Mine lamp dynamic illumination control method and system, storage medium and mine lamp

Abstract

The invention is suitable for the technical field of lighting equipment, and provides a miner lamp dynamic lighting control method and system, a storage medium and a miner lamp, and the method comprises the steps: collecting the current image data of the current environment, and extracting the actual illumination intensity distribution in the current image data; performing image decomposition on the collected current image data to obtain a reflection component and an illumination component, performing reflection enhancement on the reflection component, and performing illumination adjustment on the illumination component; re-synthesizing the reflection component after reflection enhancement and the illumination component after illumination adjustment to obtain target image data, and extracting target illumination intensity distribution in the target image data; and according to the actual illumination intensity distribution in the current image data and the target illumination intensity distribution in the target image data, dynamically adjusting the illumination brightness of each group of light sources in the mine lamp. According to the invention, the problem that the illumination quality and the image acquisition quality are poor under the existing low-illumination condition is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of lighting equipment, and in particular to a mining lamp dynamic lighting control method, system, storage medium and mining lamp. Background Art

[0002] In low-light environments such as mines, lighting equipment is an important tool to ensure the safety of miners and conduct environmental monitoring. Mining lamps, as the most common lighting equipment, are usually used to provide a stable light source. However, there are some shortcomings in traditional mining lamp lighting, especially in low light and complex lighting conditions. The brightness of the light cannot be flexibly adjusted according to changes in the environment, resulting in poor lighting effects. In low-light conditions, the collected images usually have problems such as uneven lighting and insufficient brightness, which affects the effective monitoring of the inside of the mine.

[0003] In the existing technology, most common mining lamp control systems rely on preset fixed brightness modes and are unable to dynamically adjust the light brightness according to environmental changes and image quality, resulting in difficulty in obtaining high-quality image data in low-light environments. This is particularly true in real-time monitoring of complex terrain or operational details inside mines, where there are obvious limitations. Summary of the invention

[0004] Based on this, the purpose of the present invention is to provide a mining lamp dynamic lighting control method, system, storage medium and mining lamp, so as to fundamentally solve the problems of poor lighting quality and image acquisition quality under existing low light conditions.

[0005] A mining lamp dynamic lighting control method according to an embodiment of the present invention comprises:

[0006] Collect current image data of the current environment and extract the actual light intensity distribution in the current image data;

[0007] Decomposing the collected current image data to obtain a reflection component and an illumination component, and enhancing the reflection component and adjusting the illumination component;

[0008] Resynthesize the reflection component after reflection enhancement and the illumination component after illumination adjustment to obtain target image data, and extract the target illumination intensity distribution in the target image data;

[0009] The illumination brightness of each group of light sources in the mining lamp is dynamically adjusted according to the actual illumination intensity distribution in the current image data and the target illumination intensity distribution in the target image data.

[0010] In addition, the dynamic lighting control method of a mining lamp according to the above embodiment of the present invention may also have the following additional technical features:

[0011] Furthermore, the step of extracting the actual light intensity distribution in the current image data includes:

[0012] Perform denoising on the current image data and convert the current image data from the RGB color space to the grayscale space;

[0013] Calculate the gray value of each pixel in the current image data in the gray space, and perform statistical analysis on the gray value of each pixel to calculate the light intensity distribution of the current image data;

[0014] Divide the current image data into a preset number of sub-regions, and calculate the average grayscale value of all pixels in each sub-region to obtain the light intensity estimation of each sub-region;

[0015] The illumination intensity distribution of the current image data and the illumination intensity estimation result of each sub-region are combined to generate an illumination intensity distribution map.

[0016] Furthermore, the step of performing image decomposition on the collected current image data to obtain a reflection component and an illumination component includes:

[0017] The collected current image data is converted into a grayscale image, and the grayscale image is logarithmically transformed to obtain a logarithmic domain image;

[0018] Gaussian filtering is performed on the logarithmic domain image after logarithmic transformation to obtain the logarithmic value of the estimated illumination component, and the estimated illumination component is converted from the logarithmic domain back to the linear domain;

[0019] The reflection component is calculated based on the grayscale value of the current image data and the estimated illumination component.

[0020] Furthermore, the steps of enhancing reflection of the reflection component and adjusting illumination of the illumination component include:

[0021] Input the reflection component into the trained residual network to obtain the reflection component after reflection enhancement;

[0022] Extracting the light brightness value of each pixel from the light component, and dividing the current image data into a dark area and a highlight area according to the light brightness value of each pixel;

[0023] Use nonlinear transformation or histogram equalization to enhance the brightness of dark areas, and use brightness scaling or correction to adjust the brightness of highlight areas.

