance position based on historical image information, it continues to move based on the current moving direction, achieving the purpose that the sweeping robot determines that there is no obstacle in front based on the previous frame of image information and continues to move forward, improving the reliability and accuracy of the sweeping robot's movement in the current scene.

[0036] The scene parameter adjustment device according to the second aspect embodiment of the present invention includes:

[0037] An acquisition module for acquiring historical image information of a preset distance position;

[0038] An identification module for identifying the historical image information to determine the current scene identification result of the current floor decoration scene;

[0039] An adjustment module for performing power adjustment based on the current scene identification result.

[0040] According to the scene parameter adjustment device of the embodiment of the present invention, when historical image information of a preset distance position is acquired, by identifying the historical image information, the current scene identification result of the current floor decoration scene is determined, and power adjustment is performed based on the current scene identification result. In this way, by identifying the historical image information to determine the current scene identification result, the purpose of the sweeping robot to determine whether it is currently in a dark-colored floor tile scene is achieved, and by the way that the sweeping robot performs power adjustment when it determines that it is currently in a dark-colored floor tile scene, it is ensured that the sweeping robot can generate enough point cloud data when acquiring image information again, thereby avoiding the problem of obstacle avoidance failure caused by misjudgment of obstacles and improving the obstacle avoidance flexibility and functional diversity of the sweeping robot.

[0041] One or more of the above technical solutions in the embodiments of the present invention have at least one of the following technical effects: When the sweeping robot obtains the historical image information at a preset distance position, by identifying the historical image information, the current scene recognition result of the current ground decoration scene is determined, and the power is adjusted based on the current scene recognition result. In this way, by identifying the historical image information to determine the current scene recognition result, the purpose of the sweeping robot to judge whether it is currently in a dark-colored floor tile scene is achieved. And by adjusting the power when the sweeping robot determines that it is currently in a dark-colored floor tile scene, it is ensured that when the sweeping robot obtains the image information again, enough point cloud data can be generated, thus avoiding the problem of obstacle avoidance failure caused by misjudgment of obstacles and improving the obstacle avoidance flexibility and function diversity of the sweeping robot.

[0042] Further, the sweeping robot determines the current scene recognition result of the current ground decoration scene based on the target gray value obtained from the gray analysis of the historical image information and a preset gray threshold. In this way, by combining the image gray characteristics and the preset gray threshold to determine the current scene recognition result, the accuracy and reliability of the sweeping robot to determine the current scene are achieved.

[0043] Furthermore, the sweeping robot adjusts the moving speed based on the current scene recognition result of the current ground decoration scene. In this way, it is ensured that when the sweeping robot is currently in dark-colored floor tiles, it can avoid colliding with obstacles by adjusting the moving speed, improving the flexibility and reliability of the sweeping robot to adjust parameters.

[0044] Still further, the sweeping robot determines the current scene recognition result of the current ground decoration scene based on the current point cloud data obtained from the point cloud recognition of the historical image information and a preset point cloud data threshold. In this way, by combining the point cloud data characteristics and the preset point cloud data threshold to determine the current scene recognition result, the flexibility and reliability of the sweeping robot to determine the current scene are achieved.

[0045] Still further, the sweeping robot performs obstacle detection at a preset distance position for the current point cloud data obtained by recognizing the historical image information, so as to achieve the purpose of judging whether there is an obstacle in front based on the distribution characteristics of the point cloud data characteristics, improving the reliability and accuracy of obstacle avoidance.

[0046] Still further, when the sweeping robot detects an obstacle at a preset distance position, it first determines the moving direction strategy based on the current point cloud data distributed in the current ground decoration scene, and then moves based on the moving direction strategy, improving the flexibility of the sweeping robot to move when avoiding obstacles.

[0047] Furthermore, when the sweeping robot detects an obstacle at a preset distance position, it determines whether to maintain the current moving direction and drive over the target obstacle to continue moving forward or change the moving direction to avoid the obstacle by checking whether the height data of the target obstacle determined by the current point cloud data reaches the height data threshold, thereby improving the obstacle avoidance flexibility and moving intelligence of the sweeping robot.

