Lamp control method, device, lamp, electronic device and storage medium

Abstract

The present invention provides a lamp control method, device, lamp, electronic device and storage medium, wherein the method comprises: determining light parameters of a target environment; performing human detection on the target environment based on an environment image to obtain the human posture of the target environment; and controlling the switch of the lamp based on the light parameters and the human posture. Compared with human body sensing lamps or light sensing lamps in the prior art, the lamp control method, device, lamp, electronic device and storage medium provided by the embodiments of the present invention take both light parameters and human posture into consideration when switching the lamp, thereby realizing intelligent control of the lamp switch and improving the user experience.

Description

Technical Field

[0001] The present invention relates to the field of lighting technology, and in particular to a lamp control method, a lamp control device, a lamp, an electronic device and a storage medium. Background Art

[0002] Desk lamps are mainly used for supplementary lighting on the desktop, which is convenient for reading, studying, working, etc. With the emergence of a series of smart desk lamps, turning on desk lamps has become more intelligent and convenient.

[0003] At present, smart desk lamps mainly have two ways to turn on: human body sensing and light sensing. Human body sensing means that the desk lamp will automatically turn on when it detects that the user is near the desk lamp; light sensing means that the desk lamp will automatically turn on when it detects that the light around the desk lamp is dim.

[0004] The above two turning-on methods can easily trigger the desk lamp to turn on when the user does not need to use the desk lamp, resulting in a poor user experience. Summary of the invention

[0005] The present invention provides a lamp control method, device, lamp, electronic device and storage medium, which are used to solve the defect in the prior art that a desk lamp is triggered to turn on when the user does not need to use the lamp, resulting in a poor user experience.

[0006] The present invention provides a lamp control method, comprising:

[0007] Determine the light parameters of the target environment;

[0008] Performing person detection on the target environment based on the environment image to obtain the person's posture in the target environment;

[0009] Based on the light parameters and the character's posture, the switch of the lamp is controlled.

[0010] According to the lamp control method provided by the present invention, the step of performing human detection on the target environment to obtain the human posture in the target environment includes:

[0011] Performing person detection on the target environment to obtain the person's posture and position in the target environment;

[0012] The controlling the switch of the lamp based on the light parameter and the character's posture includes:

[0013] Based on the light parameters, the character's posture, and the character's position, the switch of the lamp is controlled.

[0014] According to the lamp control method provided by the present invention, the step of performing person detection on the target environment to obtain the person's posture and position in the target environment includes:

[0015] Acquire the environment image;

[0016] Performing target detection and image segmentation on the environment image to obtain person blocks and device blocks in the environment image;

[0017] Performing posture detection on the character image block to obtain the character posture of the target environment;

[0018] Performing relationship detection on the character block and the device block to obtain a positional relationship between the character block and the device block;

[0019] Based on the positional relationship between the character block and the device block, the position of the character in the target environment is determined.

[0020] Preset Conditions According to the lamp control method provided by the present invention, the performing of human detection on the target environment to obtain the human posture in the target environment includes:

[0021] When the light parameters meet the preset light parameters, human detection is performed on the target environment to obtain the human posture in the target environment.

[0022] The lamp control method provided by the present invention further includes:

[0023] When the lamp is in an on state, the brightness and / or color temperature of the lamp is controlled based on the posture of the person.

[0024] According to the lamp control method provided by the present invention, the brightness and / or color temperature of the lamp is controlled based on the character's posture, including:

[0025] Determining a type of operation of the character based on the character's posture;

[0026] Based on the type of the person's job, the brightness and / or color temperature of the lamp is controlled.

[0027] The present invention also provides a lamp control device, comprising:

[0028] A light parameter determination unit, used to determine the light parameters of the target environment;

[0029] A person posture determination unit, used for performing person detection on the target environment based on the environment image to obtain the person posture of the target environment;

[0030] A lamp switch control unit is used to control the switch of the lamp based on the light parameters and the character's posture.

[0031] The present invention further provides a lamp, comprising a lamp body, a light sensor and a camera mounted on the lamp body, and the above-mentioned lamp control device, wherein the light sensor and the camera are respectively connected to the lamp control device;

[0032] The light sensor is used to collect light parameters of the target environment, and the camera is used to collect environmental images.

[0033] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, any one of the above-mentioned lamp control methods is implemented.

