A garbage cleaning method, system and medium based on texture recognition

Abstract

The invention relates to a garbage cleaning method and system based on texture recognition and a medium. The method comprises the steps of obtaining a ground image of a target area; performing texture identification and image analysis on garbage in the ground image, and judging whether liquid garbage exists in the target area or not; determining a cleaning strategy of the target area according to whether liquid garbage exists in the target area or not; and cleaning the target area according to the cleaning strategy. On the basis of the short-wave infrared camera, the ground image can be collected in real time in the working process of the cleaning equipment, the cleaning strategy of the target area can be accurately determined and executed in combination with the texture recognition and image analysis technology, and compared with traditional intelligent cleaning equipment, the cleaning effect is better, the process is simple, and the execution efficiency is high.

Description

(19) State Intellectual Property Office (12) Invention Patent Application (10) Application Publication Number (43) Application Publication Date (21) Application Number 202511959306.4 (22) Application Date 2023.02.02 (62) Divisional Application Data 202310080243.X 2023.02.02 (71) Applicant: ZhuiMi Innovation Technology (Suzhou) Co., Ltd. Address: Units 1, 2, and 3, Building 8, No. 1688, Songwei Road, Guoxiang Street, Wuzhong Economic Development Zone, Suzhou City, Jiangsu Province, 215000 (72) Inventors: Ren Ping, Liang Heming, Yu Shunchang (74) Patent Agency: Beijing Runping Intellectual Property Agency Co., Ltd. 11283 Patent Attorney: Zheng Haitao (51) Int.Cl. A47L 11 / 24 (2006.01) A47L 11 / 40 (2006.01) G06V 20 / 10 (2022.01) G06V 10 / 54 (2022.01) G06V 10 / 22 (2022.01) (54) Invention Title: A Garbage Cleaning Method, System, and Medium Based on Texture Recognition (57) Abstract: This invention relates to a garbage cleaning method, system, and medium based on texture recognition. The method includes: acquiring a ground image of a target area; performing texture recognition and image analysis on the garbage in the ground image to determine whether liquid garbage exists in the target area; determining a cleaning strategy for the target area based on the presence of liquid garbage; and cleaning the target area according to the cleaning strategy. This invention is based on a short-wave infrared camera, which can acquire ground images in real time during the operation of the cleaning equipment. Combined with texture recognition and image analysis technology, it can accurately determine and execute the cleaning strategy for the target area. Compared with traditional intelligent cleaning equipment, the cleaning effect is better, the process is simple, and the execution efficiency is high. Claims 2 pages, Description 14 pages, Drawings 5 ​​pages, CN 121465443 A 2026.02.06 CN 1 21 46 54 43 A 1. A waste cleaning method based on texture recognition, used in a cleaning device, characterized in that the method includes: acquiring a ground image of a target area; performing texture recognition and image analysis on the waste in the ground image to determine whether liquid waste exists in the target area; determining a cleaning strategy for the target area based on the presence of liquid waste; and cleaning the target area according to the cleaning strategy. 2. The waste cleaning method based on texture recognition according to claim 1, characterized in that acquiring the ground image of the target area includes: acquiring the ground image of the target area using a short-wave infrared camera installed on the cleaning device. 3. The waste cleaning method based on texture recognition according to claim 2, characterized in that when the short-wave infrared camera...When set at the front end of the cleaning device, determining whether liquid waste exists in the target area includes: performing texture recognition on the waste in the front-end ground image to obtain a first waste texture result; performing image analysis based on the first waste texture result to determine whether liquid waste exists in the target area. 4. The waste cleaning method based on texture recognition according to claim 3, wherein determining the cleaning strategy of the target area based on whether liquid waste exists in the target area includes: when liquid waste exists in the target area, obtaining the location of the liquid waste based on the first waste texture result; obtaining the current cleaning mode of the cleaning device, and determining the cleaning strategy of the target area based on the current cleaning mode and the location of the liquid waste. 5. The waste cleaning method based on texture recognition according to claim 4, wherein determining the cleaning strategy of the target area based on the current cleaning mode and the location of the liquid waste includes: when the current cleaning mode is a mopping mode or a sweeping and mopping mode, performing a mopping operation on both the target area and the liquid waste present in the target area based on the location of the liquid waste; when the current cleaning mode is a sweeping mode, performing a sweeping operation on the target area, and performing an obstacle avoidance operation on the liquid waste present in the target area based on the location of the liquid waste. 6. The waste cleaning method based on texture recognition according to claim 1, characterized in that determining the cleaning strategy of the target area based on whether liquid waste exists in the target area includes: when there is no liquid waste in the target area, directly obtaining the current cleaning mode of the cleaning equipment, and determining the cleaning strategy of the target area based on the current cleaning mode. 7. The waste cleaning method based on texture recognition according to claim 6, characterized in that the current cleaning mode includes a mopping mode, a sweeping mode, and a sweeping-mopping mode; determining the cleaning strategy of the target area based on the current cleaning mode includes: when the current cleaning mode is a mopping mode, performing a mopping operation on the target area; when the current cleaning mode is a sweeping mode, performing a sweeping operation on the target area; when the current cleaning mode is the sweeping-mopping mode, performing both sweeping and mopping operations on the target area. 8. The waste cleaning method based on texture recognition according to claim 1, characterized in that before performing texture recognition and image analysis on the waste in the ground image, it includes: performing texture recognition and image analysis on the ground in the ground image to obtain the ground condition of the target area; and preprocessing the ground image based on the ground condition. 9. A texture recognition-based waste cleaning system for cleaning equipment, characterized in that the system comprises: an image acquisition module for acquiring a ground image of a target area; an image recognition module, communicatively connected to the image acquisition module, for performing texture recognition and image analysis on the waste in the ground image to determine whether liquid waste exists in the target area; andA cleaning control module, communicatively connected to the image recognition module, is used to determine the cleaning strategy for the target area based on whether liquid waste exists in the target area; and to clean the target area according to the cleaning strategy. 10. A computer storage medium, characterized in that the computer storage medium includes: at least one instruction, which, when executed, implements the steps of the method as claimed in any one of claims 1 to 8. Claims 2 / 2 Page 3 CN 121465443 A Waste Cleaning Method, System and Medium Based on Texture Recognition

[0001] This application is a divisional application of the invention patent with application number 202310080243.X, application date 2023-02-02, and invention title "Waste Cleaning Method, System, Medium and Cleaning Equipment Based on Texture Recognition". Technical Field

[0002] The present invention relates to the field of cleaning equipment, and particularly to a waste cleaning method, system and medium based on texture recognition. Background Art

[0003] With the development of science and technology, existing cleaning equipment is becoming increasingly intelligent. For example, since traditional cleaning equipment cannot autonomously sense garbage on the ground, cameras are installed on the cleaning equipment to take pictures and process images of the area to be cleaned in order to intelligently sense the garbage in that area.

