Control method and system for intelligent faucet

Abstract

The invention relates to the technical field of intelligent control, and particularly discloses a control method and system for an intelligent faucet, and the method comprises the following steps: S1, setting a shooting region below the faucet, and setting a shooting point at the faucet to obtain an image of the region in real time; analyzing the image by using an image recognition technology to judge whether a target appears in the shooting area or not and judge whether the target carries a container or not; s2, if the target carries the container, obtaining the size information of the container through the detection point by using an infrared detection technology; the container volume and the pool volume are obtained and compared, and if the container volume is smaller than the pool volume, the drainage time is determined; s3, if the volume of the container is larger than or equal to the volume of the pool, the critical volume of the container is determined according to the three-dimensional model, and according to the critical volume, the critical volume is used as the water discharging amount to calculate the water discharging time.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to a control method and system for an intelligent faucet. Background Art

[0002] The control of smart faucets is a complex process involving multiple technologies and methods. It integrates advanced sensing technology, control algorithms and user interaction design to achieve precise control of water flow and temperature, while providing a more convenient, hygienic and safer user experience.

[0003] In the existing technology, although smart faucets integrate a variety of advanced technologies, their intelligent functions are often simply superimposed without truly combining intelligent technology with the user experience, ignoring the actual convenience of the product; for example, when users need to fill a basin of water, they must continue to keep their hands in the sensing area to ensure that the water flow is not interrupted; although this design reflects the characteristics of intelligence to a certain extent, it actually brings great inconvenience to users. Summary of the invention

[0004] The purpose of the present invention is to provide a control method and system for an intelligent faucet to solve the above technical problems.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] A control method for an intelligent faucet comprises the following steps:

[0007] Step S1: Select a shooting area below the faucet, and set a shooting point and a detection point at the faucet, wherein the shooting point is used to obtain an image of the shooting area in real time, and the detection point is based on infrared detection technology and is used to monitor whether there is an obstacle below the faucet; if the detection point detects that there is an obstacle below the faucet, the image is obtained, and image recognition is performed on the image in real time. If a target is identified in the image, it is determined whether the target in the image carries a container, and the target includes a human hand;

[0008] Step S2: If the target carries a container, the detection point obtains the size information of the container, which is recorded as the container size, and the container size includes the length, width, height and radius of the container; obtains the size information of the pool, which is recorded as the pool size; obtains the volume V1 of the container according to the container size, and obtains the volume V0 of the pool according to the pool size; if V1<V0, the volume V1 is used as the water discharge amount, and the water discharge time t=V1 / v of the faucet is obtained, where v is the volume of water discharged by the faucet per unit time;

[0009] Step S3: If V1≥V0, an object entity is obtained according to the image, the object entity consists of a container and a pool, and an overall three-dimensional model is established according to the object entity, the size of the container and the size of the pool; the critical volume of the container is obtained according to the overall three-dimensional model, and the critical volume is the maximum volume of water that the container can carry without overflowing the container; at this time, the critical volume is used as the water release amount, and the water release time is obtained.

[0010] As a further solution of the present invention: the process of identifying whether there is a target in the image includes:

[0011] Collect a number of sample images, the sample images include static images, dynamic images, targets at different positions and with different skin colors; perform feature extraction on the sample images to obtain a number of feature points of the target, convert the extracted feature points into feature vectors, recorded as sample feature vectors; obtain the feature vectors in the images, obtain the similarity between the sample feature vectors and the feature vectors, if the similarity belongs to a preset first similarity threshold, then the target exists in the image; if the similarity does not belong to the preset first similarity threshold, then the target does not exist in the image.

[0012] As a further solution of the present invention: the process of determining whether the target in the image carries a container includes:

[0013] A plurality of container sample images are collected, wherein the container sample images include container images of different types, shapes and colors; feature recognition is performed on the container sample images to obtain a feature vector of the container, which is recorded as a container sample feature vector; an area occupied by a target is marked in the image, which is recorded as a target area, and an area outside the target area in the image is recorded as an identification area, and a feature vector of the identification area is obtained, which is recorded as an identification feature vector; a similarity between the container sample feature vector and the identification feature vector is obtained, which is recorded as a container similarity; if the container similarity belongs to a preset second similarity threshold, the target carries a container; otherwise, the target does not carry a container.