[0034] The present invention further provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the lamp control method described in any one of the above is implemented.

[0035] The present invention further provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned lamp control methods.

[0036] The lamp control method, device, lamp, electronic device and storage medium provided by the present invention determine the light parameters of the target environment; perform human detection on the target environment to obtain the human posture in the target environment; and control the switch of the lamp based on the light parameters and the human posture. Compared with the human body sensing lamp or light sensing lamp in the prior art, when the lamp is switched on and off, the light parameters and the human posture are taken into consideration at the same time to prevent the desk lamp from automatically turning on at will, thereby realizing intelligent control of the lamp switch and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 This is one of the flow charts of the lamp control method provided by the present invention;

[0039] Figure 2 This is the second flow chart of the lamp control method provided by the present invention;

[0040] Figure 3 It is a flow chart of a method for detecting a person's posture and position provided by the present invention;

[0041] Figure 4 This is the third flow chart of the lamp control method provided by the present invention;

[0042] Figure 5 is a structural schematic diagram of a lamp control device provided by the present invention;

[0043] Figure 6 is a structural schematic diagram of a lamp provided by the present invention;

[0044] Figure 7 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are 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.

[0046] In the field of smart desk lamp control, there are two main ways to turn on the desk lamp: human body sensing and light sensing. Human body sensing turns on the desk lamp, and when a person walks near the desk lamp, it will also turn on. Many users are accustomed to placing the desk lamp on the desk next to the bed. When the user is resting in bed, it is easy to trigger the desk lamp to turn on, making the desk lamp a product that interferes with the user's rest, becomes a nuisance to the user, and the user experience is poor.

[0047] The light sensor turns on the desk lamp, and the desk lamp turns on automatically at night. If the user is not working near the desk lamp, turning on the desk lamp is just ineffective.

[0048] Based on this, the embodiment of the present invention provides a lamp control method, which can realize intelligent control of the lamp switch when the user needs to use the lamp, thereby improving the user experience. It should be noted that the lamp control method provided by the embodiment of the present invention can be used not only for table lamps, but also for other lamps such as floor lamps and wall lamps, and the embodiment of the present invention does not specifically limit this.

[0049] Figure 1 is one of the flow charts of the lamp control method provided by the present invention, such as Figure 1 As shown, the method includes:

[0050] Step 110, determining light parameters of the target environment.

[0051] Specifically, the target environment refers to the environment around the lamp. For example, the lighting area formed after the lamp is turned on can be determined as the target environment. Since the power and model of the lamps are different, the size of the lighting area formed after turning on is different. The target environment can be flexibly set according to the power and model of the lamp, and the embodiment of the present invention does not specifically limit this.

[0052] The light parameter of the target environment may reflect the current light condition of the target environment. The light parameter may be the brightness of the light and may be represented by a brightness value or a brightness level, such as strong / medium / weak.

[0053] The light parameters of the target environment can be obtained through the light sensor, and the light sensor can be installed on the lamp body.

[0054] In another embodiment, a camera installed on the lamp may be used to acquire an environmental image of the target environment, and an average value of pixel brightness values ​​of the environmental image may be used as the light parameter of the target environment.

[0055] Step 120 , performing human detection on the target environment based on the environment image to obtain human postures in the target environment.

[0056] Specifically, the target environment is first photographed using a camera on the lamp to obtain an environment image, and based on the obtained environment image, human detection is performed on the target environment.

[0057] The camera can be fixedly mounted on the lamp or rotatably mounted on the lamp to collect environmental images at different angles. The camera can be a visible light camera, an infrared camera, or a dual camera, such as an infrared camera and a visible light camera, or a dual visible light camera.

[0058] The person detection here refers to detecting whether there is a person in the target environment. When a person is detected in the target environment, the person's posture is further detected.

[0059] When an infrared camera is used, it can directly sense whether a person exists; when a visible light camera is used, it can first identify whether the environmental image includes a human face image. When a person is sensed or a human face image is identified in the environmental image, the person's posture is further detected.

[0060] Taking infrared cameras as an example, infrared cameras include infrared array sensors. Due to the difference in surface temperature of people and other objects in the target environment, the thermal radiation energy emitted is also different. The difference in thermal radiation energy between the sensing object and the background is used to obtain the outline of the infrared thermal image. By identifying the dot matrix image in the infrared thermal image, the posture of the person in the target environment is intuitively displayed.