[0004] However, in this type of cleaning equipment, it is usually necessary to detect and analyze the ground before vacuuming, and then detect and analyze the ground again after vacuuming is completed and the floor is mopped; the whole process is cumbersome, inefficient, and the control precision of the entire technical solution is insufficient, resulting in poor cleaning effect. Summary of the Invention

[0005] Therefore, the technical problem to be solved by the present invention is how to detect and analyze ground images in real time during the operation of the cleaning equipment, so as to intelligently determine the cleaning strategy of the target area, thereby improving the execution efficiency and cleaning effect of the cleaning equipment.

[0006] To solve the above technical problems, the present invention provides a waste cleaning method based on texture recognition, used in a cleaning device. The method includes: acquiring a ground image of a target area using a short-wave infrared camera installed on the cleaning device; performing texture recognition and image analysis on the waste in the ground image to obtain the waste situation in the target area; obtaining a cleaning strategy for the target area based on the waste situation; and cleaning the target area according to the cleaning strategy.

[0007] Optionally, the short-wave infrared camera is installed at the front end and / or rear end of the cleaning device.

[0008] Optionally, when the short-wave infrared camera is installed at the front end of the cleaning device, the target area is the front end area of ​​the cleaning device, and the ground image is the front end ground image of the cleaning device; the step of performing texture recognition and image analysis on the ground image to obtain the waste situation in the target area includes: performing texture recognition and image analysis on the front end ground image...The waste in the target area is subjected to texture recognition to obtain a first waste texture result; image analysis is performed based on the first waste texture result to determine whether liquid waste exists in the target area.

[0009] Optionally, the step of obtaining a cleaning strategy for the target area based on the waste situation includes: when liquid waste exists in the target area, obtaining the location of liquid waste based on the first waste texture result; obtaining the current cleaning mode of the cleaning equipment, and determining the cleaning strategy for the target area based on the current cleaning mode and the location of liquid waste.

[0010] Optionally, the current cleaning mode includes a mopping mode, a sweeping mode, and a sweeping-mopping mode; determining the cleaning strategy for the target area based on the current cleaning mode and the liquid debris location includes: when the current cleaning mode is the mopping mode or the sweeping-mopping mode, performing a mopping operation on the target area and the liquid debris present in the target area based on the liquid debris location; when the current cleaning mode is the sweeping mode, performing a sweeping operation on the target area, and performing an obstacle avoidance operation on the liquid debris present in the target area based on the liquid debris location.

[0011] Optionally, obtaining the cleaning strategy for the target area based on the debris situation further includes: when there is no liquid debris in the target area, directly obtaining the current cleaning mode of the cleaning device, and determining the cleaning strategy for the target area based on the current cleaning mode.

[0012] Optionally, the current cleaning mode includes a mopping mode, a sweeping mode, and a sweeping-mopping mode; determining the cleaning strategy for the target area based on the current cleaning mode includes: when the current cleaning mode is the mopping mode, performing a mopping operation on the target area; when the current cleaning mode is the sweeping mode, performing a sweeping operation on the target area; when the current cleaning mode is the sweeping-mopping mode, performing both sweeping and mopping operations on the target area.

[0013] Optionally, when the short-wave infrared camera is located at the rear end of the cleaning device, the target area is the rear end area of ​​the cleaning device and the rear end area has been cleaned at least once, and the ground image is the rear end ground image of the cleaning device; performing texture recognition and image analysis on the ground image to obtain the garbage situation in the target area includes: performing texture recognition on the garbage in the rear end ground image to obtain a second garbage texture result; performing image analysis based on the second garbage texture result to obtain the target garbage quantity in the target area; and calculating the cleanliness of the target area based on the target garbage quantity.

[0014] Optionally, obtaining the cleaning strategy for the target area based on the garbage situation includes: determining the...The system checks whether the cleanliness level exceeds a first preset threshold. When the cleanliness level exceeds the first preset threshold, it determines that the cleanliness level of the target area meets the requirements and completes the cleaning of the target area. When the cleanliness level does not exceed the first preset threshold, it obtains and stores the location of the target area. Based on the location of the target area, it performs a secondary cleaning operation on the target area.

[0015] Optionally, when the shortwave infrared cameras are respectively installed at the front and rear ends of the cleaning equipment, the target area includes the front and rear areas of the cleaning equipment, and the rear area has been cleaned at least once; the ground image includes the front and rear ground images of the cleaning equipment; the step of performing texture recognition and image analysis on the ground image to obtain the garbage situation in the target area includes: performing texture recognition on the garbage in the front ground image to obtain a third garbage texture result; and performing texture recognition on the garbage in the rear ground image to obtain a fourth garbage texture recognition result; performing image analysis based on the third garbage texture result to obtain a first garbage quantity in the front area of ​​the cleaning equipment; and calculating a first cleanliness level of the front area based on the first garbage quantity; performing image analysis based on the fourth garbage texture result to obtain a second garbage quantity in the rear area of ​​the cleaning equipment; and calculating a second cleanliness level of the rear area based on the second garbage quantity.

[0016] Optionally, obtaining the cleaning strategy for the target area based on the garbage situation includes: acquiring the current cleaning mode of the target area; determining whether the difference between the second cleanliness and the first cleanliness is greater than or equal to a second preset threshold; when the difference between the second cleanliness and the first cleanliness is greater than or equal to the second preset threshold, determining that the second cleanliness meets the requirements and completing the cleaning of the back-end area; and continuing to perform cleaning operations on the front-end area according to the current cleaning mode; when the difference between the second cleanliness and the first cleanliness is less than the second preset threshold, determining that the second cleanliness does not meet the requirements; and continuing to perform cleaning operations on both the front-end area and the back-end area according to the current cleaning mode. Specification 2 / 14 pages 5 CN 121465443 A

[0017] Optionally, before performing texture recognition and image analysis on the garbage in the ground image to obtain the garbage situation of the target area, the method further includes: performing texture recognition and image analysis on the ground in the ground image to obtain the ground situation of the target area; and preprocessing the ground image according to the ground situation.

[0018] Furthermore, the present invention also proposes a waste cleaning system based on texture recognition for use in cleaning equipment. The system includes: a parameter acquisition module, communicatively connected to the heating unit, for acquiring the operating parameters of the heating unit; and an image...An acquisition module is used to acquire a ground image of a target area using a short-wave infrared camera installed on the cleaning device; an image recognition module is communicatively connected to the image acquisition module and is used to perform texture recognition and image analysis on the garbage in the ground image to obtain the garbage situation in the target area; and a cleaning control module is communicatively connected to the image recognition module and is used to obtain a cleaning strategy for the target area based on the garbage situation; and to clean the target area according to the cleaning strategy.

[0019] Optionally, the short-wave infrared camera is installed at the front end and / or the rear end of the cleaning device.