[0048] Furthermore, when the sweeping robot determines based on historical image information that there is no obstacle at the preset distance position, it continues to move based on the current moving direction, achieving the purpose that the sweeping robot determines that there is no obstacle in front based on the previous frame of image information and continues to move forward, improving the reliability and accuracy of the sweeping robot's movement in the current scenario.

[0049] Additional aspects and advantages of the present invention will be given in part in the following description, will become apparent in part from the following description, or will be learned through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments or related technologies. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0051] Figure 1 is a flowchart of the method for adjusting scene parameters provided by an embodiment of the present invention;

[0052] Figure 2 is the second distribution diagram of the current point cloud data provided by an embodiment of the present invention;

[0053] Figure 3 is the second distribution diagram of the current point cloud data provided by an embodiment of the present invention;

[0054] Figure 4 is a structural diagram of the scene parameter adjustment device provided by an embodiment of the present invention;

[0055] Figure 5 is a physical structure diagram of the electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0056] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below with reference to the accompanying drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention without making creative efforts fall within the protection scope of the present invention.

[0057] Currently, many floor-sweeping robots use the principle of line-structured light ranging to detect obstacles during the cleaning process to achieve the purpose of obstacle avoidance. The principle of line-structured light ranging is that a laser emitter with a wavelength of 800 nm emits a linearly arranged light beam. The light beam is projected onto the front obstacle and received by an infrared camera with the corresponding wavelength to generate two-dimensional image information. The two-dimensional image information is the image information generated on the pixels of the sensor after the light beam hits the obstacle. The gray value of each pixel represents its signal intensity. Then, the two-dimensional image information is converted into depth information using the principle of triangulation ranging and presented as point cloud data. The point cloud data is also to convert the image information of the corresponding pixels within the set gray threshold range into depth information according to the signal intensity represented by each pixel, and the pixels outside the gray threshold range will not generate depth information. Since the laser emitter emits a light beam in the near-infrared band of 800 nm, the laser beam in this near-infrared band is easily absorbed by dark-colored substances (such as being absorbed by black floor tiles or black obstacles). Therefore, in a dark-colored substance scenario, the signal-to-noise ratio of the laser emitter decreases. For example, when the floor-sweeping robot is on black floor tiles, it will generate less power data or cannot generate point cloud data. When the point cloud data is less, the floor-sweeping robot will misjudge as being close to an obstacle because no point cloud data is generated when it is very close to the obstacle. At this time, the floor-sweeping robot will avoid it, then detect again, and avoid again, resulting in a circling phenomenon and causing the obstacle avoidance to fail.

[0058] Based on the above problems, the present invention provides a method, device, equipment, and storage medium for adjusting scene parameters. The execution subject of the method for adjusting scene parameters can be a floor-sweeping robot, and this floor-sweeping robot at least has functions such as image generation, gray-scale analysis, point cloud generation, data storage, parameter adjustment, and data processing.

[0059] The following combines Figures 1-5 Describe the method, device, electronic equipment, and storage medium for adjusting scene parameters provided by the present invention. And, the following method embodiments are described by taking the execution subject as a floor-sweeping robot as an example.

[0060] Figure 1 For the flow diagram of the method for adjusting scene parameters provided by the present invention, as Figure 1 shown, this method for adjusting scene parameters includes the following steps:

[0061] Step 110: Obtain historical image information at a preset distance position.

[0062] The preset distance position is the position at a preset distance from the floor cleaning robot, and the preset distance can be fixed. The historical image information is relative to the current image information, that is, the previous frame image information of the current image information. For example, when the second frame of image information is currently generated, the first frame of image information is the historical image information.

[0063] It can be understood that an infrared sensor and an infrared camera are provided on the floor cleaning robot. The infrared camera can also be replaced by an infrared camera. The infrared sensor is used to emit an infrared beam obliquely downward to the preset distance position, and the direction and angle of emitting the infrared beam are also fixed. The wavelength of the infrared beam can be between 800 and 900 nm, or above 900 nm. Based on this, when the floor cleaning robot moves, it will emit an infrared beam to the preset distance position in real time, and generate image information in real time by receiving the signal returned after the infrared beam is projected onto an object at the preset distance position through the infrared camera, and obtain the historical image information from the generated image information.

