Adaptive dimming control method and system for multi-light-source data acquisition

Abstract

The invention discloses a self-adaptive dimming control method and system for multi-light-source data acquisition, and relates to the technical field of intelligent control. The method comprises the following steps: capturing a real-time image of an operation area for multi-angle analysis, obtaining a multi-angle illumination image data set for illumination analysis, and identifying illumination defect information; mapping the shadow distribution data to an operation area for analysis and identification, generating a plurality of shadow sub-areas, performing multi-light-source optimization according to the glare intensity data and the plurality of shadow sub-areas, and generating multi-light-source initial combination parameters; and driving the multi-light-source combined shadowless lamp to perform illumination control according to the multi-light-source initial combination parameters, updating and adjusting the multi-light-source initial combination parameters according to a control result in combination with the real-time image of the surgical area, and generating a multi-light-source dynamic combination to perform real-time illumination control on the shadowless lamp. The technical problem that in the prior art, a shadowless lamp cannot be dynamically adjusted according to a real-time scene, and consequently the lighting effect is poor is solved, and the technical effect of improving the lighting effect is achieved.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology, specifically to an adaptive dimming control method and system for multi-source data acquisition. Background Technology

[0002] As the core lighting equipment in the operating room, the quality of shadowless lamps directly affects the visibility and safety of surgery. Existing shadowless lamps typically reduce shadows in the surgical area through multi-source illumination at fixed angles. However, in complex surgical scenarios, issues such as dynamic obstruction by surgical instruments and medical staff, as well as fixed lighting angles, can still easily lead to uneven lighting, residual shadows, or excessive glare. This not only affects the clarity of the surgical field but may also increase the visual burden on the surgeon and reduce surgical precision. Although some shadowless lamps have manual or preset mode adjustment functions, they lack the ability to intelligently recognize and dynamically adjust to real-time scenarios. This results in an inability to optimize lighting in a timely manner according to changes in illumination during surgery, leading to poor lighting effects and failing to meet the lighting requirements of high-precision surgical procedures. Summary of the Invention

[0003] This application provides an adaptive dimming control method and system for multi-source data acquisition, which solves the technical problem in the prior art that shadowless lamps cannot dynamically adjust according to the real-time scene, resulting in poor lighting effects.

[0004] The first aspect of this application provides an adaptive dimming control method for multi-source data acquisition, the method comprising: Real-time images of the surgical area are captured and analyzed from multiple angles to obtain a multi-angle illumination image dataset for light analysis, identifying illumination defect information, including shadow distribution data and glare intensity data. The shadow distribution data is mapped to the surgical area for analysis and identification, generating multiple shadow sub-regions. Based on the glare intensity data and the multiple shadow sub-regions, multi-source optimization is performed to generate initial multi-source combination parameters. The multi-source combined shadowless lamp is driven for illumination control according to the initial multi-source combination parameters. Based on the control results and the real-time images of the surgical area, the initial multi-source combination parameters are updated and adjusted to generate a dynamic multi-source combination for real-time illumination control of the shadowless lamp.

[0005] A second aspect of this application provides an adaptive dimming control system for multi-source data acquisition, the system comprising: Analysis Module: Captures real-time images of the surgical area for multi-angle analysis, obtains a multi-angle illumination image dataset for illumination analysis, and identifies illumination defect information, including shadow distribution data and glare intensity data; Parameter Generation Module: Maps the shadow distribution data to the surgical area for analysis and identification, generates multiple shadow sub-regions, and optimizes multiple light sources based on the glare intensity data and the multiple shadow sub-regions to generate initial combination parameters for multiple light sources; Parameter Adjustment Module: Drives the multi-light source combined shadowless lamp for illumination control according to the initial combination parameters of multiple light sources, and updates and adjusts the initial combination parameters of multiple light sources based on the control results and the real-time images of the surgical area to generate a dynamic combination of multiple light sources for real-time illumination control of the shadowless lamp.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages: First, real-time images of the surgical area are captured and analyzed from multiple angles to obtain a multi-angle lighting image dataset for illumination analysis, identifying lighting defect information, including shadow distribution data and glare intensity data. Then, the shadow distribution data is mapped to the surgical area for analysis and labeling, generating multiple shadow sub-regions. Based on the glare intensity data and these shadow sub-regions, multi-source optimization is performed to generate initial multi-source combination parameters. Finally, the multi-source combined shadowless lamp is driven for lighting control according to the initial multi-source combination parameters. Based on the control results and real-time images of the surgical area, the initial multi-source combination parameters are updated and adjusted to generate a dynamic multi-source combination for real-time lighting control of the shadowless lamp. This solves the technical problem in existing technologies where shadowless lamps cannot dynamically adjust according to the real-time scene, resulting in poor lighting effects, and achieves a significant improvement in lighting performance. Attached Figure Description

[0007] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0008] Figure 1 This is a schematic flowchart of an adaptive dimming control method for multi-source data acquisition provided in an embodiment of this application. Figure 2 This is a schematic diagram of the adaptive dimming control system for multi-source data acquisition provided in an embodiment of this application.

[0009] Figure labeling: Analysis module 11, parameter generation module 12, parameter adjustment module 13. Detailed Implementation

[0010] This application provides an adaptive dimming control method and system for multi-source data acquisition, which solves the technical problem in the prior art that shadowless lamps cannot dynamically adjust according to real-time scenes, resulting in poor lighting effects.