[0020] Optionally, when the short-wave infrared camera is installed at the front end of the cleaning device, the target area is the front end area of ​​the cleaning device, and the ground image is the front end ground image of the cleaning device; the image recognition module is specifically used to: perform texture recognition on the garbage in the front end ground image to obtain a first garbage texture result; perform image analysis based on the first garbage texture result to determine whether liquid garbage exists in the target area.

[0021] Optionally, when the shortwave infrared camera is located at the rear end of the cleaning equipment, the target area is the rear end area of ​​the cleaning equipment and the rear end area has been cleaned at least once, and the ground image is the rear end ground image of the cleaning equipment; the image recognition module is specifically used for: performing texture recognition on the garbage in the rear end ground image to obtain a second garbage texture result; performing image analysis based on the second garbage texture result to obtain the target garbage quantity in the target area; and calculating the cleanliness of the target area based on the target garbage quantity.

[0022] Optionally, when the shortwave infrared cameras are respectively installed at the front and rear ends of the cleaning equipment, the target area includes the front and rear areas of the cleaning equipment, and the rear area has been cleaned at least once; the ground image includes the front ground image and the rear ground image of the cleaning equipment; the image recognition module is specifically used for: performing texture recognition on the garbage in the front ground image to obtain a third garbage texture result; and performing texture recognition on the garbage in the rear ground image to obtain a fourth garbage texture recognition result; performing image analysis based on the third garbage texture result to obtain a first garbage quantity in the front area of ​​the cleaning equipment; and calculating a first cleanliness level of the front area based on the first garbage quantity; performing image analysis based on the fourth garbage texture result to obtain a second garbage quantity in the rear area of ​​the cleaning equipment; and calculating a second cleanliness level of the rear area based on the second garbage quantity.

[0023] In addition, the present invention also proposes a computer storage medium, the computer storage medium including: at least one instruction, which, when the instruction is executed, implements the aforementioned method steps of the texture recognition-based garbage cleaning method.

[0024] In addition, the present invention also proposes a cleaning device, comprising: a device body; a short-wave infrared camera disposed on the device body; and the aforementioned texture recognition-based garbage cleaning system disposed on the device body and communicatively connected to the short-wave infrared camera, for: performing texture recognition and image analysis based on ground images of the target area collected by the short-wave infrared camera to obtain the garbage situation of the target area; obtaining a cleaning strategy for the target area based on the garbage situation; and cleaning the target area according to the cleaning strategy.

[0025] Optionally, it further comprises: a cleaning component disposed on the device body and communicatively connected to the texture recognition-based garbage cleaning system, for cleaning the target area under the control of the texture recognition-based garbage cleaning system.

[0026] Optionally, it further comprises: a power supply module disposed on the device body and electrically connected to both the short-wave infrared camera and the texture recognition-based garbage cleaning system, for supplying power to the short-wave infrared camera and the texture recognition-based garbage cleaning system respectively.

[0027] The technical solution provided by the present invention has the following advantages: The garbage cleaning method, system and medium based on texture recognition provided by the present invention, compared with ordinary cameras or lasers, can more effectively identify small-scale, transparent liquid and other types of garbage or stains, and collect images containing these types of garbage; by setting the short-wave infrared camera on the cleaning equipment, the ground image of the target area can be collected in real time at any working stage of the cleaning equipment; based on the texture recognition and image analysis of the ground image, small-scale dust, transparent liquid and other types of garbage or stains in the target area can be identified, and the garbage situation in the target area can be accurately grasped regardless of whether the cleaning equipment is in the vacuuming stage or the mopping stage; finally, the corresponding cleaning strategy is obtained and executed according to the accurate garbage situation, and the optimal cleaning effect can be obtained; The present invention is based on a short-wave infrared camera, which can collect ground images in real time during the working process of the cleaning equipment. Combined with texture recognition and image analysis technology, the cleaning strategy of the target area can be accurately determined and executed. Compared with traditional intelligent cleaning equipment, the cleaning effect is better, the process is simple and the execution efficiency is high.

[0028] Brief Description of the Drawings: In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0029] Figure 1 is a flowchart of a garbage cleaning method based on texture recognition in Embodiment 1 of the present invention;Figure 2 is a flowchart of texture recognition and image analysis of garbage in ground images in Embodiment 1 of the present invention; Figure 3 is a flowchart of obtaining a cleaning strategy for the target area based on the garbage situation in Embodiment 1 of the present invention; Figure 4 is a flowchart of texture recognition and image analysis of garbage in ground images in Embodiment 2 of the present invention; Figure 5 is a flowchart of obtaining a cleaning strategy for the target area based on the garbage situation in Embodiment 2 of the present invention; Figure 6 is a flowchart of obtaining a cleaning strategy for the target area based on the garbage situation in Embodiment 3 of the present invention; Figure 7 is a flowchart of obtaining a cleaning strategy for the target area based on the garbage situation in Embodiment 3 of the present invention; Figure 8 is a structural diagram of a garbage cleaning system based on texture recognition in Embodiment 4 of the present invention; Figure 9 is a structural diagram of another garbage cleaning system based on texture recognition in Embodiment 4 of the present invention; Figure 10 is a structural diagram of a cleaning device in Embodiment 4 of the present invention; Figure 11 is a structural diagram of another cleaning device in Embodiment 4 of the present invention. Detailed Description

[0030] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. The present invention will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present invention can be combined with each other as described on page 4 / 14 of the specification, CN 121465443 A.

[0031] It should be noted that the terms "first," "second," etc. in the specification, claims, and drawings of the present invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0032] In the present invention, unless otherwise stated, the directional terms such as "upper," "lower," "top," and "bottom" are generally used in relation to the direction shown in the drawings, or in relation to the component itself in the vertical, perpendicular, or gravitational direction; similarly, for ease of understanding and description, "inner" and "outer" refer to the inner and outer contours relative to the components themselves, but the above directional terms are not used to limit the present invention.

[0033] In the conventional technology, by installing a camera on the cleaning equipment to take pictures and process images of the area to be cleaned in order to intelligently sense the garbage in the area, the entire detection and analysis process of such cleaning equipment is cumbersome, has low execution efficiency, and poor cleaning effect. To solve the above-mentioned technical problems, the present invention proposes a waste cleaning method, system, and medium based on texture recognition.

[0034] The waste cleaning method, system, and medium based on texture recognition proposed in this invention can be applied to various cleaning equipment. In the following embodiments, the present invention is illustrated using a floor scrubber as an example.

[0035] Embodiment 1 As shown in Figure 1, this embodiment provides a waste cleaning method based on texture recognition for use in cleaning equipment. The method includes:S110: Obtain a ground image of the target area using a short-wave infrared camera installed on the cleaning equipment; S120: Perform texture recognition and image analysis on the garbage in the ground image to obtain the garbage situation in the target area; S130: Obtain a cleaning strategy for the target area based on the garbage situation; S140: Clean the target area according to the cleaning strategy.