[0061] In another embodiment, a human posture model, such as an openpose model, may be used to detect human postures in an environment image. The openpose model is a posture detection framework used to detect human joints, such as key points such as the neck, shoulders, elbows, and legs, and connect the key points to obtain the corresponding human posture. Of course, other trained posture detection models may also be used to detect human postures to obtain human postures.

[0062] The obtained character postures may specifically include sitting posture, lying posture, semi-recumbent posture and standing posture, etc.

[0063] Step 130: Controlling the switch of the lamp based on the light parameters and the person's posture.

[0064] Specifically, based on the light parameters of the target environment and the person's posture, the switch of the lamp can be controlled. The switch of the lamp refers to turning the lamp on or off.

[0065] Considering that in the prior art, lamps are automatically turned on at night or in low light conditions, and human body sensing lamps are automatically turned on as long as they sense a person, both methods affect the user experience. The lamp control method provided in the embodiment of the present invention takes into account both light parameters and human posture when switching the lamp on and off.

[0066] For example, the lamps are turned on only when both the light parameters and the character's posture meet the preset conditions; otherwise, as long as any one of the light parameters or the character's posture does not meet the preset conditions, the closed lamps will not be turned on, and the turned-on lamps will automatically turn off under the control of the control device.

[0067] Furthermore, the preset conditions here can be adjusted according to the specific use environment of the lamp. For example, when the lamp is set at the bedside for reading lighting before going to bed, the preset condition of the person's posture can be semi-recumbent or sitting. When the person's posture is detected to be semi-recumbent or sitting, the lamp is controlled to turn on; when the person's posture is detected to be lying, the lamp is controlled to turn off. When the lamp is set at the desk for supplementary lighting for work or study, the preset condition of the person's posture can be sitting. Only when the person's posture is detected to be sitting, the lamp is controlled to turn on.

[0068] It should be noted that the light parameters and the character posture can be obtained at the same time. In order to improve the control efficiency of the lamps and save power consumption, the character detection and character posture can be obtained only when the light parameters meet the preset conditions; or the light detection and light parameters can be obtained only when the character posture meets the preset conditions. The embodiment of the present invention does not make specific limitations on this.

[0069] That is to say, step 110 and step 120 may be executed simultaneously or sequentially, and the execution order of the two is not limited.

[0070] Compared with human body sensing lamps or light sensing lamps in the prior art, the lamp control method provided by the embodiment of the present invention takes into account light parameters and human posture when controlling the switching of the lamp, thereby realizing intelligent control of the switching of the lamp and improving the user experience.

[0071] Based on the above embodiments, Figure 2 This is the second flow chart of the lamp control method provided by the present invention. Figure 2 As shown, step 120 specifically includes:

[0072] Step 121, performing person detection on the target environment to obtain the person's posture and position in the target environment;

[0073] Accordingly, step 130 specifically includes:

[0074] Step 131, based on the light parameters, the person's posture, and the person's position, control the switch of the lamp.

[0075] Specifically, based on performing person detection on the target environment and obtaining the person's posture in the target environment, the person's position in the target environment can also be obtained.

[0076] The position of a person can be represented by the distance between the person and the lamp. The distance between the person and the lamp can be detected by an infrared sensor or an ultrasonic detection device. The closer the distance between the person and the lamp, the greater the probability that the person currently needs to use the lamp. At the same time, the switch of the lamp is controlled by combining the light parameters and the person's posture.

[0077] The position of a person can also be represented by the relative position relationship between the person and other objects in the target environment. The environment image can be obtained by shooting with a camera, and the relative position relationship between the person and other objects in the target environment can be obtained by image analysis, thereby obtaining the position of the person.

[0078] For example, when a desk lamp is placed on a table, the positional relationship between the person and the table can be used to determine whether the person is in front of the table. At the same time, the light parameters and the person's posture can be combined to determine whether the person needs to use the desk lamp and control the switch of the desk lamp. When a floor lamp is placed next to a bed or sofa, the positional relationship between the person and the bed or sofa can be used to determine whether the person is on the bed or sofa. At the same time, the light parameters and the person's posture can be combined to control the switch of the floor lamp.

