49 results about "SRGB" patented technology

The invention discloses a low-illumination image enhancement modeling method, an enhancement method, equipment and a storage medium, and relates to the field of image enhancement. The method comprises the steps that a training image is used for training a low-illumination image enhancement model, and the training process comprises the steps that the training image is input into a color gamut conversion module, and a linear rawRGB image and a reconstructed sRGB image are obtained; inputting the linear rawRGB image into a downsampling module to obtain a first sub-image and a second sub-image; performing enhancement processing on the second sub-graph; extracting frequency domain brightness guide signals of the first sub-image and the enhanced second sub-image to generate a guide signal; estimating a reflectivity component, an illuminance component and a brightness enhancement parameter in parallel by using an illumination enhancement decoupling network based on the guide signal; and calculating a multi-task loss function based on a model output result, and updating model parameters. According to the method, the problem of dependence on paired training data which is difficult to obtain is solved, and excellent brightness improvement and detail recovery effects are kept.

The invention discloses an underground coal mine image enhancement method, equipment and a medium. The method comprises the following steps: acquiring an underground sRGB image of a coal mine and a corresponding infrared image; obtaining a dust density estimation map according to the infrared image; obtaining a dust sensing intensity factor according to the sRGB image and the dust density estimation map; performing brightness enhancement on the sRGB image according to the dust sensing intensity factor to obtain a self-adaptive HVI image; and obtaining an enhanced sRGB image after enhancement according to the self-adaptive HVI image. The method can adapt to complex working conditions of underground dust scattering and uneven illumination, and the coal mine underground image is optimized and enhanced by estimating the dust density of the quantized environment and enhancing illumination.

The invention discloses a color correction method adopting residual correction. The method comprises the following steps: S1, inputting an image: inputting the image shot by a camera into processing equipment; s2, obtaining a color correction matrix: converting an RGB color space of the input image into a standard color space, such as sRGB and DCI-P3; s3, residual error correction: based on a preset specific color sample set, calculating a residual error between the color value corrected by the color correction matrix and a corresponding standard color value, constructing a residual error space, carrying out three-dimensional Gaussian filtering and downsampling processing on the residual error space, and carrying out residual error correction on the color value corrected by the color correction matrix according to a residual error correction table; and S4, Gamma correction: converting the RGB value of the linear color space into a nonlinear display value. The method is more suitable for color correction of special occasions (imaging of an endoscope), a residual correction (RC) link is added on the basis of a color correction matrix (CCM), the conversion precision of specific colors can be improved, and the overall precision can be guaranteed.

The invention provides an image enhancement method and apparatus, an electronic device and a storage medium. The method comprises the steps of obtaining an intensity component of a to-be-enhanced image in an sRGB color space, and an original hue component and a saturation component of the to-be-enhanced image in an HSV color space; determining a color density modulation factor, a perception hue and a saturation adaptive factor according to the intensity component and the original hue component; determining a color plane component of the image to be enhanced in the HVI color space according to the color density modulation factor, the saturation component, the saturation adaptive factor and the perceptual hue; and inputting the enhanced intensity component, the color density modulation factor, the saturation adaptive factor and the enhanced color plane component into a reverse conversion module to obtain an enhanced image in the sRGB color space, thereby effectively overcoming the inherent defects of the traditional color space in low-light image enhancement.

The invention discloses a closed-loop simulation evaluation method and system for a backlight diffusion model, and relates to the technical field of display systems, and the method comprises the steps: carrying out the calculation based on an initial linear image, and obtaining a partition backlight value; fitting screen front backlight and reference screen front backlight are determined based on the partition backlight values; determining a fitting liquid crystal value based on the fitting screen front backlight and the initial linear image; determining a reference liquid crystal value based on the reference screen front backlight and the initial linear image; multiplying the fitting liquid crystal value and the reference liquid crystal value by the reference screen front backlight to correspondingly obtain a fitting linear image and a reference linear image; respectively converting the fitting linear image and the reference linear image into sRGB formats, and correspondingly obtaining a fitting sRGB image and a reference sRGB image; comparing the fitting sRGB image with the reference sRGB image to obtain a perception difference; and evaluating the image quality of the fitted sRGB image. According to the method, the performance of generating the fast approximation model for fitting the sRGB image can be fully evaluated.