[0064] Step 120: Identify the historical image information to determine the current scene recognition result of the current floor decoration scene.

[0065] It can be understood that the current floor decoration scene can be the current floor tile scene, and the current scene recognition result can include a dark color floor tile scene and a light color floor tile scene. Based on this, the floor cleaning robot can determine whether the floor tile scene where the floor cleaning robot is currently located is dark or light by identifying the historical image information. Dark colors can be colors that absorb infrared beams, such as black; light colors are colors that do not absorb infrared beams, such as white. Considering that the floor cleaning robot needs to ensure the cleanliness after cleaning for each floor tile, the size of the floor cleaning robot itself, and the size of each floor tile, it still takes a certain amount of time for the floor cleaning robot to enter and exit a floor tile, and multiple frames of image information are generated for the current floor decoration scene during this period. If the second frame of image information is currently generated, it can be identified based on the first frame of image information to determine whether the current floor tile scene is a dark color floor tile scene that absorbs infrared beams or a light color floor tile scene that does not absorb infrared beams. Exemplarily, the dark color floor tile scene can include one of a black floor tile scene, a gray floor tile scene, a dark blue floor tile scene, a navy blue floor tile scene, and a maroon floor tile scene, etc., and the light color floor tile scene can include one of a white floor tile scene, a scarlet floor tile scene, a bright orange floor tile scene, a golden yellow floor tile scene, a emerald green floor tile scene, a powder blue floor tile scene, and a lavender floor tile scene.

[0066] It can be understood that when laying floor tiles indoors, for a certain area, the same color system of floor tiles can be laid in a large piece or multiple small pieces. Therefore, the size of the floor tiles of the same color system is usually larger than the size of the sweeping robot itself, and it can ensure that the current scene recognition result is determined within the time to generate a frame of image information.

[0067] Step 130, perform power adjustment based on the current scene recognition result.

[0068] It can be understood that when the sweeping robot determines that the current scene recognition result is a dark color system floor tile scene, the power of the infrared sensor can be increased, such as increasing the current, so that the next frame of image information is obtained based on the infrared sensor with increased power; when the sweeping robot determines that the current scene recognition result is a light color system floor tile scene, the power of the infrared sensor can be restored to the initial power, so as to achieve the purpose of saving power consumption and delaying the service life of the infrared sensor.

[0069] According to the scene parameter adjustment method of the embodiment of the present invention, when the sweeping robot obtains the historical image information at the preset distance position, by recognizing the historical image information, the current scene recognition result of the current floor decoration scene is determined, and power adjustment is performed based on the current scene recognition result. In this way, by the way of recognizing the historical image information to determine the current scene recognition result, the purpose of the sweeping robot to judge whether it is currently in a dark color system floor tile scene is achieved, and by the way that the sweeping robot performs power adjustment when it determines that it is currently in a dark color system floor tile scene, it is ensured that the sweeping robot can generate enough point cloud data when obtaining image information again, thus avoiding the problem of obstacle avoidance failure caused by misjudgment of obstacles, and improving the obstacle avoidance flexibility and function diversity of the sweeping robot.

[0070] According to an embodiment of the present invention, since when the sweeping robot enters a dark color system floor tile scene, the image information it generates is usually a grayscale image, the current floor tile scene can be quickly recognized by combining the characteristics of the grayscale image. Based on this, to recognize the historical image information and determine the current scene recognition result of the current floor decoration scene, the implementation process may include:

[0071] First, perform grayscale recognition on the historical image information to determine the target grayscale value of the historical image information; then, based on the target grayscale value and the preset grayscale threshold, determine the current scene recognition result of the current floor decoration scene.

