阅读说明：本技术 防疫消毒清洁机器人消毒清洁作业效果检测方法及装置 (Method and device for detecting disinfection and cleaning operation effect of epidemic prevention disinfection and cleaning robot ) 是由 李亮 张斌 张岁寒 景斌 陈凯 廖国勇 于 2020-04-15 设计创作，主要内容包括：本发明公开了一种防疫消毒清洁机器人消毒清洁作业效果检测方法及装置,所述方法包括步骤：分别获取并保存机器人沿预设的规划行驶路径进行清扫前、后的地面未清洁图像和已清洁图像；对所述未清洁图像和已清洁图像进行比对；当对比不合格时,控制机器人先沿预设的规划行驶路径后退至需二次消毒清洁区域,再沿规划行驶路径前行进行再次消毒清洁；重复前述步骤,直到完成所有区域作业且清洁效果达标。本发明不会增加洗地机没有必要的运动距离,提高了洗地机工作效率、大幅缩短洗地机行走距离,减少了能源浪费。(The invention discloses a method and a device for detecting the disinfection and cleaning operation effect of an epidemic prevention disinfection and cleaning robot, wherein the method comprises the following steps: respectively acquiring and storing an uncleaned image and a cleaned image of the ground before and after the robot cleans along a preset planning driving path; comparing the uncleaned image and the cleaned image; when the comparison is unqualified, the robot is controlled to retreat to an area needing secondary disinfection and cleaning along a preset planning driving path, and then moves forward along the planning driving path to carry out secondary disinfection and cleaning; and repeating the steps until all the area operations are completed and the cleaning effect reaches the standard. The invention can not increase the unnecessary movement distance of the floor cleaning machine, improves the working efficiency of the floor cleaning machine, greatly shortens the walking distance of the floor cleaning machine and reduces the energy waste.)

1. A method for detecting the disinfection and cleaning operation effect of an epidemic prevention disinfection and cleaning robot is characterized by comprising the following steps:

respectively acquiring and storing an uncleaned image and a cleaned image of the ground before and after the robot cleans along a preset planning driving path;

comparing the uncleaned image and the cleaned image;

when the comparison is unqualified, the robot is controlled to retreat to an area needing secondary disinfection and cleaning along a preset planning driving path, and then moves forward along the planning driving path to carry out secondary disinfection and cleaning;

and repeating the steps until all the area operations are completed and the cleaning effect reaches the standard.

2. The method for detecting the effect of the disinfection and cleaning operation of the epidemic prevention disinfection and cleaning robot as claimed in claim 1,

the floor unclean image and the cleaned image are RGB images and are acquired separately by a depth camera.

3. The method for detecting the effect of the disinfecting and cleaning operation of the epidemic prevention disinfecting and cleaning robot as claimed in claim 1, wherein before comparing the uncleaned image with the cleaned image, the method further comprises the steps of:

and preprocessing the uncleaned image and the cleaned image to obtain related characteristic parameters of the soil on the ground before and after cleaning, wherein the related characteristic parameters of the soil on the ground comprise a brightness parameter, a soil area and the number.

4. The method for detecting the effect of the disinfection and cleaning operation of the epidemic prevention disinfection and cleaning robot as claimed in claim 3, wherein said brightness parameter is obtained by the steps of:

respectively converting the uncleaned image and the cleaned image into gray level images;

and calculating the difference of deviation 128 of each pixel point of the gray-scale image, then summing and averaging the whole image, and recording the result as P to obtain the brightness parameters of the uncleaned image and the cleaned image.

5. The method for detecting the effect of the disinfecting and cleaning operation of the epidemic prevention disinfecting and cleaning robot as claimed in claim 3, wherein the area and the number of the stains are obtained by the following steps:

constructing a cascade self-coding structure to carry out positioning segmentation on stains in the uncleaned image and the cleaned image based on an FCN semantic segmentation network;

classifying the divided stains by using a Convolutional Neural Network (CNN), and calculating the area of the stains through the minimum convex hull area;

and marking the divided stains and counting to obtain the number of the stains.

6. The method for detecting the effects of the disinfection and cleaning operation of the epidemic prevention disinfection and cleaning robot as claimed in any one of claims 3 to 5, wherein comparing the uncleaned image and the cleaned image specifically comprises the steps of:

comparing the brightness parameters, stain area and number of the uncleaned image and the cleaned image;

and when the stain quantity and the area of the cleaned image are larger than those of the uncleaned image and/or the brightness parameter of the cleaned image is smaller than that of the uncleaned image, judging that the cleaning effect is unqualified.