Embodiments of the present application disclose a method for image processing, an electronic device, an apparatus and a computing system, the method comprising: inputting an original RAW image to an image processing neural network; respectively extracting time domain features of the original RAW image by using a time domain UNET subnetwork to obtain a time domain feature map; extracting frequency domain features of the original RAW image by using a frequency domain UNET subnetwork to obtain a frequency domain feature map; and fusing the time domain feature map and the frequency domain feature map to output an sRGB image. In this way, when mapping the original RAW image to the sRGB image, the time domain UNET subnetwork and the frequency domain UNET subnetwork are connected in parallel to respectively extract the time domain feature map and the frequency domain feature map, and the frequency domain feature map can make up for the information defects of the time domain feature map, comprehensively utilize the time domain information and the frequency domain information of the image, further optimize the performance of the image processor, and improve the image processing effect.

This invention relates to the field of image processing technology, and provides a method for joint super-resolution and low-light enhancement processing based on RAW and sRGB images. The method includes: degrading a high-quality RAW image to obtain a low-quality RAW image and a low-quality sRGB image; performing maximum entropy downsampling on the high-quality RAW image to generate a fully sampled linear RAW image, and then generating a high-quality sRGB image through ISP pipeline rendering; constructing a joint super-resolution and low-light enhancement processing network; and training the joint super-resolution and low-light enhancement processing network using the low-quality RAW image, the low-quality sRGB image, and the high-quality sRGB image. This invention solves the problems of missing training datasets and mismatch between reference images and low-light, low-resolution input images in joint image super-resolution and low-light enhancement processing, and overcomes the limitations of traditional processing methods that use only a single sRGB or RAW image, thereby achieving higher image quality.

The invention discloses a shield tunnel water leakage image segmentation method suitable for a low-light environment, a storage medium and equipment. The shield tunnel water leakage image segmentation method suitable for the low-light environment comprises the following steps: acquiring a real-time sRGB image of a shield tunnel in the low-light environment; performing inverse operation on the obtained real-time sRGB image to obtain a pseudo RAW format image; and inputting the obtained pseudo RAW format image into a pre-trained instance segmentation model, and segmenting to obtain a water leakage disease area image of the shield tunnel. According to the invention, the image of the water leakage disease area of the shield tunnel can be quickly segmented in an extremely low light environment, and water leakage disease detection is realized.

The invention relates to an image processing method and device and electronic equipment, and relates to the technical field of image processing. The method specifically comprises the following steps: performing color gamut conversion processing from a color space RGB domain to a standard color space sRGB domain on an original image to obtain a first target image; performing semantic segmentation on the first target image to obtain an initial prediction category graph of the first target image; and on the basis of a second target prediction category map of a historical second target image, correcting the initial prediction category map of the first target image to obtain a first target prediction category map of the first target image, thereby obtaining the first target prediction category map of the first target image based on the second target prediction category map of the historical second target image. And the initial prediction category graph is corrected to obtain the first target prediction category graph, so that the accuracy and efficiency of obtaining the semantic segmentation result of the first target image are improved, the quality of obtaining the first target prediction category graph is ensured, and the user experience is improved.

The present invention discloses a method for identifying the night visibility level based on feature extraction, which includes: obtaining a night color image; extracting the luminance histogram data of the night color image, and obtaining a luminance feature vector through three-layer MLP processing; extracting the saturation image data S of the night color image, merging the saturation image data S with the night color image data RGB to form four-channel data, and obtaining a feature vector of SRGB through convolutional neural network processing; after merging and connecting the luminance feature vector of the night color image and the SRGB feature vector, performing class judgment through a discriminator to achieve the identification of the night visibility level. The present invention uses a feature fusion method to extract multiple features for classifier training, realizes feature complementarity, and realizes the identification of the night visibility level in the case of fog. Since the visibility at night is not high and the image degradation is serious, by effectively extracting different features of the night fog image, the accuracy rate of visibility level classification will be greatly improved.

