Equipment control method and device based on gesture recognition, lamp and medium

Abstract

The embodiment of the invention provides an equipment control method and device based on gesture recognition, a lamp and a medium, and the method comprises the steps: obtaining a first gesture signal made by a target object when target equipment is in an idle state, and entering a current control period; when the first gesture signal is a first target gesture, controlling the target device to enter a first target state, so that the target device executes a first target operation in the first target state; when the target device in the first target state detects that the first gesture signal is interrupted, the target device is controlled to enter a critical state, so that the target device stops executing the first target operation in the critical state; when the target device is in the critical state, the second gesture signal made by the target object is obtained, and under the condition that the target device has the first target state in the current control period, the target device is controlled to continue to enter the first target state, so that the target device continues to execute the first target operation, and the reliability of device control can be improved.

Description

Technical Field

[0001] This disclosure relates to the field of intelligent control technology, and in particular to a device control method, apparatus, lamp and medium based on gesture recognition. Background Technology

[0002] Gesture control is widely used in smart lighting fixtures, smart home appliances, and other devices due to its non-contact and intuitive interaction method. Users can make different gestures in front of these devices to perform corresponding intelligent interactive control. The stability of gesture signals is crucial for improving the reliability of device control. However, in related technologies, when the user's palm is at the edge of the device's distance detection range, or when the user's palm inevitably trembles slightly or moves slightly due to breathing, the gesture signal recognized by the device is prone to interruption. This reduces the accuracy of the device's recognition of gesture intentions and ultimately reduces the reliability of device control. Summary of the Invention

[0003] The main objective of this disclosure is to provide a device control method, apparatus, lamp, and medium based on gesture recognition, which can improve the reliability of device control.

[0004] To achieve the above objectives, a first aspect of this disclosure provides a device control method based on gesture recognition, comprising: When the target device is idle, acquire the first gesture signal made by the target object and enter the current control cycle; When the first gesture signal is a first target gesture, the target device is controlled to enter a first target state, so that the target device performs a first target operation in the first target state; When the target device detects an interruption of the first gesture signal while in the first target state, it controls the target device to enter a critical state, so that the target device stops performing the first target operation in the critical state; When the target device receives a second gesture signal from the target object while in the critical state, and the target device exists in the first target state within the current control cycle, the target device is controlled to continue entering the first target state so that the target device continues to perform the first target operation.

[0005] In some embodiments, after acquiring the first gesture signal made by the target object when the target device is in an idle state and entering the current control cycle, the device control method based on gesture recognition further includes: When the first gesture signal is the second target gesture, the target device is controlled to enter the second target state, so that the target device performs the second target operation in the second target state; The first target gesture and the second target gesture are different, the first target state and the second target state are different, the first target state includes at least a hovering state, and the second target state includes at least a single-scan state and a double-scan state.

[0006] In some embodiments, after controlling the target device to enter a second target state when the first gesture signal is a second target gesture, so that the target device performs a second target operation in the second target state, the gesture recognition-based device control method further includes: When the target device detects an interruption of the first gesture signal while in the second target state, it controls the target device to enter a critical state, so that the target device stops performing the second target operation in the critical state; When the target device receives a second gesture signal from the target object while in the critical state, and the target device does not exist in the first target state during the current control cycle, the target device is controlled to re-enter the critical state.

[0007] In some embodiments, after controlling the target device to enter a second target state when the first gesture signal is a second target gesture, so that the target device performs a second target operation in the second target state, the gesture recognition-based device control method further includes: When the target device detects an interruption of the first gesture signal while in the second target state, it controls the target device to re-enter the idle state to enter the next control cycle.

[0008] In some embodiments, when the target device acquires a second gesture signal made by the target object in the critical state, and the target device exists in the first target state within the current control cycle, controlling the target device to continue entering the first target state so that the target device continues to perform the first target operation includes: The timing begins after the target device enters the critical state; When the target device receives a second gesture signal from the target object during the waiting time period after the timer starts in the critical state, and the target device is in the first target state during the current control cycle, the target device is controlled to continue entering the first target state so that the target device continues to perform the first target operation.

[0009] In some embodiments, after the target device enters the critical state and starts timing, the gesture recognition-based device control method further includes: If the target device does not detect any hand gesture signal from the target object within the waiting time period after the timing starts in the critical state, the target device is controlled to re-enter the idle state after the timing reaches the end of the waiting time period to enter the next control cycle.

[0010] In some embodiments, when the target device exists in the first target state during the current control cycle, controlling the target device to continue entering the first target state so that the target device continues to perform the first target operation includes: When the second gesture signal is consistent with the first gesture signal, if the target device exists in the first target state within the current control cycle, the target device is controlled to continue entering the first target state so that the target device continues to perform the first target operation. When the second gesture signal is inconsistent with the first gesture signal, the target device is controlled to re-enter the idle state to enter the next control cycle.