[0072] Among them, the target gray value can be the average gray value of the historical image information, which is used to reflect the light and darkness of the overall historical image information. The preset gray threshold can be a preset average gray threshold. The average gray threshold can collect image information of various common dark-colored floor tiles (such as various black floor tiles) using an infrared sensor, and determine and store the average gray threshold in the sweeping robot by analyzing the average gray value of each frame of image information; the average gray value can also be for the same dark-colored floor tile scene, using sweeping robots with different infrared sensors to collect the point cloud data of the dark-colored floor tile scene respectively, and determining and storing the average gray threshold in the sweeping robot by performing deep learning on the point cloud data collected by each sweeping robot. Here, the method for determining the average gray threshold is not specifically limited.

[0073] When the sweeping robot determines the average gray value of the historical image information, it can compare the average gray value with the preset gray threshold. If the average gray threshold is lower than the gray threshold, it is determined that the current scene recognition result of the current floor decoration scene is a dark-colored floor tile scene; conversely, if the average gray value is higher than the gray threshold, it is determined that the current scene recognition result of the current floor decoration scene is a light-colored floor tile scene.

[0074] According to the scene parameter adjustment method of the embodiment of the present invention, the sweeping robot determines the current scene recognition result of the current floor decoration scene based on the target gray value obtained from the gray analysis of the historical image information and the preset gray threshold, and determines the current scene recognition result by combining the image gray characteristics and the preset gray threshold, realizing the accuracy and reliability of the sweeping robot to determine the current scene it is in.

[0075] It can be understood that when the sweeping robot determines that the current floor tile scene is a dark-colored floor tile, in order to avoid the failure of obstacle avoidance and increase the power to ensure that the next frame of image information is obtained using the infrared sensor after the power increase, but since the power switch requires time and the frame rate is also limited, and in order to avoid the sweeping robot colliding with the obstacle in front when moving on the dark-colored floor tile, the sweeping robot needs to move slowly. Based on this, after determining the current scene recognition result of the current floor decoration scene, the method of the present invention can further include:

[0076] Adjust the moving speed based on the current scene recognition result.

[0077] It can be understood that if the current scene recognition result is a dark-colored floor tile scene, the sweeping robot not only needs to increase the power of the infrared sensor but also needs to reduce the moving speed to ensure that the sweeping robot moves slowly on the dark-colored floor tiles. For example, when the sweeping robot moves at 30 centimeters per second on light-colored floor tiles, then when it enters the dark-colored floor tiles, it moves at 5 cm per second or 10 cm per second, within the time to generate one frame of image information; similarly, when the sweeping robot comes out of the dark-colored floor tiles and enters the light-colored floor tiles, it will also reduce the power of the infrared sensor to the initial power while increasing the moving speed of the sweeping robot to the initial moving speed.

[0078] According to the scene parameter adjustment method provided by the embodiment of the present invention, the sweeping robot adjusts the moving speed based on the current scene recognition result of the current floor decoration scene, so as to ensure that when the sweeping robot is currently in the dark-colored floor tiles, it can avoid colliding with obstacles by adjusting the moving speed, improving the flexibility and reliability of the sweeping robot to adjust parameters.

[0079] It can be understood that considering that the point cloud data not only represents the three-dimensional space coordinates but also represents the intensity value, and the intensity value is the intensity of the returned signal recorded according to the surface reflectivity of the object, the sweeping robot can convert the generated image information into point cloud data, and thus determine the current scene recognition result based on the obtained point cloud data. Based on this, the specific implementation process of step 120 may further include:

[0080] First, perform point cloud recognition on the historical image information to determine the current point cloud data distributed in the current floor decoration scene; then, based on the current point cloud data and the preset point cloud data threshold, determine the current scene recognition result of the current floor decoration scene.

[0081] Among them, the preset point cloud threshold is used to represent that the amount of distributed point cloud data is sufficient to indicate that the current floor tile is a dark-colored floor tile.