Provided in the present application are laminated glass and a projection system. The laminated glass has a light-transmitting region and a shielding region, wherein at least one display region is provided in the shielding region. The display region has a P-light reflectivity RLp for P-polarized light which is incident at an incident angle of 65° and has a wavelength of 380 nm-780 nm, wherein the P-light reflectivity RLp satisfies RLp≥30%; and the display region has a maximum difference U for a reflected color sRGB value of the P-polarized light which is incident at the incident angle of 65° and has the wavelength of 380 nm-780 nm, wherein the maximum difference U satisfies U≤15. By means of the laminated glass and projection system that are provided in the present application, the brightness of projection display is enhanced and the energy utilization rate of a projection apparatus is improved, such that the energy consumption of the projection apparatus is reduced, and full-color and neutral display can also be achieved, thus avoiding color distortion of a displayed image, such that the displayed image is more natural and beautiful, thereby improving the visual comfort of human eyes observing the displayed image.

The invention discloses a lightweight RAW-to-sRGB image mapping method and system based on single-phase opto-color, and relates to the technical field of computer vision and image processing, and the method comprises the steps: taking RAW image data as input, carrying out preprocessing to suppress noise, generating clean RAW data, and enabling four channels of the RAW image data to correspond to denoised Bayer data; extracting edge features and illumination features from the clean RAW data through an IEEM module, and outputting an illumination attention map from the illumination features; processing the image data into opposite colors, extracting multi-feeling features of opposite color channels, and calculating to obtain single-phase opposite color features; edge constraint is carried out on the single-phase color features by using the edge features to obtain color features after attention constraint and residual fusion; on the basis of color features, an illumination attention map is introduced for pixel-by-pixel weighting, and brightness adaptive adjustment is carried out; and finally generating a feature map. The feature map is processed through a plurality of convolution layers and an up-sampling layer, and the feature map is converted into a final sRGB image.

A binary logic circuit for performing an interpolation calculation between two endpoint values E0 and E1 using a weighting index i for generating an interpolated result P, the values E0 and E1 being formed from Adaptive Scalable Texture Compression (ASTC) low-dynamic range (LDR) colour endpoint values C0 and C1 respectively, the circuit comprising: an interpolation unit configured to perform an interpolation between the colour endpoint values C0 and C1 using the weighting index i to generate a first intermediate interpolated result C2; and combinational logic circuitry configured to receive the interpolated result C2 and to perform one or more logical processing operations to calculate the interpolated result P according to the equation P=└((C2<<8)+C2+32) / 64┘ when the interpolated result is not to be compatible with an sRGB colour space, and according to the equation P=└((C2<<8)+128·64+32) / 64┘ when the interpolated result is to be compatible with an sRGB colour space.

The present invention relates to a neural network-based dual-domain joint image denoising method. The method comprises a training phase, in which a given simulated noise model is used to generate a set of purely simulated images to train a dual-domain image denoising network; and an inference phase, in which the trained dual-domain image denoising network is directly applied to the denoising locations in the raw and sRGB domains of any camera's image processing to perform image denoising. Compared with existing technologies, this method offers advantages such as significantly improved denoising performance and generalization capabilities.