[0011] To achieve the above objectives, a second aspect of this disclosure provides a device control apparatus based on gesture recognition, comprising: The gesture signal acquisition module is used to acquire the first gesture signal made by the target object when the target device is in an idle state, and then enter the current control cycle; An operation control module is used to control the target device to enter a first target state when the first gesture signal is a first target gesture, so that the target device performs a first target operation in the first target state; An interruption detection module is used to detect an interruption of the first gesture signal when the target device is in the first target state, and control the target device to enter a critical state so that the target device stops performing the first target operation in the critical state; The state transition module is used to acquire a second gesture signal made by the target object when the target device is in the critical state, and to control the target device to continue entering the first target state if the target device exists in the first target state during the current control cycle, so that the target device continues to perform the first target operation.

[0012] To achieve the above objectives, a third aspect of this disclosure provides a lighting fixture, the lighting fixture including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the gesture recognition-based device control method described in the first aspect embodiment.

[0013] To achieve the above objectives, a fourth aspect of this disclosure provides a storage medium, which is a computer-readable storage medium storing a computer program that, when executed by a processor, implements the gesture recognition-based device control method described in the first aspect embodiment.

[0014] The beneficial effects of the embodiments disclosed herein include: This embodiment of the present disclosure acquires a first gesture signal when the target device is idle and enters a control cycle. After detecting that the first gesture signal is a first target gesture, the device is triggered to enter a first target state and execute the corresponding operation. When the first gesture signal is interrupted, the control process is not terminated directly, but the device is controlled to enter a critical state to stop the operation. If a second gesture signal is acquired in the critical state and the first target state exists in the current control cycle, the device is controlled to continue to enter the first target state and execute the corresponding operation. Therefore, by setting a control cycle and a critical state, this embodiment of the present disclosure can use the critical state as an interaction buffer window when the first gesture signal is interrupted due to non-subjective factors such as slight hand movement or shaking. The first target operation can be restored within the same control cycle through the second gesture signal, ensuring the continuity of gesture intent recognition and the determinism of state switching, and ultimately improving the reliability of device control. Attached Figure Description

[0015] Figure 1 This is a schematic flowchart of a device control method based on gesture recognition provided in an embodiment of this disclosure; Figure 2 This is a flowchart of the lighting control process provided in the embodiments of this disclosure; Figure 3 This is another schematic flowchart of the device control method based on gesture recognition provided in this embodiment of the present disclosure; Figure 4 This is a schematic diagram of the functional modules of the device control device based on gesture recognition provided in an embodiment of this disclosure; Figure 5 This is a schematic diagram of a lighting application scenario provided in the embodiments of this disclosure; Figure 6 This is a schematic diagram of the hardware structure of the lamp provided in the embodiments of this disclosure. Detailed Implementation

[0016] The accompanying drawings in the embodiments clearly and completely describe the technical solutions in the embodiments of this disclosure. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments in this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0017] It is understood that in the specific embodiments of this disclosure, which involve retrieving the first gesture signal, the second gesture signal, and related data, when the above embodiments of this disclosure are applied to specific products or technologies, permission or consent from the subject is required, and the collection, use, and processing of related data must comply with relevant laws, regulations, and standards.

[0018] Furthermore, when the embodiments of this disclosure need to retrieve the first gesture signal, the second gesture signal, and related data, separate permission or separate consent for the first gesture signal, the second gesture signal, and related data will be obtained through pop-up windows or redirection to a confirmation page. After clearly obtaining separate permission or separate consent for the first gesture signal, the second gesture signal, and related data, the necessary first gesture signal, the second gesture signal, and related data for enabling the embodiments of this disclosure to operate normally will be obtained.

[0019] In this disclosure, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0020] Please see Figure 1 , Figure 1 This is a flowchart illustrating a gesture recognition-based device control method provided in an embodiment of this disclosure. This gesture recognition-based device control method can be applied to a target device or to a server connected to the target device. Further, the gesture recognition-based device control method includes steps S101 to S104: Step S101: When the target device is in an idle state, acquire the first gesture signal made by the target object and enter the current control cycle; Step S102: When the first gesture signal is the first target gesture, control the target device to enter the first target state so that the target device can perform the first target operation in the first target state; Step S103: When the target device detects an interruption of the first gesture signal in the first target state, it controls the target device to enter a critical state so that the target device stops performing the first target operation in the critical state. Step S104: When the target device is in a critical state, it acquires the second gesture signal made by the target object. If the target device has a first target state within the current control cycle, it controls the target device to continue to enter the first target state so that the target device continues to perform the first target operation.

[0021] Regarding step S101 above, the target device is the device to be controlled in this embodiment of the disclosure. This device can be any device capable of gesture-based interactive control, such as a smart lamp (hereinafter referred to as a lamp), smart home appliance, etc. Further, the target device may be equipped with a gesture recognition module. This module can recognize the gesture signals made by the target object, process them, and then perform corresponding control operations to achieve gesture-based interactive control. For example, the gesture recognition module can be an infrared sensor, an ultrasonic sensor, a millimeter-wave radar, a camera, a capacitive sensing module, etc., to acquire the required gesture signals through different technical means. This embodiment of the disclosure does not impose specific limitations on this.

[0022] The idle state (IDLE) is the initial state of the target device, where no gesture interaction task is being executed and only gesture signals are being continuously collected. For example, the standby state of a smart lamp when no gesture is detected.

[0023] The target object is the object that makes a gesture in order to interact with the target device. For example, the target object can be a user, or it can be a terminal object such as a robot.

