Indicator lamp control method and system for self-service consignment equipment, medium and product

Abstract

The invention provides an indicator light control method and system for self-service consignment equipment, a medium and a product. According to the method, a control processing unit firstly obtains the current service operation state of the self-service consignment equipment, collects a static image frame of the environment where the equipment is located, obtains a foreground shielding area through area recognition, and determines other areas as environment reference areas. Then, the control processing unit calculates a gray statistical value of the environment reference area, calculates a minimum visual identification brightness value meeting the human eye visual identification requirement based on the gray statistical value, and converts the minimum visual identification brightness value into a target duty ratio; and finally, the control processing unit generates a first pulse width modulation driving signal or a second pulse width modulation driving signal according to different service operation states, so that the indicating lamp emits light according to the corresponding driving signal. The method relieves the technical problem that the indicating lamp is difficult to adapt to a complex and changeable illumination environment, and realizes adaptive adjustment of the brightness of the indicating lamp along with the environment illumination intensity.

Description

Technical Field

[0001] This application relates to the field of computer vision technology, and in particular to indicator light control methods, systems, media, and products for self-service baggage check-in equipment. Background Technology

[0002] With the development of smart airports, self-service baggage check-in machines have been widely used in terminal departure halls, becoming an important facility for improving passenger travel efficiency. To guide passengers to quickly find available machines, self-service baggage check-in machines typically use light signals to visually display the current operating status of the machines to passengers on site.

[0003] In related technologies, indicator light control methods typically employ a preset fixed parameter mode. After detecting a change in device status (such as becoming idle), the control unit retrieves the preset color and a fixed brightness value corresponding to that status (usually a constant duty cycle or current), and outputs a corresponding drive signal to drive the indicator light to remain constantly lit with a constant luminous intensity, thereby providing basic status indication functionality.

[0004] However, airport terminal environments typically feature large glass curtain walls and internal lighting sources. This overlapping environment of natural and artificial light results in complex and dynamic background lighting conditions for self-service baggage check-in equipment. When strong outdoor light shines in and overlaps with indoor lighting, the constant-brightness indicator lights may be overwhelmed by the surrounding bright environment due to insufficient contrast, making it difficult for passengers at a distance to visually detect the equipment's availability signal. Conversely, in dim lighting conditions (such as on rainy days or at night), the brightness becomes glaring when natural light is absent. Summary of the Invention

[0005] This application provides a method, system, medium, and product for controlling indicator lights in self-service check-in equipment, which alleviates the technical problem that indicator lights are difficult to adapt to complex and changing lighting environments, and realizes the adaptive adjustment of indicator light brightness according to ambient light intensity.

[0006] In a first aspect, this application provides a method for controlling indicator lights on self-service baggage check-in equipment. The method is applied to a control processing unit of a control system, which also includes a self-service baggage check-in equipment and indicator lights, both connected to the control processing unit. The method includes: acquiring the current operational status of the self-service baggage check-in equipment and collecting static image frames of the environment in which the equipment is located according to a preset environmental monitoring cycle. The current operational status includes at least an idle state and a user operation state. The static image frames are used for region recognition to obtain a foreground occlusion region. The region in the static image frame excluding the foreground occlusion region is determined as an environmental reference region, where the foreground occlusion region represents the image range corresponding to an active subject or movable object. The grayscale statistical value of the environmental reference region is calculated. Based on the preset mapping relationship between background grayscale values ​​and visual recognition brightness, the minimum visual recognition brightness value that meets the preset human eye visual discrimination requirements in the current environment is calculated based on grayscale statistics. The minimum visual recognition brightness value is then converted into the corresponding target duty cycle. During the current environmental monitoring cycle, when the current business operation state is idle, a first pulse width modulation drive signal is generated, maintaining a duty cycle that periodically fluctuates between the preset duty cycle and the target duty cycle. During the current environmental monitoring cycle, when the current business operation state is user operation state, a second pulse width modulation drive signal is generated, maintaining a duty cycle at the value corresponding to the target duty cycle. The first or second pulse width modulation drive signal is then applied to the indicator light to drive it to illuminate.

[0007] By adopting the above technical solution, the control processing unit first acquires the current operational status of the self-service check-in equipment and collects static image frames of the environment in which the equipment is located according to a preset environmental monitoring cycle. Then, it identifies the foreground occlusion area through region recognition and designates the remaining area as the environmental reference area, mitigating the interference of moving subjects and movable objects on the ambient light detection. Next, the control processing unit calculates the grayscale statistical value of the environmental reference area, which is used to quantify the light intensity of the environmental reference area. Based on the preset mapping relationship between background grayscale values ​​and visual recognition brightness, the control processing unit calculates the minimum visual recognition brightness value that meets the visual discrimination requirements of the human eye based on the grayscale statistical value, and converts it into a target duty cycle, realizing the correlation between the indicator light target brightness and the ambient light intensity. Finally, for different operational statuses, the control processing unit generates a first pulse width modulation drive signal with periodically fluctuating duty cycle and a second pulse width modulation drive signal with a constant duty cycle, respectively. These drive signals are then applied to the indicator lights, causing the indicator lights to emit light according to the corresponding drive signals, realizing the adaptive adjustment of the indicator light brightness according to the ambient light intensity. This method alleviates the technical problem that constant brightness indicator lights cannot adapt to complex and changing lighting environments, and enables indicator lights to have sufficient visual recognition in strong light environments, while the brightness of indicator lights will not be dazzling in dim environments.

[0008] In conjunction with some embodiments of the first aspect, in some embodiments, calculating the grayscale statistical value of the environment reference region specifically includes: determining the image center coordinates of the static image frame, and dividing the environment reference region into multiple pixel sub-regions; calculating the spatial Euclidean distance of each pixel sub-region relative to the image center coordinates; assigning visual interference weights to each pixel sub-region based on the spatial Euclidean distance; and obtaining the ambient lighting reference value of the environment reference region by weighted calculation based on the average grayscale value of each pixel sub-region and the corresponding visual interference weight, and using the ambient lighting reference value as the grayscale statistical value.

[0009] By employing the above technical solution, the control processing unit first divides the environmental reference area into multiple pixel sub-regions. Then, it assigns visual interference weights based on the spatial Euclidean distance between each sub-region and the image center coordinates, reducing the influence of interference factors in non-core areas. Next, the control processing unit calculates the ambient illumination reference value based on the average grayscale value of each sub-region and its corresponding weight, using this as the grayscale statistical value. This method reduces the impact of interference factors on the illumination detection results and improves the accuracy of the ambient illumination reference value.

[0010] In conjunction with some embodiments of the first aspect, in some embodiments, after obtaining the ambient illumination reference value of the ambient reference area through weighted calculation, the method further includes: obtaining a brightness distribution histogram of the ambient reference area, and statistically analyzing the proportion of pixels whose brightness values ​​are in a preset highlight saturation range; when the proportion of pixels is greater than a preset proportion threshold, generating a highlight compensation gain coefficient that is positively correlated with the proportion of pixels; and using the highlight compensation gain coefficient to correct the ambient illumination reference value to obtain a corrected ambient illumination reference value.

[0011] By employing the above technical solution, the control processing unit first statistically analyzes the percentage of pixels in the high-saturation region of the environmental reference area to quantize the impact of high-saturation on illumination quantization. Then, when the percentage of pixels exceeds a preset threshold, a positively correlated highlight compensation gain coefficient is generated to correct the ambient illumination reference value. This method compensates for the illumination quantization deviation caused by high-saturation regions, improving the accuracy of the ambient illumination reference value.

[0012] In conjunction with some embodiments of the first aspect, in some embodiments, after the step of calculating the grayscale statistical values ​​of the environmental reference area, the method further includes: establishing a temporal sliding window for storing historical N frames of grayscale statistical values, calculating the data variance of the grayscale statistical values ​​in the temporal sliding window, where N is an integer greater than 1; when the data variance is greater than a preset convergence threshold, determining the duty cycle of the previous environmental monitoring cycle as the target duty cycle of the current environmental monitoring cycle; when the data variance is less than or equal to the preset convergence threshold, determining the mapping relationship between the preset background grayscale value and the visual recognition brightness based on the Weber-Fechner law.