[0014] As a further solution of the present invention: when the target in the image does not carry a container, the specific process includes:

[0015] The image in which the target is first recognized is obtained, recorded as the starting image, and the shooting time of the starting image is obtained, where the shooting time is the moment when the image is obtained at the shooting point; and whether the target exists in the latest image obtained at the shooting point is identified in real time. If it is identified that the target does not exist in the latest image, the shooting time of the latest image is obtained and recorded as the ending time; if the target in the image does not carry a container, the faucet starts to discharge water from the starting time until it stops at the ending time.

[0016] As a further solution of the present invention: the process of obtaining the container size by the detection point includes:

[0017] The detection point is used to transmit and receive infrared beam signals, and the infrared beam signal is composed of a plurality of infrared signals. When a container passes through the infrared beam signal, a plurality of infrared signals are reflected to the detection point, and the reflected plurality of infrared signals are used as signals to be measured. The detection point obtains the container size according to the signals to be measured.

[0018] As a further solution of the present invention: the time when the faucet starts to discharge water is recorded as the starting time t0, and the shooting time of the latest image obtained by the shooting point is obtained in real time, which is recorded as the latest time T; if there is no target or container in the latest image obtained by the shooting point, and t0+T≤t, the faucet stops discharging water directly.

[0019] As a further solution of the present invention: the process of establishing the overall three-dimensional model includes:

[0020] The establishment of the overall three-dimensional model is based on three-dimensional modeling software. According to the size of the container and the size of the pool, the three-dimensional geometric models of the container and the pool are determined respectively; and according to the object entity, the positional relationship between the two three-dimensional geometric models is obtained, and the positional relationship is the relative position of the two three-dimensional geometric models in space; the position of the three-dimensional geometric model is adjusted, and the three-dimensional geometric model is rotated so that the two three-dimensional geometric models satisfy the positional relationship, and finally the overall three-dimensional model is obtained.

[0021] As a further solution of the present invention: a control system for an intelligent faucet, comprising:

[0022] Shooting module: a shooting area is selected below the faucet, and shooting points and detection points are set at the faucet. The shooting point is used to obtain an image of the shooting area in real time. The detection point is based on infrared detection technology and is used to monitor whether there is an obstacle below the faucet. If the detection point detects that there is an obstacle below the faucet, the image is obtained and image recognition is performed on the image in real time. If a target is identified in the image, it is determined whether the target in the image carries a container, and the target includes a human hand.

[0023] Water discharge volume determination module: If the target carries a container, the detection point obtains the size information of the container, which is recorded as the container size, and the container size includes the length, width, height and radius of the container; obtains the size information of the pool, which is recorded as the pool size; obtains the volume V1 of the container according to the container size, and obtains the volume V0 of the pool according to the pool size; if V1<V0, the volume V1 is used as the water discharge amount, and the water discharge time t=V1 / v of the faucet is obtained, where v is the volume of water discharged by the faucet per unit time;

[0024] If V1≥V0, an object entity is obtained according to the image, the object entity consists of a container and a pool, and an overall three-dimensional model is established according to the object entity, the container size and the pool size; the critical volume of the container is obtained according to the overall three-dimensional model, and the critical volume is the maximum volume of water that the container can carry without overflowing the container; at this time, the critical volume is used as the water release amount, and the water release time is obtained.

[0025] Beneficial effects of the present invention:

[0026] The present invention automatically detects targets and containers through image recognition technology to achieve automatic operation of the smart faucet, reduce human intervention, and improve ease of use; uses infrared detection technology to obtain container size information to ensure the accuracy of water discharge and avoid waste of water resources; calculates the critical volume by establishing an overall three-dimensional model to effectively prevent water from overflowing the container; calculates the water discharge time according to the actual volume of the container to achieve precise control, save water and improve water resource utilization; simplifies the user operation process, provides a more user-friendly experience, and meets the needs of different scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The present invention will be further described below in conjunction with the accompanying drawings.