7. The method for detecting the effect of the disinfection and cleaning operation of the epidemic prevention disinfection and cleaning robot as claimed in claim 1,

and when the comparison is unqualified, the robot is controlled to decelerate along a preset planned driving path and retreat to the area needing secondary disinfection and cleaning, and then the ground washing power of the robot is increased and/or the robot moves forwards at a low speed along the planned driving path to disinfect and clean the area needing secondary disinfection and cleaning again.

8. The utility model provides an epidemic prevention disinfection cleaning machines people disinfection cleaning operation effect detection device which characterized in that includes:

the image acquisition module is used for respectively acquiring and storing an uncleaned image and a cleaned image of the ground before and after cleaning when the robot travels along a preset planning travel path through the depth camera;

the image comparison module is used for comparing the uncleaned image with the cleaned image;

and the control module is used for controlling the robot to retreat to an area needing secondary disinfection and cleaning along a preset planning driving path and then move forward along the planning driving path to disinfect and clean again when the comparison is unqualified.

9. A storage medium including a stored program, characterized in that, when the program is executed, the program controls a device on which the storage medium is located to execute the method for detecting the effect of the disinfection and cleaning operation of the epidemic prevention disinfection and cleaning robot as claimed in any one of claims 1 to 7.

10. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the method for detecting the effect of the disinfection and cleaning operation of the robot according to any one of claims 1 to 7 when executing the program.

Technical Field

The invention relates to the field of environment-friendly robots, in particular to a method and a device for detecting the disinfection and cleaning operation effect of an epidemic prevention disinfection and cleaning robot.

Background

When the floor cleaning and floor sucking operation is carried out on the ground through the floor washing machine, because the operation parameters are uniformly set in advance, an area which is difficult to reach the standard after one-time cleaning can occur when the floor which is difficult to clean is faced, and at the moment, the area needs to be judged and cleaned for the second time. The existing automatic intelligent floor washing machine in the market needs to perform path planning on a place for secondary washing after judging the floor washing effect, the existing path planning method is used for path planning, namely, all ground images in one area are compared with a washing standard image and then path planning is performed again, and if unqualified ground images are far away, the problems of low operation efficiency, time waste, energy waste and the like caused by replanning and washing after counting all unqualified areas are solved.

Disclosure of Invention

The invention provides a method for detecting the disinfection and cleaning operation effect of an epidemic prevention disinfection and cleaning robot, aiming at solving the technical problems of low efficiency, time waste and energy waste when secondary cleaning is carried out due to poor ground washing effect of the existing ground washing machine.

The technical scheme adopted by the invention is as follows:

a method for detecting the disinfection and cleaning operation effect of an epidemic prevention disinfection and cleaning robot comprises the following steps:

respectively acquiring and storing an uncleaned image and a cleaned image of the ground before and after the robot cleans along a preset planning driving path;

comparing the uncleaned image and the cleaned image;

when the comparison is unqualified, the robot is controlled to retreat to an area needing secondary disinfection and cleaning along a preset planning driving path, and then moves forward along the planning driving path to carry out secondary disinfection and cleaning;

and repeating the steps until all the area operations are completed and the cleaning effect reaches the standard.

Further, the floor unclean image and the cleaned image are RGB images and are acquired separately by a depth camera.

Further, before comparing the unclean image and the cleaned image, the method further comprises the following steps:

and preprocessing the uncleaned image and the cleaned image to obtain related characteristic parameters of the soil on the ground before and after cleaning, wherein the related characteristic parameters of the soil on the ground comprise a brightness parameter, a soil area and the number.

Further, the brightness parameter is obtained by:

respectively converting the uncleaned image and the cleaned image into gray level images;

and calculating the difference of deviation 128 of each pixel point of the gray-scale image, then summing and averaging the whole image, and recording the result as P to obtain the brightness parameters of the uncleaned image and the cleaned image.

Further, the stain area and amount are obtained by:

constructing a cascade self-coding structure to carry out positioning segmentation on stains in the uncleaned image and the cleaned image based on an FCN semantic segmentation network;

classifying the divided stains by using a Convolutional Neural Network (CNN), and calculating the area of the stains through the minimum convex hull area;

and marking the divided stains and counting to obtain the number of the stains.