[0013] By adopting the above technical solution, the control processing unit first stores historical grayscale statistics and calculates data variance through a time-series sliding window to quantify the degree of ambient light fluctuation. Then, based on the comparison between the variance and a preset convergence threshold, the control processing unit determines the source of the current target duty cycle. When the light fluctuation is severe, the historical duty cycle is used; when it is stable, the brightness mapping relationship is determined based on the Weber-Fechner law. This method takes into account both the dynamic stability of ambient light and the characteristics of human visual perception, alleviating the problem of frequent brightness jumps in indicator lights caused by light fluctuations.

[0014] In conjunction with some embodiments of the first aspect, in some embodiments, after the step of collecting static image frames of the environment where the self-service check-in equipment is located according to a preset environmental monitoring cycle, the method further includes: calculating the full-image texture complexity value of the static image frame; determining that the static image frame is in a visual occlusion state when the image texture complexity value is less than the occlusion determination threshold; in response to the visual occlusion state, receiving related environmental images collected in real time by at least two related self-service check-in equipment through the communication network between self-service check-in equipment; determining an alternative brightness reference value in the current environment based on the related environmental images, and using the alternative brightness reference value as the grayscale statistical value of the environmental reference area.

[0015] By adopting the above technical solution, the control processing unit first determines whether a static image frame is in a state of visual occlusion by analyzing the image texture complexity, thus identifying scenarios where image acquisition by a single device fails. Then, the control processing unit acquires environmental images of associated devices through the communication network between self-service check-in devices and determines alternative brightness reference values ​​as grayscale statistical values. This method enables the acquisition of effective illumination data even in occluded scenarios, achieving continuous adaptive adjustment of indicator light brightness.

[0016] In conjunction with some embodiments of the first aspect, in some embodiments, determining an alternative brightness reference value in the current environment based on associated environmental images specifically includes: acquiring a pre-constructed device location topology relationship; selecting images from multiple associated environmental images whose viewing angles overlap with those of the self-service check-in equipment as candidate images; calculating the global brightness mean of the candidate images; determining the location weight coefficient of the global brightness mean of the image based on the distance between the self-service check-in equipment corresponding to the candidate images in the device location topology relationship; and using the location weight coefficient to perform a weighted summation of the global brightness mean of the image to obtain the alternative brightness reference value.

[0017] By adopting the above technical solution, the control processing unit first filters candidate images of overlapping fields of view based on the topological relationship of the device location, ensuring the relevance of the candidate images to the device's environment. Then, the control processing unit assigns positional weights based on the distance between the associated automated baggage handling equipment and the device itself, and performs a weighted summation of the global brightness mean of the candidate images to obtain a substitute brightness reference value. This method improves the matching degree between the substitute brightness reference value and the actual ambient lighting of the automated baggage handling equipment, enhances the reliability of lighting data in occluded scenarios, and thus enables accurate adjustment of the indicator light brightness.

[0018] In conjunction with some embodiments of the first aspect, in some embodiments, generating a first pulse width modulation (PWM) drive signal whose duty cycle periodically fluctuates between a preset baseline maintenance duty cycle and a target duty cycle specifically includes: determining the luminance modulation contrast coefficient under the current environment according to the Weber-Fechner law; calculating the preset baseline maintenance duty cycle in reverse based on the target duty cycle and the luminance modulation contrast coefficient, such that the difference between the preset baseline maintenance duty cycle and the target duty cycle increases with the enhancement of ambient light; constructing a periodic mapping function with the target duty cycle as the upper limit of the peak and the preset baseline maintenance duty cycle as the lower limit of the trough; and generating the first pulse width modulation (PWM) drive signal using the periodic mapping function.

[0019] By employing the above technical solution, the control processing unit first determines the brightness modulation contrast coefficient based on the Weber-Fechner law. Then, the control processing unit calculates the basic duty cycle in reverse, constructs a periodic mapping function to generate the first pulse width modulation drive signal for the duty cycle fluctuation. This method makes the idle status indicator light exhibit periodic brightness fluctuations, which are more easily noticed by passengers compared to constant brightness, thus optimizing the idle status lighting indication effect.

[0020] In a second aspect, this application provides a control system including a control processing unit, a self-service check-in device, and an indicator light, wherein the self-service check-in device and the indicator light are respectively connected to the control processing unit; the control processing unit includes one or more processors and a memory; the memory is coupled to the one or more processors and is used to store computer program code, the computer program code including computer instructions, wherein the one or more processors call the computer instructions to cause the control processing unit to perform the method described in the first aspect and any possible implementation thereof.

[0021] Thirdly, this application provides a computer-readable storage medium including instructions that, when executed on a control processing unit, cause the control processing unit to perform the method described in the first aspect and any possible implementation thereof.

[0022] Fourthly, this application provides a computer program product, including a computer program / instructions that, when executed on a control processing unit, cause the control processing unit to perform the method described in the first aspect and any possible implementation thereof.

[0023] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages: 1. By employing the technical means of periodically acquiring static image frames of the environment, dividing the foreground occlusion area and the environment reference area, calculating the grayscale statistical value of the environment reference area to determine the target duty cycle adapted to the current environment, and generating differentiated pulse width modulation drive signals according to different business states of equipment idle / user operation, the technical problem of constant brightness indicator lights being difficult to adapt to the complex dynamic lighting environment of airports, being easily submerged in strong light and glaring in dim environment is effectively alleviated, and the technical effect of adaptive adjustment of indicator light brightness according to the ambient light intensity is achieved.

[0024] 2. By employing a technique that determines whether a static image frame is in a visually occluded state based on the complexity of the image texture, and then obtaining the associated device's environmental image and determining a substitute brightness reference value through the inter-device communication network when the image acquisition of a single device is occluded, the technical problem of the inability to obtain ambient light data and the resulting failure of indicator light brightness adjustment is effectively alleviated. This achieves the technical effect of continuous adaptive adjustment of indicator light brightness in occluded scenarios.

[0025] 3. By employing technical means such as determining the brightness modulation contrast coefficient based on the Weber-Fechner law, calculating the basic maintenance duty cycle in reverse and constructing a periodic mapping function, and generating a first pulse width modulation drive signal whose duty cycle fluctuates between the target duty cycle and the basic maintenance duty cycle, the technical problem of constant brightness indicator lights in the idle state of self-service baggage check-in equipment being difficult for passengers to notice in the complex airport environment is effectively alleviated. This achieves the technical effect of improving the visual recognition of idle state indicator lights and adapting to the prompting needs of complex airport environments. Attached Figure Description

[0026] Figure 1 This is a flowchart illustrating an indicator light control method for self-service baggage check-in equipment in an embodiment of this application. Figure 2 This is another flowchart illustrating the indicator light control method for self-service baggage check-in equipment in this application embodiment; Figure 3 This is a schematic diagram of the physical device structure of a control processing unit in an embodiment of this application. Detailed Implementation

[0027] The terminology used in the following embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification and appended claims of this application, the singular expressions “a,” “an,” “the,” “the,” “the,” and “this” are intended to include the plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this application refers to any or all possible combinations including one or more of the listed items.

[0028] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more.

[0029] The following describes the process of the method provided in this implementation. Please refer to [link / reference]. Figure 1 This is a flowchart illustrating an indicator light control method for self-service baggage check-in equipment in an embodiment of this application.

[0030] 101. Obtain the current operational status of the self-service check-in equipment and collect static image frames of the environment in which the self-service check-in equipment is located according to the preset environmental monitoring cycle. The current operational status includes at least the idle status and the user operation status.

[0031] Self-service baggage check-in equipment refers to automated hardware terminals installed in airports or other transportation hubs for passengers to check in their baggage independently; the preset environmental monitoring cycle refers to the time interval trigger signal set by the clock or timer inside the control processing unit to ensure continuous monitoring of changes in external lighting without overloading the processor; a static image frame refers to instantaneous digital image data captured by the control processing unit through a camera sensor, which includes lighting information, surrounding objects, and background features in the environment; an idle state indicates that the automated baggage check-in equipment is in standby mode, powered on but not operated; a user operation state indicates that the automated baggage check-in equipment is actively responding to user input, printing tags, or transferring baggage.