[0082] It can be understood that during the continuous movement of the sweeping robot in the room, an infrared beam is emitted in real time at a preset distance position diagonally downward in the front. The emitted infrared beam first hits the floor tile. If there is no obstacle in the front, it will always hit the floor tile. When the floor tile is a dark-colored floor tile, the number of current point cloud data obtained by recognizing the historical image information will be very small, and the number of point cloud data will change with the color depth of the floor tile. For example, the darker the color of the floor tile, the fewer the number of point cloud data; therefore, based on the number of current point clouds obtained by recognizing the historical image information and the preset point cloud data, it can be determined whether the current scene recognition result is a dark-colored floor tile scene or a light-colored floor tile scene.

[0083] Exemplarily, when the current scene recognition result indicates that the sweeping robot is currently in a dark-colored floor tile scene, less current point cloud data can be determined through the recognition of historical image information. For example, when it is determined that the sweeping robot is currently on a black floor tile, after performing point cloud recognition on the historical image information obtained for the black floor tile scene, a distribution map of the current point cloud data as shown in Figure 2 can be obtained; conversely, when the current scene recognition result indicates that the sweeping robot is currently in a light-colored floor tile scene, more current point cloud data can be determined through the recognition of historical image information. For example, when it is determined that the sweeping robot is currently on a non-black floor tile, after performing point cloud recognition on the historical image information obtained for the non-black floor tile scene, a distribution map of the current point cloud data as shown in Figure 3 can be obtained.

[0084] According to the scene parameter adjustment method of the embodiments of the present invention, the sweeping robot determines the current scene recognition result of the current floor decoration scene based on the current point cloud data obtained by performing point cloud recognition on the historical image information and a preset point cloud data threshold. In this way, by combining the characteristics of the point cloud data and the preset point cloud data threshold, the current scene recognition result is determined, achieving the flexibility and reliability of the sweeping robot to determine the current scene it is in.

[0085] It can be understood that if the point cloud data not only represents the spatial three-dimensional coordinates and intensity values but also contains distance information, height information, and angle information, then it is possible to determine whether there is an obstacle ahead. Based on this, after determining the current point cloud data distributed in the current floor decoration scene, the method of the present invention may further include:

[0086] Performing obstacle detection for a preset distance position based on the current point cloud data.

[0087] It can be understood that when the sweeping robot recognizes that the current point cloud data contains distance information, height information, and angle information, it can determine the distance between the sweeping robot and the object ahead, the height of the object ahead, and the angle at which the infrared beam is projected onto the object ahead. Then, based on the distance information, height information, and angle information contained in the current point cloud data, obstacle detection can be performed based on the current point cloud data. It can be understood that when the current point cloud data does not contain height information and distance information, the height information and distance information can also be calculated based on the spatial three-dimensional coordinates represented by the current point cloud data itself and the principle of triangulation ranging. No specific limitation is made here.

[0088] According to the scene parameter adjustment method of the embodiments of the present invention, the sweeping robot performs obstacle detection for a preset distance position on the current point cloud data obtained by recognizing the historical image information, thereby achieving the purpose of determining whether there is an obstacle ahead based on the distribution characteristics of the point cloud data characteristics, and improving the reliability and accuracy of obstacle avoidance.

[0089] It can be understood that when the floor cleaning robot detects an obstacle ahead, it doesn't necessarily need to avoid the obstacle. For example, when the height of the obstacle is very low, it can directly roll over it. Based on this, after detecting the obstacle at the preset distance position, the method of the present invention may further include:

[0090] First, based on the detection success result of the obstacle and the current point cloud data, determine the moving direction strategy; and then further move based on the moving direction strategy.

[0091] It can be understood that during the movement of the floor cleaning robot on the indoor ground, it will emit an infrared beam in a direction obliquely downward in real time towards a preset distance position ahead. If there is an obstacle at the preset distance position ahead, the infrared beam will first hit the ground and then hit the obstacle. As the floor cleaning robot continuously moves forward, the infrared beam hitting the obstacle will slowly move from the bottom to the top of the obstacle. If the height calibrated for the floor cleaning robot placed on the ground in advance is 0, then if the height information reflected by the current point cloud data is also 0, it is considered that there is no obstacle at the preset distance position ahead; on the contrary, if the height information reflected by the current point cloud data is greater than 0, it is considered that there is an obstacle at the preset distance position ahead. Therefore, when the floor cleaning robot determines that there is an obstacle at the preset distance position based on the height information extracted from the current point cloud data, it can further determine the moving direction strategy based on the height information reflected by the current point cloud data.