The application discloses a method for improving color accuracy of a liquid crystal display, which is characterized in that a backlight device of the display is matched, a body color temperature and a luminance characteristic value are designed, a preheating time of the display is set, after the display is started and waits for the preheating time, maximum luminance cycle detection of the whole machine, body color coordinate cycle detection of the whole machine, automatic algorithm debugging of a Gamma multi-stage wide coefficient range, accurate color temperature debugging, sRGB and DCI-P3 color space matrix conversion are carried out in a darkroom environment, then a plurality of color pictures are outputted for color accuracy test, an average color accuracy value is calculated, parameters corresponding to color accuracy values meeting preset requirements are written into the display, and the parameters are called by different color space image modes. The application quantitatively designs liquid crystal backlight luminance, color temperature and other characteristics, then accurately calculates and debugs the display online, corrects color temperature, color gamut overlap, white balance, Gamma and other parameters affecting the color accuracy value, carries out real-time color space conversion according to the measured characteristics of the display screen, adjusts color data and luminance data of each display in real time, so that the color restoration of the liquid crystal display is improved, the color accuracy value of each display is reduced, and the color accuracy is improved.

The present invention provides an underwater image color restoration method. In the method, 8-bit RGB pixel values of pixels in an underwater image are converted to a linear sRGB space for adjustment processing, adjusted pixel values are converted to 8-bit RGB pixel values, and then the acquired 8-bit RGB pixel values are fused with the adjusted pixel values to obtain a restored underwater image. Therefore, a foreground object in the underwater image or an underwater video processed using the solution of the present invention is natural and rich in color; in addition, the natural blue and green colors of background seawater are preserved, and the viewing effect of an entire picture is improved significantly and is comparable to or even better than the effect that can be achieved in the past after considerable manual toning.

The embodiment of the invention provides an image generation method and device, electronic equipment and a storage medium, and relates to the technical field of image denoising. The method comprises the following steps: acquiring a to-be-processed image in an original RAW format; based on an interpolation algorithm, converting the to-be-processed image into a standard red-green-blue sRGB format to obtain a to-be-blurred image; for each color channel of the to-be-blurred image, performing Gaussian convolution blurring on the pixel value of each pixel position in the to-be-blurred image under the color channel to obtain a blurred pixel value of each pixel position for the color channel; for each pixel position, acquiring a fuzzy pixel value of the pixel position for the corresponding to-be-utilized color channel to obtain a fuzzy RAW image; the to-be-utilized color channel corresponding to one pixel position is a color channel at the pixel position in the to-be-processed image; and adding noise into the fuzzy RAW image to obtain a noise RAW image. The noise distribution in the noise RAW image is closer to the real noise distribution.

The invention discloses an sRGB-to-RAW video reconstruction method and system based on compressed key frame guidance, and relates to the technical field of video reconstruction. The method comprises the following steps: designing a key frame selection strategy based on a real-world RAW-sRGB pairwise data set, and dynamically selecting a proper key frame; designing an RAW compression reconstruction module, a time domain alignment module, a space-frequency combined mask module and an sRGB guided refined recovery module, and constructing an sRGB-to-RAW video reconstruction model based on compressed key frame guidance; designing a loss function, training an sRGB-to-RAW video reconstruction model by using a deep learning Pytorch framework, and repeatedly traversing a data set until the model is converged; and inputting the RAW key frame and the sRGB video sequence into the trained sRGB-to-RAW video reconstruction model to obtain a reconstructed RAW video sequence. According to the method disclosed by the invention, the high-quality RAW video is reconstructed under the condition that the storage is limited so as to be used for subsequent video editing or visual tasks.

The application discloses a color difference adjustment method and a liquid crystal display screen. The color difference adjustment method calls a first color calibration matrix in a display mode through an sRGB color space, calls a second color calibration matrix in the display mode through a DCI-P3 color space, and configures the third color calibration matrix in other modes through the DCI-P3 color space according to color coordinate differences, so that the color shown by the DCI-P3 color space in the other modes is closer to the color shown by the sRGB color space in the display mode, thereby reducing the color difference between the DCI-P3 color space and the sRGB color space in different modes, and further improving the display color difference between different color gamuts.