[0011] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0012] It should be noted that the terms "comprising" and "having" are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or modules that are not explicitly listed or that are inherent to these processes, methods, products, or devices.

[0013] Example 1, as Figure 1 As shown, this application provides an adaptive dimming control method for multi-source data acquisition, wherein the method includes: Real-time images of the surgical area are captured and analyzed from multiple angles to obtain a multi-angle lighting image dataset for illumination analysis, and lighting defect information is identified, including shadow distribution data and glare intensity data.

[0014] In this embodiment, image acquisition devices deployed at multiple locations within the operating room are used to image the surgical area in real time. These devices may include high-definition cameras, infrared cameras, or other sensors capable of capturing light. Multiple image acquisition devices simultaneously acquire raw image data of the surgical area from multiple angles. This raw image data is then spatially registered and fused to generate a multi-angle lighting image dataset covering the surgical area. Subsequently, pixel-by-pixel analysis of the multi-angle lighting image dataset is performed to determine the light distribution of the surgical area at different angles. Based on preset light and color temperature thresholds, shadow distribution data corresponding to insufficiently illuminated areas and glare intensity data corresponding to excessively illuminated areas are identified, thereby obtaining lighting defect information for subsequent lighting optimization.

[0015] Furthermore, real-time images of the surgical area are captured and analyzed from multiple angles to obtain a multi-angle illumination image dataset. Methods include: Multiple image sensors are deployed for multiple shadowless lamps within the surgical area; images of the surgical area are acquired at the same time using the multiple image sensors to obtain original multi-angle images; feature recognition is performed on the original multi-angle images to obtain common feature points; the original multi-angle images are spatially registered based on the common feature points to generate multi-angle registered images; and the multi-angle registered images are fused to compensate for blind spots in the field of vision to generate the multi-angle illumination image dataset.

[0016] Preferably, within the surgical area, multiple shadowless lamp positions corresponding to the surgical area are traversed according to a preset distribution principle. Image sensors are deployed within the illumination range of each shadowless lamp. These image sensors can be high-definition cameras, infrared cameras, or other imaging units suitable for real-time imaging. Multiple image sensors synchronously acquire images of the surgical area at the same time point to obtain raw multi-angle image data. Next, feature extraction algorithms (such as SIFT, SURF, or ORB operators) are invoked to perform feature recognition operations on the raw multi-angle images, identifying key point information in each image. The key points are then matched based on the RANSAC random consistency algorithm to obtain multiple common feature points. Then, perspective transformation and affine transformation are performed based on the common feature points to complete the spatial registration of images from different angles, generating geometrically aligned multi-angle registered images. Finally, image fusion algorithms (such as weighted average fusion or Poisson fusion) are used to fuse the multi-angle registered images, and edge interpolation compensation methods are combined to reconstruct pixels in the blind areas of each angle's imaging range, generating a multi-angle illumination image dataset covering the entire surgical area.

[0017] Furthermore, the method involves obtaining a multi-angle lighting image dataset for illumination analysis to identify lighting defect information, including shadow distribution data and glare intensity data. A pixel-by-pixel illumination analysis is performed on the multi-angle lighting image dataset to generate illumination distribution data, which includes illumination intensity distribution data and illumination color temperature distribution data. Ideal lighting parameters are retrieved to set illumination intensity threshold ranges and illumination color temperature threshold ranges. Based on the illumination intensity distribution data, the multi-angle lighting image dataset is compared with the illumination intensity threshold ranges. When the illumination intensity distribution data is lower than the lower limit of the illumination intensity threshold range, shadow distribution data is identified. When the illumination intensity distribution data is higher than the upper limit of the illumination intensity threshold range, glare intensity data is identified. Based on the illumination color temperature distribution data, the multi-angle lighting image dataset is compared with the illumination color temperature threshold range to determine color temperature anomaly regions. Illumination defects are located according to the color temperature anomaly regions, combined with the glare intensity data and the shadow distribution data, generating illumination defect information.

[0018] Specifically, grayscale calculations and color space conversions are performed pixel-by-pixel on the multi-angle lighting image dataset to extract the illuminance and color temperature values ​​of each pixel, thereby generating illumination distribution data, which includes illuminance intensity distribution data and illumination color temperature distribution data. Pre-set ideal lighting parameters, consisting of standard illuminance and standard color temperature ranges, are retrieved to construct illuminance intensity and color temperature threshold ranges. Based on the illuminance intensity distribution data, a threshold comparison method is used to traverse the lighting area point by point. When the detection result is below the lower limit of the illuminance intensity threshold range, the corresponding area is marked as shadow distribution data; when the detection result is above the upper limit of the illuminance intensity threshold range, the corresponding area is marked as glare intensity data. Based on the illumination color temperature distribution data, the color temperature value of each pixel is compared with the illumination color temperature threshold range one by one. When the detection result exceeds the illumination color temperature threshold range, the corresponding area is determined to be a color temperature aberration area. The shadow distribution data, glare intensity data and color temperature anomaly areas are spatially overlaid and jointly analyzed. Region segmentation and edge detection algorithms are used to extract the boundaries and locate the anomaly areas, and complete lighting defect information is output.

[0019] The shadow distribution data is mapped to the surgical area for analysis and identification, generating multiple shadow sub-regions. Based on the glare intensity data and the multiple shadow sub-regions, multi-light source optimization is performed to generate initial combination parameters for the multi-light source.