[0036] Compared with ordinary cameras or lasers, short-wave infrared cameras can more effectively identify small-scale, transparent liquid, and other types of garbage or stains, and collect images containing these types of garbage. The garbage cleaning method based on texture recognition provided in this embodiment utilizes a short-wave infrared camera installed on the cleaning equipment to collect ground images of the target area in real time at any working stage of the cleaning equipment; based on texture recognition and image analysis of the ground image, small-scale dust, transparent liquid, and other types of garbage or stains in the target area can be identified. Whether the cleaning equipment is in the vacuuming stage or the mopping stage, the garbage situation in the target area can be accurately grasped; finally, the corresponding cleaning strategy is obtained and executed based on the accurate garbage situation to obtain the best cleaning effect.

[0037] This embodiment is based on a short-wave infrared camera, which can collect ground images in real time during the operation of the cleaning equipment. Combined with texture recognition and image analysis technology, it can accurately determine and execute the cleaning strategy for the target area. Compared with traditional intelligent cleaning equipment, the cleaning effect is better, the process is simple, and the execution efficiency is high.

[0038] In this embodiment, the short-wave infrared camera is set at the front end of the cleaning equipment.

[0039] Since the cleaning equipment cleans its front-end area according to its own movement trajectory, after the front-end area is cleaned, the front-end area will become the rear-end area of ​​the cleaning equipment; if the area still needs to be cleaned again, it will turn its direction, and at this time the rear-end area will become the new front-end area of ​​the cleaning equipment and be cleaned. By setting the short-wave infrared camera at the front end of the cleaning equipment, images of its front-end area can be collected in real time. Combined with texture recognition and image analysis methods, the garbage situation in the front-end area can be accurately identified, including small dust, transparent liquid and other stains in the front-end area, and then the corresponding cleaning strategy can be intelligently matched to optimize the cleaning effect.

[0040] Preferably, when the shortwave infrared camera is set at the front end of the cleaning equipment, the target area is the front end area of ​​the cleaning equipment, and the ground image is the front end ground image of the cleaning equipment; As shown in Figure 2, S120 includes: S121: performing texture recognition on the garbage in the front end ground image to obtain a first garbage texture result; S122: performing image analysis based on the first garbage texture result to determine whether liquid garbage exists in the target area.

[0041] In the above S120 step, the presence or absence of liquid garbage in the target area is taken as its corresponding garbage situation, so...The appropriate cleaning strategy is then matched based on the presence of liquid waste. In this embodiment, the specific methods for image texture recognition and image analysis based on the first waste texture result employ existing texture recognition and image analysis algorithms; specific details are not elaborated here.

[0042] Preferably, as shown in Figure 3, S130 includes: S131: When liquid waste exists in the target area, the location of the liquid waste is obtained based on the first waste texture result; S132: The current cleaning mode of the cleaning equipment is obtained, and the cleaning strategy for the target area is determined based on the current cleaning mode and the location of the liquid waste.

[0043] When liquid waste exists in the target area, since the cleaning equipment has different cleaning modes, the handling method of liquid waste differs under different cleaning modes. Therefore, when it is determined from the front-end ground image that liquid waste exists in the target area (specifically the front-end area), the location of the liquid waste (i.e., liquid waste location) is obtained again based on the first waste texture result, facilitating the subsequent execution of the corresponding cleaning strategy based on this location to achieve the optimal cleaning effect for the target area.

[0044] Specifically, in S132, the cleaning strategy for the target area is determined based on the current cleaning mode and the location of the liquid waste, including: S1321: When the current cleaning mode is mopping mode or sweeping and mopping mode, mopping operation is performed on the target area and the liquid waste present in the target area based on the location of the liquid waste; S1322: When the current cleaning mode is sweeping mode, sweeping operation is performed on the target area, and obstacle avoidance operation is performed on the liquid waste present in the target area based on the location of the liquid waste.

[0045] When the current cleaning mode is mopping mode or sweeping and mopping mode, the entire target area and liquid waste are mopped together directly according to the liquid waste location. This not only enables the cleaning of other types of waste (such as solid waste) in the target area according to the user's required working mode, but also enables the cleaning of liquid waste. This effectively avoids the problem of poor cleaning effect caused by the inability to accurately identify liquid waste in traditional technologies. When the current cleaning mode is sweeping mode, the target area is swept and the liquid waste is avoided. This enables the cleaning of the target area according to the user's required working mode, while avoiding the phenomenon of large-scale contamination of the target area by liquid waste due to sweeping operation. This effectively ensures the cleaning effect in sweeping mode.

[0046] Preferably, S130 further includes: S133: When there is no liquid waste in the target area, the current cleaning mode of the cleaning device is directly obtained, and the cleaning strategy of the target area is determined according to the current cleaning mode.

[0047] When there is no liquid waste in the target area, the target area can be cleaned directly according to the current cleaning mode, which can efficiently clean the entire target area.

[0048] Specifically, the current cleaning mode includes mopping mode, sweeping mode, and sweeping-mopping mode; in S133, the cleaning strategy for the target area is determined according to the current cleaning mode, including: when the current cleaning mode is mopping mode, mopping operation is performed on the target area; when the current cleaning mode is sweeping mode, sweeping operation is performed on the target area; when the current cleaning mode is the sweeping-mopping mode, sweeping and mopping operations are performed on the target area. Specification 6 / 14 page 9 CN 121465443 A

[0049] When the current cleaning mode is mopping mode, mopping operation is performed directly on the entire target area; similarly, when the current cleaning mode is sweeping mode, sweeping operation is performed directly on the entire target area; when the current cleaning mode is sweeping mode, sweeping and mopping operations are performed directly on the entire target area, thus intelligently realizing the cleaning of the entire target area.

[0050] Preferably, before S120, it further includes: performing texture recognition and image analysis on the ground in the ground image to obtain the ground condition of the target area; preprocessing the ground image according to the ground condition.

[0051] Compared with traditional cameras, shortwave infrared cameras have a good recognition effect on ground of different materials and obstacles on the ground. Therefore, based on the ground images collected by the shortwave infrared camera, texture recognition and image analysis of the ground can identify information such as the ground and obstacles in the target area (i.e., ground conditions). Before performing texture recognition and image analysis on the garbage in the ground image, preprocessing the ground image according to the ground conditions can improve the quality of the ground image, thereby improving the garbage recognition effect in subsequent texture recognition and image analysis of garbage, and thus obtaining more accurate ground conditions. The specific implementation method of texture recognition and image analysis of the ground in the ground image also adopts conventional methods in the field, which is understandable to those skilled in the art, and the specific details will not be elaborated here.

[0052] In optional embodiments, the preprocessing of the ground image includes, but is not limited to, filtering, binarization, neighborhood filling, and annotation. Filtering can denoise the image and eliminate useless information. Binarization or neighborhood filling can binarize the area identified as the ground based on the identified ground conditions, making it the background of the garbage in the ground image, thus avoiding interference between ground texture and garbage texture. Annotation can label obstacles in the identified ground conditions, thus avoiding interference between obstacle texture and garbage texture recognition.