The invention relates to the technical field of image processing, and provides a super-resolution and low-illumination enhancement combined processing method based on RAW and sRGB images. The method comprises the following steps: performing degradation processing on a high-quality RAW image to obtain a low-quality RAW image and a low-quality sRGB image; performing maximum entropy down-sampling processing on the high-quality RAW image to generate a full-sampled linear RAW image, and generating a high-quality sRGB image through ISP pipeline rendering; constructing a super-resolution and low-illumination enhancement combined processing network; and training the super-resolution and low-illumination enhancement combined processing network by using the low-quality RAW image, the low-quality sRGB image and the high-quality sRGB image. According to the method, the problems that a training data set of image super-resolution and illumination enhancement combined processing is missing and a reference image is not matched with a low-illumination and low-resolution input image are solved, and the limitation of a traditional processing method when a single sRGB image or a RAW image is used for processing can be overcome, so that higher image quality can be obtained.

The application discloses a composite film structure capable of realizing color inkless printing by using ultrafast laser, and a printing method and equipment.The dielectric surface of a metal / dielectric composite film is irradiated by focused ultrafast laser pulses, so that an oxidation reaction is induced on the dielectric film surface to form a transparent oxide film, and finally a three-layer composite film of metal / dielectric / oxide is formed from bottom to top.The thickness of the oxide film at the corresponding position is controlled by changing the total energy density of irradiation, so as to change the color of the composite film surface at the corresponding position.The method for realizing color inkless printing by using ultrafast laser has a resolution of 20000 dpi.The composite film structure can form double-resonance absorption in the visible light band, so that the color gamut formed can cover more than 85% sRGB.The printing method does not involve any organic matter and toxic substances, and is environment-friendly.

Provided in the present application are a color gamut conversion method, an apparatus, a computer device, a computer storage medium and a computer program product. The method comprises: acquiring pixel information and color gamut information of a target image; determining whether the color gamut information meets a condition of the valid color gamut of a display device; if not, on the basis of the pixel information, obtaining chromaticity information corresponding thereto, the chromaticity information comprising chromaticity coordinates and a pixel luminance value; on the basis of a color gamut conversion algorithm and on the basis of the chromaticity information and the valid color gamut, determining target chromaticity information; and sending the target chromaticity information to the display device for display. When the color gamut of a lamp cannot completely present all of colors in the sRGB color gamut, the present application can convert a partial pattern exceeding the sRGB color gamut of a picture into the color gamut of the lamp, thereby ensuring the continuity of overall pattern colors presented by the lamp, and effectively reducing color distortion.

This invention discloses an image detail restoration method based on an attention mechanism in a vehicle-mounted night vision system, comprising: acquiring an image tensor of a low-light night vision image; inputting the image tensor into a pre-trained image generation model and performing feature mapping on it; generating a detail-restored image at the output layer according to the mapping parameters of the feature mapping; wherein, the mapping parameters of the feature mapping represent the color matrix and gamma value of the sRGB standard image learned by the image generation model in pre-training; this invention overcomes the shortcomings of existing image enhancement methods by combining local features extracted by convolutional layers with global dependency features captured by self-attention layers; when processing low-light images, convolutional layers focus on detail restoration, while self-attention layers can capture the relationship between distant pixels in the image, thereby effectively restoring global information, so that the restored image is enhanced in both detail and global structure.

A backlit display for emitting a display light, said display comprising a backlight configured to emit a high circadian stimulation backlight spectrum having a spectral power distribution (SPD) with an overall power, and a blue range from 440-490 nm with a blue SPD power of at least 25% of said overall power, a pixel array comprising at least three filters, said at least three filter comprising at least a first filter, a second filter, and third filter, forming at least three sub-pixels, wherein said backlight is configured to backlight said pixel array, and wherein said display light has a gamut having an sRGB coverage of at least 85%.