[0079] Based on any of the above embodiments, Figure 3 is a flow chart of the method for detecting the posture and position of a person provided by the present invention, such as Figure 3 As shown, step 121 specifically includes:

[0080] Step 121-1, acquiring the environment image;

[0081] Step 121-2, performing target detection and image segmentation on the environment image to obtain person blocks and device blocks in the environment image;

[0082] Step 121-3, performing posture detection on the character image block to obtain the character posture of the target environment;

[0083] Step 121-4, performing relationship detection on the character block and the equipment block to obtain the position relationship between the character block and the equipment block;

[0084] Step 121 - 5 , determining the position of the character in the target environment based on the positional relationship between the character tile and the device tile.

[0085] Specifically, the environmental image of the target environment can be obtained through the camera installed on the lamp, and then the person detection can be performed. In order to improve the accuracy of subsequent person detection, the environmental image can be further enhanced, wherein the image enhancement may include but is not limited to: histogram equalization, wavelet denoising, median filtering, mean filtering, etc. After the environmental image is enhanced, the image quality will be improved, thereby improving the accuracy of person detection.

[0086] Here, person detection for environmental images may specifically include person posture detection and person position detection. Person blocks and device blocks may be obtained through target detection and image segmentation, and posture detection and relationship detection may be performed respectively.

[0087] In order to obtain the person tiles and device tiles in the environment image, the trained object detection model can be used to perform object detection on the environment image. The objects here may include people and devices, and the devices may include home or office equipment such as tables, chairs, sofas, and beds. Based on the result of the object detection, that is, the position of the external frame of the person and / or device in the environment image, the environment image is segmented to obtain the person tiles and device tiles in the environment image.

[0088] On the basis of obtaining the character image block, the character image block can be subjected to posture detection to obtain the character posture.

[0089] Posture detection of a character block can be achieved by calculating image similarity. First, a sample posture image containing a preset posture is obtained, and the posture of the character in the character block is detected by calculating the similarity between the character block and the sample posture image. The greater the similarity, the greater the probability that the character posture of the character block is the same as the preset posture indicated by the sample posture image; the smaller the similarity, the smaller the probability that the character posture of the character block is the same as the preset posture indicated by the sample posture image.

[0090] Furthermore, after normalizing the similarity, the probability of the character block corresponding to each preset posture can be obtained. The preset posture with the highest probability is taken as the character posture corresponding to the character block.

[0091] For character position detection, it can be achieved by performing relationship detection on character blocks and device blocks based on the character blocks and the device blocks.

[0092] By performing relationship detection on the character tiles and the equipment tiles, the positional relationship between the character tiles and the equipment tiles can be obtained, wherein the positional relationship between the character tiles and the equipment tiles may include the size of the tiles' bounding box and whether there is overlap between the tiles' bounding boxes. When there is overlap between the tiles, the size of the overlapping area is further determined.

[0093] Then, the position of the person in the target environment is determined based on the positional relationship between the person tile and the device tile. The person position thus obtained can reflect the positional relationship between the person and the device in the target environment, for example, whether the person is in front of the table.

[0094] It should be noted that the position of the person in the embodiment of the present invention may be the position of the entire person, or may be the position of a part of the person, such as the position of the face, and may also be multi-dimensional position information including both the position of the entire person and the position of a part of the person.

[0095] The method provided by the embodiment of the present invention obtains the posture and position of the person by performing target detection, image segmentation, posture detection and relationship detection on the environmental image. Multiple information can be acquired in one collection, thereby controlling the switching of lamps more accurately and intelligently, realizing intelligent control of the switching of lamps and enhancing the user experience.

[0096] Based on any of the above embodiments, step 131 specifically includes:

[0097] When the light parameters, the character's posture, and the character's position in the target environment all meet preset conditions, the lamp is controlled to turn on.

[0098] Specifically, the preset conditions may include a preset light brightness value and a pre-stored environment image, and a preset character posture and character position are extracted from the environment image.

[0099] When it is detected that the light of the current environment is weakened to the set light brightness value, and the posture and position of the person meet the preset posture and position of the person, the closed lamps are controlled to turn on the lighting. Conversely, when it is detected that any of the light parameters of the current environment, the posture of the person, or the position of the person does not meet the preset conditions, the closed lamps will not turn on, and the opened lamps will automatically turn off.

[0100] Based on any of the above embodiments, step 120 specifically includes:

[0101] When the light parameters meet the preset light parameters, human detection is performed on the target environment to obtain the human posture in the target environment.