[0028] Figure 1 It is a flow chart of a control method for an intelligent faucet of the present invention. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0030] See also Figure 1 As shown, the present invention is a control method for an intelligent faucet, comprising the following steps:

[0031] Step S1: Select a shooting area below the faucet, and set a shooting point and a detection point at the faucet, wherein the shooting point is used to obtain an image of the shooting area in real time, and the detection point is based on infrared detection technology and is used to monitor whether there is an obstacle below the faucet; if the detection point detects that there is an obstacle below the faucet, the image is obtained, and image recognition is performed on the image in real time. If a target is identified in the image, it is determined whether the target in the image carries a container, and the target includes a human hand;

[0032] It can be understood that a suitable shooting area is selected below the faucet to ensure that the user and the container he carries can be clearly captured in the area; a shooting point is set at the faucet, and the shooting point is equipped with a high-definition camera to obtain images of the shooting area in real time; through advanced image recognition technology, the system will automatically analyze these images to determine whether there is a target (such as a human hand) in the shooting area; once the target in the image is identified, the system will further determine whether the target is carrying a container, so as to decide whether to perform subsequent operations;

[0033] It should be noted that the process of the detection point monitoring whether there is an obstacle under the faucet includes:

[0034] The detection point monitors the reflected infrared signal in real time, and determines whether there is an obstacle under the faucet according to the strength of the reflected infrared signal; if the reflected infrared signal is strong, it indicates that an object blocks the propagation of the infrared light, and thus it is determined that there is an obstacle; otherwise, it is considered that there is no obstacle;

[0035] As a preferred embodiment of the present invention, the process of identifying whether there is a target in the image includes:

[0036] Collecting a number of sample images, the sample images including static images, dynamic images, and targets at different positions and with different skin colors; performing feature extraction on the sample images to obtain a number of feature points of the target, converting the extracted feature points into feature vectors, recorded as sample feature vectors; obtaining feature vectors in the images, obtaining similarities between the sample feature vectors and feature vectors, and if the similarity belongs to a preset first similarity threshold, the target exists in the image; if the similarity does not belong to the preset first similarity threshold, the target does not exist in the image;

[0037] It is understandable that a series of diverse sample images need to be collected. These sample images should cover a variety of possible scenarios and conditions, including static images, dynamic images, targets in different locations, and targets of different skin colors; feature extraction is performed on all collected sample images; this step involves using computer vision algorithms to identify key points or salient areas in the image and converting these points into a mathematically tractable form, namely a feature vector; each feature vector represents a unique representation of the target in the image; for the image to be detected, feature extraction is also performed to obtain its feature vector; this feature vector is compared with the feature vector previously obtained from the sample image to calculate the similarity between them. This usually involves complex mathematical operations, such as cosine similarity, Euclidean distance, etc.; the calculated similarity value is compared with a preset first similarity threshold; if the similarity exceeds this threshold, it is considered that there is a target in the image; conversely, if the similarity is lower than the threshold, it is considered that there is no target in the image; this threshold is determined based on a large amount of experimental data to ensure that both accurate target identification and false alarms can be avoided;

[0038] As a preferred embodiment of the present invention, the process of determining whether the target in the image carries a container includes:

[0039] Collect a number of container sample images, wherein the container sample images include container images of different types, shapes and colors; perform feature recognition on the container sample images to obtain a feature vector of the container, which is recorded as a container sample feature vector; mark the area occupied by the target in the image, which is recorded as the target area, and record the area outside the target area in the image as the identification area, obtain the feature vector of the identification area, which is recorded as the identification feature vector; obtain the similarity between the container sample feature vector and the identification feature vector, which is recorded as the container similarity; if the container similarity belongs to a preset second similarity threshold, the target carries a container; otherwise, the target does not carry a container;

[0040] As a preferred embodiment of the present invention, when the target in the image does not carry a container, the specific process includes:

[0041] The image in which the target is first recognized is obtained, recorded as the starting image, and the shooting time of the starting image is obtained, where the shooting time is the moment when the image is obtained at the shooting point; and whether the target exists in the latest image obtained at the shooting point is identified in real time. If it is identified that the target does not exist in the latest image, the shooting time of the latest image is obtained and recorded as the ending time; if the target in the image does not carry a container, the faucet starts to discharge water from the starting time until it stops at the ending time;