Further, comparing the uncleaned image and the cleaned image specifically comprises the steps of:

comparing the brightness parameters, stain area and number of the uncleaned image and the cleaned image;

when the number and area of stains in the cleaned image is greater than the number and area of stains in the uncleaned image,

and/or when the brightness parameter of the cleaned image is smaller than that of the uncleaned image, judging that the cleaning effect is unqualified.

Further, when the comparison is unqualified, the robot is controlled to decelerate along a preset planned driving path and retreat to the area needing secondary disinfection and cleaning, and then the ground washing power of the robot is increased and/or the robot moves forwards at a low speed along the planned driving path to disinfect and clean the area needing secondary disinfection and cleaning again.

In another aspect, the present invention provides an apparatus for detecting the effect of a disinfection and cleaning operation of an epidemic prevention disinfection and cleaning robot, comprising:

the image acquisition module is used for respectively acquiring and storing an uncleaned image and a cleaned image of the ground before and after cleaning when the robot travels along a preset planning travel path through the depth camera;

the image comparison module is used for comparing the uncleaned image with the cleaned image;

and the control module is used for controlling the robot to retreat to an area needing secondary disinfection and cleaning along a preset planning driving path and then move forward along the planning driving path to disinfect and clean again when the comparison is unqualified.

The invention also provides a storage medium which comprises a stored program, and when the program runs, the device where the storage medium is located is controlled to execute the method for detecting the effect of the disinfection and cleaning operation of the epidemic prevention disinfection and cleaning robot.

The invention also provides electronic equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the program to realize the method for detecting the disinfection and cleaning operation effect of the epidemic prevention disinfection and cleaning robot.

The invention has the following beneficial effects:

the invention judges the area with qualified floor washing by comparing the uncleaned image and the cleaned image of the ground before and after cleaning, and simultaneously, after the area with unqualified floor washing is detected, the floor washing machine can immediately back up to the area with qualified floor washing without cleaning and then cleans the area again until the area is clean.

In addition to the objects, features and advantages described above, other objects, features and advantages of the present invention are also provided. The present invention will be described in further detail below with reference to the accompanying drawings.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the invention and, together with the description, serve to explain the invention and not to limit the invention. In the drawings:

fig. 1 is a schematic flow chart of a method for detecting the disinfection and cleaning operation effect of an epidemic prevention disinfection and cleaning robot in the preferred embodiment of the invention.

Fig. 2 is a schematic front view of the epidemic prevention disinfection cleaning robot.

Fig. 3 is a schematic composition diagram of the unmanned system of the epidemic prevention disinfection cleaning robot.

Fig. 4 is a flow chart illustrating a luminance parameter calculation process according to a preferred embodiment of the present invention.

FIG. 5 is a schematic view of the process for determining the area and amount of soil according to the preferred embodiment of the present invention.

Fig. 6 is a schematic view of a cleaning effect determination flow in the preferred embodiment of the present invention.

Fig. 7 is a schematic view of an effect detection device for the disinfection and cleaning operation of the epidemic prevention disinfection and cleaning robot in the preferred embodiment of the invention.

In the figure: 1. a brush disc assembly; 2. a hub motor; 3. a steering device; 4. a water absorption assembly; 5. a brush disc push rod; 6. a water absorption pushing rod; 7. a traveling wheel; 8. a walking machine body; 9. a spray disinfection device; 10. a steering wheel; 11. an unmanned system; 12. a water tank assembly; 13. an electrical control system; 14. a front lower ultrasonic sensor; 15. a solid-state area array radar; 16. a single line laser radar; 17. front upper ultrasonic radar; 18. a front depth camera; 19. a side ultrasonic sensor; 20. an inertial measurement unit; 21. a multiline laser radar; 22. a rear depth camera; 23. a rear ultrasonic sensor; 24. and an industrial personal computer.

Detailed Description

It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.

Referring to fig. 1, a preferred embodiment of the present invention provides a method for detecting the effect of a disinfection and cleaning operation of an epidemic prevention disinfection and cleaning robot, comprising the steps of:

s1, respectively acquiring and storing an uncleaned image and a cleaned image of the ground before and after the robot cleans along a preset planning driving path;

s2, comparing the uncleaned image with the cleaned image;

s3, when the comparison is unqualified, controlling the robot to retreat to an area needing secondary disinfection and cleaning along a preset planning driving path, and then to advance along the planning driving path for secondary disinfection and cleaning;

and S4, repeating the steps until all the area operations are completed and the cleaning effect reaches the standard.