[0102] Specifically, considering that performing light parameter detection and person detection simultaneously for a long time will consume more power, in order to improve the energy saving of the lamp, when it is detected that the light parameters meet the preset light parameters, that is, the light brightness value is weak and the lamp may need to be turned on, person detection can be performed to obtain the person's posture.

[0103] Then, based on the light parameters and the character's posture, the lights are turned on and off.

[0104] The method provided by the embodiment of the present invention performs human detection on a target environment when light parameters meet preset light parameters, obtains the posture of the human in the target environment, improves the energy-saving performance of the lamp, and further enhances the user experience.

[0105] Based on any of the above embodiments, the lamp control method further includes:

[0106] Step 410 , when the lamp is in an on state, the brightness and / or color temperature of the lamp is controlled based on the posture of the person.

[0107] Specifically, when the lamp is in the on state, the brightness and / or color temperature of the lamp can be further adjusted according to the posture of the person.

[0108] It can be seen from the description of the above embodiments that when the lamp is in the on state, the posture of the person may be a sitting posture or a semi-lying posture.

[0109] When the character posture is a sitting posture or a semi-recumbent posture, the character posture is further refined based on the refined features that can further reflect the character status. For example, the refined features may specifically include the age characteristics, identity identification, working status, sight direction or expression characteristics of the current character. The refined features can be obtained by further feature extraction of the environmental image corresponding to the sitting posture or semi-recumbent posture. Then, the refined type corresponding to the sitting posture or semi-recumbent posture is determined based on the refined features. For example, it may include reading sitting posture, mobile phone sitting posture, adult sitting posture, child sitting posture, etc.

[0110] In another embodiment, the positional relationship between the target object and the person can be obtained based on target detection to determine the detailed type corresponding to the sitting posture or semi-lying posture. For example, if the person holds a book, a pen, a mobile phone, or a mouse, the sitting posture for reading, doing homework, operating a mobile phone, or operating a computer can be determined.

[0111] It is understandable that the person may have different requirements for the brightness and / or color temperature of the lamp when they are in different detailed postures, such as working status or different identity identification. Therefore, the brightness and / or color temperature of the lamp can be further controlled according to the detailed type corresponding to the sitting posture or semi-recumbent posture.

[0112] For example, when the detected person's posture is a sitting posture for reading, it can be considered that the current person is in a reading state, and the brightness and / or color temperature of the lamp can be adjusted to a range suitable for reading. For another example, when the detected person's posture is a sitting posture of a child, it can be considered that the current person is a child in the stage of visual development, and the brightness and / or color temperature of the lamp can be adjusted to a range most suitable for children. For another example, the brightness and / or color temperature modes preferred by family members can be pre-set to obtain lamp modes corresponding to different personal identity identifications. The identity identification of the person currently using the lamp is determined by the detected posture of the person carrying the identity identification, so that the lamp is adjusted to the lamp mode corresponding to the current identity identification to control the brightness and / or color temperature of the lamp.

[0113] Based on any of the above embodiments, Figure 4 FIG. 3 is a flow chart of the lamp control method provided by the present invention. Figure 4 As shown, step 410 specifically includes:

[0114] Step 411, determining the character's operation type based on the character's posture;

[0115] Step 412: Control the brightness and / or color temperature of the lamp based on the type of the person's job.

[0116] Specifically, the character's job type may include reading, writing, operating a computer, operating a mobile phone, etc. The sitting posture or semi-recumbent posture may be further detected, and the character's current job type may be determined based on the detected detailed type of the sitting posture or semi-recumbent posture.

[0117] For further detection of sitting or semi-recumbent posture, the determination of the person's work type can be achieved through target detection and image segmentation. First, the environment image corresponding to the sitting or semi-recumbent state is obtained, and target detection and image segmentation are performed on the environment image to identify the target object contained in the environment image and the positional relationship between the target object and the person. The target object can be a book, exercise book, pen, mouse, keyboard, computer or mobile phone, etc.

[0118] Based on the target object and the positional relationship between the target object and the person, the subdivision types of sitting or semi-lying posture can be obtained. For example, based on the positional relationship between the person's hands and the mouse and / or keyboard, the probability of each preset person's job type is determined, and the computer operation with the highest probability is determined as the person's job type. Similarly, other job types such as reading, writing, and operating a mobile phone can be determined.