[0053] It should be understood that in S140, the specific implementation method of the cleaning device executing the cleaning strategy to achieve cleaning of the target area is prior art in the art, and its specific details will not be elaborated here.

[0054] Embodiment Two This embodiment provides a garbage cleaning method based on texture recognition for use in a cleaning device. The method includes:S210: Obtain ground images of the target area using a short-wave infrared camera installed on the cleaning equipment; S220: Perform texture recognition and image analysis on the garbage in the ground images to obtain the garbage situation in the target area; S230: Obtain a cleaning strategy for the target area based on the garbage situation; S240: Clean the target area according to the cleaning strategy.

[0055] Similar to Embodiment 1, this embodiment is based on a short-wave infrared camera, which can collect ground images in real time during the operation of the cleaning equipment. Combined with texture recognition and image analysis technology, it can accurately determine and execute the cleaning strategy for the target area. Compared with traditional intelligent cleaning equipment, the cleaning effect is better, and the process is simple and efficient.

[0056] In this embodiment, the short-wave infrared camera is installed at the rear end of the cleaning equipment.

[0057] Based on the description in Embodiment 1, the rear end area of ​​the cleaning equipment is usually an area that has been cleaned at least once. Taking this area as the target area, the short-wave infrared camera can collect ground images of this area and perform texture recognition and image analysis, which can also optimize the cleaning effect and execution efficiency.

[0058] Preferably, when the shortwave infrared camera is set at the rear end of the cleaning equipment, the target area is the rear end area of ​​the cleaning equipment and the rear end area has been cleaned at least once, and the ground image is the rear end ground image of the cleaning equipment; As shown in Figure 4, S220 includes: S221: performing texture recognition on the garbage in the rear end ground image to obtain a second garbage texture result; Specification 7 / 14 pages 10 CN 121465443 A S222: performing image analysis based on the second garbage texture result to obtain the target garbage quantity in the target area; S223: calculating the cleanliness of the target area based on the target garbage quantity.

[0059] Based on the advantage of the shortwave infrared camera in recognizing small-sized dust and other garbage, by performing texture recognition and image analysis on the garbage in the rear end ground image, the garbage situation remaining in the rear end area after at least one cleaning (i.e., the target garbage quantity in the target area) can be identified, and thus the cleanliness of the target area can be grasped. This cleanliness can measure the cleaning effect of the target area after cleaning, and thus facilitates the matching of appropriate cleaning strategies based on the cleanliness.

[0060] In an optional embodiment, in S222, during the process of obtaining the target garbage quantity of the target area based on the second garbage texture result, the texture pixels identified as garbage can be counted to obtain the number of target garbage pixels (i.e., the target garbage quantity); of course, the area of ​​the texture area identified as garbage can also be calculated, and the area of ​​the area can be used as the target garbage quantity. In S223, the ratio of the target garbage pixel quantity to the total pixels of the ground image can be used as the cleanliness of the target area; the ratio of the texture area to the area of ​​the ground image can also be used as the cleanliness of the target area.

[0061] Preferably, as shown in FIG5, S230 includes:S231: Determine whether the cleanliness exceeds the first preset threshold; S232: When the cleanliness exceeds the first preset threshold, determine that the cleanliness of the target area meets the requirements, and complete the cleaning of the target area; S233: When the cleanliness does not exceed the first preset threshold, obtain and store the location of the target area; perform a second cleaning operation on the target area based on the location of the target area.

[0062] Through the above steps, it is possible to detect whether the cleaning of the target area meets the standard, and thus determine whether the target area needs to be cleaned again to achieve the best cleaning effect. The first preset threshold can be set and adjusted according to the actual situation, which is understandable to those skilled in the art.

[0063] In S233, when the target area needs to be cleaned twice, the front area of ​​the cleaning device is cleaned first according to the current cleaning mode. After the front area is cleaned, the cleaning device turns around and moves to the target area according to the target area positioning. The target area can then be cleaned according to the current cleaning mode, that is: when the current cleaning mode is mopping mode, mopping operation is performed on the target area; when the current cleaning mode is sweeping mode, sweeping operation is performed on the target area; when the current cleaning mode is the sweeping and mopping mode, sweeping and mopping operation are performed on the target area.

[0064] Preferably, before S220, the method further includes: performing texture recognition and image analysis on the ground in the ground image to obtain the ground condition of the target area; and preprocessing the ground image according to the ground condition.

[0065] Similar to S120 in Embodiment 1, texture recognition and image analysis are performed on the ground to identify information such as the ground and obstacles in the target area (i.e., ground conditions). Before performing texture recognition and image analysis on the garbage in the ground image, the ground image is preprocessed according to the ground conditions to improve the quality of the ground image. This can improve the garbage identification effect in subsequent texture recognition and image analysis of the garbage, and thus obtain more accurate ground conditions.

[0066] Embodiment 3 This embodiment provides a garbage cleaning method based on texture recognition for use in cleaning equipment. The method includes: S310: using a short-wave infrared camera installed on the cleaning equipment to acquire a ground image of the target area; S320: performing texture recognition and image analysis on the garbage in the ground image to obtain the garbage conditions of the target area; S330: obtaining a cleaning strategy for the target area based on the garbage conditions; S340: cleaning the target area according to the cleaning strategy.

[0067] Similar to Embodiments 1 and 2, this embodiment is based on a short-wave infrared camera, which can acquire ground images in real time during the operation of the cleaning equipment. Combined with texture recognition and image analysis technology, it can accurately determine the target area to be cleaned.The strategy is executed, resulting in better cleaning effect compared to traditional intelligent cleaning equipment, with a simpler process and higher execution efficiency.

[0068] In this embodiment, there are two short-wave infrared cameras, respectively set at the front and rear ends of the cleaning equipment.

[0069] Based on the descriptions of Embodiment 1 and Embodiment 2, the short-wave infrared camera at the front end of the cleaning equipment can better collect images of the ground to be cleaned in its front area and accurately identify the garbage situation in the front area; at the same time, the short-wave infrared camera at the rear end of the cleaning equipment can better collect images of the ground that has been cleaned at least once in its rear area and accurately identify the garbage situation in the rear area, so as to grasp the cleanliness level of the rear area after cleaning. With two short-wave infrared cameras, the garbage situation in the target area can be accurately grasped at any stage of the real-time operation of the cleaning equipment, so as to match a suitable cleaning strategy and achieve the best cleaning effect with the fastest execution efficiency.