[0024] Furthermore, the step of resynthesizing the reflection component after reflection enhancement and the illumination component after illumination adjustment to obtain the target image data comprises:

[0025] Normalizing the reflection component after reflection enhancement and the illumination component after illumination adjustment;

[0026] Multiply the normalized reflection component and illumination component pixel by pixel to generate target image data;

[0027] Perform contrast adjustment and color correction on the target image data.

[0028] Furthermore, the step of dynamically adjusting the illumination brightness of each group of light sources in the mining lamp according to the actual illumination intensity distribution in the current image data and the target illumination intensity distribution in the target image data includes:

[0029] Calculate the illumination difference between the actual illumination intensity distribution and the target illumination intensity distribution;

[0030] Calculate the adjustment coefficient of each group of light sources based on the lighting differences;

[0031] The lighting brightness of each group of light sources in the mining lamp is adjusted according to the calculated adjustment coefficient.

[0032] Another embodiment of the present invention aims to provide a mining lamp dynamic lighting control system, the system comprising:

[0033] The data acquisition module is used to collect the current image data of the current environment and extract the actual light intensity distribution in the current image data;

[0034] An image decomposition module is used to decompose the collected current image data into a reflection component and an illumination component, and to enhance the reflection component and adjust the illumination component;

[0035] An image synthesis module, used to resynthesize the reflection component after reflection enhancement and the illumination component after illumination adjustment to obtain target image data, and extract the target illumination intensity distribution in the target image data;

[0036] The lighting adjustment module is used to dynamically adjust the lighting brightness of each group of light sources in the mining lamp according to the actual lighting intensity distribution in the current image data and the target lighting intensity distribution in the target image data.

[0037] Furthermore, the data acquisition module includes:

[0038] A data conversion unit, used for performing denoising on the current image data and converting the current image data from the RGB color space to the grayscale space;

[0039] A first data calculation unit is used to calculate the gray value of each pixel in the current image data in the gray space, and perform statistical analysis on the gray value of each pixel to calculate the light intensity distribution of the current image data;

[0040] A second data calculation unit, used for dividing the current image data into a preset number of sub-regions, and calculating the average grayscale value of all pixels in each sub-region to obtain an estimation of the light intensity of each sub-region;

[0041] The data generating unit is used to combine the illumination intensity distribution of the current image data and the illumination intensity estimation result of each sub-area to generate an illumination intensity distribution map.

[0042] Another embodiment of the present invention aims to provide a storage medium storing a program, which, when executed by a processor, implements the dynamic lighting control method for a mining lamp as described above.

[0043] Another embodiment of the present invention aims to provide a mining lamp, comprising a memory, a processor, and a program stored in the memory and executable on the processor, wherein the processor implements the mining lamp dynamic lighting control method as described above when executing the program.

[0044] The dynamic lighting control method for a mining lamp provided by an embodiment of the present invention can effectively improve the brightness and contrast of an image by decomposing and processing the collected image, including adjusting the illumination component and enhancing the reflection component, so that the mining lamp can provide a clearer image under low light conditions, thereby improving the monitoring effect; by real-time analysis of the actual illumination intensity distribution in the current image data and the target illumination intensity distribution in the target image data, the adjustment coefficient of the light brightness is calculated, and the brightness of each group of lights is dynamically adjusted, so that the lighting can be flexibly adjusted according to environmental changes, thereby making the illumination more uniform and effectively avoiding the situation of being too bright or too dark; by improving the lighting effect and improving the image acquisition quality, it can help to more clearly monitor the working conditions inside the mine, ensure the safety of miners, and reduce operational errors caused by insufficient illumination in mine operations by optimizing the lighting; by adjusting the light brightness in real time according to the actual illumination intensity of the current environment and the target illumination requirement, the purpose of adaptive adjustment is achieved, so that the mining lamp can adapt to different working scenes and illumination conditions, and provide the best lighting effect. The problem of poor illumination quality and image acquisition quality under existing low light conditions is solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 is a flow chart of a mining lamp dynamic lighting control method in a first embodiment of the present invention;

[0046] Figure 2 It is a structural schematic diagram of a mining lamp dynamic lighting control system in a second embodiment of the present invention;

[0047] Figure 3 It is a schematic structural diagram of a mining lamp in a third embodiment of the present invention;

[0048] The following specific implementations will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0049] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0050] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0051] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0052] Embodiment 1

[0053] See also Figure 1 , which shows a mining lamp dynamic lighting control method in a first embodiment of the present invention. For the sake of convenience, only the parts related to the embodiment of the present invention are shown. The mining lamp dynamic lighting control method provided by the embodiment of the present invention includes:

[0054] Step S10, collecting current image data of the current environment, and extracting actual light intensity distribution in the current image data;