[0032] Specifically, the control processing unit first monitors or polls the main control program of the self-service check-in equipment in real time through an internal bus interface or software API interface to determine the current operational status. Simultaneously, to adapt to the complex and variable lighting environment of the airport hall (such as changes in natural light due to cloud cover or the activation of nighttime lights), the control processing unit maintains a visual acquisition thread independent of the business logic. When the internal timer reaches the preset environmental monitoring cycle (e.g., every 2 or 5 seconds), the control processing unit sends an acquisition command to the connected visual acquisition device (such as an industrial camera or wide-angle camera). The control processing unit then reads the latest image data from the frame buffer queue as a static image frame.

[0033] 102. Perform region identification on the static image frame to obtain the foreground occlusion region. Determine the region in the static image frame other than the foreground occlusion region as the environmental reference region. The foreground occlusion region represents the image range corresponding to the moving subject or movable object.

[0034] Region recognition refers to the image segmentation or object detection process in computer vision, aiming to classify images at the semantic or pixel level; foreground occlusion region is used to represent the set of pixels in a static image frame occupied by non-fixed facilities such as passenger bodies, trolleys, and suitcases. These objects are usually mobile and can block ambient light; environmental reference region refers to the background part in a static image frame that can realistically reflect or represent the current ambient light level, such as the floor, walls, ceiling, or distant fixed facilities; active subject refers to passengers or staff checking in luggage; movable object specifically refers to non-permanent objects such as luggage and trolleys; image range represents the set of coordinates covered by the subject or object on the two-dimensional image plane.

[0035] Specifically, when passengers approach the equipment to conduct business, their bodies block light from the overhead lights or windows, causing some areas of the image captured by the camera to darken. If the control processing unit directly uses the overall image brightness to adjust the indicator lights, it might mistakenly interpret the environment as darkening and increase the brightness of the indicator lights, resulting in glare. Therefore, the control processing unit calls image analysis algorithms to perform pixel-level or feature-level scanning of the input static image frames. The control processing unit first identifies newly appearing areas or areas with biometric features (such as faces or limbs) or specific rigid body features (such as the outline of a suitcase) in the image and marks them as foreground occlusion areas. Subsequently, the control processing unit uses logical NOT operations to extract all remaining areas in the image. The control processing unit determines this unoccluded area as the environmental reference area, serving as the data source for subsequent calculations of ambient light intensity, thus ensuring that when someone is operating the equipment, the indicator light brightness is still adjusted based on the background ambient light (such as sunlight from outside the window) rather than human shadows.

[0036] In some embodiments, optionally, the control processing unit first loads a pre-trained lightweight convolutional neural network (such as U-Net or MobileNet). Then, the control processing unit inputs a static image frame into the lightweight convolutional neural network, and the network's output layer calculates the classification probability for each pixel (e.g., classifying it as "person," "object," or "background"). Finally, the control processing unit aggregates pixels labeled "person" and "object" to generate a mask, defining it as a foreground occlusion region, and defines pixels labeled "background" as an environment reference region. It is understood that other methods can also be used, and this is not limited to these methods.

[0037] 103. Calculate the grayscale statistics of the environmental reference area.

[0038] Gray-scale statistical values ​​represent the quantitative values ​​of the overall illumination intensity of the environmental reference area. They are usually scalar values ​​between 0 and 255 (8-bit depth), reflecting the brightness of the environment.

[0039] Specifically, since the original static image frame is usually a color image based on the RGB (red, green, blue) color model, the control processing unit first performs color space conversion, weighting and fusing the RGB three-channel data into a single-channel grayscale data. The control processing unit only traverses and reads pixels within the environmental reference area, ignoring pixel data in foreground occlusion areas. During the traversal, the control processing unit performs statistical analysis on the pixel brightness values. This step involves more than just summation; the control processing unit can also remove extreme values ​​(such as noise caused by specular reflection) or perform calculations based on the weight of pixel position. Finally, the control processing unit outputs a single numerical value, namely the grayscale statistical value, which is linearly or non-linearly proportional to the ambient light intensity around the self-service check-in equipment.

[0040] In some embodiments, optionally, the control processing unit first converts each pixel within the environmental reference area into a grayscale value using a psychological brightness formula (e.g., Gray = 0.299 × R + 0.587 × G + 0.114 × B). Then, the control processing unit sums the grayscale values ​​of all pixels in the environmental reference area to obtain a total brightness sum and counts the total number of pixels in that area. Finally, the control processing unit divides the total brightness sum by the total number of pixels to obtain the arithmetic mean as the grayscale statistical value. Optionally, the control processing unit first constructs a grayscale histogram array of length 256. Then, the control processing unit iterates through all pixels in the environmental reference area, counts the frequency of each grayscale level, and fills the histogram. Finally, the control processing unit finds the median or modal value of the interval with the most concentrated pixel distribution in the histogram and determines it as the grayscale statistical value to resist interference from local highlights or shadows.

[0041] In some embodiments, to ensure the robustness of the computational logic, the control processing unit performs a validity check before computation. If, after foreground culling, the number of pixels in the remaining environmental reference area is zero (i.e., full image occlusion has occurred) or lower than a preset minimum sample size threshold (e.g., 5% of the total number of pixels), the current static image frame is determined to be invalid. In this case, the control processing unit retrieves the valid grayscale statistics calculated and cached in the previous environmental monitoring cycle as the result of this computation, or uses a preset safe default grayscale value (e.g., 128 representing medium brightness), thereby avoiding calculation errors due to division by zero and maintaining the continuity of the control signal.

[0042] 104. Based on the mapping relationship between the preset background grayscale value and the visual recognition brightness, calculate the minimum visual recognition brightness value that meets the preset human eye visual discrimination requirements in the current environment based on the grayscale statistical value, and convert the minimum visual recognition brightness value into the corresponding target duty cycle.

[0043] The preset background grayscale value refers to a pre-stored or calibrated set of reference grayscale data representing different ambient light levels; the visual recognition brightness represents the photometric brightness (usually measured in nits or lumens) that the indicator light needs to achieve under specific background lighting conditions, which should be clearly distinguishable from the background by the human eye without causing glare; the mapping relationship defines the correspondence between ambient grayscale and the required indicator light brightness; the minimum visual recognition brightness value refers to the lower limit threshold of brightness that can be effectively perceived by passengers in the current environment; the target duty cycle refers to the proportion of the high-level time in the pulse width modulation signal output by the control processing unit to the drive circuit in order for the indicator light to reach the brightness value.

[0044] Specifically, the control processing unit first reads the calculated grayscale statistics, which objectively reflects the current physical lighting environment. Next, the control processing unit retrieves the internally stored mapping relationship, which reflects the principle of Weber's Law: the brighter the background, the greater the increase in light intensity must be to produce a perceptible difference. The control processing unit substitutes the grayscale statistics into this mapping relationship to calculate the minimum visually discernible brightness value in the current environment; this value is a theoretical photometric measure. To drive hardware execution, the control processing unit performs analog-to-digital conversion logic, mapping this theoretical brightness value to circuit control parameters based on the indicator light hardware's current-brightness characteristic curve, i.e., calculating the precise target duty cycle (e.g., a specific value between 0% and 100%). This process ensures that under strong direct sunlight, the control processing unit outputs a high duty cycle to prevent the light from being overwhelmed; and under cloudy or rainy conditions or at night, it outputs a low duty cycle to prevent glare.

[0045] In some embodiments, optionally, the control processing unit first calls a logarithmic function or a power function (such as the Gamma correction formula), then uses the grayscale statistics as the input function as the independent variable to calculate the normalized brightness coefficient, and then multiplies the coefficient by the maximum register value of the PWM controller (such as 255 or 1024), and rounds it to obtain the target duty cycle.

[0046] 105. During the current environmental monitoring cycle, when the current business operation status is idle, a first pulse width modulation drive signal is generated, in which the duty cycle maintains a periodic fluctuation between the preset duty cycle and the target duty cycle.