[0020] Furthermore, the shadow distribution data is mapped to the surgical area for analysis and identification, generating multiple shadow sub-regions. Based on the glare intensity data and these multiple shadow sub-regions, multi-light source optimization is performed to generate initial multi-light source combination parameters. The method includes: A two-dimensional planar network is constructed based on the surgical area. The shadow distribution data is analyzed to obtain multiple shadow pixels. These shadow pixels are mapped to the two-dimensional planar network to determine multiple shadow grid cells, each containing a shadow depth value. Cluster analysis is performed on the multiple shadow grid cells to generate multiple boundary parameters. The multiple shadow sub-regions are delineated according to the boundary parameters, and the mean shadow depth is calculated to generate multiple depth level labels. These labels are then back-annotated to the multiple shadow grid cells to determine multiple shadow depth grid coordinates. Based on the multiple shadow depth grid coordinates, the two-dimensional planar network is combined with glare intensity data for reverse selection to determine multiple glare point locations. The glare intensity data is read, and the multiple shadow depth grid coordinates are used to enhance the light intensity of multiple light sources, generating first light source adjustment data. The glare intensity data is then divided into intensity levels to generate multiple glare intensity levels. Based on the glare intensity levels, the light intensity of multiple light sources at the multiple glare point locations is reduced, generating second light source adjustment data. The first light source adjustment data and the second light source adjustment data are combined and optimized using a multi-objective approach to generate the initial combination parameters for the multiple light sources.

[0021] A two-dimensional planar mesh is established based on the spatial coordinate system of the surgical area, dividing the surgical area into several equally divided meshes (e.g., one mesh cell for every 5mm × 5mm area). The shadow distribution data is analyzed, and the grayscale value or brightness loss of shadow pixels is mapped to the corresponding mesh cell, thus obtaining multiple shadow mesh cells containing shadow depth values. Subsequently, a clustering analysis algorithm (e.g., the density-based DBSCAN algorithm) is used to traverse multiple shadow mesh cells, and spatial aggregation is performed based on the difference in shadow depth between adjacent cells to generate multiple boundary parameters. Multiple shadow sub-regions are delineated based on the boundary parameters, and the mean shadow depth of each sub-region is calculated to obtain a depth level label, which is then back-labeled to the corresponding shadow mesh cells to determine the coordinates of multiple shadow depth meshes.

[0022] Multiple glare points are determined by overlaying multiple shadow depth grid coordinates with glare intensity data and using a threshold-based inverse selection method (marking a grid cell as a glare point when its light intensity exceeds a preset threshold). For shadow areas, a linear gain function (e.g., the light intensity increase ratio is proportional to the shadow depth value) is used to calculate the light source enhancement parameters, resulting in the first light source adjustment data. For glare areas, glare intensity values ​​are categorized (high, medium, low) and an exponential decay function is used to reduce the light intensity of the corresponding light source, resulting in the second light source adjustment data. Finally, the first and second light source adjustment data are used as inputs to call a multi-objective optimization algorithm (e.g., multi-objective function optimization based on a genetic algorithm) to iteratively optimize the light source parameters with the goals of improving illumination uniformity, reducing glare impact, and controlling energy consumption, obtaining the optimal solution as the initial combination parameters for the multiple light sources.

[0023] Furthermore, cluster analysis is performed on the multiple shaded mesh cells to generate multiple boundary parameters. The method includes: Based on the shadow depth value, the multiple shadow mesh cells are traversed to calculate the adjacent difference, generating multiple spatial adjacent shadow depth differences; it is determined whether the multiple spatial adjacent shadow depth differences are within a preset tolerance range; if the multiple spatial adjacent shadow depth differences are within the preset tolerance range, the multiple shadow mesh cells are identified, and cluster analysis is performed on the multiple shadow mesh cells according to the identification results to generate a set of shadow regions; based on the set of shadow regions, geometric boundary calculation is performed to determine the multiple boundary parameters.

[0024] Specifically, the shadow depth values ​​of multiple shadow grid cells are iterated one by one, and the depth difference between adjacent grid cells is calculated. For example, the adjacent pixel difference method or Euclidean distance calculation method is used to obtain multiple spatial adjacent shadow depth differences. A preset tolerance range is called to determine whether the spatial adjacent shadow depth difference is within the tolerance range. If the depth difference between adjacent grid cells is less than the preset tolerance threshold, the two grid cells are determined to belong to the same region, are uniformly identified, and on this basis, a clustering method based on connected component analysis is used to cluster the identified grid cells to generate multiple shadow region sets.

[0025] After obtaining the set of shaded regions, geometric boundary calculations are further performed based on each set. Specifically, Canny edge detection combined with a polygon approximation algorithm can be used to extract geometric contours and obtain the boundary parameters of each shaded region, including the set of boundary point coordinates, boundary length, and boundary shape features.

[0026] The multi-source combined shadowless lamp is driven to perform lighting control according to the initial combination parameters of the multi-source light source. Based on the control results and the real-time image of the surgical area, the initial combination parameters of the multi-source light source are updated and adjusted to generate a dynamic combination of multi-source light sources for real-time lighting control of the shadowless lamp.