[0055] Among them, in one embodiment of the present invention, first, it is necessary to use a camera or other imaging device to capture an image of the current environment. This is usually achieved by calling the API of the image acquisition hardware. A common method is to use a camera interface, such as OpenCV, to capture images in real time. Further, the actual light intensity distribution in the current image data is extracted. Specifically, the above-mentioned step of extracting the actual light intensity distribution in the current image data includes:

[0056] Perform denoising on the current image data and convert the current image data from the RGB color space to the grayscale space;

[0057] Calculate the gray value of each pixel in the current image data in the gray space, and perform statistical analysis on the gray value of each pixel to calculate the light intensity distribution of the current image data;

[0058] Divide the current image data into a preset number of sub-regions, and calculate the average grayscale value of all pixels in each sub-region to obtain the light intensity estimation of each sub-region;

[0059] The illumination intensity distribution of the current image data and the illumination intensity estimation result of each sub-region are combined to generate an illumination intensity distribution map.

[0060] Specifically, since the noise in the image will affect the accuracy of the light intensity, the image needs to be denoised first to eliminate the noise in the image and enhance the accuracy of the light information. Common denoising methods include Gaussian blurring, median filtering, etc. Gaussian filtering reduces noise by smoothing the image through a Gaussian function. Median filtering reduces image noise by taking the median of the surrounding pixels. The light intensity can usually be estimated by the brightness (grayscale value) of the image. At this time, converting the image from the RGB color space to the grayscale space can simplify the extraction of the light intensity. Therefore, it is necessary to convert the image from the RGB color space to the grayscale space, where each pixel value of the grayscale image represents the brightness of the pixel. The conversion formula is:

[0061] L=0.299R+0.587G+0.114B

[0062] Where R, G and B are the values ​​of the red, green and blue channels of each pixel in the image. In the grayscale image, the grayscale value (brightness) of each pixel represents the light intensity of the pixel. At this time, by counting the grayscale values ​​of all pixels in the entire image and generating a histogram of the grayscale value or other statistical analysis results, the overall light intensity distribution of the image can be understood. It should be noted that it is also possible to convert the image from the RGB color space to the HSV color space and extract the brightness (Value) channel, wherein the brightness channel directly reflects the light intensity in the image. Further, in order to obtain a local light intensity estimate, the image can be divided into a preset number of sub-regions (such as a grid), and the size of each sub-region can be adjusted according to actual needs. Then, in each sub-region, the average grayscale value of all pixels in the sub-region is calculated as the light intensity estimate of the sub-region. Then, according to the distribution information (histogram or statistical results) of the grayscale value of each pixel and the light intensity estimate of each sub-region, the results are merged to generate a final light intensity distribution diagram, wherein the light intensity distribution can be displayed as a graph or a numerical table. The graphics can include grayscale images or heat maps. Grayscale images show the light intensity distribution of an image, while heat maps use color coding to show the light intensity of different areas. Therefore, by calculating the histogram of the grayscale value distribution and combining it with the light intensity estimation of the sub-region, a complete light intensity distribution map can be generated. In other words, the image is denoised and the color space is converted to extract brightness information. The light distribution is analyzed by calculating the grayscale value of each pixel and generating a histogram. The image is divided into multiple sub-regions, and the average grayscale value of each sub-region is calculated as the local light intensity estimate. The light intensity distribution map is obtained by merging the histogram and the sub-region estimation, and can be visualized in the form of a heat map.

[0063] Step S20, performing image decomposition on the collected current image data to obtain a reflection component and an illumination component, and performing reflection enhancement on the reflection component and illumination adjustment on the illumination component;

[0064] Among them, in one embodiment of the present invention, the collected current image data is subjected to image decomposition to obtain the reflection component and the illumination component, which usually relies on the image decomposition algorithm, especially the decomposition method based on the Retinex theory. Among them, the Retinex theory proposes that the brightness of the image is determined by two main factors: Reflectance Component: represents the inherent reflection property or color of the surface of the object. Illumination Component: represents the intensity of the ambient light. According to the Retinex theory, the brightness of the image I (x, y) is the product of the reflection component R (x, y) and the illumination component L (x, y), that is:

[0065] I(x,y) = R(x,y) L(x,y), where I(x,y) is the pixel intensity at coordinate (x,y). R(x,y) is the reflection component at coordinate (x,t), and L(x,y) is the illumination component at coordinate (x,y).

[0066] At this time, the step of performing image decomposition on the collected current image data to obtain the reflection component and the illumination component includes:

[0067] The collected current image data is converted into a grayscale image, and the grayscale image is logarithmically transformed to obtain a logarithmic domain image;

[0068] Gaussian filtering is performed on the logarithmic domain image after logarithmic transformation to obtain the logarithmic value of the estimated illumination component, and the estimated illumination component is converted from the logarithmic domain back to the linear domain;

[0069] The reflection component is calculated based on the grayscale value of the current image data and the estimated illumination component.