[0042] It can be understood that the system will obtain the image in which the target is first recognized, which is recorded as the starting image; this image marks the entry of the target into the monitoring area; at the same time, the system will record the shooting time of the starting image, that is, the moment when the shooting point first captures the target; this time point is crucial for the subsequent water release control; the system will continue to monitor the latest image obtained by the shooting point in real time to determine whether the target still exists in the monitoring area; for each frame of the latest image obtained, the system will perform target recognition; if at a certain moment it is recognized that the target no longer exists in the latest image, the system will immediately execute the next step; once it is confirmed that the target no longer exists in the latest image, the system will record the shooting time at this moment as the end time; this indicates that the target has left the monitoring area or has been removed; based on the above recorded time points, if the target in the image does not carry a container, the faucet will start to release water from the starting time until the end time; this can ensure that sufficient water resources are provided during the existence of the target, and the water source is turned off in time after the target leaves to avoid waste;

[0043] Step S2: If the target carries a container, the detection point obtains the size information of the container, which is recorded as the container size, and the container size includes the length, width, height and radius of the container; obtains the size information of the pool, which is recorded as the pool size; obtains the volume V1 of the container according to the container size, and obtains the volume V0 of the pool according to the pool size; if V1<V0, the volume V1 is used as the water discharge amount, and the water discharge time t=V1 / v of the faucet is obtained, where v is the volume of water discharged by the faucet per unit time;

[0044] It can be understood that the water discharge time t is calculated based on the volume v of water discharged from the faucet per unit time; this time is obtained by dividing the container volume V1 by the water discharge rate v; when the container volume is smaller than the pool volume, it often means that the container can be placed inside the pool, and the volume of water that the container can hold is usually the container volume;

[0045] As a preferred embodiment of the present invention, the process of obtaining the container size at the detection point includes:

[0046] The detection point is used to transmit and receive infrared beam signals, and the infrared beam signals are composed of a plurality of infrared signals. When the container passes through the infrared beam signal, a plurality of infrared signals are reflected to the detection point, and the reflected plurality of infrared signals are used as signals to be measured. The detection point obtains the container size according to the signals to be measured.

[0047] It should be noted that the detection point is equipped with an infrared transmitter for emitting a number of infrared beam signals to the monitoring area; these infrared beams cover a certain spatial range to form a detection area; when the container passes through the detection area formed by the infrared beams, part of the infrared beams will hit the surface of the container and be reflected back; the infrared receiver on the detection point is responsible for capturing these reflected infrared signals; all reflected infrared signals will be collected to form a group of signals to be tested; this group of signals contains the position and shape information of the container in the detection area; the processing unit inside the detection point will analyze this group of signals to be tested; by calculating the time difference, angle difference and other information between different infrared signals, the size, shape and other dimensional information of the container can be inferred; finally, according to the analysis results, the detection point can accurately obtain the size data of the container, including but not limited to the length, width, height and possible radius (for circular or cylindrical containers);

[0048] Step S3: If V1≥V0, an object entity is obtained according to the image, the object entity is composed of a container and a pool, and an overall three-dimensional model is established according to the object entity, the size of the container and the size of the pool; a critical volume of the container is obtained according to the overall three-dimensional model, the critical volume is the maximum volume of water that the container can carry without overflowing the container; at this time, the critical volume is used as the water release amount, and the water release time is obtained;

[0049] It should be noted that an object entity model is generated based on the image data. This model consists of two parts, the container and the pool, and accurately reflects their positions and shapes in space. Using the object entity, the container size and the pool size, the system will build an overall three-dimensional model. This model not only includes the geometric shapes of the container and the pool, but may also include their material properties and other relevant information. Based on the overall three-dimensional model, the critical volume of the container is calculated. The critical volume refers to the maximum volume of water that the container can carry without overflowing the container. This calculation takes into account factors such as the shape of the container, the size of the opening, and the relative position of the pool.

[0050] As a preferred embodiment of the present invention, the time when the faucet starts to release water is recorded as the starting time t0, and the shooting time of the latest image obtained by the shooting point is obtained in real time and recorded as the latest time T; if there is no target and container in the latest image obtained by the shooting point, and t0+T≤t, the faucet directly stops releasing water;

[0051] It is understandable that if there are no targets or containers in the latest image, and the time interval from the start time to the latest time is less than or equal to the preset time threshold, it means that there are no targets or containers in the monitoring area since the water discharge started, or the targets and containers have been away for a period of time; based on the above judgment, if the stop condition is met, the system will directly instruct the faucet to stop discharging water; this avoids unnecessary waste of water resources and ensures the efficient operation of the system