[0027] Furthermore, the method involves driving a multi-source combined shadowless lamp for illumination control according to the initial combination parameters of the multi-source lights, and updating and adjusting the initial combination parameters of the multi-source lights based on the control results and the real-time image of the surgical area to generate a dynamic combination of multi-source lights. The initial combination parameters of the multiple light sources are sent to the control unit of multiple light source modules of the shadowless lamp to drive the multiple light source modules to adjust the illumination and determine the first illumination control data. Based on the first illumination control data, multiple image sensors are activated to capture images of the surgical area and obtain regional feedback images. The effect is verified according to the regional feedback images to generate a real-time illumination effect dataset. A preset illumination target threshold is retrieved, and the real-time illumination effect dataset is compared and analyzed with the preset illumination target to obtain the residual illumination deviation value. The initial combination parameters of the multiple light sources are updated and adjusted according to the real-time images of the surgical area based on the residual illumination deviation value to generate the dynamic combination of the multiple light sources.

[0028] Specifically, the initial combination parameters of multiple light sources are sent to the control units of multiple light source modules in the shadowless lamp via a control bus. Each control unit drives an LED light source array and independently adjusts it according to the brightness, color temperature, and illumination angle values ​​in the initial combination parameters, thereby outputting the first round of lighting effect and generating the first lighting control data. Based on the first lighting control data, the control unit synchronously activates multiple image sensors deployed around the surgical area. These image sensors acquire regional feedback images under a unified clock and transmit them to the image processing unit. The image processing unit calculates the light intensity distribution using brightness statistical methods (such as histogram mean analysis) and the color temperature distribution using color space conversion methods (such as RGB→CIE Lab conversion), generating a real-time lighting effect dataset. The system calls preset lighting target thresholds, including the desired light intensity range, desired color temperature range, and lighting uniformity index; it compares the real-time lighting effect dataset with the preset thresholds pixel by pixel. If the brightness of a local area is detected to be lower than the lower threshold, a shadow residual deviation value is generated; if the brightness is higher than the upper threshold, a glare residual deviation value is generated; if the color temperature exceeds the threshold range, a color temperature residual deviation value is generated. Finally, based on the real-time images of the surgical area, the initial combination parameters of the multi-light source are updated and adjusted according to the residual illumination deviation value. Specifically, an incremental adjustment-based parameter correction method is used: the output brightness of the light source corresponding to the shadow area is linearly increased, the output brightness of the light source corresponding to the glare area is exponentially decreased, and the color temperature abnormal area is corrected by adjusting the ratio of cool white light to warm white light. After the above updates, a dynamic combination of multi-light sources is generated and redistributed to the shadowless lamp control unit to achieve real-time adaptive lighting control of the surgical area.

[0029] Furthermore, the method involves retrieving a preset lighting target threshold, comparing and analyzing the real-time lighting effect dataset with the preset lighting target, and obtaining the lighting residual deviation value. The illuminance data in the real-time lighting effect dataset is compared point-by-point with the expected intensity threshold to generate a first residual deviation matrix; the color temperature data in the real-time lighting effect dataset is compared point-by-point with the expected color temperature threshold to generate a second residual deviation matrix; regions in the first residual deviation matrix with negative values ​​and absolute values ​​exceeding the intensity tolerance are identified and located to determine residual shadow regions, which contain the first lighting residual deviation value; regions in the second residual deviation matrix with positive values ​​and absolute values ​​exceeding the intensity tolerance are identified and located to determine residual glare regions, which contain the second lighting residual deviation value.

[0030] The system calls the preset lighting target threshold and compares the light intensity data in the real-time lighting effect dataset pixel by pixel with the expected intensity threshold, that is, calculates the intensity difference of all pixels to obtain the first residual deviation matrix; similarly, the color temperature data in the real-time lighting effect dataset is compared pixel by pixel with the expected color temperature threshold to obtain the second residual deviation matrix.

[0031] Region identification is performed on the first residual deviation matrix: if the difference of a certain pixel is negative and its absolute value exceeds the preset intensity tolerance, then the point is determined to belong to the residual shadow region; adjacent abnormal points are merged by connected component analysis to obtain the complete residual shadow region, and its difference is marked as the first lighting residual deviation value.

[0032] Region identification is performed on the second residual deviation matrix: if the difference of a certain pixel is positive and its absolute value exceeds the intensity tolerance, then the point is determined to belong to the residual glare region. Similarly, the connected component analysis method is used to aggregate adjacent points into regions, and their difference is marked as the second lighting residual deviation value.

[0033] Furthermore, the method for updating and adjusting the initial combination parameters of the multi-light source based on the residual illumination deviation value according to the real-time image of the surgical area to generate the dynamic combination of the multi-light source includes: Based on the real-time image of the surgical area, the initial combination parameters of the multi-light source are incrementally solved based on the first residual illumination deviation value to obtain the increment of the first light source parameters; the initial combination parameters of the multi-light source are algebraically superimposed based on the increment of the first light source parameters to determine the first control parameters of the light source to be executed; based on the real-time image of the surgical area, the initial combination parameters of the multi-light source are incrementally solved based on the second residual illumination deviation value to obtain the second control parameters of the light source to be executed; a feasibility verification is performed based on the first control parameters of the light source to be executed and the second control parameters of the light source to be executed, a control cycle is set according to the verification result, and the initial combination parameters of the multi-light source are updated and adjusted according to the control cycle to generate the dynamic combination of the multi-light source.