[0070] Preferably, when the shortwave infrared cameras are respectively set at the front end and the rear end of the cleaning equipment, the target area includes the front end area and the rear end area of ​​the cleaning equipment, and the rear end area has been cleaned at least once; the ground image includes the front end ground image and the rear end ground image of the cleaning equipment; As shown in FIG6, S320 includes: S321: performing texture recognition on the garbage in the front end ground image to obtain a third garbage texture result; and performing texture recognition on the garbage in the rear end ground image to obtain a fourth garbage texture recognition result; S322: performing image analysis based on the third garbage texture result to obtain a first garbage quantity in the front end area of ​​the cleaning equipment; and calculating a first cleanliness level of the front end area based on the first garbage quantity; S323: performing image analysis based on the fourth garbage texture result to obtain a second garbage quantity in the rear end area of ​​the cleaning equipment; and calculating a second cleanliness level of the rear end area based on the second garbage quantity.

[0071] By performing texture recognition and image analysis on the front end ground image and the rear end ground image respectively, the corresponding cleanliness level (i.e., the first cleanliness level and the second cleanliness level) can be obtained. Based on the first cleanliness level and the second cleanliness level, it is convenient to intuitively match and execute appropriate cleaning strategies according to the data, which is highly efficient.

[0072] It should be understood that the execution order of S322 and S323 is not important. S322 can be executed first, followed by S323; or S323 can be executed first, followed by S322; or both steps can be performed simultaneously. The specific methods for obtaining the first and second quantities of garbage in S322 and S323 are the same as the method for obtaining the target quantity of garbage in S222 of Embodiment Two. The methods for calculating the first cleanliness based on the first quantity of garbage and the second cleanliness based on the second quantity of garbage are also the same as the method for calculating the cleanliness of the target area in S223 of Embodiment Two. Specific details will not be elaborated here.

[0073] Preferably, as shown in FIG7, S330 includes:S331: Obtain the current cleaning mode of the target area; S332: Determine whether the difference between the second cleanliness level and the first cleanliness level is greater than or equal to the second preset threshold; S333: When the difference between the second cleanliness level and the first cleanliness level is greater than or equal to the second preset threshold, determine that the second cleanliness level meets the requirements, and complete the cleaning of the back-end area; and continue to perform cleaning operations on the front-end area according to the current cleaning mode; S334: When the difference between the second cleanliness level and the first cleanliness level is less than the second preset threshold, determine that the second cleanliness level does not meet the requirements; and continue to perform cleaning operations on both the front-end area and the back-end area according to the current cleaning mode.

[0074] By comparing the difference between the second cleanliness and the first cleanliness with the second preset threshold, it can be determined whether the second cleanliness meets the requirements, and thus whether the cleaning work performed on the back-end area of ​​the cleaning equipment meets the standards. When the difference between the second cleanliness and the first cleanliness is greater than or equal to the first preset threshold, it indicates that the cleanliness of the back-end area has been greatly improved after cleaning, and its cleanliness (i.e., the second cleanliness) meets the requirements. No secondary cleaning is required, and only the cleaning operation on the front-end area needs to be performed according to the current cleaning mode. When the difference between the second cleanliness and the first cleanliness is less than the first preset threshold, it indicates that the cleanliness of the back-end area has not been improved compared with the front-end area (usually the area to be cleaned), and its cleanliness (i.e., the second cleanliness) does not meet the requirements. Secondary cleaning is still required, and the cleaning operation is performed on both the front-end area and the back-end area. The second preset threshold can be set and adjusted according to the actual situation.

[0075] Through the above steps, this embodiment can match appropriate cleaning strategies for the front-end and back-end areas based on the difference between the second cleanliness and the first cleanliness, so as to achieve the optimal cleaning effect for the entire target area.

[0076] It should be understood that step S331 can be performed before or after step S332, so that cleaning operations are performed according to the current cleaning mode in steps S333 and S334.

[0077] Specifically, in S333, during the process of continuing to perform cleaning operations on both the front-end and back-end areas according to the current cleaning mode, the cleaning operation is first performed on the front-end area according to the current cleaning mode. After the front-end area is cleaned, the body of the cleaning device is turned around, and the cleaning operation is performed on the back-end area according to the current cleaning mode. The specific process of performing cleaning operations according to the current cleaning mode is the same as step S133 in Embodiment 1, and the specific details will not be repeated here.

[0078] Preferably, before S320, the method further includes: performing texture recognition and image analysis on the ground in the ground image to obtain the ground condition of the target area; and preprocessing the ground image according to the ground condition.

[0079] Similar to S120 in Embodiment 1 and S220 in Embodiment 2, texture recognition and image analysis are performed on the ground to identify information such as the ground and obstacles in the target area (i.e., ground conditions). Before performing texture recognition and image analysis on the garbage in the ground image, the ground image is preprocessed according to the ground conditions to improve the quality of the ground image. This can improve the garbage identification effect in subsequent texture recognition and image analysis of the garbage, and thus obtain more accurate ground conditions.

[0080] Embodiment 4 is shown in Figure 8. This embodiment provides a garbage cleaning system based on texture recognition for cleaning equipment. The system includes: an image acquisition module for acquiring ground images of the target area using a short-wave infrared camera installed on the cleaning equipment; an image recognition module, which is communicatively connected to the image acquisition module, for performing texture recognition and image analysis on the garbage in the ground image to obtain the garbage conditions of the target area; and a cleaning control module, which is communicatively connected to the image recognition module, for obtaining a cleaning strategy for the target area according to the garbage conditions; and cleaning the target area according to the cleaning strategy.

[0081] The texture recognition-based garbage cleaning system provided in this embodiment, by setting the short-wave infrared camera on the cleaning equipment, can collect ground images of the target area in real time during any working stage of the cleaning equipment. The image acquisition module acquires these ground images, and the image recognition module performs texture recognition and image analysis on the ground images to identify small-scale dust, transparent liquid, and other types of garbage or stains in the target area. Whether the cleaning equipment is in the vacuuming or mopping stage, it can accurately grasp the garbage situation in the target area. Finally, the cleaning control module obtains the corresponding cleaning strategy based on the accurate garbage situation and executes it to achieve the best cleaning effect. Specification 10 / 14 pages 13 CN 121465443 A

[0082] This embodiment is based on a short-wave infrared camera, which can collect ground images in real time during the working process of the cleaning equipment. Combined with texture recognition and image analysis technology, it can accurately determine and execute the cleaning strategy of the target area. Compared with traditional intelligent cleaning equipment, the cleaning effect is better, the process is simple, and the execution efficiency is high.

[0083] Specifically, the short-wave infrared camera is set at the front end and / or the rear end of the cleaning equipment.

[0084] In a first optional embodiment, when the shortwave infrared camera is set at the front end of the cleaning equipment, the target area is the front end area of ​​the cleaning equipment, and the ground image is the front end ground image of the cleaning equipment; the image recognition module is specifically used to: perform texture recognition on the garbage in the front end ground image to obtain a first garbage texture result; perform image analysis based on the first garbage texture result to determine whether liquid garbage exists in the target area.