[0070] Specifically, the color image is converted into a grayscale image. For color images, the weighted average method is usually used to convert the RGB image into a grayscale image. For example: L = 0.299R + 0.587G + 0.114B, where R, G, and B are the values ​​of the red, green, and blue channels of each pixel in the image. The grayscale image is then logarithmically transformed to convert the multiplication relationship into an addition relationship. This helps with subsequent decomposition processing. Use the logarithmic transformation formula: log(I(x,y)) = log(R(x,y)) + log(L(x,y)). Gaussian filtering is then applied to the logarithmic transformed image to estimate the illumination component. Gaussian filtering can smooth the image, remove local details, and retain global illumination information. The formula is as follows:

[0071] log(L(x,y))=G(x,y)*log(I(x,y))

[0072] Where G(x,y) is the Gaussian kernel and * indicates the convolution operation. The result log(L(x,y)) is the logarithm of the estimated illumination component. The estimated illumination component is then converted from the logarithmic domain back to the linear domain. Specifically, an exponential function is used to restore it from the logarithmic domain back to the linear domain:

[0073] L(x,y)=exp(log(L(x,y)))

[0074] The reflection component is then calculated using the current image data and the estimated illumination component. The formula is as follows:

[0075]

[0076] where ∈ is a small constant (e.g. 1×10 -8) to avoid division by zero errors.

[0077] Furthermore, in addition to the above-mentioned Retinex theory decomposition method to decompose the collected current image data to obtain the reflection component and the illumination component, a deep learning method (such as a Retinex-based neural network) can also be used for image decomposition. Specifically, first use an image data set containing real reflection and illumination components to train a deep neural network module. Then the collected image is input into the trained deep neural network model, and the deep neural network module outputs the corresponding decomposition to obtain the reflection component and illumination component. Commonly used network structures for denoising include the Retinex-Net network structure and the Deep Retinex network structure, in which Retinex-Net is based on a deep convolutional neural network (CNN), and extracts the reflection component and illumination component from the input image through network learning. Deep Retinex is a Retinex model based on deep learning, which combines multi-scale feature extraction and generative adversarial network (GAN) for image decomposition.

[0078] Furthermore, the reflection component is enhanced and the illumination component is adjusted, and the steps include:

[0079] Input the reflection component into the trained residual network to obtain the reflection component after reflection enhancement;

[0080] Extracting the light brightness value of each pixel from the light component, and dividing the current image data into a dark area and a highlight area according to the light brightness value of each pixel;

[0081] Use nonlinear transformation or histogram equalization to enhance the brightness of dark areas, and use brightness scaling or correction to adjust the brightness of highlight areas.

[0082] Specifically, the residual network (Residual Network, ResNet) can be used to enhance the reflection component to effectively improve the details and quality of the image. The residual network solves the training problem in the deep network by introducing residual connections, so that the network can learn more refined features. The specific implementation steps of using the residual network to enhance the reflection component are: 1. Normalize the reflection component image so that its pixel value is in the range of [0,1]. Divide the data set into a training set, a validation set, and a test set. 2. Construct a deep convolutional neural network containing a residual block. The residual block usually includes the following parts: Convolution layer: used to extract image features. Batch normalization (BatchNormalization) is used to standardize data to improve the stability of network training. Activation function: ReLU (Rectified Linear Unit) is usually used as the activation function. Residual connection: In the residual block, the input data and the data after convolution are added to form a residual map. 3. Train the network, including selecting an appropriate loss function to measure the difference between the network output and the target image, and selecting an optimization algorithm to train the network. Commonly used loss functions include: Mean Square Error (MSE): used to measure the pixel difference between the predicted image and the target image. The optimization algorithms include, for example, the Adam adaptive learning rate optimization algorithm, which is suitable for processing large amounts of data and complex models. The training process includes: forward propagation, inputting the reflection component image into the network to obtain the prediction result. Calculating the loss, calculating the difference between the prediction result and the actual target through the loss function. Backward propagation, using the optimization algorithm to update the network weights to reduce the loss value. Iterative training, repeating the above process until the network performance is stable. Fourth, apply the network for reflection enhancement, input the reflection component to be enhanced into the trained residual network, and the network outputs the enhanced reflection component, which usually shows richer details and higher contrast.