[0034] For the residual shadow areas identified by real-time images, the incremental adjustment of the light source is calculated based on the first residual illumination deviation value. Specifically, a proportional gain control method is adopted, using the formula: ,in, For the desired illuminance, This represents the measured illuminance at the current location. This is the gain coefficient. It is obtained through the above formula. As the first light source parameter increment, the first light source parameter increment is algebraically superimposed with the initial combination parameters of multiple light sources to obtain the first light source control parameters to be executed, thereby increasing the brightness of the light source corresponding to the shadow area.

[0035] For the residual glare area identified by real-time images, incremental solutions are performed based on the residual deviation value of the second illumination. A nonlinear attenuation function is employed. ,in, The suppression coefficient is used to obtain the second light source control parameter to be executed, which is used to reduce the light intensity output in the glare area.

[0036] After obtaining the control parameters for the first and second light sources to be executed, a feasibility check is performed. Specifically, the output brightness of each light source is compared one by one to see if it exceeds the preset brightness range, and extreme value constraints are used to determine if there are parameter conflicts or over-limit situations. If there are over-limit or conflicts, a first control cycle is set; if there are slight deviations but no over-limits, a second control cycle is set; if there are no abnormalities, a third control cycle is set. Finally, an appropriate parameter update frequency is selected according to the control cycle, and the verified light source control parameters are updated to the initial combination parameters of the multi-light source to generate a dynamic combination of multiple light sources.

[0037] Furthermore, based on the control parameters of the first and second light sources to be executed, a feasibility verification is performed. A control period is set according to the verification results. The initial combination parameters of the multiple light sources are updated and adjusted according to the control period to generate the dynamic combination of the multiple light sources. The method includes: The system iterates through the first and second light source control parameters to be executed, comparing the brightness of each light source and extracting the first and second brightness parameter values. Based on the light source module, extreme value analysis is performed, and a light source brightness range is defined according to the light source extreme values. Based on the light source brightness range, it is determined whether there is a conflict between the first and second brightness parameter values, generating a first conflict verification result and a second conflict verification result. When the first and second conflict verification results contain at least one out-of-limit or conflicting abnormal result, a first control cycle is set. When the first or second conflict verification result contains at least one non-mutational abnormal result and does not contain out-of-limit or conflicting abnormal results, a second control cycle is set. When neither the first nor the second conflict verification result has any abnormal markers, a third control cycle is set.

[0038] First, all light source control parameters are iterated through, and the corresponding brightness parameter values ​​are extracted for each of the first and second light source control parameters to be executed, and recorded as the first brightness parameter value and the second brightness parameter value, respectively. Then, extreme value analysis is performed based on the hardware performance parameters of each light source module, such as constraining the allowable brightness range and allowable rate of change for each light source module to define the light source brightness range. Next, the first and second brightness parameter values ​​are compared with the light source brightness range. If either parameter exceeds the upper or lower limit of the brightness range, or if two parameters conflict on the same light source (e.g., one requires increasing brightness, and the other requires decreasing brightness), an over-limit anomaly or conflict anomaly is determined, and a corresponding conflict verification result is generated. In this case, the system sets a first control cycle, for example, an update cycle of 0.5 seconds, to ensure that the light source completes rapid correction within a short time. If the first or second brightness parameter value is abnormal but does not exceed the brightness range, and only exhibits slight fluctuations or no sudden changes, a non-sudden change anomaly flag is generated, and the system sets a second control cycle, for example, an update cycle of 1 second. If all light source parameters are found to be within the allowable range during the traversal process, and there are no conflicts or abnormal markers, the verification is deemed successful. The system sets a third control cycle, for example, an update cycle of 2 seconds, to reduce unnecessary frequent adjustments.

[0039] In summary, the embodiments of this application have at least the following technical effects: First, real-time images of the surgical area are captured and analyzed from multiple angles to obtain a multi-angle lighting image dataset for illumination analysis, identifying lighting defect information, including shadow distribution data and glare intensity data. Then, the shadow distribution data is mapped to the surgical area for analysis and labeling, generating multiple shadow sub-regions. Based on the glare intensity data and these shadow sub-regions, multi-source optimization is performed to generate initial multi-source combination parameters. Finally, the multi-source combined shadowless lamp is driven for lighting control according to the initial multi-source combination parameters. Based on the control results and real-time images of the surgical area, the initial multi-source combination parameters are updated and adjusted to generate a dynamic multi-source combination for real-time lighting control of the shadowless lamp. This solves the technical problem in existing technologies where shadowless lamps cannot dynamically adjust according to the real-time scene, resulting in poor lighting effects, and achieves a significant improvement in lighting performance.

[0040] Example 2, based on the same inventive concept as the adaptive dimming control method for multi-source data acquisition in the foregoing examples, such as... Figure 2 As shown, this application provides an adaptive dimming control system for multi-source data acquisition, wherein the system includes: Analysis module 11: Captures real-time images of the surgical area for multi-angle analysis, obtains a multi-angle illumination image dataset for illumination analysis, and identifies illumination defect information, including shadow distribution data and glare intensity data; Parameter generation module 12: Maps the shadow distribution data to the surgical area for analysis and identification, generates multiple shadow sub-regions, and optimizes multiple light sources based on the glare intensity data and the multiple shadow sub-regions to generate initial combination parameters for multiple light sources; Parameter adjustment module 13: Drives the multi-light source combined shadowless lamp for illumination control according to the initial combination parameters of multiple light sources, and updates and adjusts the initial combination parameters of multiple light sources based on the control results and the real-time images of the surgical area to generate a dynamic combination of multiple light sources for real-time illumination control of the shadowless lamp.