[0092] It can be understood that a receiving infrared camera can be set beside the infrared camera set in the floor cleaning robot, and both the infrared camera and the infrared sensor can be set directly in front of the floor cleaning robot to ensure that the infrared sensor emits an infrared beam obliquely downward in front. The infrared camera captures the emitted infrared beam and measures the distance using the triangulation method. Since the shapes of the obstacles are different and may be uneven, when the infrared light hits the obstacle, the point will deform on the obstacle. At this time, the specific shape of the obstacle can also be determined by calculating different distances.

[0093] According to the scene parameter adjustment method provided by the embodiment of the present invention, when the floor cleaning robot detects an obstacle at the preset distance position, it first determines the moving direction strategy based on the current point cloud data distributed in the current ground decoration scene, and then moves based on the moving direction strategy, improving the flexibility of the floor cleaning robot during obstacle avoidance movement.

[0094] It can be understood that if the current point cloud data determined by the floor cleaning robot has multiple heights representing different positions of the obstacle, it can be determined whether to avoid the obstacle based on the maximum height value of the obstacle. Based on this, based on the detection success result of the obstacle and the current point cloud data, determining the moving direction strategy, the implementation process includes:

[0095] First, based on the successful result of obstacle detection, determine the detected target obstacle; then, based on the current point cloud data, determine the height data of the target obstacle; and then, based on the height data and a preset height data threshold, determine the movement direction strategy, where the movement direction strategy includes one of adjusting the current movement direction and maintaining the current movement direction.

[0096] Among them, the target obstacle includes movable obstacles, such as users, pets, etc.; it can also include immovable obstacles, such as sofas, doors, thresholds, etc. No specific limitation is made here.

[0097] It can be understood that when the sweeping robot determines that the number of current point cloud data is multiple and the multiple current point cloud data represent their distribution at different height positions on the obstacle, the maximum height data of the obstacle can be further determined based on the multiple different height data. If the maximum height data of the obstacle is greater than the preset height data threshold, it is necessary to avoid it. At this time, the sweeping robot will adjust the current movement direction. For example, when the current movement direction is forward straight movement, the current movement direction can be adjusted to left turn straight movement or right turn straight movement, etc.; conversely, if the maximum height data of the obstacle is less than or equal to the preset height data threshold, the current movement direction can be maintained and continue to move forward, that is, continue to move forward after pressing over the obstacle.

[0098] According to the scenario parameter adjustment method provided by the embodiments of the present invention, when the sweeping robot detects an obstacle at a preset distance position, it determines whether the sweeping robot maintains the current movement direction and presses over the target obstacle to continue moving forward or changes the movement direction to avoid the obstacle by whether the height data of the target obstacle determined by the current point cloud data reaches the height data threshold, thereby improving the obstacle avoidance flexibility and movement intelligence of the sweeping robot.

[0099] It can be understood that if the sweeping robot determines that there is no obstacle at a preset distance position ahead based on the current point cloud data, it can continue to move forward. Based on this, after detecting obstacles at the preset distance position, the method of the present invention can further include:

[0100] Based on the failed result of obstacle detection, continue to move based on the current movement direction.

[0101] It can be understood that when the height of the sweeping robot placed on the ground is pre-calibrated to 0 and the height information reflected by the current point cloud data is also 0, it can be considered that there is no obstacle at a preset distance position ahead. And even if the number of current point cloud data is multiple, the multiple current point cloud data are also generated based on the corresponding infrared beams hitting the floor tiles in real time. At this time, it can be considered that the sweeping robot is moving in a spacious and obstacle-free area, without adjusting the current movement direction, and can continue to move based on the current movement direction.