The embodiment can be applied to a plurality of sweeper with automatic walking, such as the epidemic prevention disinfection and cleaning robot shown in fig. 3 and 4, which integrates disinfection and cleaning and sweeping, and comprises a walking machine body 8, a water tank assembly 12, a brush disc assembly 1, a water absorption assembly 4, a spray disinfection device 9, an unmanned system 11 and an electrical control system 13.

The bottom of walking organism 8 is provided with walking wheel 7, and the top is provided with the steering wheel 10 that is used for manual driving, wherein, is located walking wheel 7 of walking organism 8 front end through turn to device 3 with walking organism 8 is connected, is convenient for turn to, is located walking wheel 7 of walking organism 8 rear end then only provides power, does not possess and turns to the function. The walking wheel 7 is provided with the wheel hub motor 2 which is driven by electric energy provided by a lithium battery to rotate a wheel body, the detection method for the disinfection and cleaning operation effect of the epidemic prevention disinfection and cleaning robot takes the lithium battery as power energy, the epidemic prevention disinfection and cleaning robot is driven to walk by the wheel hub motor 2, the wheel hub motor 2 and the walking wheel 7 are integrally installed, the structure of the robot can be effectively simplified, and the structure of the robot is more compact and reliable.

The water tank assembly 12 is fixedly arranged on the walking machine body 8 and is used for containing a disinfection solution for operation and sweeping waste water, on one hand, the water tank assembly 12 provides the prepared disinfection solution, and on the other hand, a user can collect the sweeping waste water in a sealing manner, so that secondary pollution of the waste water generated by the robot sweeping operation to the environment is prevented;

the brush disc assembly 1 is movably arranged at the front end of the walking machine body 8 and mainly cleans the ground in a rotating mode.

The assembly 4 activity of absorbing water sets up 8 bottoms of walking organism just are located brush dish assembly 1 rear for collect waste water of sweeping the floor and carry extremely water tank assembly 12, the robot is at the operation in-process of walking, brush dish assembly 1 rotates according to the settlement speed and sprays the disinfection solution that mixes, cleans and disinfects ground, and the sewage after cleaning is then through being located brush dish assembly 1 rear absorb water assembly 4 collect the back and carry extremely carry out subsequent innocent treatment in the sewage collection of water tank assembly 12.

The spray disinfection device 9 is arranged on the water tank assembly 12 and connected with disinfection solution in the water tank assembly 12, and is used for spraying disinfection on the surface of a specified object according to a set time length, wherein the surface of the specified object is specifically a part which is frequently contacted by a human body in an operation area, and comprises object surfaces which are easily touched by the human body, such as a seat, a door handle, a handrail and the like.

The electric control system 13 is electrically connected with the walking machine body 8, the water tank assembly 12, the brush disc assembly 1, the water absorption assembly 4, the spray disinfection device 9 and the unmanned system 11 respectively, and is used for controlling the action of each part of executive elements according to manual operation or a driving strategy of the unmanned system 11.

The unmanned system 11 comprises a sensing layer and a decision layer, the sensing layer performs map construction, positioning, navigation and obstacle avoidance after correcting relevant errors through data fusion of sensors, and the decision layer comprises an industrial personal computer 24.

Wherein, the perception layer specifically includes:

the multi-line laser radar 21 is arranged at the upper end of the walking machine body 8, is electrically connected with the industrial personal computer 24 through an Ethernet interface, and is used for constructing a map, positioning and navigating;

the front lower ultrasonic sensor 14, the front upper ultrasonic radar 17, the side ultrasonic sensor 19 and the rear ultrasonic sensor 23 are respectively arranged at the front lower end, the front upper end, the two side edges and the rear end of the walking machine body 8, are electrically connected with the industrial personal computer 24 through RS485 interfaces and are used for avoiding obstacles on the front, the back, the left and the right of the robot;

the single-line laser radar 16 is arranged at the front end of the walking machine body 8, is electrically connected with the industrial personal computer 24 through an Ethernet interface, and is used for constructing a map, positioning and avoiding barriers;

the solid-state area array radar 15 is arranged at the front end of the walking machine body 8, is electrically connected with the industrial personal computer 24 through an Ethernet interface, and is used for obstacle avoidance and ground cliff detection;

the inertial measurement unit 20 is electrically connected with the industrial personal computer 24 through an RS232 interface, and is used for correcting positioning and navigation by combining the multi-line laser radar 21 and the single-line laser radar 16;

the front depth camera 18 and the rear depth camera 22 are both made of realsent 435 cameras, are respectively arranged at the front end and the rear end of the walking machine body 8, are electrically connected with the industrial personal computer 24 through a USB interface, and can be used for identifying objects and avoiding obstacles through machine vision.