[0083] Further, the luminance value I(x, y) of each pixel is extracted from the illumination component L(x, y). For a grayscale image, the luminance can be directly used as the pixel value; for a color image, it can be obtained by converting the RGB values into luminance values. At this time, according to the luminance value I(x, y) of each pixel, the image is divided into a dark region and a highlight region. For example, a threshold T can be set. When the luminance value I(x, y) < T, the pixel is classified into the dark region; when I(x, y) ≥ T, the pixel is classified into the highlight region. Nonlinear transformation (such as Gamma correction) or histogram equalization is performed on the pixels in the dark region to enhance the luminance of these regions. Histogram equalization is used to stretch the luminance distribution in the dark region to make more details visible, especially in very dark regions. Luminance scaling or correction is performed on the highlight region to avoid loss of image information caused by over-bright regions. The luminance can be compressed by a scaling factor. Through an adaptive method, the luminance is adjusted according to the local luminance distribution in the highlight region to maintain the overall luminance balance of the image.

[0084] Further, in other embodiments of the present invention, the reflection enhancement of the reflection component may further include: increasing the contrast of the image by equalizing the grayscale histogram of the image. This method makes the details in low-contrast regions more obvious by expanding the grayscale range of the image. Adaptive histogram equalization is performed in local regions of the image to enhance the local contrast of the image. By calculating the second derivative of the image, the edge information of the image is highlighted, making the details clearer. A high-pass filter (such as the Laplacian operator) is applied to enhance the details and edges of the image. And the illumination adjustment of the illumination component includes: performing equalization processing on the illumination component to reduce the non-uniformity of illumination. A nonlinear function (such as a logarithmic function or an exponential function) is used to adjust the illumination component to simulate different illumination conditions or improve the current illumination effect. A deep learning method (such as an illumination enhancement network) is used to automatically learn and adjust the illumination component.

[0085] Step S30, the reflection component after reflection enhancement and the illumination component after illumination adjustment are recombined to obtain target image data, and the target illumination intensity distribution in the target image data is extracted;

[0086] Among them, in one embodiment of the present invention, the step of recombining the reflection component after reflection enhancement and the illumination component after illumination adjustment to obtain target image data includes:

[0087] Performing normalization processing on the reflection component after reflection enhancement and the illumination component after illumination adjustment;

[0088] The normalized reflection component and illumination component are multiplied pixel by pixel to generate target image data;

[0089] Perform contrast adjustment and color correction on the target image data.

[0090] Specifically, first, the reflection component after reflection enhancement and the illumination component after illumination adjustment are normalized. The purpose of normalization is to limit the pixel values ​​of the image to a specific range (usually 0,1) so that numerical stability can be maintained in subsequent calculations. After normalization, the reflection component and the illumination component are multiplied pixel by pixel. This step is to generate the final target image according to the formula I(x,y)=R(x,y)·L(x,y). It is also necessary to ensure that the values ​​of the synthesized image data are within an appropriate range (such as 0 to 255) to prevent numerical overflow or insufficient values ​​caused by multiplication. If necessary, apply clipping or normalization. If the original image is a color image, the color space problem needs to be handled during the synthesis process. Ensure that the reflection component and the illumination component use the same color space when synthesized. The generated target image may have insufficient contrast, so the image needs to be contrast adjusted. Contrast enhancement can be performed by contrast stretching or using histogram equalization. The purpose of color correction is to make the synthesized image have more natural colors, and the overall color balance of the image can be adjusted by a white balance algorithm.

[0091] The specific extraction of target illumination intensity distribution in target image data may refer to the above description, and is not specifically limited here.

[0092] Step S40, dynamically adjusting the illumination brightness of each group of light sources in the mining lamp according to the actual illumination intensity distribution in the current image data and the target illumination intensity distribution in the target image data;

[0093] Among them, in one embodiment of the present invention, the step of dynamically adjusting the illumination brightness of each group of light sources in the mining lamp according to the actual illumination intensity distribution in the current image data and the target illumination intensity distribution in the target image data includes:

[0094] Calculate the illumination difference between the actual illumination intensity distribution and the target illumination intensity distribution;

[0095] Calculate the adjustment coefficient of each group of light sources based on the lighting differences;

[0096] The lighting brightness of each group of light sources in the mining lamp is adjusted according to the calculated adjustment coefficient.