[0119] Furthermore, feature extraction can be performed on the person blocks in the environmental image to obtain the person's line of sight features and / or facial expression features, etc., and the extracted line of sight features and / or facial expression features can be fused with the positional relationship between the target object and the person, and the person's job type can be determined based on the fused result.

[0120] Based on the job type of the person, the brightness and / or color temperature of the lamp can be controlled according to the job type, and the brightness and / or color temperature of the lamp can be adjusted to the mode that best suits the current job type, while realizing intelligent control of the lamp and improving the user experience.

[0121] Based on any of the above embodiments, a lamp control method is provided, the method comprising:

[0122] S1, determining light parameters of a target environment, and when the light parameters meet preset light parameters, performing person detection on the target environment to obtain a person's posture and position in the target environment.

[0123] The light parameters are detected by a light detection element, such as a light sensor, disposed on the lamp and can reflect the light conditions around the lamp.

[0124] The person detection device, such as a camera, arranged on the lamp is used to detect the person and obtain the person's posture in the target environment.

[0125] S2, when the posture and position of the person in the target environment meet preset conditions, control the lamp to turn on.

[0126] The character posture refers to the character's sitting posture, lying posture, etc. near the lamp.

[0127] The preset condition refers to that the person is sitting next to the table where the lamp, such as a desk lamp, is placed.

[0128] The lamp control device provided by the present invention is described below. The lamp control device described below and the lamp control method described above can be referenced to each other.

[0129] Based on any of the above embodiments, Figure 5 is a schematic diagram of the structure of the lighting control device 500 provided by the present invention, such as Figure 5 As shown, the device 500 includes:

[0130] A light parameter determination unit 510, configured to determine light parameters of a target environment;

[0131] A person posture determination unit 520, configured to perform person detection on the target environment based on the environment image to obtain the person posture of the target environment;

[0132] The lamp switch control unit 530 is used to control the switch of the lamp based on the light parameters and the character's posture.

[0133] Compared with human body sensing lamps or light sensing lamps in the prior art, the lamp control device provided by the embodiment of the present invention takes into account light parameters and human posture when controlling the switching of the lamp, thereby realizing intelligent control of the switching of the lamp and improving the user experience.

[0134] Based on any of the above embodiments, the character posture determination unit 520 is further used for:

[0135] Performing person detection on the target environment to obtain the person's posture and position in the target environment; accordingly,

[0136] The lamp switch control unit 530 is further configured to:

[0137] Based on the light parameters, the character's posture, and the character's position, the switch of the lamp is controlled.

[0138] Based on any of the above embodiments, the character posture determination unit 520 is further used for:

[0139] Acquire the environment image;

[0140] Performing target detection and image segmentation on the environment image to obtain person blocks and device blocks in the environment image;

[0141] Performing posture detection on the character image block to obtain the character posture of the target environment;

[0142] Performing relationship detection on the character block and the device block to obtain a positional relationship between the character block and the device block;

[0143] Based on the positional relationship between the character block and the device block, the position of the character in the target environment is determined.

[0144] Based on any of the above embodiments, the lamp switch control unit 530 is further configured to:

[0145] When the light parameters, the character's posture, and the character's position in the target environment all meet preset conditions, the lamp is controlled to turn on.

[0146] Based on any of the above embodiments, the character posture determination unit 520 is further used for:

[0147] When the light parameters meet the preset light parameters, human detection is performed on the target environment to obtain the human posture in the target environment.

[0148] Based on any of the above embodiments, the lighting control device further includes a mode control unit, which is used to:

[0149] When the lamp is in an on state, the brightness and / or color temperature of the lamp is controlled based on the posture of the person.

[0150] Based on any of the above embodiments, the mode control unit is further configured to:

[0151] Determining a type of operation of the character based on the character's posture;

[0152] Based on the type of the person's job, the brightness and / or color temperature of the lamp is controlled.

[0153] Based on any of the above embodiments, Figure 6 is a schematic diagram of the structure of the lamp provided by the present invention, such as Figure 6 As shown, an embodiment of the present invention provides a lamp, including a lamp body 610, a light sensor 620 and a camera 630 installed on the lamp body, and the lamp control device 500 as described above, wherein the light sensor and the camera are respectively connected to the lamp control device.

[0154] It is understandable that the light sensor is used to detect the light parameters of the target environment, and the camera is used to detect people in the target environment to obtain the posture of the people in the target environment.