[0024] The first gesture signal is the signal corresponding to the gesture action made by the target object that can be captured by the device, such as the gesture signal corresponding to the user's single scan, multiple scan, or hover gesture to control the lamp.

[0025] The current control cycle, as provided in this embodiment, is a time window from when the target device detects the first gesture signal until the gesture intent is completely terminated, used to lock the range of gesture signals and control intents for the same user intent. Furthermore, one control cycle corresponds to the control requirement of one gesture intent.

[0026] It should be noted that when the target device is in an idle state, which is the initial state in which the device does not respond to any gestures, continuous detection of gesture signals is the basis for ensuring the start of interaction, ensuring that subsequent processes are triggered only when the device is ready, and avoiding interference from invalid signals. Setting the current control cycle can avoid the pain point of chaotic switching between actions. By defining a unified control cycle, the acquisition of subsequent gesture signals, state transitions, and operation execution are limited to the same interaction scenario, preventing cross-interference of gestures with different intentions, providing a prerequisite for the coherent recognition of subsequent gesture intentions and state recovery, and ensuring the independence and integrity of the interaction process.

[0027] Regarding step S102 above, the first target gesture is a specific gesture made by the target object that conforms to the device's preset valid interaction rules. It is a key signal that triggers the device to enter the corresponding working state, such as a single scan, multiple scan, or hover gesture made by the user to control the lamp.

[0028] The first target state is the function execution state that the target device enters after responding to the first target gesture. For example, the first target state can be a single scan state (SWIPE_S), a multi-scan state (SWIPE_M), or a hover detection state (HOVER_DETECT). Each state is bound to a specific gesture intent to ensure that the device only performs the corresponding operation in that state and avoids accidental function triggering.

[0029] The first target operation is the specific functional action of the device corresponding to the first target state, such as the smart lamp switch operation triggered by a single scan gesture, the color temperature adjustment operation triggered by multiple scan gestures, and the brightness adjustment operation triggered by a hover gesture. Its execution logic is determined by the preset gesture and function mapping relationship of the device. This disclosure embodiment does not impose specific restrictions on this. The operation control for different gestures in this disclosure embodiment does not represent a restriction on the operation type, but is only an example.

[0030] It should be noted that the embodiments of this disclosure can establish a precise mapping from valid gestures and target states to functional operations. By identifying the first target gesture and filtering invalid signals, it ensures that the device only responds to gestures with clear user intent, avoiding misoperations caused by cluttered signals. At the same time, the gesture signals are converted into executable states and operations for the device, laying the foundation for the buffer logic and state recovery mechanism of subsequent critical states, and ensuring the orderly start of the interaction process.

[0031] Regarding step S103 above, the first gesture signal interruption refers to the loss or instability of the gesture signal of the target device in the first target state due to reasons other than the user's subjective intention to terminate the interaction. For example, the signal weakening caused by the user's palm being at the edge of the sensor's detection range, slight movement caused by breathing or slight shaking, and signal discontinuity caused by external environmental interference. It is not a behavior of the user actively ending the interaction.

[0032] The critical state (CRITICAL) is a buffer state provided in the embodiments of this disclosure. It is a transition channel connecting the control state (such as the first and second target states) and the idle state of the target device. It is not a state that directly terminates the interaction. Its function is to provide an observation window for signal interruption and avoid the device from misinterpreting the user's intention due to instantaneous signal fluctuations.

[0033] Stopping the execution of the first target operation is a behavior in a critical state, that is, the device temporarily suspends the current function action, such as pausing brightness adjustment, color temperature adjustment, etc., but does not clear the state record of the current control cycle, maintaining the recoverability of the interaction process, which is different from the traditional logic of directly returning to the idle state.

[0034] It should be noted that, in response to the pain point of the prior art where operation is terminated as soon as the signal is interrupted, the embodiments of this disclosure construct a fault-tolerant buffer by introducing a critical state. This not only avoids unexpected interruptions to operation caused by non-subjective factors such as slight hand movements or unstable signals at the edge, but also prevents the device from continuously erroneously executing during the signal interruption by stopping the operation. At the same time, it reserves an interface for subsequent gesture signal recovery, ensuring the continuity of interaction and the determinism of state switching.

[0035] Regarding step S104 above, the second gesture signal is the gesture signal made by the target object during the critical state. Its essence is the continuation or recovery of the first gesture signal. For example, it is a supplementary action for the user to maintain the original gesture intention after the signal is interrupted, such as stabilizing the gesture after hovering and shaking, or a continuous action to approach the sensor again after the edge signal is discontinuous. It can be recognized by the device as a valid signal in the same interaction scenario.

[0036] The existence of a first target state within the current control cycle is the condition for state recovery. This condition locks the interaction range of the same user intent. The control cycle starts from the detection of the first gesture signal and ends when the gesture intent is completely terminated, ensuring that the previous target state is only restored within the same interaction scenario, avoiding cross-interference between gestures of different intents.

[0037] Continuing to enter the first target state and execute the first target operation is the recovery logic of the critical state. That is, after the device confirms that the second gesture signal belongs to the same intention in the same control cycle, it seamlessly connects to the previous functional state without requiring the user to re-trigger the complete gesture, thus achieving a continuous operation.