[0041] Furthermore, the analysis module 11 is used to perform the following methods: Multiple image sensors are deployed for multiple shadowless lamps within the surgical area; images of the surgical area are acquired at the same time using the multiple image sensors to obtain original multi-angle images; feature recognition is performed on the original multi-angle images to obtain common feature points; the original multi-angle images are spatially registered based on the common feature points to generate multi-angle registered images; and the multi-angle registered images are fused to compensate for blind spots in the field of vision to generate the multi-angle illumination image dataset.

[0042] Furthermore, the analysis module 11 is used to perform the following methods: A pixel-by-pixel illumination analysis is performed on the multi-angle lighting image dataset to generate illumination distribution data, which includes illumination intensity distribution data and illumination color temperature distribution data. Ideal lighting parameters are retrieved to set illumination intensity threshold ranges and illumination color temperature threshold ranges. Based on the illumination intensity distribution data, the multi-angle lighting image dataset is compared with the illumination intensity threshold ranges. When the illumination intensity distribution data is lower than the lower limit of the illumination intensity threshold range, shadow distribution data is identified. When the illumination intensity distribution data is higher than the upper limit of the illumination intensity threshold range, glare intensity data is identified. Based on the illumination color temperature distribution data, the multi-angle lighting image dataset is compared with the illumination color temperature threshold range to determine color temperature anomaly regions. Illumination defects are located according to the color temperature anomaly regions, combined with the glare intensity data and the shadow distribution data, generating illumination defect information.

[0043] Furthermore, the parameter generation module 12 is used to perform the following method: A two-dimensional planar network is constructed based on the surgical area. The shadow distribution data is analyzed to obtain multiple shadow pixels. These shadow pixels are mapped to the two-dimensional planar network to determine multiple shadow grid cells, each containing a shadow depth value. Cluster analysis is performed on the multiple shadow grid cells to generate multiple boundary parameters. The multiple shadow sub-regions are delineated according to the boundary parameters, and the mean shadow depth is calculated to generate multiple depth level labels. These labels are then back-annotated to the multiple shadow grid cells to determine multiple shadow depth grid coordinates. Based on the multiple shadow depth grid coordinates, the two-dimensional planar network is combined with glare intensity data for reverse selection to determine multiple glare point locations. The glare intensity data is read, and the multiple shadow depth grid coordinates are used to enhance the light intensity of multiple light sources, generating first light source adjustment data. The glare intensity data is then divided into intensity levels to generate multiple glare intensity levels. Based on the glare intensity levels, the light intensity of multiple light sources at the multiple glare point locations is reduced, generating second light source adjustment data. The first light source adjustment data and the second light source adjustment data are combined and optimized using a multi-objective approach to generate the initial combination parameters for the multiple light sources.

[0044] Furthermore, the parameter generation module 12 is used to perform the following method: Based on the shadow depth value, the multiple shadow mesh cells are traversed to calculate the adjacent difference, generating multiple spatial adjacent shadow depth differences; it is determined whether the multiple spatial adjacent shadow depth differences are within a preset tolerance range; if the multiple spatial adjacent shadow depth differences are within the preset tolerance range, the multiple shadow mesh cells are identified, and cluster analysis is performed on the multiple shadow mesh cells according to the identification results to generate a set of shadow regions; based on the set of shadow regions, geometric boundary calculation is performed to determine the multiple boundary parameters.

[0045] Furthermore, the parameter adjustment module 13 is used to perform the following method: The initial combination parameters of the multiple light sources are sent to the control unit of multiple light source modules of the shadowless lamp to drive the multiple light source modules to adjust the illumination and determine the first illumination control data. Based on the first illumination control data, multiple image sensors are activated to capture images of the surgical area and obtain regional feedback images. The effect is verified according to the regional feedback images to generate a real-time illumination effect dataset. A preset illumination target threshold is retrieved, and the real-time illumination effect dataset is compared and analyzed with the preset illumination target to obtain the residual illumination deviation value. The initial combination parameters of the multiple light sources are updated and adjusted according to the real-time images of the surgical area based on the residual illumination deviation value to generate the dynamic combination of the multiple light sources.

[0046] Furthermore, the parameter adjustment module 13 is used to perform the following method: The illuminance data in the real-time lighting effect dataset is compared point-by-point with the expected intensity threshold to generate a first residual deviation matrix; the color temperature data in the real-time lighting effect dataset is compared point-by-point with the expected color temperature threshold to generate a second residual deviation matrix; regions in the first residual deviation matrix with negative values ​​and absolute values ​​exceeding the intensity tolerance are identified and located to determine residual shadow regions, which contain the first lighting residual deviation value; regions in the second residual deviation matrix with positive values ​​and absolute values ​​exceeding the intensity tolerance are identified and located to determine residual glare regions, which contain the second lighting residual deviation value.

[0047] Furthermore, the parameter adjustment module 13 is used to perform the following method: Based on the real-time image of the surgical area, the initial combination parameters of the multi-light source are incrementally solved based on the first residual illumination deviation value to obtain the increment of the first light source parameters; the initial combination parameters of the multi-light source are algebraically superimposed based on the increment of the first light source parameters to determine the first control parameters of the light source to be executed; based on the real-time image of the surgical area, the initial combination parameters of the multi-light source are incrementally solved based on the second residual illumination deviation value to obtain the second control parameters of the light source to be executed; a feasibility verification is performed based on the first control parameters of the light source to be executed and the second control parameters of the light source to be executed, a control cycle is set according to the verification result, and the initial combination parameters of the multi-light source are updated and adjusted according to the control cycle to generate the dynamic combination of the multi-light source.