[0097] Specifically, for the current image data collected under the current environment, the actual light intensity distribution is obtained through the pixel brightness value or through color space conversion (for example, converting the RGB image into a grayscale image or a brightness channel). The target image data is an image after reflection enhancement and light adjustment, and its light intensity distribution is extracted by the same method. Then the light difference between the actual light intensity distribution and the target light intensity distribution is calculated pixel by pixel. The light distribution in the image is mapped to the light area of ​​the mining lamp. Assume that the mining lamp is divided into multiple light groups, and each light group is responsible for a different area (which can be a predefined area or adaptively adjusted according to the light distribution). Corresponding to the image area illuminated by each group of light sources, the average light difference of the area is calculated. According to the light difference, the adjustment coefficient is calculated for each group of lights, and the adjustment coefficient is related to the size of the light difference. If the light difference is large, the adjustment coefficient is large, otherwise the adjustment coefficient is small. Then, according to the adjustment coefficient of each group of lights, the brightness of each group of light sources in the mining lamp is adjusted. At the same time, the light distribution of the current image is continuously monitored by a camera or a light sensor, and the brightness of each group of lights is continuously adjusted to ensure that the brightness of the entire lighting area is uniform and adapts to environmental changes. To avoid excessive adjustment of lights, the brightness can be limited to a certain range. The adjusted brightness can be kept between the maximum and minimum brightness allowed by clipping or smoothing functions. Therefore, the light intensity distribution is extracted from the current image data and the target image data, and the light difference is calculated pixel by pixel. According to the area covered by different light sources, the average value of the light difference in the area is calculated, and the brightness adjustment coefficient of each group of lights is obtained. The brightness of each group of lights is dynamically adjusted according to the adjustment coefficient, and real-time feedback control is performed to maintain the consistency and stability of the ambient lighting.

[0098] In summary, the dynamic lighting control method of the mining lamp in the above embodiment of the present invention can effectively improve the image brightness and contrast by decomposing and processing the collected image, including adjusting the illumination component and enhancing the reflection component, so that the mining lamp can provide a clearer image under low light conditions, thereby improving the monitoring effect; by real-time analysis of the actual illumination intensity distribution in the current image data and the target illumination intensity distribution in the target image data, the adjustment coefficient of the light brightness is calculated, and the brightness of each group of lights is dynamically adjusted, so that the lighting can be flexibly adjusted according to environmental changes, thereby making the illumination more uniform and effectively avoiding the situation of being too bright or too dark; by improving the lighting effect and improving the image acquisition quality, it can help to more clearly monitor the working conditions inside the mine, ensure the safety of miners, and reduce the operation errors caused by insufficient illumination in mine operations by optimizing the lighting; by adjusting the light brightness in real time according to the actual illumination intensity of the current environment and the target illumination requirement, the purpose of adaptive adjustment is achieved, so that the mining lamp can adapt to different working scenes and illumination conditions and provide the best lighting effect. The problem of poor lighting quality and image acquisition quality under existing low light conditions is solved.

[0099] Embodiment 2

[0100] See also Figure 2 , is a schematic diagram of the structure of a mining lamp dynamic lighting control system provided by the second embodiment of the present invention. For the convenience of description, only the parts related to the embodiment of the present invention are shown. The mining lamp dynamic lighting control system includes:

[0101] The data acquisition module 11 is used to acquire the current image data of the current environment and extract the actual light intensity distribution in the current image data;

[0102] An image decomposition module 12 is used to decompose the collected current image data to obtain a reflection component and an illumination component, and to enhance the reflection component and adjust the illumination component;

[0103] An image synthesis module 13 is used to synthesize the reflection component after reflection enhancement and the illumination component after illumination adjustment to obtain target image data, and extract the target illumination intensity distribution in the target image data;

[0104] The lighting adjustment module 14 is used to dynamically adjust the lighting brightness of each group of light sources in the mining lamp according to the actual lighting intensity distribution in the current image data and the target lighting intensity distribution in the target image data.

[0105] Furthermore, in one embodiment of the present invention, the data acquisition module 11 includes:

[0106] A data conversion unit, used for performing denoising on the current image data and converting the current image data from the RGB color space to the grayscale space;

[0107] A first data calculation unit is used to calculate the gray value of each pixel in the current image data in the gray space, and perform statistical analysis on the gray value of each pixel to calculate the light intensity distribution of the current image data;

[0108] A second data calculation unit, used for dividing the current image data into a preset number of sub-regions, and calculating the average grayscale value of all pixels in each sub-region to obtain an estimation of the light intensity of each sub-region;

[0109] The data generating unit is used to combine the illumination intensity distribution of the current image data and the illumination intensity estimation result of each sub-area to generate an illumination intensity distribution map.

[0110] Furthermore, in one embodiment of the present invention, the image decomposition module 12 includes:

[0111] A data conversion unit, used for converting the collected current image data into a grayscale image, and performing logarithmic transformation on the grayscale image to obtain a logarithmic domain image;

[0112] an illumination component determination unit, configured to perform Gaussian filtering on the logarithmic domain image after logarithmic transformation to obtain a logarithmic value of the estimated illumination component, and to convert the estimated illumination component from the logarithmic domain back to the linear domain;

[0113] The reflection component determination unit is used to calculate the reflection component according to the gray value of the current image data and the estimated illumination component.