[0038] It should be noted that by controlling the logic of cycle locking, critical state buffering, and same intention recovery, the embodiments of this disclosure solve the problem of inability to continuously recover after the interruption of gesture signals in the prior art. It allows users to quickly resume operation through a second gesture signal after a non-subjective signal interruption without repeating the standard gesture, thus improving the naturalness of the interaction. Furthermore, by limiting the boundary of the control cycle, it prevents the mis-connection of gestures with different intentions, ensuring the accuracy of state recovery. Ultimately, it achieves a single intention and continuous response, greatly improving the reliability of device control.

[0039] In summary, this embodiment of the present disclosure, through the execution of the device control method based on gesture recognition in steps S101 to S104, acquires a first gesture signal when the target device is idle to enter the control cycle. After detecting that the first gesture signal is a first target gesture, the device is triggered to enter the first target state to execute the corresponding operation. When the first gesture signal is interrupted, the control process is not directly terminated, but the device is controlled to enter a critical state to stop the operation. If a second gesture signal is acquired in the critical state and the first target state exists in the current control cycle, the device is controlled to continue to enter the first target state to execute the corresponding operation. Therefore, by setting a control cycle and a critical state, this embodiment of the present disclosure can use the critical state as an interaction buffer window when the first gesture signal is interrupted due to non-subjective factors such as slight hand movement or shaking. The first target operation can be restored within the same control cycle through the second gesture signal, ensuring the continuity of gesture intent recognition and the determinism of state switching, and ultimately improving the reliability of device control.

[0040] The following is a detailed description of the further contents included in steps S101 to S104 in the embodiments of this disclosure.

[0041] Furthermore, in some embodiments, after acquiring the first gesture signal made by the target object when the target device is in an idle state and entering the current control cycle in step S101 above, the device control method based on gesture recognition in this embodiment of the present disclosure further includes step S201: Step S201: When the first gesture signal is the second target gesture, control the target device to enter the second target state so that the target device can perform the second target operation in the second target state; Among them, the first target gesture and the second target gesture are different, the first target state and the second target state are different, the first target state includes at least the hovering state, and the second target state includes at least the single-scan state and the double-scan state.

[0042] In the above steps, the second target gesture is another preset valid interactive gesture that is clearly distinguishable from the first target gesture. It is a signal that triggers the device to enter the second target state. For example, if the first target gesture is a hover gesture, the second target gesture can be a single scan or multiple scan gesture, corresponding to functional requirements such as turning lights on and off and adjusting color temperature, forming a differentiated interactive logic with the first target gesture.

[0043] The second target state is a dedicated function execution state that the target device enters after responding to the second target gesture. For example, the second target state can be a single scan state (SWIPE_S) or a multi-scan state (SWIPE_M). It is independent of the first target state in terms of state attributes and execution logic, ensuring that different gesture intentions correspond to clear state channels and avoiding state confusion.

[0044] The second target operation is the specific functional action of the device corresponding to the second target state. It is different from the first target operation. For example, the smart lamp switch operation triggered by a single swipe gesture, and the color temperature adjustment operation triggered by a double swipe gesture. The operation logic is determined based on the mapping relationship between the second target gesture, the second target state and the second target operation preset by the device, to ensure the accurate matching of gesture and function.

[0045] It should be noted that the embodiments of this disclosure solve the pain points of ambiguous gesture intent recognition and chaotic function response by clearly distinguishing between the first target gesture and the second target gesture, as well as the corresponding target state and operation. At the same time, combined with the control cycle and critical state design of the embodiments of this disclosure, independent and coherent interaction paths are provided for different types of gestures. This not only ensures the rapid response of instantaneous gestures such as single scan / double scan, but also lays the foundation for state processing after subsequent signal interruption. This further enhances the accuracy of gesture intent recognition and the determinism of state switching, allowing the device to accurately execute corresponding operations according to different gesture needs of users, thereby improving the flexibility and reliability of interaction.

[0046] Furthermore, in some embodiments, in step S201 above, when the first gesture signal is the second target gesture, the target device is controlled to enter the second target state so that the target device performs the second target operation in the second target state. The device control method based on gesture recognition in this embodiment further includes steps S202 and S203: Step S202: When the target device detects an interruption of the first gesture signal while in the second target state, it controls the target device to enter a critical state so that the target device stops performing the second target operation in the critical state. Step S203: When the target device is in a critical state, it acquires the second gesture signal made by the target object. If the target device does not have a first target state in the current control cycle, it controls the target device to re-enter the critical state.

[0047] In the above steps, detecting the first gesture signal interruption in the second target state refers to the loss or instability of the gesture signal caused by reasons other than the user's subjective intention to terminate the interaction, when the target device is in single-scan state (SWIPE_S) or dual-scan (multi-scan) state (SWIPE_M). Common scenarios include weak and intermittent signals caused by the user's gesture being at the edge of the sensor's effective detection range, signal fluctuations caused by natural micro-movements of the hand during the scanning process, and momentary signal interruptions caused by external environmental interference, etc., which are not actions taken by the user to actively end the scanning interaction.