[0048] Furthermore, the parameter adjustment module 13 is used to perform the following method: The system iterates through the first and second light source control parameters to be executed, comparing the brightness of each light source and extracting the first and second brightness parameter values. Based on the light source module, extreme value analysis is performed, and a light source brightness range is defined according to the light source extreme values. Based on the light source brightness range, it is determined whether there is a conflict between the first and second brightness parameter values, generating a first conflict verification result and a second conflict verification result. When the first and second conflict verification results contain at least one out-of-limit or conflicting abnormal result, a first control cycle is set. When the first or second conflict verification result contains at least one non-mutational abnormal result and does not contain out-of-limit or conflicting abnormal results, a second control cycle is set. When neither the first nor the second conflict verification result has any abnormal markers, a third control cycle is set.

[0049] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0050] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0051] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. A method of adaptive dimming control for multi-light source data acquisition, characterized in that, The method comprises: Capturing real-time images of the surgical area for multi-angle analysis, obtaining a multi-angle lighting image dataset for lighting analysis, identifying lighting defect information, the lighting defect information including shadow distribution data and glare intensity data; Mapping the shadow distribution data to the surgical area for analysis and identification, generating multiple shadow sub-areas, and performing multi-light source optimization according to the glare intensity data combined with the multiple shadow sub-areas to generate multi-light source initial combination parameters; According to the multi-light source initial combination parameters, drive the multi-light source combined shadowless lamp for lighting control, according to the control result combined with the real-time image of the surgical area, update and adjust the multi-light source initial combination parameters, generate multi-light source dynamic combination to control the shadowless lamp for real-time lighting control.

2. The adaptive dimming control method for multi-light source data acquisition of claim 1, wherein, Capturing real-time images of the surgical area for multi-angle analysis, obtaining a multi-angle lighting image dataset, the method comprising: Traverse the surgical area to arrange multiple image sensors for multiple shadowless lamps in the surgical area; Image acquisition of the surgical area at the same time point through the multiple image sensors to obtain original multi-angle images; Based on the original multi-angle images, feature recognition is performed to obtain common feature points, and the original multi-angle images are spatially registered according to the common feature points to generate multi-angle registration images; Based on the multi-angle registration images, the visual field blind area is compensated by fusion to generate the multi-angle lighting image dataset.

3. The adaptive dimming control method for multi-source data acquisition of claim 1, wherein, Obtaining a multi-angle lighting image dataset for lighting analysis, identifying lighting defect information, the lighting defect information including shadow distribution data and glare intensity data, the method comprising: Traverse the multi-angle lighting image dataset for pixel-by-pixel lighting analysis to generate lighting distribution data, the lighting distribution data including lighting intensity distribution data and lighting color temperature distribution data; Call the ideal lighting parameter to set the lighting intensity threshold range and the lighting color temperature threshold range; Based on the lighting intensity distribution data, traverse the multi-angle lighting image dataset and compare with the lighting intensity threshold range, when the lighting intensity distribution data is lower than the lower limit value of the lighting intensity threshold range, identify the shadow distribution data; When the lighting intensity distribution data is higher than the upper limit value of the lighting intensity threshold range, identify the glare intensity data; Based on the lighting color temperature distribution data, traverse the multi-angle lighting image dataset and compare with the lighting color temperature threshold range to determine the color temperature abnormal area; According to the color temperature abnormal area, combine the glare intensity data and the shadow distribution data to locate the lighting defects and generate the lighting defect information.

4. The adaptive dimming control method for multi-source data acquisition of claim 1, wherein, Mapping the shadow distribution data to the surgical area for analysis and identification, generating multiple shadow sub-areas, and performing multi-light source optimization according to the glare intensity data combined with the multiple shadow sub-areas to generate multi-light source initial combination parameters, the method comprising: Based on the surgical area, a two-dimensional plane network is constructed, and the shadow distribution data is analyzed to obtain multiple shadow pixel points; Map the multiple shadow pixel points to the two-dimensional plane network to determine multiple shadow grid cells, and the multiple shadow grid cells contain shadow depth values; Traverse the plurality of shadow grid cells for cluster analysis to generate a plurality of boundary parameters; According to the plurality of boundary parameters, the plurality of shadow sub-regions are demarcated for shadow depth mean value calculation to generate a plurality of depth level labels, which are reversely labeled to the plurality of shadow grid cells to determine a plurality of shadow depth grid coordinates; Based on the plurality of shadow depth grid coordinates, the two-dimensional plane network is combined with glare intensity data to reversely select to determine a plurality of glare point positions; Read the glare intensity data to perform multi-light source light intensity enhancement on the plurality of shadow depth grid coordinates to generate first light source adjustment data; Based on the glare intensity data, intensity division is performed to generate a plurality of glare intensity levels; According to the glare intensity levels, the plurality of glare point positions are subjected to multi-light source light intensity reduction to generate second light source adjustment data; The first light source adjustment data and the second light source adjustment data are subjected to multi-objective combination optimization to generate the multi-light source initial combination parameters.