[0114] Furthermore, in one embodiment of the present invention, the image decomposition module 12 includes:

[0115] A reflection component processing unit, used for inputting the reflection component into a trained residual network to obtain a reflection enhanced reflection component;

[0116] A region division unit, used for extracting the light brightness value of each pixel from the light component, and dividing the current image data into a dark area and a highlight area according to the light brightness value of each pixel;

[0117] The illumination component processing unit is used to enhance the brightness of the dark area by using nonlinear transformation or histogram equalization, and to adjust the brightness of the highlight area by using brightness scaling or correction.

[0118] Furthermore, in one embodiment of the present invention, the image synthesis module 13 includes:

[0119] A data processing unit, used for normalizing the reflection component after reflection enhancement and the illumination component after illumination adjustment;

[0120] An image generating unit, used for performing pixel-by-pixel multiplication of the normalized reflection component and illumination component to generate target image data;

[0121] The image processing unit is used to perform contrast adjustment and color correction on the target image data.

[0122] Furthermore, in one embodiment of the present invention, the lighting adjustment module 14 includes:

[0123] An illumination difference calculation unit, used to calculate the illumination difference between the actual illumination intensity distribution and the target illumination intensity distribution;

[0124] An adjustment coefficient calculation unit, used to calculate the adjustment coefficient of each group of light sources according to the illumination difference;

[0125] The lighting adjustment unit is used to adjust the lighting brightness of each group of light sources in the mining lamp according to the calculated adjustment coefficient.

[0126] The implementation principle and technical effects of the mining lamp dynamic lighting control system provided in the embodiment of the present invention are the same as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference may be made to the corresponding contents in the aforementioned method embodiment.

[0127] Embodiment 3

[0128] Another aspect of the present invention is to provide a mining lamp, see Figure 3 , shown is a mining lamp in the third embodiment of the present invention, including a memory 20, a processor 10, and a program 30 stored in the memory 20 and executable on the processor. When the processor 10 executes the program 30, the mining lamp dynamic lighting control method as in the above embodiment is implemented.

[0129] In some embodiments, the processor 10 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 20, such as executing access restriction programs.

[0130] The memory 20 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 20 can be an internal storage unit of the miner's lamp, such as the hard disk of the miner's lamp. In other embodiments, the memory 20 can also be an external storage device of the miner's lamp, such as a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card, etc. equipped on the miner's lamp. Further, the memory 20 can also include both the internal storage unit of the miner's lamp and the external storage device. The memory 20 can be used not only to store application software and various types of data installed in the miner's lamp, but also to temporarily store data that has been output or is to be output.

[0131] It should be pointed out that Figure 3 The structure shown does not constitute a limitation on the mining lamp. In other embodiments, the mining lamp may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0132] In summary, the mining lamp in the above embodiment of the present invention can effectively improve the image brightness and contrast by decomposing and processing the collected image, including adjusting the illumination component and enhancing the reflection component, so that the mining lamp can provide a clearer image under low light conditions, thereby improving the monitoring effect; by real-time analysis of the actual illumination intensity distribution in the current image data and the target illumination intensity distribution in the target image data, the adjustment coefficient of the light brightness is calculated, and the brightness of each group of lights is dynamically adjusted, so that the lighting can be flexibly adjusted according to environmental changes, thereby making the illumination more uniform and effectively avoiding the situation of being too bright or too dark; by improving the lighting effect and improving the image acquisition quality, it can help to more clearly monitor the working conditions inside the mine, ensure the safety of miners, and reduce operational errors caused by insufficient illumination in mine operations by optimizing the lighting; by adjusting the light brightness in real time according to the actual illumination intensity of the current environment and the target illumination requirement, the purpose of adaptive adjustment is achieved, so that the mining lamp can adapt to different working scenes and illumination conditions and provide the best lighting effect. The problem of poor illumination quality and image acquisition quality under existing low light conditions is solved.

[0133] The embodiment of the present invention further provides a storage medium on which a program is stored. When the program is executed by a processor, the dynamic lighting control method for a mining lamp as described in the above embodiment is implemented.

[0134] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be assigned to different functional units or modules as needed, that is, the internal structure of the storage device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the implementation method can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application.

[0135] Those skilled in the art will appreciate that the logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be embodied in any storage medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For purposes of this specification, a "storage medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0136] More specific examples of readable storage media (a non-exhaustive list) include the following: an electrical connection with one or more wirings (electronic devices), a portable computer disk case (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and editable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the storage medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or processing in another suitable manner as necessary, and then stored in a memory.

[0137] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0138] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0139] The above-described embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the attached claims.

Claims

1. A mining lamp dynamic lighting control method, characterized in that: The method comprises: Collect current image data of the current environment and extract the actual light intensity distribution in the current image data; Decomposing the collected current image data to obtain a reflection component and an illumination component, and enhancing the reflection component and adjusting the illumination component; Resynthesize the reflection component after reflection enhancement and the illumination component after illumination adjustment to obtain target image data, and extract the target illumination intensity distribution in the target image data; The illumination brightness of each group of light sources in the mining lamp is dynamically adjusted according to the actual illumination intensity distribution in the current image data and the target illumination intensity distribution in the target image data.