[0048] The critical state (CRITICAL) is still a transitional buffer state connecting the second target state and the idle state. It is essentially the same as the critical state in step S103. It is used to provide a time-dimensional observation window for the signal interruption of swiping gestures and avoid the device misjudging the user's intention due to instantaneous signal fluctuations.

[0049] Stopping the execution of the second target operation is a behavior for swiping gestures in a critical state. That is, the device temporarily suspends the current swiping operation, such as stopping the execution of turning lights on and off or adjusting color temperature, but does not clear the state record of the current control cycle. Only the historical record of the second target state is retained. This is different from the traditional logic of directly returning to the idle state and reserves an interface for subsequent intent determination.

[0050] It should be noted that swiping gestures are prone to signal interruption at the sensor edge. Traditional solutions may misinterpret continuous swiping with the same intention as multiple independent commands. However, this step incorporates signal interruption into buffer observation by transitioning from the second target state to the critical state, avoiding false triggering of multiple responses from a single swiping gesture. At the same time, temporarily stopping the operation can prevent the device from continuously executing invalid actions during the signal interruption, ensuring the accuracy of the operation and enhancing the robustness of swiping gesture interaction.

[0051] The following example uses the target device as a lighting fixture, which can recognize gesture signals through an infrared sensor. The example further illustrates the process, with the first target state being a hovering state and the second target state being a single-scan or dual-scan state. Please refer to [link / reference needed]. Figure 2 , Figure 2 This is a flowchart of the lighting control process provided in this embodiment. In this embodiment, when the lighting fixture is idle, after detecting a user's gesture signal through an infrared sensor, the current control cycle begins. The first gesture signal is judged to determine its action type. Different action types in this embodiment include hovering, single scan, or double scan. If the corresponding type is identified, the lighting fixture is controlled to enter the corresponding state to trigger the corresponding action, realizing the gesture interaction operation. If the gesture signal is interrupted, the lighting fixture enters a critical state. In the critical state, the lighting fixture suspends the execution of the corresponding interaction operation. Then, if a second gesture signal is detected in the critical state, it is determined whether the previous action state was hovering. If so, the interaction operation corresponding to hovering is resumed.

[0052] In addition, in some embodiments, in step S201 above, when the first gesture signal is the second target gesture, the target device is controlled to enter the second target state so that the target device performs the second target operation in the second target state. Afterwards, the device control method based on gesture recognition may further include step S204: Step S204: When the target device detects an interruption of the first gesture signal while in the second target state, it controls the target device to re-enter the idle state to enter the next control cycle.

[0053] In the above steps, if the target device detects an interruption of the first gesture signal while in the second target state, this embodiment of the present disclosure can also control the target device to re-enter the idle state to enter the next control cycle. Entering the next control cycle means that after the device returns to the idle state, it starts a new independent time window to capture and respond to the new gesture intent of the target object. The next control cycle is independent of the previous control cycle, does not inherit the state record of the previous cycle, and only corresponds to the new gesture intent control requirements.

[0054] It should be noted that the embodiments disclosed herein can accurately match the essential differences between single / double scan and hover gestures. Hover gestures, due to their prolonged duration, are susceptible to signal interruption caused by hand tremors and other factors, and the intent is easily misinterpreted, thus requiring a critical state buffer. In contrast, single / double scans are instantaneous gestures with clear intents, without the signal fluctuation issues caused by prolonged holding; signal interruption means the intent is terminated, and a direct reset is possible without buffering. Therefore, this embodiment, through a simple logic of interruption, return to idle, and start a new cycle, ensures both the rapid completion of single / double scan interactions and strengthens the logical isolation of different gesture intents, avoiding misinterpretation of the interruption signal from the previous scan cycle as a new intent. Simultaneously, it allows the device to quickly respond to subsequent new gestures, clearly isolating different gesture intents, improving the naturalness and reliability of the interaction, thus complementing the critical buffer logic of hover scenarios and achieving differentiated and precise processing of different types of gestures.

[0055] For further details, please refer to Figure 3 , Figure 3 This is another flowchart illustrating the device control method based on gesture recognition provided in this disclosure. In some embodiments, in step S104 above, when the target device is in a critical state, a second gesture signal made by the target object is obtained. If the target device exists in a first target state within the current control cycle, the process of controlling the target device to continue entering the first target state so that the target device continues to perform the first target operation may further include the following steps S1041 to S1042: Step S1041: Start timing after the target device enters the critical state; Step S1042: During the waiting time period after the target device starts timing in the critical state, the second gesture signal made by the target object is obtained. If the target device has a first target state in the current control cycle, the target device is controlled to continue to enter the first target state so that the target device continues to perform the first target operation.

[0056] In the above steps, the trigger condition for the target device to start timing after entering the critical state is that the device transitions from the first target state to the critical state. The timing is executed by the timing module built into the target device, such as the timer unit of a microcontroller, which provides the time dimension for determining the buffer logic of the critical state. The starting point of the timing is completely synchronized with the entry time of the critical state to ensure the accuracy of the time window; the timing process does not affect the device's ability to collect gesture signals, and only records the duration of the critical state.