[0085] Preferably, the cleaning control module is specifically used to:When liquid waste is present in the target area, the liquid waste location is obtained based on the first waste texture result; the current cleaning mode of the cleaning device is obtained, and the cleaning strategy for the target area is determined based on the current cleaning mode and the liquid waste location; when there is no liquid waste in the target area, the current cleaning mode of the cleaning device is directly obtained, and the cleaning strategy for the target area is determined based on the current cleaning mode.

[0086] Specifically, the cleaning control module determines the cleaning strategy for the target area based on the current cleaning mode and the liquid waste location, including: when the current cleaning mode is mopping mode or sweeping and mopping mode, mopping operation is performed on the target area and the liquid waste present in the target area based on the liquid waste location; when the current cleaning mode is sweeping mode, sweeping operation is performed on the target area, and obstacle avoidance operation is performed on the liquid waste present in the target area based on the liquid waste location.

[0087] Specifically, the cleaning control module determines the cleaning strategy for the target area based on the current cleaning mode, including: when the current cleaning mode is mopping mode, performing mopping operation on the target area; when the current cleaning mode is sweeping mode, performing sweeping operation on the target area; when the current cleaning mode is the sweeping and mopping mode, performing sweeping and mopping operation on the target area.

[0088] In a second optional embodiment, when the short-wave infrared camera is set at the rear end of the cleaning device, the target area is the rear end area of ​​the cleaning device and the rear end area has been cleaned at least once, and the ground image is the rear end ground image of the cleaning device; the image recognition module is specifically used to: perform texture recognition on the garbage in the rear end ground image to obtain a second garbage texture result; perform image analysis based on the second garbage texture result to obtain the target garbage quantity in the target area; and calculate the cleanliness of the target area based on the target garbage quantity.

[0089] Preferably, the cleaning control module is specifically used to: determine whether the cleanliness exceeds a first preset threshold; when the cleanliness exceeds the first preset threshold, determine that the cleanliness of the target area meets the requirements and complete the cleaning of the target area; when the cleanliness does not exceed the first preset threshold, obtain the location of the target area and store it; and perform a second cleaning operation on the target area according to the location of the target area.

[0090] In the third optional embodiment, when the short-wave infrared cameras are respectively set at the front end and the rear end of the cleaning equipment, the target area includes the front end area and the rear end area of ​​the cleaning equipment, and the rear end area has been cleaned at least once; the ground image includes the front end ground image and the rear end ground image of the cleaning equipment; the image recognition module is specifically used to: perform texture recognition on the garbage in the front end ground image to obtain a third garbage texture result; and perform texture recognition on the garbage in the rear end ground image to obtain a fourth garbage texture recognition result; perform image analysis according to the third garbage texture result to obtain a first garbage count in the front end area of ​​the cleaning equipment.The system calculates the first cleanliness of the front-end area based on the first amount of garbage; performs image analysis based on the fourth garbage texture result to obtain the second amount of garbage in the back-end area of ​​the cleaning device; and calculates the second cleanliness of the back-end area based on the second amount of garbage.

[0091] Preferably, the cleaning control module is specifically used to: obtain the current cleaning mode of the target area; determine whether the difference between the second cleanliness and the first cleanliness is greater than or equal to a second preset threshold; when the difference between the second cleanliness and the first cleanliness is greater than or equal to the second preset threshold, determine that the second cleanliness meets the requirements, and complete the cleaning of the back-end area; and continue to perform cleaning operations on the front-end area according to the current cleaning mode; when the difference between the second cleanliness and the first cleanliness is less than the second preset threshold, determine that the second cleanliness does not meet the requirements; and continue to perform cleaning operations on both the front-end area and the back-end area according to the current cleaning mode.

[0092] Preferably, as shown in FIG9, the system further includes: an image preprocessing module, which is communicatively connected to the image acquisition module and the image recognition module, and is used to: perform texture recognition and image analysis on the ground in the ground image to obtain the ground condition of the target area; and preprocess the ground image according to the ground condition.

[0093] The functions of each module of the texture recognition-based garbage cleaning system described in this embodiment correspond to the steps of the texture recognition-based garbage cleaning methods in Embodiments 1 to 3. For details not covered in this embodiment, please refer to the specific descriptions of Embodiments 1 to 3 and Figures 1 to 7, which will not be repeated here.

[0094] Embodiment 5 This embodiment also provides a texture recognition-based garbage cleaning device, including a processor, a memory, and a computer program stored in the memory and run on the processor. When the computer program runs, it implements the method steps of the texture recognition-based garbage cleaning methods in Embodiments 1 to 3.

[0095] Through the computer program stored in the memory and running on the processor, based on a short-wave infrared camera, ground images can be collected in real time during the operation of the cleaning equipment. Combined with texture recognition and image analysis technology, the cleaning strategy of the target area can be accurately determined and executed. Compared with traditional intelligent cleaning equipment, the cleaning effect is better, the process is simple, and the execution efficiency is high.

[0096] The processor referred to may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), or field-programmable gate arrays (FPGAs).Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc. The processor is the control center of the computer device, connecting various parts of the entire computer device through various interfaces and lines.

[0097] The memory can be used to store computer programs and / or models. The processor realizes various functions of the computer device by running or executing the computer programs and / or models stored in the memory specification (pages 12 / 14, CN 121465443 A) and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area. The program storage area can store the operating system and at least one application program required for a function (e.g., sound playback function, image playback function, etc.); the data storage area can store data created according to the use of the mobile phone (e.g., audio data, video data, etc.). Furthermore, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0098] It should be understood that each block of the flowchart and / or block diagram, and combinations of blocks in the flowchart and / or block diagram, may be implemented by a computer program. These computer programs may be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that instructions executable by the processor of the computer or other programmable data processing apparatus create means for implementing the functions specified in one or more blocks of the flowchart and / or one or more blocks of the block diagram.

[0099] These computer programs may also be stored in a computer-readable storage medium capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0100] These computer programs may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions that execute on the computer or other programmable apparatus provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.

[0101] This embodiment also provides a computer storage medium, which includes at least one instruction that, when executed, implements the method steps of the texture recognition-based garbage cleaning method of Embodiments 1 to 3.

[0102] By executing the computer storage medium containing at least one instruction, ground images can be acquired in real time during the operation of the cleaning equipment based on a short-wave infrared camera. Combined with texture recognition and image analysis technology, the cleaning strategy for the target area can be accurately determined and executed. Compared with traditional intelligent cleaning equipment, the cleaning effect is better, and the process is simple and efficient.

[0103] Similarly, for details not covered in this embodiment, please refer to the specific descriptions of Embodiments 1 to 4 and Figures 1 to 9, which will not be repeated here.

[0104] As shown in Figure 10, this embodiment provides a cleaning device, including: a device body; a short-wave infrared camera mounted on the device body; and the aforementioned texture recognition-based garbage cleaning system mounted on the device body and communicatively connected to the short-wave infrared camera, used for: performing texture recognition and image analysis based on the ground image of the target area collected by the short-wave infrared camera to obtain the garbage situation of the target area; obtaining a cleaning strategy for the target area based on the garbage situation; and cleaning the target area according to the cleaning strategy.