[0102] According to the scene parameter adjustment method provided by the present invention, when the sweeping robot determines that there is no obstacle at the preset distance position based on historical image information, it continues to move based on the current moving direction, achieving the purpose that the sweeping robot determines that there is no obstacle in front based on the previous frame of image information and continues to move forward, improving the reliability and accuracy of the sweeping robot moving in the current scene.

[0103] It can be understood that when the current scene recognition result indicates that the sweeping robot is currently in a light-colored floor tile scene, if there is an obstacle at the preset distance position, as the sweeping robot continues to move forward, the infrared beam will also continuously hit the obstacle. At this time, it can be judged whether the color of the obstacle is a dark color based on the image information generated by hitting the obstacle. If it is recognized that the color of the obstacle is a dark color, less point cloud data will also be recognized and determined; conversely, if it is recognized that the color of the obstacle is a light color, more point cloud data will be recognized and determined. And whether to perform an obstacle avoidance operation requires further judging the height data of the obstacle based on the acquired point cloud data. The process of judging whether to avoid obstacles based on the height data can be mutually referred to with the foregoing embodiments and will not be elaborated here.

[0104] The scene parameter adjustment device provided by the present invention will be described below. The scene parameter adjustment device described below can be mutually referred to with the scene parameter adjustment method described above.

[0105] Refer to Figure 4 , which is a schematic structural diagram of the scene parameter adjustment device provided by the present invention. As Figure 4 shown, the scene parameter adjustment device 400 includes:

[0106] An acquisition module 410, configured to acquire historical image information of a preset distance position;

[0107] An identification module 420, configured to identify the historical image information to determine the current scene recognition result of the current ground decoration scene;

[0108] An adjustment module 430, configured to perform power adjustment based on the current scene recognition result.

[0109] It can be understood that the identification module 420 can specifically be configured to perform gray-scale identification on the historical image information to determine the target gray-scale value of the historical image information; based on the target gray-scale value and a preset gray-scale threshold, determine the current scene recognition result of the current ground decoration scene.

[0110] It can be understood that the recognition module 420 can specifically also be used to perform point cloud recognition on historical image information to determine the current point cloud data distributed in the current ground decoration scene; and based on the current point cloud data and a preset point cloud data threshold, determine the current scene recognition result of the current ground decoration scene.

[0111] It can be understood that the adjustment module 430 can specifically also be used to adjust the moving speed based on the current scene recognition result.

[0112] It can be understood that the device of the present invention can further include a detection module, which can specifically be used to perform obstacle detection on a preset distance position based on the current point cloud data.

[0113] It can be understood that the device of the present invention can further include a processing module, which can specifically be used to determine a moving direction strategy based on the successful detection result of the obstacle and the current point cloud data; and move based on the moving direction strategy.

[0114] It can be understood that the processing module can specifically also be used to determine the detected target obstacle based on the successful detection result of the obstacle; determine the height data of the target obstacle based on the current point cloud data; and determine the moving direction strategy based on the height data and a preset height data threshold, where the moving direction strategy includes one of adjusting the current moving direction and maintaining the current moving direction.

[0115] It can be understood that the processing module can specifically also be used to continue moving based on the current moving direction based on the failed detection result of the obstacle.

[0116] Figure 5 An example of the physical structure diagram of an electronic device is shown as Figure 5 shown. The electronic device 500 may include: a processor 510, a communications interface 520, a memory 530, and a communication bus 540. Among them, the processor 510, the communications interface 520, and the memory 530 communicate with each other through the communication bus 540. The processor 510 can call the logical instructions in the memory 530 to execute the following methods:

[0117] Obtain historical image information of a preset distance position;

[0118] Perform recognition on the historical image information to determine the current scene recognition result of the current ground decoration scene;

[0119] Perform power adjustment based on the current scene recognition result.

[0120] In addition, when the logical instructions in the above-mentioned memory 530 can be implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the related technology, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0121] On the other hand, an embodiment of the present invention discloses a computer program product. The computer program product includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the methods provided in the above-mentioned method embodiments. For example, it includes:

[0122] Obtain historical image information at a preset distance position;

[0123] Identify the historical image information to determine the current scene recognition result of the current ground decoration scene;

[0124] Perform power adjustment based on the current scene recognition result.