[0057] It should be noted that minor, non-subjective interruptions such as slight hand tremors or breathing movements during hovering are usually short-lived, while actual interaction termination is accompanied by a longer signal loss. By starting a timer at the critical state, signal recovery can be linked to timeout, preventing interaction stutters caused by indefinite device waiting and enhancing the logical rigor of de-jittering and intent continuation at critical states.

[0058] The waiting time period is a preset time window of the device, adapted to the characteristics of hover gesture interaction. Its duration is set based on the typical duration of a user's natural hand shaking and slight breathing movements. In one embodiment, such as... Figure 2 As shown, based on actual practical experience, the preset waiting time period can be set to 700ms to ensure that it can cover most of the recovery time of non-subjective interruptions, while avoiding the impact of excessive waiting time on the efficiency of interactive response.

[0059] The waiting time period after the timing starts in the critical state is a time constraint condition for the effective recovery of the signal. This means that only if the second gesture signal is detected within this period is it determined to be a continuation of the same interaction intention; if it exceeds this period, it is considered that the user has subjectively terminated the interaction to avoid invalid waiting.

[0060] It should be noted that the anti-shake performance of hover gestures has been further optimized through the timing window and timed recovery logic. On the one hand, the setting of the waiting time period provides a precise fault tolerance range for non-subjective interruptions, ensuring that slight user tremors will not cause operation interruption and improving the naturalness of interaction. On the other hand, limiting the effective recovery of the second gesture signal to within the timing period avoids the device's false response to invalid signals that have timed out. At the same time, by filtering the condition of the existence of the first target state, confusion with other gesture intentions is eliminated, and the determinism of state switching is strengthened.

[0061] Furthermore, in some embodiments, after the timing of step S1041 begins after the target device enters a critical state, the device control method based on gesture recognition may further include step 1043: Step S1043: If no hand gesture signal is detected from the target object within the waiting time period after the target device starts timing in the critical state, the target device is controlled to re-enter the idle state after the timing reaches the end of the waiting time period, so as to enter the next control cycle.

[0062] In the above steps, not detecting any gesture signal made by the target object means that within the above waiting time period, the device's gesture recognition module did not capture any gesture action that meets the characteristics of a valid signal, which means that the user has subjectively terminated the hovering interaction, such as actively removing the palm, or objectively has no intention to continue the interaction.

[0063] When the timer reaches the end of the waiting period, the target device re-enters the idle state (IDLE). This means that when no gesture signal is received after the waiting period expires, the device terminates the buffering logic of the current critical state and returns to the initial monitoring state. Entering the next control cycle means that after the device returns to the idle state, it starts a completely new time window independent of the previous cycle to lock onto new user gesture intentions. For example... Figure 2 As shown, if no gesture signal is detected within the 700ms waiting period, the light fixture will return to the idle state.

[0064] It should be noted that when there is no gesture signal within the waiting time period, it is determined that the user has actively terminated the interaction. The device is quickly reset by returning to the idle state, avoiding invalid critical state occupation and improving the interaction response efficiency. At the same time, it can start the next control cycle when the next gesture signal is obtained, realizing the logical isolation of different gesture intentions, eliminating the influence of residual state from the previous cycle on the new interaction, providing a recovery opportunity for non-subjective interruption, and providing a clear termination mechanism for true termination, thus strengthening the determinism of state switching.

[0065] Furthermore, in some embodiments, the present disclosure embodiments may further include a determination of the consistency between the second gesture signal and the first gesture signal during the resumption of the first target operation. In step S104 or step S1042, if the target device exists in the first target state within the current control cycle, controlling the target device to continue entering the first target state so that the target device continues to perform the first target operation may further include the following steps: (1) When the second gesture signal is consistent with the first gesture signal, if the target device has a first target state in the current control cycle, control the target device to continue to enter the first target state so that the target device continues to perform the first target operation; (2) When the second gesture signal is inconsistent with the first gesture signal, the target device is controlled to re-enter the idle state in order to enter the next control cycle.

[0066] In the above steps, the second gesture signal being consistent with the first gesture signal means that the characteristics of the second gesture signal are completely matched with the first gesture signal, and the two belong to the same continuous signal of the user's intention. The characteristics of this determination include quantifiable indicators such as the trajectory shape of the gesture action, the duration of the signal, the range of position change, and the pulse frequency. For example, if the first gesture signal is hovering, the position change is less than the threshold, and the signal is stable, and the second gesture signal also meets the characteristics of hovering, then it is determined to be consistent.

[0067] It should be noted that the embodiments of this disclosure can enhance the coherence recognition of gesture intent through step (1), accurately matching the characteristics of hovering gestures that are maintained for a long time and are easily affected by shaking. Specifically, when the second gesture signal is consistent with the first gesture signal, it is determined to be a continuation of the user's intent after non-subjective interruption. By restoring the first target state and operation, frequent interruptions of operation caused by slight shaking and breathing micro-movements are avoided, solving the pain point of frequent jumps between the interruption and recovery of the hovering state; at the same time, combined with the boundary limitation of the control cycle, it is ensured that the operation is restored only within the same intent, further improving the reliability of device control.