[0047] The preset baseline duty cycle represents the brightness parameter of the indicator light at the trough of the breathing light effect, which is lower than the target duty cycle (peak). The first pulse width modulation drive signal refers to the electrical signal generated by the control processing unit, whose duty cycle changes with time in a specific waveform (such as a sine wave or a triangular wave). Periodic fluctuation refers to a dynamic visual effect (often called a breathing light effect) designed to attract the attention of distant passengers in a complex airport background through dynamic changes in brightness. The Weber-Fechner law is used in this step to determine the amplitude of the fluctuation, that is, the amount of light intensity change perceived by the human eye is proportional to the logarithm of the physical light intensity.

[0048] Specifically, when the control processing unit confirms that the current business operation status is idle, its control strategy switches from constant display to dynamic attraction. Although the control processing unit has calculated the target duty cycle (as the peak of the brightest moment) to adapt to the environment, the breathing effect will fail if the trough (darkest moment) of the breathing effect is not set reasonably. For example, under strong light, if the trough is too dark, it looks like the light is off; under weak light, if the trough is too bright, the breathing effect is not obvious. Therefore, the control processing unit needs to generate a PWM signal that varies with time. The control processing unit constructs a function that changes the duty cycle value over time, using the target duty cycle as the upper limit and the calculated basic maintenance duty cycle as the lower limit. In each PWM clock cycle, the control processing unit refreshes the value of the output register, so that the pulse width of the output signal presents a smooth cycle of narrow to wide and then wide to narrow. The generated first pulse width modulation drive signal is applied to the indicator light, thus forming a visual effect where the brightness changes with the ambient light (the brighter the ambient light, the brighter the indicator light) and has a dynamic breathing effect.

[0049] In some embodiments, the control processing unit generates a dynamic fluctuation signal based on the Weber-Fechner law through the following steps: The control processing unit first reads the gray-scale statistical value of the environmental reference area calculated in step 103 (denoted as G). envThe Weber-Fechner law formula is used to calculate the luminance modulation contrast coefficient (denoted as η) under the current environment. The calculation formula is: η = K × ln(1 + G) env Where η represents the brightness modulation contrast coefficient, used to quantify the depth ratio of the breathing effect; K is a preset sensitivity constant, typically ranging from 0.1 to 0.3, used to adjust the overall response rate to changes in illumination; ln is the natural logarithm operator; the constant 1 is used to prevent negative infinity from occurring during logarithmic operations; G env This is the normalized grayscale statistical value, typically ranging from 0 to 1. This formula causes the brightness modulation contrast coefficient η to increase non-linearly with increasing ambient light.

[0050] Then, the control processing unit calculates the preset baseline maintenance duty cycle in reverse, based on the target duty cycle and the luminance modulation contrast coefficient. The control processing unit calculates the preset baseline maintenance duty cycle (denoted as D1, as the upper limit of fluctuation) based on the determined target duty cycle (D1, as the upper limit of fluctuation) and the calculated luminance modulation contrast coefficient η. The calculation formula is: D0 = D1 × (1 - η). Where D0 represents the preset baseline maintenance duty cycle, i.e., the duty cycle value at the darkest moment in the breathing effect; D1 represents the target duty cycle, i.e., the duty cycle value at the brightest moment in the breathing effect; (1 - η) is the retention coefficient, used to determine the proportional relationship between the trough and the peak. When calculating using the above formula, the control processing unit limits the amplitude of the luminance modulation contrast coefficient η. The control processing unit presets a maximum contrast threshold η. max (For example, a value of 0.8 or 0.9, and strictly less than 1). When the value of η calculated according to the formula is greater than η... max At that time, the control processing unit assigns η the value η. max This limiting process ensures that the retention factor (1-η) is always positive, thus guaranteeing that the calculated base sustaining duty cycle D0 is always within the effective driving range and preventing the generation of invalid negative pulse width signals. The formula clarifies the calculation logic of the control processing unit obtaining the base sustaining duty cycle D0 by subtracting an amplitude component (i.e., D1×η) from the target duty cycle D1. Therefore, when the ambient light G... env During enhancement, the brightness modulation contrast coefficient η increases, leading to a decrease in the retention coefficient (1-η), which in turn reduces the calculated preset baseline maintenance duty cycle D0. This achieves the technical effect that the difference between the preset baseline maintenance duty cycle and the target duty cycle (i.e., the breathing depth ΔD=D1-D0) increases with the enhancement of ambient light.

[0051] Finally, the control processing unit constructs a periodic mapping function with the target duty cycle as the upper limit of the peak (D1) and the preset basic maintenance duty cycle as the lower limit of the trough (D0). The control processing unit uses the current timestamp t of the system clock and substitutes it into the formula: D(t) = D0 + [(D1-D0) / 2] × [(1+sin(ω×t))]. Where D(t) represents the instantaneous duty cycle value output at the current time t; (D1-D0) / 2 represents the amplitude radius of the fluctuation, i.e., the distance from the center line to the peak or trough; ω represents the preset angular frequency, in radians per second, used to determine the speed of the breathing effect (period T = 2π / ω); the value of (1+sin(ω×t)) ranges from 0 to 2, causing D(t) to change periodically between D1 and D0. The above-described construction of a periodic mapping function using a sine function (sin) is only a preferred embodiment of this application. In practical applications, this periodic mapping function can also be constructed based on a triangular wave function, a trapezoidal wave function, or a Gaussian pulse function. As long as the function can achieve a smooth fluctuation between the target duty cycle (D1) and the basic maintenance duty cycle (D0) over time, it falls within the scope of this application's technical concept. In particular, the D(t) calculated using the above formula ensures that the breathing depth automatically increases as ambient light intensifies, which is key to achieving visibility in strong light and softness in low light.

[0052] The control processing unit calculates the instantaneous duty cycle value D(t) at each moment in real time according to the periodic mapping function, and outputs the calculation result to the duty cycle configuration register of the pulse width modulation controller, thereby driving the indicator light to produce a breathing effect that adapts the brightness interval to the current ambient light intensity, and finally generating the first pulse width modulation drive signal.

[0053] 106. During the current environmental monitoring cycle, when the current business operation status is user operation status, generate a second pulse width modulation drive signal with a duty cycle maintained at the value corresponding to the target duty cycle.

[0054] The second pulse width modulation drive signal refers to an electrical signal with a constant duty cycle generated by the control processing unit, whose high-level to low-level ratio remains constant over multiple consecutive clock cycles.

[0055] Specifically, when the control processing unit detects a change in the service status to a user operation status, the focus is on "eliminating interference and providing clear guidance." Unlike the effect in the idle state, users need a stable light source to read screen information or check luggage tags when operating the device. Dynamically changing light may distract users or cause visual fatigue. Therefore, the control processing unit first obtains the target duty cycle calculated in step 104. It should be noted that although the signal is constant, this constant value is adapted to ambient light, remaining consistently bright in strong light (high duty cycle) and consistently dim in weak light (low duty cycle). The control processing unit writes this target duty cycle value into the comparison register of the PWM generator, generating a second pulse width modulation drive signal with a stable waveform and no frequency fluctuations, conveying the semantic signal that the self-service check-in device is "busy" or "serving".

[0056] 107. Apply the first pulse width modulation drive signal or the second pulse width modulation drive signal to the indicator light to drive the indicator light to illuminate.

[0057] Indicator lights are light-emitting entities installed on the body of self-service check-in equipment, and are usually composed of light-emitting diode arrays, LED light strips or light guide strips.

[0058] Specifically, because the I / O pin output current capability of the control processing unit (usually a microcontroller MCU or CPU) is limited (typically only in the milliamp range), it is insufficient to directly illuminate a high-power indicator light strip. Therefore, the control processing unit outputs the generated PWM signal (first or second pulse width modulation drive signal) to a dedicated drive circuit interface. The control processing unit controls the conduction and cutoff of the power switching transistor (such as a MOSFET or transistor) in the drive circuit by changing the pin level. When the PWM signal is high, the switching transistor is on, and power current flows through the indicator light; when the PWM signal is low, the switching transistor is off, and the current is interrupted. Since the frequency of the PWM signal is usually very high (e.g., above 1kHz), utilizing the persistence of vision effect of the human eye, the indicator light does not flicker but exhibits an effective average brightness proportional to the duty cycle. Through this step, the control processing unit successfully transforms ambient light data and business status logic into visible optical feedback.