[0125] On another aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is implemented to execute the scene parameter adjustment method provided in the above-mentioned embodiments. For example, it includes:

[0126] Obtain historical image information at a preset distance position;

[0127] Identify the historical image information to determine the current scene recognition result of the current ground decoration scene;

[0128] Perform power adjustment based on the current scene recognition result.

[0129] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative work.

[0130] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution or the part that contributes to the related technology can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0131] Finally, it should be noted that the above embodiments are only used to illustrate the present invention, rather than to limit the present invention. Although the present invention has been described in detail with reference to the embodiments, those of ordinary skill in the art should understand that various combinations, modifications or equivalent replacements of the technical solutions of the present invention do not depart from the spirit and scope of the technical solutions of the present invention, and should all be covered by the scope of the claims of the present invention.

Claims

1. A method for adjusting scene parameters, characterized in that Including: Obtain historical image information at a preset distance position; the historical image information is the previous frame image information of the current image information; Identify the historical image information to determine the current scene recognition result of the current ground decoration scene; Perform power adjustment based on the current scene recognition result; The performing power adjustment based on the current scene recognition result includes: When it is determined that the current scene recognition result is a dark-colored floor tile scene, perform power adjustment to ensure that enough point cloud data can be generated when obtaining image information again.

2. The method for adjusting scenario parameters according to claim 1, wherein The identifying the historical image information to determine the current scene recognition result of the current ground decoration scene includes: Perform grayscale identification on the historical image information to determine the target grayscale value of the historical image information; Based on the target grayscale value and a preset grayscale threshold, determine the current scene recognition result of the current ground decoration scene.

3. The method for adjusting scene parameters according to claim 1, wherein After determining the current scene recognition result of the current ground decoration scene, the method further includes: Perform moving speed adjustment based on the current scene recognition result.

4. The method for adjusting scene parameters according to claim 1, characterized in that, The identifying the historical image information to determine the current scene recognition result of the current ground decoration scene includes: Perform point cloud identification on the historical image information to determine the current point cloud data distributed in the current ground decoration scene; Based on the current point cloud data and a preset point cloud data threshold, determine the current scene recognition result of the current ground decoration scene.

5. The method for adjusting scenario parameters according to claim 4, wherein After determining the current point cloud data distributed in the current ground decoration scene, the method further includes: Perform obstacle detection for the preset distance position based on the current point cloud data.

6. The method for adjusting scene parameters according to claim 5, wherein After performing obstacle detection for the preset distance position, the method further includes: Based on the detection success result of the obstacle and the current point cloud data, determine a moving direction strategy; Move based on the moving direction strategy.

7. The method for adjusting scene parameters according to claim 6, wherein The determining a moving direction strategy based on the detection success result of the obstacle and the current point cloud data includes: Based on the detection success result of the obstacle, determine the detected target obstacle; Based on the current point cloud data, determine the height data of the target obstacle; Based on the height data and a preset height data threshold, determine a moving direction strategy, and the moving direction strategy includes one of adjusting the current moving direction and maintaining the current moving direction.

8. The method for adjusting scene parameters according to claim 5, characterized in that, After performing obstacle detection for the preset distance position, the method further includes: Based on the detection failure result of the obstacle, continue to move in the current moving direction.

9. A scene parameter adjustment device, characterized in that, Including: An acquisition module, configured to obtain historical image information at a preset distance position; the historical image information is the previous frame image information of the current image information; An identification module, configured to identify the historical image information to determine the current scene recognition result of the current ground decoration scene; An adjustment module, configured to perform power adjustment based on the current scene recognition result; Specifically, the adjustment module is configured to: when it is determined that the current scene recognition result is a dark-colored floor tile scene, perform power adjustment to ensure that enough point cloud data can be generated when obtaining image information again.

10. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the scenario parameter adjustment method according to any one of claims 1 to 8.

11. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the scenario parameter adjustment method according to any one of claims 1 to 8.

12. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the scenario parameter adjustment method according to any one of claims 1 to 8.

Images