[0068] Conversely, if the second gesture signal is inconsistent with the first gesture signal, it means that the characteristics of the second gesture signal are fundamentally different from those of the first gesture signal, such as differences in trajectory shape, action type, signal parameters, etc., indicating signals from different user intentions. For example, if the first gesture signal is hovering and the second gesture signal is a single swipe, their signal characteristics do not match, and they are judged to be inconsistent. This means that the user may have generated a new interaction intention, or the second gesture signal may be an interference signal.

[0069] It should be noted that the embodiments of this disclosure achieve clear isolation of different gesture intentions through step (2), solving the pain points of chaotic switching between actions and instruction sticking. Specifically, when the second gesture signal is inconsistent with the first gesture signal, by directly returning to the idle state and starting the next control cycle, it avoids misjudging the new intention gesture as a continuation of the previous intention, or the device's erroneous response caused by cross-interference of different intention signals, such as misjudging a single scan after a hover interruption as a hover continuation; at the same time, by strictly distinguishing the processing logic of consistent and inconsistent signals, the determinism of state switching is strengthened, ensuring that the device only responds to the single intention clearly defined by the user, further improving the accuracy and reliability of gesture interaction.

[0070] Please see Figure 4 This disclosure also provides a device control apparatus based on gesture recognition, which can implement the above-described device control method based on gesture recognition. The device control apparatus based on gesture recognition includes: The gesture signal acquisition module 401 is used to acquire the first gesture signal made by the target object when the target device is in an idle state, and enter the current control cycle. The operation control module 402 is used to control the target device to enter the first target state when the first gesture signal is the first target gesture, so that the target device can perform the first target operation in the first target state; The interruption detection module 403 is used to control the target device to enter a critical state when the target device detects an interruption of the first gesture signal in the first target state, so that the target device stops executing the first target operation in the critical state. The state transition module 404 is used to acquire the second gesture signal made by the target object when the target device is in a critical state, and control the target device to continue to enter the first target state if the target device exists in the first target state within the current control cycle, so that the target device continues to perform the first target operation.

[0071] In summary, the gesture recognition-based device control device, through the gesture recognition-based device control method described in the above embodiments, acquires a first gesture signal when the target device is idle and enters a control cycle. After detecting that the first gesture signal is a first target gesture, it triggers the device to enter a first target state and execute the corresponding operation. When the first gesture signal is interrupted, the control process is not directly terminated, but the device is controlled to enter a critical state to stop operation. If a second gesture signal is acquired in the critical state and the first target state exists in the current control cycle, the device is controlled to continue entering the first target state and execute the corresponding operation. Therefore, by setting a control cycle and a critical state, when the first gesture signal is interrupted due to non-subjective factors such as slight hand movement or shaking, the critical state can be used as an interaction buffer window to restore the first target operation within the same control cycle through the second gesture signal. This ensures the continuity of gesture intent recognition and the determinism of state switching, ultimately improving the reliability of device control.

[0072] The specific implementation of the gesture recognition-based device control device is basically the same as the specific embodiment of the gesture recognition-based device control method described above, and will not be repeated here. Subject to meeting the requirements of the embodiments of this disclosure, the gesture recognition-based device control device may also be equipped with other functional modules to implement the gesture recognition-based device control method in the above embodiments.

[0073] This disclosure also provides a lighting fixture, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the aforementioned gesture recognition-based device control method. Furthermore, the lighting fixture in this embodiment may also be equipped with the gesture recognition-based device control device described in the above embodiments to implement the gesture recognition-based device control method described in the above embodiments.

[0074] For example, please refer to Figure 5 , Figure 5This is a schematic diagram of a lighting application scenario provided by an embodiment of this disclosure. In this embodiment, for the infrared gesture control scenario of intelligent lighting, this embodiment proposes a finite state machine control method based on five states: idle, single scan, multi-scan (or dual scan), hover, and critical state. This method addresses the problems in the prior art, such as false triggering caused by intermittent gesture signals at extreme distances, frequent state jumps caused by hand tremors or breathing micro-movements during hovering, and chaotic switching between different gesture actions. By introducing critical states as buffers and confirmation channels, and combining them with control cycle definition, timer intention judgment, and gesture signal consistency judgment mechanism, this method achieves the desired results. When a light fixture detects a signal interruption in single-scan / multi-scan / hover mode, it does not directly return to the idle state. Instead, it enters a critical state and starts timing. If a signal consistent with the original gesture is obtained within a preset waiting time period and is in the same control cycle, the corresponding operation continues. If no valid signal is detected, it resets to the idle state and enters a new control cycle. At the same time, differentiated processing logic is designed for the characteristics of single-scan / multi-scan and hover gestures. This achieves clear isolation of gesture intent and anti-jitter preservation, while the lightweight algorithm ensures real-time performance, ultimately improving the naturalness and reliability of the light fixture's gesture control.

[0075] Please see Figure 6 , Figure 6 The hardware structure of a lamp according to another embodiment is illustrated. The lamp includes: The processor 601 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this disclosure. The memory 602 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 602 can store operating devices and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 602 and is called and executed by the processor 601 using the gesture recognition-based device control method of the embodiments of this disclosure. The input / output interface 603 is used to implement information input and output; The communication interface 604 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 605 transmits information between various components of the device (e.g., processor 601, memory 602, input / output interface 603, and communication interface 604); The processor 601, memory 602, input / output interface 603, and communication interface 604 are connected to each other within the device via bus 605.