[0059] The indicator light control method for self-service check-in equipment described in this application involves a control processing unit that first acquires the operational status of the self-service check-in equipment and captures static image frames of the environment. Then, it uses region recognition to divide the foreground occlusion area into an environmental reference area, eliminating interference from moving objects or subjects on light detection. Next, the control processing unit calculates the grayscale statistics of the environmental reference area, determines the target duty cycle based on a preset mapping relationship, and establishes the adaptation between ambient light and indicator light brightness. Finally, for idle or user-operated states, the control processing unit generates differentiated pulse width modulation drive signals and applies them to the indicator lights, achieving targeted brightness adjustment. This method alleviates the technical problem of indicator lights being unable to adapt to complex and changing lighting environments, realizing adaptive adjustment of indicator light brightness according to ambient light intensity.

[0060] The following provides a more detailed description of the process of the method provided in this implementation. Please refer to [link / reference]. Figure 2 This is another flowchart illustrating the indicator light control method for self-service check-in equipment in this application embodiment.

[0061] 201. Obtain the current operational status of the self-service baggage check-in device and collect static image frames of the environment in which the self-service baggage check-in device is located according to the preset environmental monitoring cycle. The current operational status includes at least the idle state and the user operation state. (Refer to the execution process of step 101) 202. Perform region identification on the static image frame to obtain the foreground occlusion region. Define the region in the static image frame excluding the foreground occlusion region as the environmental reference region. The foreground occlusion region represents the image range corresponding to the moving subject or movable object. (Refer to the execution process of step 102) 203. Calculate the full-image texture complexity of a static image frame.

[0062] Image texture complexity is a scalar value used to quantify the frequency of pixel grayscale spatial changes, edge richness, and detail clarity in a static image frame. It reflects the richness of information contained in the image.

[0063] Specifically, in the complex environment of airports, the cameras of self-service baggage check-in machines may be leaned on by unsuspecting passengers, briefly obstructed by large luggage passing by, or covered by posters. In these cases of severe obstruction, the image typically appears as large areas of monotonous color blocks (such as pure black, pure gray, or some blurry, single fabric texture), lacking the spatial depth and edge details expected of a normal environment. Therefore, the control processing unit performs image processing algorithms to mathematically transform the entire image and calculate the overall image texture complexity value. This process aims to convert the flatness of the image into a specific numerical value from the perspective of the frequency domain or statistical domain. This value is only high when the image contains rich environmental features (such as light edges, crowd outlines, and building lines); conversely, if the image loses high-frequency information due to obstruction, the value will decrease.

[0064] 204. When the image texture complexity value is less than the occlusion determination threshold, the static image frame is determined to be in a state of visual occlusion.

[0065] The occlusion threshold is a pre-set critical value used to distinguish between the normal field of view and the field of view covered by objects at close range. This value is usually the lower limit obtained by statistical analysis of a large number of occluded samples (such as clothing and the surface of boxes). The visual occlusion state is used to indicate that the camera acquisition window of the self-service check-in equipment is physically blocked by external objects, resulting in the inability to obtain the lighting information of the distant environment.

[0066] Specifically, in a normal airport departure hall environment, due to the presence of ceiling light strips, floor tile gaps, distant counters, and flowing crowds, the images captured by the camera contain rich high-frequency texture information, and their complexity values ​​are usually maintained at a high level. However, when the camera is obstructed, the imaging plane focuses on the surface of a very close object (such as the surface of a backpack or a passenger's back), resulting in a blurred focal plane and a lack of obvious edge features within the field of view, causing the complexity value to drop precipitously. The control processing unit compares the calculated image texture complexity value with the occlusion determination threshold. When the image texture complexity value is less than the occlusion determination threshold, the control processing unit determines that the current low texture features are not caused by a dark environment (pure black environments usually also have noisy textures), but by physical occlusion. At this time, the control processing unit updates the visual flag in the system state machine to the visual occlusion state, avoiding the erroneous judgment of an extremely dark environment (mistakenly thinking it is late at night) due to a completely black screen and misleading the indicator light output brightness.

[0067] 205. In response to visual occlusion, receive real-time images of the associated environment from at least two associated self-service check-in devices via the communication network between the self-service check-in devices.

[0068] Associated self-service check-in equipment refers to other self-service check-in equipment that is geographically adjacent to the current self-service check-in equipment and is located in the same lighting area; communication network refers to the local area network, industrial bus or wireless mesh network that connects various self-service check-in equipment for data exchange between equipment; associated environmental image refers to unobstructed real-time images or pre-processed image data captured by the cameras of associated self-service check-in equipment.

[0069] Specifically, when the control processing unit confirms that it is in a state of visual obstruction, it means that its own camera has failed and cannot be used as a basis for adjusting the brightness of the indicator lights. Since airport self-service check-in machines are usually arranged in rows, the lighting environment (such as sunlight angle and overhead light brightness) of adjacent machines is highly consistent. The control processing unit broadcasts or unicasts data requests to the local area network via the network interface card (NIC) to address its associated self-service check-in machines. To prevent data deviations caused by the failure or obstruction of a single neighboring device, the control processing unit requests data from at least two neighbors. The control processing unit receives real-time image data packets from its neighbors via a communication protocol; these images represent the actual, unobstructed ambient lighting conditions of the area at the current moment.

[0070] To reduce bandwidth consumption on the dedicated network for self-service baggage check-in equipment and ensure data security, the aforementioned associated environmental images are not original high-resolution RAW format images. Before transmission, the associated self-service baggage check-in equipment downsamples the acquired images (e.g., compresses them to QVGA resolution) or only extracts the luminance channel (Y channel) data for transmission. This lightweight data transmission method makes it possible to complete data interaction between multiple devices within a millisecond-level control cycle without affecting the normal baggage check-in data flow.

[0071] 206. Determine the alternative brightness reference value in the current environment based on the associated environmental image, and use the alternative brightness reference value as the gray-scale statistical value of the environmental reference area.

[0072] The alternative brightness reference value refers to a virtual value synthesized through calculation to simulate the current ambient light intensity when the current self-service check-in equipment is unable to effectively collect light data. This value is used to take over and replace the original grayscale statistical value.

[0073] Specifically, although the self-service check-in devices are in the same large environment, the specific micro-environment of each device (such as whether it is next to a pillar or directly under a spotlight) still differs. Directly taking the value of a single device may introduce local bias. Therefore, the control processing unit first analyzes the received multiple images and extracts the brightness component. Subsequently, based on the spatial relationship between each device and itself, the control processing unit calculates a value that comprehensively reflects the overall illumination level of the current area, i.e., a substitute brightness reference value. Finally, the control processing unit forcibly writes this substitute brightness reference value into the register address in memory that originally stored the grayscale statistics of the environment reference area. This operation allows the subsequent "target duty cycle calculation" module to operate according to the standard Weber-Fechner law logic without needing to be aware of whether there is occlusion at the front end, thus ensuring the universality of the control logic and the robustness of the system.

[0074] Through the above steps, the alternative brightness reference value obtained by the control processing unit under visual occlusion is logically equivalent to the grayscale statistical value described in step 103. Once the alternative brightness reference value is determined, the control processing unit uses this alternative brightness reference value to substitute into the mapping relationship between the preset background grayscale value and the visual recognition brightness, and continues the subsequent target duty cycle calculation and drive signal generation process. This ensures that the subsequent illumination-brightness mapping logic is consistent and universal regardless of whether the device is occluded.

[0075] In some embodiments, the determination of alternative brightness reference values ​​based on associated environmental images can be achieved through the following steps: The control processing unit first reads the pre-built device location topology relationship (referring to a pre-configured data structure or mapping table describing the arrangement order, relative distance, and orientation angle of each self-service check-in device in physical space, such as a JSON-formatted device layout coordinate diagram) in the memory, and traverses the metadata (header information) of all received associated environmental images. The control processing unit compares the field of view parameters in the metadata with its own field of view parameters, eliminates images whose fields of view are completely non-overlapping due to back-to-back placement or obstruction, and selects images whose viewing angle overlaps with that of the self-service check-in device (indicating that the camera acquisition ranges of different devices intersect in three-dimensional space and can observe the visible range of the same environmental area) as candidate images to ensure the relevance of the lighting data source.