The application discloses a camera imaging optimization method and system based on a complex light environment, wherein an sRGB image with low brightness or overexposure is input into a U-Net neural network for inference calculation to obtain a linear Raw-RGB image before camera image signal processing; the Raw-RGB image is input into another U-Net neural network to obtain a pixel-by-pixel adjustment map, and the ambient light intensity is adjusted and corrected; subsequently, the Raw-RGB image after adjustment is subjected to inference of image signal processing parameters, including a white balance parameter, a color space conversion matrix and a gamma correction parameter, by using a neural network composed of a self-attention mechanism coding module; and finally, the Raw-RGB image is restored to an sRGB image with adjusted brightness through a simulated image signal processing process. The application avoids directly processing the nonlinear sRGB image output by the camera, adjusts the light intensity of the linear Raw-RGB image obtained through conversion, and finally restores the nonlinear sRGB image, thereby having good ability to restore low-brightness and overexposed images.

The invention discloses a video denoising algorithm and device based on a dense attention denoising network. According to the method, a four-channel Bayer format RAW noise video is obtained, a sliding window forms a three-frame image group after frame extraction, the three-frame image group is input into an encoder-decoder network containing a triple attention module for denoising, and an sRGB video is generated through image signal processing. The method has the advantages of network lightweight design, low parameter quantity, denoising precision and real-time performance, solves the problems of sRGB domain processing defects and difficult deployment of a traditional model, and is suitable for an embedded platform.

The invention is suitable for the technical field of computer vision, and provides an image restoration method and system based on the sRGB standard and a storage medium, and the method comprises the steps: collecting a target image of a target region through a camera, and analyzing a gray histogram of the target image, obtaining a linear color space value and a nonlinear image digital signal, and carrying out decoding transformation according to a preset rule; wherein the preset rule is # imgabs0 #; g'is a gray value of gamma coding; g is a linear gray value; o is a deviation value; m is the maximum gray value of the byte picture; t is a light and dark area segmentation threshold value in the transformed image; s is a smoothing factor, and the value range of # imgabs 1 # is 0.1-1; through the steps of the invention, the image can be restored by selecting a proper G value, o, t and m value, and a clear pattern can be restored after the image with small background difference and less light is processed.

The application discloses a lamp bead light-emitting calibration method and device, computer equipment and a storage medium, and the method comprises the following steps: acquiring a measured lamp bead, a first color coordinate and a maximum luminous flux of the measured lamp bead; acquiring an RGB color value of the measured lamp bead in an SRGB color gamut; linearly correcting the RGB color value and converting the linearly corrected RGB color value to an XYZ colorimetric coordinate; converting the RGB color value of the XYZ colorimetric coordinate to a Yxy coordinate system to obtain a second color coordinate corresponding to the RGB color value; acquiring a duty cycle of the measured lamp bead in combination with the first color coordinate, the second color coordinate and the maximum luminous flux, and setting a pulse width modulation value of the measured lamp bead based on the duty cycle, and then calibrating the light emission of the measured lamp bead by using the pulse width modulation value. The application can realize real-time sensing and adjustment of the brightness, color temperature and spectral distribution of the unmanned aerial vehicle light, and improve the visual effect and viewing experience of the unmanned aerial vehicle light show.

The application discloses a low-illumination image enhancement modeling method and device, an enhancement method and a storage medium, and relates to the field of image enhancement. The method comprises training a low-illumination image enhancement model by using training images, and the training process comprises the following steps: inputting the training images into a color gamut conversion module to obtain a linear rawRGB image and a reconstructed sRGB image; inputting the linear rawRGB image into a down-sampling module to obtain a first sub-image and a second sub-image; performing enhancement processing on the second sub-image; extracting a frequency domain brightness guide signal of the first sub-image and the enhanced second sub-image to generate a guide signal; based on the guide signal, using an illumination enhancement decoupling network to estimate a reflectivity component, an illumination component and a brightness enhancement parameter in parallel; and calculating a multi-task loss function based on a model output result and updating model parameters. The application solves the dependence on paired training data which is difficult to obtain, and maintains excellent brightness improvement and detail restoration effects.