[0052] As a preferred embodiment of the present invention, the process of establishing the overall three-dimensional model includes:

[0053] The overall three-dimensional model is established based on three-dimensional modeling software, and the three-dimensional geometric models of the container and the pool are determined respectively according to the size of the container and the pool; and the positional relationship of the two three-dimensional geometric models is obtained according to the object entity, and the positional relationship is the relative position of the two three-dimensional geometric models in space; the position of the three-dimensional geometric model is adjusted, and the three-dimensional geometric model is rotated so that the two three-dimensional geometric models satisfy the positional relationship, and finally the overall three-dimensional model is obtained;

[0054] It should be noted that, based on the previously obtained container dimensions and pool dimensions, three-dimensional modeling software is used to create three-dimensional geometric models of the container and pool respectively; these models will accurately reflect the shape, size and other geometric features of the container and pool; the image is used to obtain the object entity and determine the relative position relationship of the container and pool in space; this position relationship describes the relative layout of the two three-dimensional geometric models in space; in the three-dimensional modeling software, the position of the three-dimensional geometric models of the container and pool is adjusted according to the obtained position relationship; this may include operations such as translation and rotation to ensure that the position relationship requirements are met.

[0055] A control system for an intelligent faucet, comprising:

[0056] Shooting module: a shooting area is selected below the faucet, and shooting points and detection points are set at the faucet. The shooting point is used to obtain an image of the shooting area in real time. The detection point is based on infrared detection technology and is used to monitor whether there is an obstacle below the faucet. If the detection point detects that there is an obstacle below the faucet, the image is obtained and image recognition is performed on the image in real time. If a target is identified in the image, it is determined whether the target in the image carries a container, and the target includes a human hand.

[0057] Water discharge volume determination module: If the target carries a container, the detection point obtains the size information of the container, which is recorded as the container size, and the container size includes the length, width, height and radius of the container; obtains the size information of the pool, which is recorded as the pool size; obtains the volume V1 of the container according to the container size, and obtains the volume V0 of the pool according to the pool size; if V1<V0, the volume V1 is used as the water discharge amount, and the water discharge time t=V1 / v of the faucet is obtained, where v is the volume of water discharged by the faucet per unit time;

[0058] If V1≥V0, an object entity is obtained according to the image, the object entity consists of a container and a pool, and an overall three-dimensional model is established according to the object entity, the container size and the pool size; the critical volume of the container is obtained according to the overall three-dimensional model, and the critical volume is the maximum volume of water that the container can carry without overflowing the container; at this time, the critical volume is used as the water release amount, and the water release time is obtained.

[0059] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A control method for an intelligent faucet, characterized in that: The following steps are involved: Step S1: Select a shooting area below the faucet, and set shooting points and detection points at the faucet, wherein the shooting points are used to obtain images of the shooting area in real time, and the detection points are based on infrared detection technology to monitor whether there are obstacles below the faucet; If the detection point detects that there is an obstacle under the faucet, the image is acquired and image recognition is performed on the image in real time. If a target is identified in the image, it is determined whether the target in the image carries a container, and the target includes a human hand; Step S2: If the target carries a container, the detection point obtains the size information of the container, which is recorded as the container size, and the container size includes the length, width, height and radius of the container; obtains the size information of the pool, which is recorded as the pool size; obtains the volume V1 of the container according to the container size, and obtains the volume V0 of the pool according to the pool size; if V1<V0, the volume V1 is used as the water discharge amount, and the water discharge time t=V1 / v of the faucet is obtained, where v is the volume of water discharged by the faucet per unit time; Step S3: If V1≥V0, an object entity is obtained according to the image, the object entity consists of a container and a pool, and an overall three-dimensional model is established according to the object entity, the size of the container and the size of the pool; the critical volume of the container is obtained according to the overall three-dimensional model, and the critical volume is the maximum volume of water that the container can carry without overflowing the container; at this time, the critical volume is used as the water release amount, and the water release time is obtained.

2. A control method for an intelligent faucet according to claim 1, characterized in that: In step S1, the process of identifying whether there is a target in the image includes: Collect a number of sample images, the sample images include static images, dynamic images, targets at different positions and with different skin colors; perform feature extraction on the sample images to obtain a number of feature points of the target, convert the extracted feature points into feature vectors, recorded as sample feature vectors; obtain the feature vectors in the images, obtain the similarity between the sample feature vectors and the feature vectors, if the similarity belongs to a preset first similarity threshold, then the target exists in the image; if the similarity does not belong to the preset first similarity threshold, then the target does not exist in the image.