5. The adaptive dimming control method for multi-source data acquisition of claim 4, wherein, Traverse the plurality of shadow grid cells for cluster analysis to generate a plurality of boundary parameters, the method comprising: Based on the shadow depth value, adjacent difference calculation is performed on the plurality of shadow grid cells to generate a plurality of spatially adjacent shadow depth differences; Determine whether the plurality of spatially adjacent shadow depth differences are within a preset tolerance range; If the plurality of spatially adjacent shadow depth differences are within the preset tolerance range, the plurality of shadow grid cells are identified, and according to the identification result, the plurality of shadow grid cells are subjected to cluster analysis to generate a shadow region set; Based on the shadow region set, geometric boundary calculation is performed to determine the plurality of boundary parameters.

6. The adaptive dimming control method for multi-source data acquisition of claim 1, wherein, According to the multi-light source initial combination parameters, a multi-light source combined shadowless lamp is driven for illumination control, and according to the control result, the multi-light source initial combination parameters are updated and adjusted in combination with the real-time image of the surgical area to generate a multi-light source dynamic combination, the method comprising: The multi-light source initial combination parameters are sent to a plurality of light source module control units of the shadowless lamp to drive a plurality of light source modules for illumination adjustment to determine first illumination control data; Based on the first illumination control data, a plurality of image sensors are activated to capture images of the surgical area to obtain area feedback images; According to the area feedback images, effect verification is performed to generate a real-time illumination effect data set; A preset illumination target threshold is called to compare and analyze the real-time illumination effect data set with the preset illumination target to obtain an illumination residual deviation value; According to the illumination residual deviation value, the multi-light source initial combination parameters are updated and adjusted based on the real-time image of the surgical area to generate the multi-light source dynamic combination.

7. The adaptive dimming control method for multi-source data acquisition of claim 6, wherein, A preset illumination target threshold is called to compare and analyze the real-time illumination effect data set with the preset illumination target to obtain an illumination residual deviation value, the method comprising: The illumination intensity data in the real-time illumination effect data set is compared with the expected intensity threshold point by point to generate a first residual deviation matrix; The color temperature data in the real-time illumination effect data set is compared with the expected color temperature threshold point by point to generate a second residual deviation matrix; identifying and locating the area with negative values and absolute values exceeding the intensity tolerance in the first residual deviation matrix to determine a residual shadow area, the residual shadow area containing first illumination residual deviation values; identifying and locating the area with positive values and absolute values exceeding the intensity tolerance in the second residual deviation matrix to determine a residual glare area, the residual glare area containing second illumination residual deviation values.

8. The adaptive dimming control method for multi-source data acquisition of claim 7, wherein, updating and adjusting the multi-light source initial combination parameters based on the illumination residual deviation values according to the real-time image of the surgical area to generate the multi-light source dynamic combination, the method comprising: incrementally solving the multi-light source initial combination parameters based on the first illumination residual deviation values according to the real-time image of the surgical area to obtain a first light source parameter increment; algebraically superimposing the multi-light source initial combination parameters based on the first light source parameter increment to determine a first to-be-executed light source control parameter; incrementally solving the multi-light source initial combination parameters based on the second illumination residual deviation values according to the real-time image of the surgical area to obtain a second to-be-executed light source control parameter; performing feasibility checking based on the first to-be-executed light source control parameter and the second to-be-executed light source control parameter, setting a control period according to the checking result, and updating and adjusting the multi-light source initial combination parameters according to the control period to generate the multi-light source dynamic combination.

9. The adaptive dimming control method for multi-source data acquisition of claim 8, wherein, performing feasibility checking based on the first to-be-executed light source control parameter and the second to-be-executed light source control parameter, setting a control period according to the checking result, and updating and adjusting the multi-light source initial combination parameters according to the control period to generate the multi-light source dynamic combination, the method comprising: comparing the first to-be-executed light source control parameter and the second to-be-executed light source control parameter one by one to extract a first brightness parameter value and a second brightness parameter value; performing extreme value analysis based on the light source module, determining a light source brightness interval according to the light source extreme value, judging whether the first brightness parameter value and the second brightness parameter value conflict based on the light source brightness interval, and generating a first conflict checking result and a second conflict checking result; when at least one of the first conflict checking result and the second conflict checking result contains an over-limit abnormal result or a conflict abnormal result, a first control period is set; when at least one of the first conflict checking result or the second conflict checking result contains an un-mutation abnormal result and does not contain an over-limit abnormal result and a conflict abnormal result, a second control period is set; when neither of the first conflict checking result and the second conflict checking result contains any abnormal mark, a third control period is set.

10. An adaptive dimming control system for multi-light source data acquisition, characterized by, The system for implementing the adaptive dimming control method for multi-light source data acquisition according to any one of claims 1-9, the system comprising: an analysis module: capturing a real-time image of a surgical area for multi-angle analysis, obtaining a multi-angle illumination image dataset for illumination analysis, and identifying illumination defect information, the illumination defect information including shadow distribution data and glare intensity data; The parameter generation module maps the shadow distribution data to the surgical area for analysis and identification, generates a plurality of shadow sub-regions, performs multi-light source optimization according to the glare intensity data in combination with the plurality of shadow sub-regions, and generates a plurality of initial combination parameters of the multi-light source; The parameter adjustment module drives the multi-light source combined shadowless lamp for illumination control according to the initial combination parameters of the multi-light source, updates and adjusts the initial combination parameters of the multi-light source according to the control result in combination with the real-time image of the surgical area, and generates a dynamic combination of the multi-light source to control the real-time illumination of the shadowless lamp.

Images