[0076] This disclosure also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described gesture recognition-based device control method.

[0077] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0078] The embodiments described in this disclosure are for the purpose of more clearly illustrating the technical solutions of this disclosure and do not constitute a limitation on the technical solutions provided by this disclosure. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by this disclosure are also applicable to similar technical problems.

[0079] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this disclosure, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0080] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0081] Those skilled in the art will understand that all or some of the steps, apparatuses, or functional modules / units in the methods disclosed above can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0082] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in this disclosure and the foregoing drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, apparatus, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0083] It should be understood that in this disclosure, "at least one item" means one or more, and "more than one" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0084] In the several embodiments provided in this disclosure, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0085] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0086] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0087] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this disclosure. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0088] The preferred embodiments of the present disclosure have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present disclosure. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and spirit of the present disclosure shall be within the scope of the claims of the present disclosure.

Claims

1. A device control method based on gesture recognition, characterized in that, include: When the target device is idle, acquire the first gesture signal made by the target object and enter the current control cycle; When the first gesture signal is a first target gesture, the target device is controlled to enter a first target state, so that the target device performs a first target operation in the first target state; When the target device detects an interruption of the first gesture signal while in the first target state, it controls the target device to enter a critical state, so that the target device stops performing the first target operation in the critical state; When the target device receives a second gesture signal from the target object while in the critical state, and the target device exists in the first target state within the current control cycle, the target device is controlled to continue entering the first target state so that the target device continues to perform the first target operation.

2. The device control method based on gesture recognition according to claim 1, characterized in that, After acquiring the first gesture signal made by the target object when the target device is in an idle state and entering the current control cycle, the device control method based on gesture recognition further includes: When the first gesture signal is the second target gesture, the target device is controlled to enter the second target state, so that the target device performs the second target operation in the second target state; The first target gesture and the second target gesture are different, the first target state and the second target state are different, the first target state includes at least a hovering state, and the second target state includes at least a single-scan state and a double-scan state.

3. The device control method based on gesture recognition according to claim 2, characterized in that, When the first gesture signal is a second target gesture, the target device is controlled to enter a second target state so that the target device performs a second target operation in the second target state. After this, the gesture recognition-based device control method further includes: When the target device detects an interruption of the first gesture signal while in the second target state, it controls the target device to enter a critical state, so that the target device stops performing the second target operation in the critical state; When the target device receives a second gesture signal from the target object while in the critical state, and the target device does not exist in the first target state during the current control cycle, the target device is controlled to re-enter the critical state.

4. The device control method based on gesture recognition according to claim 2, characterized in that, When the first gesture signal is a second target gesture, the target device is controlled to enter a second target state so that the target device performs a second target operation in the second target state. After this, the gesture recognition-based device control method further includes: When the target device detects an interruption of the first gesture signal while in the second target state, it controls the target device to re-enter the idle state to enter the next control cycle.

5. The device control method based on gesture recognition according to claim 1, characterized in that, When the target device acquires the second gesture signal made by the target object in the critical state, and the target device exists in the first target state within the current control cycle, the system controls the target device to continue entering the first target state so that the target device continues to perform the first target operation, including: The timing begins after the target device enters the critical state; When the target device receives a second gesture signal from the target object during the waiting time period after the timer starts in the critical state, and the target device is in the first target state during the current control cycle, the target device is controlled to continue entering the first target state so that the target device continues to perform the first target operation.

6. The device control method based on gesture recognition according to claim 5, characterized in that, After the target device enters the critical state and the timing begins, the gesture recognition-based device control method further includes: If the target device does not detect any hand gesture signal from the target object within the waiting time period after the timing starts in the critical state, the target device is controlled to re-enter the idle state after the timing reaches the end of the waiting time period to enter the next control cycle.

7. The device control method based on gesture recognition according to claim 1 or 5, characterized in that, If the target device exists in the first target state during the current control cycle, controlling the target device to continue entering the first target state so that the target device continues to perform the first target operation includes: When the second gesture signal is consistent with the first gesture signal, if the target device exists in the first target state within the current control cycle, the target device is controlled to continue entering the first target state so that the target device continues to perform the first target operation. When the second gesture signal is inconsistent with the first gesture signal, the target device is controlled to re-enter the idle state to enter the next control cycle.

8. A device control apparatus based on gesture recognition, characterized in that, include: The gesture signal acquisition module is used to acquire the first gesture signal made by the target object when the target device is in an idle state, and then enter the current control cycle; An operation control module is used to control the target device to enter a first target state when the first gesture signal is a first target gesture, so that the target device performs a first target operation in the first target state; An interruption detection module is used to detect an interruption of the first gesture signal when the target device is in the first target state, and control the target device to enter a critical state so that the target device stops performing the first target operation in the critical state; The state transition module is used to acquire a second gesture signal made by the target object when the target device is in the critical state, and to control the target device to continue entering the first target state if the target device exists in the first target state during the current control cycle, so that the target device continues to perform the first target operation.

9. A lamp, characterized in that, The lamp includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the device control method based on gesture recognition as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the device control method based on gesture recognition as described in any one of claims 1 to 7.

Images