3. The control method for an intelligent faucet according to claim 1, characterized in that: In step S1, the process of determining whether the target in the image carries a container includes: A plurality of container sample images are collected, wherein the container sample images include container images of different types, shapes and colors; feature recognition is performed on the container sample images to obtain a feature vector of the container, which is recorded as a container sample feature vector; an area occupied by a target is marked in the image, which is recorded as a target area, and an area outside the target area in the image is recorded as an identification area, and a feature vector of the identification area is obtained, which is recorded as an identification feature vector; a similarity between the container sample feature vector and the identification feature vector is obtained, which is recorded as a container similarity; if the container similarity belongs to a preset second similarity threshold, the target carries a container; otherwise, the target does not carry a container.

4. The control method for a smart faucet according to claim 1, characterized in that: In step S1, when the target in the image does not carry a container, the specific process includes: The image in which the target is first recognized is obtained, recorded as the starting image, and the shooting time of the starting image is obtained, where the shooting time is the moment when the image is obtained at the shooting point; and whether the target exists in the latest image obtained at the shooting point is identified in real time. If it is identified that the target does not exist in the latest image, the shooting time of the latest image is obtained and recorded as the ending time; if the target in the image does not carry a container, the faucet starts to discharge water from the starting time until it stops at the ending time.

5. The control method for an intelligent faucet according to claim 1, characterized in that: In step S2, the process of obtaining the container size by the detection point includes: The detection point is used to transmit and receive infrared beam signals, and the infrared beam signal is composed of a plurality of infrared signals. When a container passes through the infrared beam signal, a plurality of infrared signals are reflected to the detection point, and the reflected plurality of infrared signals are used as signals to be measured. The detection point obtains the container size according to the signals to be measured.

6. A control method for an intelligent faucet according to claim 4, characterized in that: In step S3, the time when the faucet starts to discharge water is recorded as the starting time t0, and the shooting time of the latest image obtained at the shooting point is obtained in real time, which is recorded as the latest time T; if there is no target or container in the latest image obtained at the shooting point, and t0+T≤t, the faucet stops discharging water directly.

7. The control method for a smart faucet according to claim 1, characterized in that: In step S3, the process of establishing the overall three-dimensional model includes: The establishment of the overall three-dimensional model is based on three-dimensional modeling software. According to the size of the container and the size of the pool, the three-dimensional geometric models of the container and the pool are determined respectively; and according to the object entity, the positional relationship between the two three-dimensional geometric models is obtained, and the positional relationship is the relative position of the two three-dimensional geometric models in space; the position of the three-dimensional geometric model is adjusted, and the three-dimensional geometric model is rotated so that the two three-dimensional geometric models satisfy the positional relationship, and finally the overall three-dimensional model is obtained.

8. A control system for an intelligent faucet, characterized in that: include: Shooting module: select a shooting area under the faucet, and set shooting points and detection points at the faucet. The shooting points are used to obtain images of the shooting area in real time. The detection points are based on infrared detection technology and are used to monitor whether there are obstacles under the faucet. If the detection point detects that there is an obstacle under the faucet, the image is acquired and image recognition is performed on the image in real time. If a target is identified in the image, it is determined whether the target in the image carries a container, and the target includes a human hand; Water discharge volume determination module: If the target carries a container, the detection point obtains the size information of the container, which is recorded as the container size, and the container size includes the length, width, height and radius of the container; obtains the size information of the pool, which is recorded as the pool size; obtains the volume V1 of the container according to the container size, and obtains the volume V0 of the pool according to the pool size; if V1<V0, the volume V1 is used as the water discharge amount, and the water discharge time t=V1 / v of the faucet is obtained, where v is the volume of water discharged by the faucet per unit time; If V1≥V0, an object entity is obtained according to the image, the object entity is composed of a container and a pool, and an overall three-dimensional model is established according to the object entity, the size of the container and the size of the pool; The critical volume of the container is obtained according to the overall three-dimensional model, and the critical volume is the maximum volume of water that the container can carry without overflowing the container; at this time, the critical volume is used as the water release amount, and the water release time is obtained.

Images