[0076] Next, the control processing unit performs pixel traversal on each candidate image frame, sums the brightness of all pixels and divides by the total number of pixels to calculate the global average brightness of each candidate image (denoted as L). i Subsequently, the control processing unit queries the device location topology again to calculate the physical straight-line distance (denoted as D) between the associated self-service check-in device to which each candidate image belongs and the current self-service check-in device. iThe control processing unit is based on the inverse proportional function logic (W). i =1 / D i Alternatively, the Gaussian decay model can be used to calculate the positional weight coefficients (W) for each image. i ), and normalize all weight coefficients (so that all W i The sum of these values ​​is 1, thus ensuring that the closer the device is, the greater its contribution to the results, because the ambient lighting conditions of the neighboring device are most similar to those of the local device.

[0077] Finally, the control processing unit uses the normalized position weight coefficients to perform a weighted summation operation on the global brightness mean of each candidate image (substitute value = Σ(L)). i ×W i This yields the final alternative brightness reference value.

[0078] 207. When the image texture complexity value is greater than or equal to the occlusion determination threshold, determine the image center coordinates of the static image frame, and at the same time divide the environment reference area into multiple pixel sub-regions.

[0079] Image center coordinates refer to the position of the center point of a static image frame on a two-dimensional plane geometry, usually represented by half the width and height coordinates of the image resolution (W / 2, H / 2); pixel sub-regions refer to several rectangular blocks, grids, or specific geometric units that are logically cut or mapped from the environmental reference area that no longer contains foreground occlusions (such as people or luggage).

[0080] Specifically, when the control processing unit determines that the image texture complexity value is greater than or equal to the occlusion determination threshold, it indicates that the camera's field of view is clear, not obstructed by objects, and the acquired image can accurately reflect the ambient lighting. At this point, in order to analyze the lighting distribution more precisely and eliminate possible local interference (such as misjudgments caused by vignetting at the lens edges or strong light in the center), the control processing unit reads the resolution parameters of the image sensor and calculates the physical geometric center coordinates of the image. Simultaneously, the control processing unit performs meshing processing on the environmental reference region determined in step 202. Since the environmental reference region may be irregularly shaped (because irregular foreground occlusion regions have been subtracted), the control processing unit divides the image into several regular grids (e.g., an N×M matrix) using a masking method, retaining only valid pixels belonging to the environmental reference region in each grid. This step not only discretizes the image but also provides basic data units for subsequent weighted calculations based on spatial distance.

[0081] 208. Calculate the spatial Euclidean distance of each pixel sub-region relative to the coordinates of the image center.

[0082] Spatial Euclidean distance refers to the length of a straight line connecting the geometric center point of each pixel sub-region to the center of the image on a two-dimensional image plane. It measures the degree to which a sub-region deviates from the center of the field of view.

[0083] Specifically, the area at the center of the image typically best represents the ambient brightness directly in front, while edge areas are easily affected by stray light, lens distortion, or non-core background. Therefore, the control processing unit traverses each valid pixel sub-region, first calculating the centroid coordinates of that sub-region (i.e., the arithmetic mean of all pixel coordinates within that region). Next, the control processing unit uses the Pythagorean theorem (distance formula) to perform calculations with the coordinates of the entire image center determined in step 207. The control processing unit calculates the square of the difference between the horizontal and vertical coordinates, combines the two numbers, and takes the square root to obtain the spatial Euclidean distance of the pixel sub-region. The control processing unit stores the calculated distance value in a distance vector array, which corresponds one-to-one with each pixel sub-region.

[0084] For example, suppose the resolution of the static image frame acquired by the control processing unit is 640×480 pixels. First, the control processing unit calculates and determines the center coordinates of the entire image to be O(320, 240).

[0085] After dividing the environmental reference area into a grid, the control processing unit identifies two specific pixel sub-regions, labeled as sub-region A and sub-region B, respectively. The control processing unit first iterates through and calculates sub-region A (assuming it's located in the ceiling area near the center of the image), obtaining its centroid coordinates as P. A (350, 280). At this point, the control processing unit performs Euclidean distance calculation. First, it calculates the difference in the horizontal coordinate: 350-320=30, and the difference in the vertical coordinate: 280-240=40; then it squares them respectively to get 900 and 1600; the two are added together to get 2500; finally, it takes the square root to get the spatial Euclidean distance of sub-region A as 50 pixels.

[0086] Subsequently, the control processing unit traverses the calculation sub-region B (assuming it is located in the distant ground region at the edge of the image) and obtains its centroid coordinates as P. B (20, 400). The control processing unit performs Euclidean distance calculation. The difference in the horizontal coordinate is 20-320=-300, and the difference in the vertical coordinate is 400-240=160; after squared, they are 90000 and 25600 respectively; adding them together, we get 115600; taking the square root, we get that the spatial Euclidean distance of sub-region B is approximately 340 pixels.

[0087] Finally, the control processing unit stores the calculated values ​​50 and 340 into the distance vector arrays respectively. It can be seen that sub-region A is closer to the center (50 is less than 340), and will be assigned a higher visual interference weight (representing high confidence) by the control processing unit in subsequent steps. Sub-region B, being farther away, will be assigned a lower weight, thus accurately quantifying the contribution of different regions to the illumination determination.

[0088] 209. Assign visual interference weights to each pixel sub-region based on spatial Euclidean distance.

[0089] Visual interference weight refers to a normalized numerical coefficient (usually between 0 and 1) used to quantify the reliability and importance of the corresponding pixel sub-region in representing the overall ambient light intensity. The magnitude of the weight is inversely proportional to the probability that the region is interfered with by external non-environmental factors (such as lens distortion and edge stray light).

[0090] Specifically, the allocation strategy for visual interference weights depends on the optical characteristics of the camera and the ambient lighting layout of the self-service check-in device. Scenario 1 (for lens optical interference): In most cases, considering the vignetting and distortion effects of wide-angle lenses, the brightness data at the image edges is unreliable. In this case, the closer to the image center (the smaller the spatial Euclidean distance), the larger the weight value is assigned; the farther away, the smaller the weight value is assigned. Scenario 2 (for ambient shadow interference): In scenarios with strong overhead lighting and users standing very close together, the central area of ​​the image is prone to falling into the shadow cast by the user's body (even if the user's body has been segmented and removed from the foreground, the remaining central background may still be in shadow). In this preset mode, the control processing unit adopts a reverse weighting strategy, that is, the farther away from the image center (the larger the spatial Euclidean distance, the closer to the ceiling light strip area above or to the sides of the image), the larger the weight value is assigned, in order to reduce the interference of the central shadow on the ambient light judgment. The control processing unit selects to use the above-mentioned monotonically decreasing function or monotonically increasing function for mapping according to the system preset or initial calibration parameters. Finally, the control processing unit normalizes all assigned weights to ensure that the sum of the weights of all sub-regions equals 1.

[0091] 210. Based on the average gray value of each pixel sub-region and the corresponding visual interference weight, the ambient light reference value of the environment reference region is obtained by weighted calculation, and the ambient light reference value is used as the gray value.

[0092] Ambient light reference value refers to a comprehensive brightness index that, after spatial location correction, represents the objective brightness of the physical space where the self-service check-in equipment is located.

[0093] Specifically, the control processing unit has obtained two sets of data: one set is the average grayscale value of each pixel sub-region (representing local brightness), and the other set is the corresponding visual interference weight (representing local confidence). The control processing unit activates the multiply-accumulate unit of the digital signal processor to traverse each pixel sub-region. In each iteration, the control processing unit multiplies the average grayscale value of the sub-region by its corresponding weight coefficient to obtain the weighted brightness component of the sub-region. Subsequently, the control processing unit sums up the weighted brightness components of all sub-regions. Since the weights have been normalized, the summed result is the ambient lighting reference value. Compared to a simple overall image average, this value effectively filters out the effects of vignetting at the lens edges and background stray light, and is closer to the perceived brightness when a human eye stands in front of the device looking directly forward. Finally, the control processing unit converts the format of this value to a system-defined standard data type and assigns it to the grayscale statistics variable.