The decision layer comprises an industrial personal computer 24 which is electrically connected with each sensor of the sensing layer respectively and used for planning a path and controlling a process according to known position information constructed by each sensor of the sensing layer, and planning a traveling path, a speed and an obstacle avoidance mode of the robot.

The walking machine body 8 is provided with a brush disc push rod 5 which is connected with the brush disc assembly 1 and is used for adjusting the operation position of the brush disc assembly 1; and the water absorption and shoving push rods 6 are connected with the water absorption assembly 4 and are used for adjusting the operation position of the water absorption and shoving in the water absorption assembly 4, each push rod is driven by a hydraulic or pneumatic system, the position adjustment of the brush disc push rod 5 and the water absorption and shoving push rod 6 can be realized, for example, the brush disc assembly 1 and the water absorption and shoving can be lifted by the push rods when the operation is carried out from a storage place to an operation area or in a transition area, or after the operation is finished, and the relative positions of the brush disc assembly 1 and the water absorption and the bottom surface can be adjusted by the push rods before or in the operation process, so that the requirements of washing and water absorption operation are met.

When the floor and corner areas are washed, disinfected and cleaned, the epidemic prevention disinfection and cleaning robot disinfection and cleaning operation effect detection method covers the working area according to a planned path of the unmanned system 11 to conduct autonomous navigation, walking and obstacle avoidance, simultaneously sprays mixed disinfection solution in all passing areas, the brushing disc assembly 1 cleans dirt and oil stain in the area, the water absorption assembly 4 absorbs the washed sewage and dirt into the sewage storage container to be stored until the sewage storage container is full, and the robot autonomously conducts disinfection and cleaning operation according to the planned path.

The detection method of the embodiment obtains the uncleaned ground image and the cleaned ground image through the front depth camera 18 and the rear depth camera 22, and the uncleaned ground image and the cleaned ground image are both RGB images.

According to the inspection method, after the uncleaned images and the cleaned images of the ground before and after the robot cleans along the preset planned driving path are obtained, the area qualified for floor cleaning is judged by comparing the uncleaned images and the cleaned images of the ground before and after cleaning, and meanwhile, after the area qualified for floor cleaning is detected, the floor cleaning machine can back up to the area qualified for floor cleaning to be cleaned again immediately and on the original road.

In another embodiment of the present invention, before comparing the unclean image and the cleaned image, the method further comprises the steps of:

and preprocessing the uncleaned image and the cleaned image to obtain related characteristic parameters of the soil on the ground before and after cleaning, wherein the related characteristic parameters of the soil on the ground comprise a brightness parameter, a soil area and the number.

In the embodiment, the brightness parameters, the stain areas and the number related to the stains on the ground before and after cleaning are obtained by preprocessing the uncleaned image and the cleaned image, so that comprehensive and reliable comparison factors are provided for the subsequent cleaning effect judgment, and necessary feasibility is provided for accurately identifying the stains.

As shown in fig. 4, in another embodiment of the present invention, the brightness parameter is obtained by:

s201, converting the uncleaned image and the cleaned image into gray level images respectively;

s202, calculating the difference of deviation 128 of each pixel point of the gray-scale image, then summing and averaging the whole image, recording the result as P, and obtaining the brightness parameters of the uncleaned image and the cleaned image.

In another embodiment of the present invention, as shown in fig. 5, the stain area and amount are obtained by the following steps:

s211, constructing a cascade self-coding structure to position and segment stains in the uncleaned image and the cleaned image based on an FCN semantic segmentation network;

s212, classifying the divided stains by using a Convolutional Neural Network (CNN), and calculating the area of the stains according to the minimum convex hull area;

and S213, marking the divided stains and counting to obtain the number of the stains.