2. The dynamic lighting control method of a mining lamp according to claim 1, characterized in that: The step of extracting the actual light intensity distribution in the current image data comprises: Perform denoising on the current image data and convert the current image data from the RGB color space to the grayscale space; Calculate the grayscale value of each pixel in the current image data in the grayscale space, and perform statistical analysis on the grayscale value of each pixel to calculate the light intensity distribution of the current image data; Divide the current image data into a preset number of sub-regions, and calculate the average grayscale value of all pixels in each sub-region to obtain the light intensity estimation of each sub-region; The illumination intensity distribution of the current image data and the illumination intensity estimation results of each sub-region are combined to generate an illumination intensity distribution map.

3. The dynamic lighting control method of a mining lamp according to claim 1, characterized in that: The step of performing image decomposition on the collected current image data to obtain a reflection component and an illumination component comprises: The collected current image data is converted into a grayscale image, and the grayscale image is logarithmically transformed to obtain a logarithmic domain image; Gaussian filtering is performed on the logarithmic domain image after logarithmic transformation to obtain the logarithmic value of the estimated illumination component, and the estimated illumination component is converted from the logarithmic domain back to the linear domain; The reflection component is calculated based on the grayscale value of the current image data and the estimated illumination component.

4. The dynamic lighting control method of a mining lamp according to claim 3, characterized in that: The steps of enhancing the reflection component and adjusting the illumination component include: Input the reflection component into the trained residual network to obtain the reflection component after reflection enhancement; Extracting the light brightness value of each pixel from the light component, and dividing the current image data into a dark area and a highlight area according to the light brightness value of each pixel; Use nonlinear transformation or histogram equalization to enhance the brightness of shadow areas, and use brightness scaling or correction to adjust the brightness of highlight areas.

5. The dynamic lighting control method of a mining lamp according to claim 1, characterized in that: The step of resynthesizing the reflection component after reflection enhancement and the illumination component after illumination adjustment to obtain target image data comprises: Normalizing the reflection component after reflection enhancement and the illumination component after illumination adjustment; Multiply the normalized reflection component and illumination component pixel by pixel to generate target image data; Perform contrast adjustment and color correction on the target image data.

6. The dynamic lighting control method of a mining lamp according to claim 1, characterized in that: The step of dynamically adjusting the illumination brightness of each group of light sources in the mining lamp according to the actual illumination intensity distribution in the current image data and the target illumination intensity distribution in the target image data comprises: Calculate the illumination difference between the actual illumination intensity distribution and the target illumination intensity distribution; Calculate the adjustment coefficient of each group of light sources based on the lighting differences; The lighting brightness of each group of light sources in the mining lamp is adjusted according to the calculated adjustment coefficient.

7. A mining lamp dynamic lighting control system, characterized in that: The system comprises: The data acquisition module is used to collect the current image data of the current environment and extract the actual light intensity distribution in the current image data; An image decomposition module is used to decompose the collected current image data into a reflection component and an illumination component, and to enhance the reflection component and adjust the illumination component; An image synthesis module, used to resynthesize the reflection component after reflection enhancement and the illumination component after illumination adjustment to obtain target image data, and extract the target illumination intensity distribution in the target image data; The lighting adjustment module is used to dynamically adjust the lighting brightness of each group of light sources in the mining lamp according to the actual lighting intensity distribution in the current image data and the target lighting intensity distribution in the target image data.

8. The mining lamp dynamic lighting control system according to claim 7, characterized in that: The data acquisition module comprises: A data conversion unit, used for performing denoising on the current image data and converting the current image data from the RGB color space to the grayscale space; A first data calculation unit is used to calculate the gray value of each pixel in the current image data in the gray space, and perform statistical analysis on the gray value of each pixel to calculate the light intensity distribution of the current image data; A second data calculation unit, used for dividing the current image data into a preset number of sub-regions, and calculating the average grayscale value of all pixels in each sub-region to obtain an estimation of the light intensity of each sub-region; The data generating unit is used to combine the illumination intensity distribution of the current image data and the illumination intensity estimation result of each sub-area to generate an illumination intensity distribution map.

9. A storage medium storing a program, characterized in that: When the program is executed by a processor, the dynamic lighting control method for a mining lamp as described in any one of claims 1 to 6 is implemented.

10. A mining lamp, characterized in that: The invention comprises a memory, a processor and a program stored in the memory and executable on the processor, wherein when the processor executes the program, the dynamic lighting control method for a mining lamp as claimed in any one of claims 1 to 6 is implemented.

Images