[0094] In some embodiments, after obtaining the ambient lighting reference value, considering extreme lighting conditions, the ambient lighting reference value can be corrected (i.e., specular compensation), and then the corrected ambient lighting reference value can be used as the grayscale statistical value. The control processing unit first performs histogram statistical analysis on the pixel data of the environmental reference area. Instead of focusing on the overall distribution, the unit concentrates on the high end of the brightness extremes, i.e., the preset highlight saturation range (e.g., [245, 255] in 8-bit grayscale). The control processing unit counts the total number of pixels falling within this range and calculates its proportion to the total number of pixels in the environmental reference area, obtaining the pixel percentage. This percentage reflects whether there is a strong light source directly shining in the field of view (such as sunlight directly hitting the lens or a bright spotlight), causing overexposure or saturation of the sensor. When the sensor is saturated, the actual physical brightness may far exceed 255, but the value is truncated to 255.

[0095] Next, the control processing unit compares the calculated pixel count percentage with a preset percentage threshold. When the pixel count percentage is less than or equal to the preset percentage threshold, it indicates no significant overexposure, and the original value is maintained. When the pixel count percentage is greater than the preset percentage threshold, the control processing unit determines that the current weighted calculation result actually underestimates the ambient brightness (because a large amount of data is truncated). At this time, the control processing unit calls the compensation algorithm to generate a highlight compensation gain coefficient greater than 0. This highlight compensation gain coefficient is positively correlated with the pixel count percentage; that is, the more saturated pixels there are, the stronger the light and the more data is truncated, and the greater the compensation gain required. For example, the control processing unit can use a linear function (highlight compensation gain coefficient = k × (pixel count percentage - preset percentage threshold)) to calculate it, where k is a compensation sensitivity constant, a preset, fixed proportional constant. It determines the aggressiveness of the compensation algorithm; the larger the k value, the more sensitive the system is to highlight areas, and even a small amount of overexposure will lead to a large numerical correction; the smaller the k value, the gentler the compensation effect. This value is usually calibrated in advance by the developers based on the dynamic range characteristics of the camera sensor.

[0096] Finally, the control processing unit corrects the previously calculated ambient light reference value using a highlight compensation gain coefficient. The correction formula is typically expressed as gain multiplication logic (corrected value = original reference value × (1 + highlight compensation gain coefficient)). Through this step, the control processing unit restores the brightness information lost due to insufficient sensor dynamic range, enabling subsequent steps to calculate a higher target duty cycle, ensuring the indicator light remains sufficiently bright even in glaring environments and improving visibility. Ultimately, the control processing unit confirms this corrected ambient light reference value as the final grayscale statistical value.

[0097] 211. Establish a time-series sliding window for storing historical N frames of grayscale statistics, and calculate the data variance of the grayscale statistics in the time-series sliding window, where N is an integer greater than 1.

[0098] A time-series sliding window refers to a fixed-length data queue buffer in random access memory allocated by the control processing unit, following the first-in-first-out principle, used to store illumination sampling data within the most recent consecutive time period; N represents the depth or capacity of the window, which is usually set according to the camera frame rate and the required filtering smoothness (e.g., N=10 or N=20); data variance is a numerical value used in statistics to measure the dispersion of a set of data, used to quantify the degree of fluctuation of ambient light over time.

[0099] Specifically, the control processing unit continuously calculates new grayscale statistical values ​​(i.e., the results of steps 103 or 210) during the continuous environmental monitoring cycle. To prevent drastic changes in indicator light brightness caused by accidental environmental changes (such as flashing lights or rapidly moving clouds), the control processing unit maintains an array of length N. Whenever a new grayscale statistical value is generated, the control processing unit adds it to the head of the window queue and removes the oldest data from the tail of the queue to maintain a constant queue length. Next, the control processing unit reads all N historical grayscale statistical values ​​currently stored in the window and executes a variance calculation algorithm. This calculation aims to assess whether the current lighting environment is in a steady state or transient state. If the variance is large, it indicates that the ambient light is changing rapidly and unstable; if the variance is small, it indicates that the ambient light is relatively constant and can serve as a reliable basis for adjusting the indicator light brightness.

[0100] 212. When the data variance is greater than the preset convergence threshold, the duty cycle of the previous environmental monitoring cycle is determined as the target duty cycle of the current environmental monitoring cycle.

[0101] The preset convergence threshold refers to the pre-calibrated critical variance value used to define whether the lighting environment is stable, and is used to distinguish between normal gradual lighting and disruptive sudden lighting. The duty cycle of the previous environmental monitoring cycle refers to the value written to the pulse width modulation register by the control processing unit in the most recent successful brightness adjustment operation.

[0102] Specifically, the control processing unit compares the calculated data variance with a preset convergence threshold. When the data variance exceeds the preset convergence threshold, it indicates that the ambient light is in a non-steady state, exhibiting high-frequency jitter or severe fluctuations. In this case, the latest calculated grayscale statistical value is likely noise or short-term interference. Directly adjusting the indicator light based on this could cause unpleasant flickering or inconsistent brightness (breathing effect disorder). Therefore, the control processing unit ignores the light requirement calculated for the current cycle, retrieves the target duty cycle value from the previous cycle stored in the register, and assigns it to the target duty cycle variable for the current cycle, maintaining the indicator light brightness unchanged. This method waits for the ambient light to stabilize, thus avoiding the illusion of visual fatigue or equipment malfunction for passengers.

[0103] 213. When the data variance is less than or equal to the preset convergence threshold, the mapping relationship between the preset background grayscale value and the visual recognition brightness is determined based on the Weber-Fechner law.

[0104] The Weber-Fechner law in psychophysics describes the principle that the subjective perception of changes in brightness is proportional to the logarithm of the physical brightness intensity.

[0105] Specifically, when the data variance is less than or equal to a preset convergence threshold, the control processing unit confirms that the ambient light has converged and is in a stable state. At this point, the control processing unit considers the current grayscale statistics to be true and reliable, and brightness updates can be performed. To ensure that the indicator lights provide consistent visual impact (i.e., appear equally conspicuous) under different lighting conditions, the control processing unit cannot simply increase the indicator light brightness linearly with the ambient light. This is because the human eye's sensitivity to brightness differences decreases under strong light. The control processing unit constructs a non-linear mapping based on the Weber-Fechner law: the brighter the environment, the more exponentially or logarithmically the brightness increment of the indicator light must be adjusted to produce the same visual difference. The control processing unit invokes this mapping relationship to calculate the optimal brightness value suitable for the current stable environment. This step ensures that the indicator lights are soft and not glaring in dim environments, and bright and not overwhelmed in bright environments.

[0106] 214. Based on the preset mapping relationship between background grayscale values ​​and visual recognition brightness, calculate the minimum visual recognition brightness value that meets the preset human eye visual discrimination requirements in the current environment based on grayscale statistics, and convert the minimum visual recognition brightness value into the corresponding target duty cycle. (Refer to the execution process of step 104) After obtaining the target duty cycle in steps 212 and 214, the subsequent execution process refers to the execution process of steps 105-107.

[0107] The indicator light control method for self-service check-in equipment in this embodiment first obtains the equipment's operational status and acquires static image frames. It then calculates the texture complexity of the entire image to determine if it is in a visually occluded state. If occlusion occurs, it acquires the associated environmental image of the equipment through the inter-device communication network and determines a substitute brightness reference value, mitigating the problem of not being able to obtain illumination data when a single device's image acquisition fails. Next, when there is no occlusion, the control processing unit determines the image center coordinates and divides the image into pixel sub-regions. It assigns visual interference weights according to spatial Euclidean distance and calculates the ambient illumination reference value using a weighted average. If necessary, it corrects the accuracy of the illumination data by using a specular compensation gain coefficient. Then, the control processing unit establishes a time-series sliding window to calculate the variance of grayscale statistical data. When fluctuations are severe, it uses the historical duty cycle; when stable, it determines the brightness mapping relationship based on the Weber-Fechner law, mitigating frequent brightness jumps. Finally, the control processing unit generates a corresponding pulse width modulation drive signal based on the operational status to achieve adaptive adjustment of the indicator light brightness. This method enables precise adaptation of indicator light brightness under complex lighting conditions, ensures the continuity of adjustment in obstructed scenarios, and alleviates the problems of poor adaptability, easy submersion, or glare of constant brightness indicator lights.