In the embodiment, the stain in the image is segmented and positioned by using the deep learning semantic segmentation network, and then the detection area and the number of the stains are counted.

As shown in fig. 6, in another embodiment of the present invention, comparing the unclean image and the cleaned image specifically comprises the steps of:

s221, comparing the brightness parameters, the stain areas and the number of the uncleaned image and the cleaned image;

s222, judging that the cleaning effect is unqualified when the stain quantity and the area of the cleaned image are larger than those of the uncleaned image and/or the brightness parameter of the cleaned image is smaller than that of the uncleaned image.

The embodiment quantitatively judges whether the cleaning effect is qualified or not by comparing the brightness parameters of the cleaned image and the uncleaned image with the size relationship of the number and the area of stains, can reflect the difference and the cleaning effect before and after cleaning more truly and accurately, and can directly judge the cleaning effect only by the brightness parameter size relationship of the cleaned image and the uncleaned image. The cleaning effect can also be directly judged only by the relationship between the number of stains and the area size of the cleaned image and the uncleaned image, for example, when the brightness parameters are not convenient to distinguish on the ground due to the color, the material and the like. Or comprehensively judging the cleaning effect when the brightness parameter, the stain quantity and the area all meet the size relation. And due to the selection of multiple modes, the flexibility is improved, and meanwhile, the judgment accuracy is ensured.

In another possible embodiment of the invention, when the comparison is not qualified, the robot is controlled to decelerate along the preset planned driving path and then move back to the area needing secondary disinfection and cleaning, and then the ground washing power of the robot is increased and/or the robot moves forwards slowly along the planned driving path to disinfect and clean the area needing secondary disinfection and cleaning again.

In this embodiment, when it is determined that the cleaning effect of the ground is not good, the epidemic prevention disinfection cleaning robot is controlled by the unmanned system 11, and the robot is decelerated along a preset planned driving path and then slowly moves to an area to be disinfected and cleaned for the second time, and the slow movement is selected to effectively reduce the shaking of the robot and the solution inside the robot, so that the moving stability of the robot is ensured. After the area needing secondary disinfection and cleaning is reached, the epidemic prevention disinfection and cleaning robot can perform cleaning operation according to preset parameters, and considering that stains in the area needing secondary disinfection and cleaning cannot reach the standard during first disinfection and cleaning because the stains are difficult to clean, the embodiment adopts two modes to ensure that the stains can be thoroughly removed and reach the standard during secondary disinfection and cleaning, and the other mode is to increase the ground washing power of the robot, namely to increase the cleaning force and the cleaning strength of the brush disc assembly 1, so as to achieve the purpose of thoroughly removing the stains; in another mode, the walking speed of the robot is reduced, namely the cleaning time is prolonged, and the aim of thoroughly removing the stains can be fulfilled to a certain extent.

As shown in fig. 7, another embodiment of the present invention provides an effect detection device for a disinfection and cleaning operation of an epidemic prevention disinfection and cleaning robot, comprising:

the image acquisition module is used for respectively acquiring and storing an uncleaned image and a cleaned image of the ground before and after cleaning when the robot travels along a preset planning travel path through the depth camera;

the image comparison module is used for comparing the uncleaned image with the cleaned image;

and the control module is used for controlling the robot to retreat to an area needing secondary disinfection and cleaning along a preset planning driving path and then move forward along the initial planning driving path to carry out secondary disinfection and cleaning when the comparison is unqualified.

Another embodiment of the present invention provides a storage medium, which includes a stored program, wherein when the program runs, the device where the storage medium is located is controlled to execute the method for detecting the operation effect of the epidemic prevention disinfection and cleaning robot.

Another embodiment of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method for detecting the disinfection and cleaning operation effect of the epidemic prevention disinfection and cleaning robot when executing the program. In order to better support image processing, the processor in this embodiment selects an arm9 processor, and in addition, in order to realize accurate processing of images by a neural network, the processor further comprises two intelmovidia neural network acceleration bars for respectively processing uncleaned images and cleaned images acquired by two front and rear cameras. It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.

The functions of the method of the present embodiment, if implemented in the form of software functional units and sold or used as independent products, may be stored in one or more storage media readable by a computing device. Based on such understanding, part of the contribution of the embodiments of the present invention to the prior art or part of the technical solution may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computing device (which may be a personal computer, a server, a mobile computing device, a network device, or the like) to execute all or part of the steps of the method described in the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.