[0105] The cleaning device provided in this embodiment, based on a short-wave infrared camera, can collect ground images in real time during operation. Combined with texture recognition and image analysis technology, it can accurately determine and execute the cleaning strategy for the target area. Compared with the traditional intelligent cleaning device (pages 13 / 14 of the manual, CN 121465443 A), the cleaning effect is better, the process is simpler, and the execution efficiency is higher.

[0106] Preferably, as shown in FIG11, it further includes: a cleaning component, disposed on the device body, and communicatively connected to the texture recognition-based waste cleaning system, for cleaning the target area under the control of the texture recognition-based waste cleaning system.

[0107] Specifically, the cleaning component in this embodiment includes at least a roller brush, a mopping component, and motors for driving the roller brush and the mopping component respectively; wherein, when the roller brush and its corresponding motor are running, a sweeping operation can be performed; when the mopping component and its corresponding motor are running, a mopping operation can be performed; when both the roller brush and its corresponding motor, and the mopping component and its corresponding motor are running, a sweeping and mopping operation can be performed.

[0108] Preferably, as shown in FIG11, it further includes: a power supply module, disposed on the device body, and electrically connected to both the short-wave infrared camera and the texture recognition-based waste cleaning system, for supplying power to the short-wave infrared camera and the texture recognition-based waste cleaning system respectively.

[0109] Specifically, the power supply unit in this embodiment can be either a battery (specifically a rechargeable battery) installed on the device body, or a power interface installed on the device body, through which a 220V AC mains power is connected.

[0110] The texture recognition-based garbage cleaning system in the cleaning equipment described in this embodiment has the same structure as the texture recognition-based garbage cleaning system in Embodiment 4. Details not covered in this embodiment can be found in the detailed descriptions of Embodiments 1 to 4 and Figures 1 to 9, and will not be repeated here.

[0111] Obviously, the embodiments described above are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, those skilled in the art can make other variations or modifications without creative effort, and all such variations should fall within the scope of protection of the present invention. Specification 14 / 14 Page 17 CN 121465443 A Figure 1 Figure 2 Figure 3 Specification Drawings 1 / 5 Page 18 CN 121465443 A Figure 4 Figure 5 Figure 6 Specification Drawings 2 / 5 Page 19 CN 121465443 A Figure 7 Figure 8 Specification Drawings 3 / 5 Page 20 CN 121465443 A Figure 9 Figure 10 Specification Drawings 4 / 5 Page 21 CN 121465443 A Figure 11 Specification Drawings 5 / 5 Page 22 CN 121465443 AA GARBAGE CLEANING METHOD, SYSTEM AND MEDIUM BASED ON TEXTURE RECOGNITION Abstract The present invention relates to a garbage cleaning method, system and medium based on texture recognition. The method comprises: acquiring a ground image of a target area; performing texture recognition and image analysis on garbage in the ground image to determine whether liquid garbage exists in the target area; determining a cleaning strategy for the target area. according to whether liquid garbage exists in the target area; and cleaning the target area according to thecleaning strategy. Based on a short-wave infrared camera, the present invention can collect ground images in real time during the operation of the cleaning device. Combined with texture recognition and image analysis technologies, the cleaning strategy for the target area can be accurately determined and implemented. Compared with traditional intelligent cleaning devices, the present invention has better cleaning effect, simpler process and high execution efficiency.

Claims

1. A waste cleaning method based on texture recognition, used in cleaning equipment, characterized in that, The method includes: Acquire ground images of the target area; Texture recognition and image analysis are performed on debris in ground images to determine whether liquid debris exists in the target area; A cleaning strategy for the target area is determined based on the presence of liquid waste; the target area is then cleaned according to the cleaning strategy.

2. The waste cleaning method based on texture recognition according to claim 1, characterized in that, The acquisition of ground images of the target area includes: acquiring ground images of the target area using a short-wave infrared camera installed on the cleaning equipment.

3. The waste cleaning method based on texture recognition according to claim 2, characterized in that, When a short-wave infrared camera is installed at the front end of the cleaning equipment, determining whether liquid waste exists in the target area includes: Texture recognition is performed on the garbage in the front-end ground image to obtain the first garbage texture result; Image analysis is performed based on the first garbage texture result to determine whether liquid garbage exists in the target area.

4. The waste cleaning method based on texture recognition according to claim 3, characterized in that, The process of determining the cleaning strategy for the target area based on the presence of liquid waste in the target area includes: When liquid debris is present in the target area, the location of the liquid debris is obtained based on the first debris texture result; Obtain the current cleaning mode of the cleaning equipment, and determine the cleaning strategy for the target area based on the current cleaning mode and the location of liquid waste.

5. The waste cleaning method based on texture recognition according to claim 4, characterized in that, The step of determining the cleaning strategy for the target area based on the current cleaning mode and the location of liquid waste includes: When the current cleaning mode is mopping mode or sweeping and mopping mode, mopping operation is performed on the target area and the liquid waste in the target area based on the location of liquid waste; When the current cleaning mode is sweeping mode, sweeping operation is performed on the target area, and obstacle avoidance operation is performed on the liquid waste in the target area based on the location of the liquid waste.

6. The waste cleaning method based on texture recognition according to claim 1, characterized in that, Determining the cleaning strategy for the target area based on the presence of liquid waste includes: When there is no liquid waste in the target area, the current cleaning mode of the cleaning equipment is directly obtained, and the cleaning strategy for the target area is determined based on the current cleaning mode.

7. The waste cleaning method based on texture recognition according to claim 6, characterized in that, Current cleaning modes include mopping, sweeping, and sweeping-mopping. Determine the cleaning strategy for the target area based on the current cleaning pattern, including: When the current cleaning mode is mopping mode, perform mopping operation on the target area; When the current cleaning mode is sweeping mode, sweeping operation is performed on the target area; When the current cleaning mode is the sweeping and mopping mode, sweeping and mopping operations are performed on the target area.

8. The waste cleaning method based on texture recognition according to claim 1, characterized in that, Prior to performing texture recognition and image analysis on the debris in the ground image, the following steps are included: Texture recognition and image analysis are performed on the ground in the ground image to obtain the ground condition of the target area; The ground images are preprocessed based on the ground conditions.

9. A texture recognition-based waste cleaning system for cleaning equipment, characterized in that, The system includes: The image acquisition module is used to acquire ground images of the target area; An image recognition module, communicatively connected to the image acquisition module, is used to perform texture recognition and image analysis on the waste in the ground image to determine whether liquid waste exists in the target area; and The cleaning control module is communicatively connected to the image recognition module and is used to determine the cleaning strategy for the target area based on whether liquid waste exists in the target area; and to clean the target area according to the cleaning strategy.

10. A computer storage medium, characterized in that, The computer storage medium includes at least one instruction that, when executed, implements the steps of the method as claimed in any one of claims 1 to 8.

Images