[0108] The methods provided in the above embodiments can be executed by a control processing unit. The control processing unit in the embodiments of this invention is described below from a hardware processing perspective; please refer to [link to relevant documentation]. Figure 3 This is a schematic diagram of the physical device structure of the control processing unit in the embodiments of this application.

[0109] It should be noted that, Figure 3 The structure of the control processing unit shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0110] like Figure 3 As shown, the control processing unit includes a Central Processing Unit (CPU) 301, which can perform various appropriate actions and processes based on a program stored in Read-Only Memory (ROM) 302 or a program loaded from storage portion 308 into Random Access Memory (RAM) 303, such as executing the methods described in the above embodiments. The RAM 303 also stores various programs and data required for system operation. The CPU 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0111] The following components are connected to I / O interface 305: input section 306 including audio input devices, push-button switches, etc.; output section 307 including a liquid crystal display (LCD) and audio output devices, indicator lights, etc.; storage section 308 including a hard disk, etc.; and communication section 309 including a network interface card such as a LAN (Local Area Network) card, modem, etc. Communication section 309 performs communication processing via a network such as the Internet. Drive 310 is also connected to I / O interface 305 as needed. Removable media 311, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 310 as needed so that computer programs read from them can be installed into storage section 308 as needed.

[0112] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing computer programs for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 309, and / or installed from removable medium 311. When the computer program is executed by central processing unit (CPU) 301, it performs the various functions defined in the present invention.

[0113] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0114] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. Each block in a flowchart or block diagram may represent a module, program segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those shown in the drawings.

[0115] Specifically, the control processing unit in this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, it implements the indicator light control method for self-service check-in equipment provided in the above embodiment.

[0116] In another aspect, the present invention also provides a computer-readable storage medium, which may be included in the control processing unit described in the above embodiments; or it may exist independently and not assembled into the control processing unit. The storage medium carries one or more computer programs that, when executed by a processor of the control processing unit, cause the control processing unit to implement the indicator light control method for self-service check-in equipment provided in the above embodiments.

[0117] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

[0118] As used in the above embodiments, depending on the context, the term "when..." can be interpreted as meaning "if...", "after...", "in response to determining...", or "in response to detecting...". Similarly, depending on the context, the phrase "when determining..." or "if (the stated condition or event) is interpreted as meaning "if determining...", "in response to determining...", "when (the stated condition or event) is detected", or "in response to detecting (the stated condition or event)".

[0119] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive), etc.

[0120] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A method for controlling indicator lights in self-service baggage check-in equipment, characterized in that, A control processing unit is applied to a control system, the control system further including a self-service check-in device and indicator lights, the self-service check-in device and the indicator lights being respectively connected to the control processing unit, the method comprising: The current operational status of the self-service check-in device is obtained, and static image frames of the environment in which the self-service check-in device is located are collected according to a preset environmental monitoring cycle. The current operational status includes at least an idle state and a user operation state. Region identification is performed on the static image frame to obtain the foreground occlusion region. The region in the static image frame other than the foreground occlusion region is determined as the environmental reference region. The foreground occlusion region represents the image range corresponding to the moving subject or movable object. Calculate the grayscale statistics of the environmental reference area; Based on the mapping relationship between the preset background grayscale value and the visual recognition brightness, the minimum visual recognition brightness value that meets the preset human eye visual discrimination requirements in the current environment is calculated based on the grayscale statistical value, and the minimum visual recognition brightness value is converted into the corresponding target duty cycle. During the current environmental monitoring cycle, when the current service operation status is idle, a first pulse width modulation drive signal is generated, in which the duty cycle maintains a periodic fluctuation between the preset duty cycle and the target duty cycle. During the current environmental monitoring cycle, when the current service operation state is the user operation state, a second pulse width modulation drive signal with a duty cycle maintained at the value corresponding to the target duty cycle is generated; The first pulse width modulation drive signal or the second pulse width modulation drive signal is applied to the indicator light to drive the indicator light to illuminate.

2. The method according to claim 1, characterized in that, Calculating the grayscale statistical values ​​of the environmental reference area specifically includes: Determine the image center coordinates of the static image frame, and divide the environment reference region into multiple pixel sub-regions; Calculate the spatial Euclidean distance of each pixel sub-region relative to the coordinates of the image center; Assign visual interference weights to each pixel sub-region based on the spatial Euclidean distance; Based on the average gray value of each pixel sub-region and the corresponding visual interference weight, the ambient light reference value of the environment reference region is obtained by weighted calculation, and the ambient light reference value is used as the gray value.

3. The method according to claim 2, characterized in that, After the step of obtaining the ambient illumination reference value of the environmental reference area through weighted calculation, the method further includes: Obtain the brightness distribution histogram of the environmental reference area and count the percentage of pixels whose brightness values ​​are in the preset high-saturation range; When the percentage of the number of pixels is greater than a preset percentage threshold, a highlight compensation gain coefficient that is positively correlated with the percentage of the number of pixels is generated. The ambient light reference value is corrected using the specular compensation gain coefficient to obtain the corrected ambient light reference value.

4. The method according to claim 1, characterized in that, After the step of calculating the grayscale statistical values ​​of the environmental reference area, the method further includes: Establish a time-series sliding window for storing the grayscale statistical values ​​of N historical frames, and calculate the data variance of the grayscale statistical values ​​in the time-series sliding window, where N is an integer greater than 1; When the data variance is greater than the preset convergence threshold, the duty cycle of the previous environmental monitoring cycle is determined as the target duty cycle of the current environmental monitoring cycle. When the data variance is less than or equal to the preset convergence threshold, the mapping relationship between the preset background grayscale value and the visual recognition brightness is determined based on the Weber-Fechner law.

5. The method according to claim 1, characterized in that, After the step of collecting static image frames of the environment where the self-service check-in equipment is located according to a preset environmental monitoring cycle, the method further includes: Calculate the full-image texture complexity value of the static image frame; When the image texture complexity value is less than the occlusion determination threshold, the static image frame is determined to be in a visual occlusion state. In response to the visual occlusion state, the system receives real-time images of the associated environment from at least two associated self-service check-in devices via the communication network between the self-service check-in devices. Based on the associated environmental image, an alternative brightness reference value is determined for the current environment, and the alternative brightness reference value is used as the grayscale statistical value of the environmental reference area.

6. The method according to claim 5, characterized in that, Determining an alternative brightness reference value for the current environment based on the associated environmental image specifically includes: Obtain the pre-built device location topology relationship, and filter out images with overlapping fields of view with the self-service check-in equipment from multiple associated environmental images as candidate images; Calculate the global average brightness of the candidate images; Based on the distance between the self-service check-in device corresponding to the candidate image and the self-service check-in device in the device location topology, the location weight coefficient of the global brightness mean of the image is determined; The alternative brightness reference value is obtained by weighting and summing the global brightness mean of the image using the location weight coefficients.

7. The method according to claim 1, characterized in that, The first pulse width modulation drive signal, whose generated duty cycle maintains a periodic fluctuation between the duty cycle and the target duty cycle based on a preset basis, specifically includes: Determine the luminance modulation contrast coefficient under the current environment according to the Weber-Fechner law; Based on the target duty cycle and the brightness modulation contrast coefficient, the preset basic maintenance duty cycle is calculated in reverse, so that the difference between the preset basic maintenance duty cycle and the target duty cycle increases as the ambient light increases; Construct a periodic mapping function with the target duty cycle as the upper limit of the peak and the preset basic duty cycle as the lower limit of the trough; The first pulse width modulation drive signal is generated using the periodic mapping function.

8. A control system, characterized in that, It includes a control processing unit, a self-service check-in device, and indicator lights, wherein the self-service check-in device and the indicator lights are respectively connected to the control processing unit; The control processing unit includes one or more processors and a memory; The memory is coupled to the one or more processors, the memory being used to store computer program code, the computer program code including computer instructions, the one or more processors invoking the computer instructions to cause the control processing unit to perform the method as described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that, When the computer instructions are executed on the control processing unit, the control processing unit performs the method as described in any one of claims 1-7.

10. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are run on the control processing unit, the control processing unit performs the method as described in any one of claims 1-7.

Images