[0155] Figure 7 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 7As shown, the electronic device may include: a processor 710, a communication interface 720, a memory 730 and a communication bus 740, wherein the processor 710, the communication interface 720 and the memory 730 communicate with each other through the communication bus 740. The processor 710 may call the logic instructions in the memory 730 to execute the lamp control method, which includes: determining the light parameters of the target environment; performing human detection on the target environment based on the environment image to obtain the human posture of the target environment; and controlling the switch of the lamp based on the light parameters and the human posture.

[0156] In addition, the logic instructions in the above-mentioned memory 730 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0157] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the lighting control method provided by the above-mentioned methods, which includes: determining the light parameters of the target environment; performing person detection on the target environment based on the environmental image to obtain the person posture of the target environment; and controlling the switch of the lamp based on the light parameters and the person posture.

[0158] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute the lighting control method provided by the above-mentioned methods, the method comprising: determining the light parameters of the target environment; performing person detection on the target environment based on the environmental image to obtain the person posture of the target environment; and controlling the switch of the lamp based on the light parameters and the person posture.

[0159] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0160] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0161] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A lamp control method, characterized in that: include: Determine the light parameters of the target environment; Performing person detection on the target environment based on the environment image to obtain the person's posture and position in the target environment; Based on the light parameters, the person's posture, and the person's position, the switch of the lamp is controlled, wherein the switch of the lamp refers to turning the lamp on or off, and the lamp is turned on when the light parameters and the person's posture meet preset conditions, and the preset conditions are determined according to the use environment of the lamp; The step of performing person detection on the target environment to obtain the person's posture and position in the target environment includes: Acquire the environment image through a camera installed on the lamp; Performing target detection and image segmentation on the environment image to obtain person blocks and device blocks in the environment image; Based on the similarity between the character image block and the sample posture image, performing posture detection on the character image block to obtain the character posture of the target environment; Performing relationship detection on the character block and the device block to obtain a positional relationship between the character block and the device block, wherein the positional relationship includes whether there is overlap between the external frames of the character block and the device block, and when there is overlap, determining the size of the overlapping area; Based on the positional relationship between the character tile and the device tile, the character position of the target environment is determined.

2. The lamp control method according to claim 1, characterized in that: The performing of person detection on the target environment to obtain the person's posture in the target environment includes: When the light parameters meet the preset light parameters, human detection is performed on the target environment to obtain the human posture in the target environment.

3. The lamp control method according to claim 1, characterized in that: Also includes: When the lamp is in an on state, the brightness and / or color temperature of the lamp is controlled based on the posture of the person.

4. The lamp control method according to claim 3, characterized in that: The controlling the brightness and / or color temperature of the lamp based on the person's posture includes: Determining a type of operation of the character based on the character's posture; Based on the type of the person's job, the brightness and / or color temperature of the lamp is controlled.

5. A lighting control device, characterized in that: include: A light parameter determination unit, used to determine the light parameters of the target environment; A person posture determination unit, used for performing person detection on the target environment based on the environment image, and obtaining the person posture and position of the person in the target environment; A lamp switch control unit, used to control the switch of the lamp based on the light parameters, the person's posture, and the person's position, wherein the switch of the lamp refers to turning the lamp on or off, and the lamp is turned on when the light parameters and the person's posture meet preset conditions, and the preset conditions are determined according to the use environment of the lamp; The character posture determination unit is specifically used for: Acquire the environment image through a camera installed on the lamp; Performing target detection and image segmentation on the environment image to obtain person blocks and device blocks in the environment image; Based on the similarity between the character image block and the sample posture image, performing posture detection on the character image block to obtain the character posture of the target environment; Performing relationship detection on the character block and the device block to obtain a positional relationship between the character block and the device block, wherein the positional relationship includes whether there is overlap between the external frames of the character block and the device block, and when there is overlap, determining the size of the overlapping area; Based on the positional relationship between the character block and the device block, the position of the character in the target environment is determined.

6. A lamp, characterized in that: It comprises a lamp body, a light sensor and a camera installed on the lamp body, and the lamp control device as claimed in claim 5, wherein the light sensor and the camera are respectively connected to the lamp control device; The light sensor is used to collect light parameters of the target environment, and the camera is used to collect environmental images.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the lamp control method according to any one of claims 1 to 4 is implemented.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the lamp control method according to any one of claims 1 to 4 is implemented.

Images