135 results about "Low dynamic range" patented technology

The invention relates to the technical field of image shooting and processing, and discloses an anti-overexposure image processing method and system under strong light based on a high dynamic range, and the method comprises the steps: collecting a plurality of frames with different exposures for the same scene through an extremely weak light full-color night vision device, carrying out the multi-frame fusion, and generating a high dynamic range image; the method comprises the following steps: mapping an image with a high dynamic range to display equipment with a low dynamic range, and readjusting the brightness and contrast of the image to realize tone mapping; different areas in the image are independently processed, an overexposure area is identified, the brightness of the overexposure area is independently reduced, and the original brightness and contrast of other areas are kept; histogram equalization parameters are dynamically adjusted according to the local brightness distribution of the image, the image contrast and details are improved, and image color correction is achieved. The problem of overexposure of the ultra-weak light full-color night vision device in a strong light environment is solved through a high dynamic range algorithm, and the image quality of the night vision device under different illumination conditions is remarkably improved.

Implementations relate to providing an HDR image format with low dynamic range compatibility. In some implementations, a computer-implemented method includes obtaining a first image depicting a scene and having a first dynamic range, obtaining a second image depicting the scene and having a second dynamic range that is different than the first dynamic range, and generating a recovery map based on the first and second images. The recovery map encodes differences in luminances between corresponding portions of the first and second images, the differences scaled by a range scaling factor including a ratio of maximum luminances of the second image and the first image. The first image and recovery map are provided in an image container that is readable to display a derived image that is based on applying the recovery map to the first image and has a dynamic range that is different than the first dynamic range.

A method includes obtaining a high dynamic range (HDR) image and generating low dynamic range (LDR) images based on the HDR image, where at least some of the LDR images are associated with different exposure levels. The method also includes generating tone-type weight maps based on the LDR images, where at least one of the LDR images is associated with two or more of the tone-type weight maps. The method further includes generating blending weights for the LDR images based on the tone-type weight maps, where the blending weights for at least one of the LDR images are based on at least two tone-type weight maps associated with at least two of the LDR images.

Embodiments relate to providing an HDR video format with low dynamic range compatibility. In some embodiments, a method includes acquiring a first video including first frames having a first dynamic range and a second video including corresponding second frames having a second dynamic range different from the first dynamic range. A recovery map track is generated including a recovery map frame for each first frame and each corresponding second frame, where the recovery map frame encodes a luminance difference between a portion of the first frame and a portion of the corresponding second frame. The first video and the recovery map track are provided in a video container that is readable to display the first video or to display a derived video based on applying the recovery map track to the first video. The derived video includes derived frames having a dynamic range different from the first dynamic range.

The invention discloses a carrier tracking method suitable for a multi-bit spread spectrum signal, and relates to the technical field of multi-bit spread spectrum, the carrier tracking method comprises the steps of coarse frequency offset correction, multi-bit spread spectrum, average phase estimation and delay phase correction.The carrier tracking method comprises the steps that firstly, a sliding DFT algorithm is adopted to estimate frequency offset, and a coarse frequency offset available correction signal is obtained; secondly, adaptively selecting the number of available windows according to historical data corresponding to the current signal-to-noise ratio; the method comprises the following steps: firstly obtaining a window intermediate point spread spectrum period, then extracting a carrier phase estimation value of the window intermediate point spread spectrum period, finally delaying a correlation value by the spread spectrum period to realize time sequence alignment and eliminate phase deviation, and finally obtaining information bits corresponding to each spread spectrum period by extracting and correcting a real part of the correlation value, matching a local sequence number and mapping. According to the method, the phase estimation precision under the low signal-to-noise ratio can be improved, parameter self-adaption to high and low dynamic scenes of a satellite is realized, the coherent judgment performance is improved, and the hardware complexity is reduced.

The invention discloses a high dynamic range imaging method for an ultrahigh-definition video, and the method comprises the following steps: collecting a low dynamic range frame of the ultrahigh-definition video, splicing images through exposure normalization and adaptive correction, and constructing multi-scale multi-channel data; extracting structure and texture features by using an improved multi-scale convolution and attention network, and calculating matching degree rearrangement support frame features; detecting a missing region in the image, and performing local recovery and sharpening on the missing region by using improved gating convolution in combination with residual errors and high-frequency enhancement branches; dynamically calculating a fusion weight, carrying out weighted fusion on the features, and outputting a final fusion feature; and inputting the fusion features into a global merging network for HDR reconstruction, and splicing the fusion features into a video sequence for coding and outputting by adopting adaptive mapping and time domain processing. The method has high robustness and noise immunity, video frames in a complex illumination environment can be effectively processed, HDR images with rich details and accurate colors are generated, and the visual effect of the video is remarkably improved.

The invention relates to an event camera assistance-based extremely high dynamic range imaging method, device and equipment and a medium, and the method comprises the following steps: collecting an image by using a dual-camera imaging system based on an event camera and an RGB camera, collecting a high dynamic range event signal by the event camera, and transmitting the high dynamic range event signal to the RGB camera; the RGB camera collects low-dynamic-range RGB images of different exposure times; inputting the event signal and the RGB image into an event camera-assisted alignment module, and assisting alignment of the RGB images with different exposure times by using the event signal; and inputting the aligned RGB images with different exposure times into a fusion module based on a diffusion model for fusion to obtain a high-dynamic image generation result. Compared with the prior art, the method has the advantages that imaging in an extremely high dynamic range can be realized, and the method is suitable for large-motion and large-exposure scenes.

Disclosed is a method for enabling exposure-guided three-dimensional (3D) reconstruction, including (i) receiving Low Dynamic Range (LDR) input image captured by camera; (ii) rendering High Dynamic Range (HDR) image corresponding to input image, using HDR 3D reconstruction model pre-trained for HDR image reconstruction of 3D environment; (iii) applying HDR to LDR tone-mapping operator on HDR image, for producing tone-mapped LDR image; (iv) determining first loss function (FLF) between input image and tone-mapped LDR image, FLF comprising weighted pixel value differences between pixels of input image and corresponding pixels of tone-mapped LDR image; (v) determining whether input image has saturated pixel(s), saturated pixel(s) comprises: highlight saturated pixel, shadow saturated pixel; (vi) de-weighting pixel value difference corresponding to saturated pixel in FLF; (vii) back-propagating gradient of FLF with respect to model parameters, through differentiable render function of HDR 3D reconstruction model, for adjusting model parameters in way that reduces FLF.

The invention belongs to the related technical field of image processing, and discloses an illumination estimation method and system based on image semantic driving and a system training method.The method comprises the steps that an original small-view-angle image in a target environment is preprocessed to obtain a low-dynamic-range illumination image, then multi-level feature extraction is conducted on the low-dynamic-range illumination image, and the low-dynamic-range illumination image is obtained; the method comprises the following steps of: obtaining a shallow-layer feature map, a middle-layer feature map and a deep-layer feature map, performing feature enhancement processing on the middle-layer feature map, performing weighting processing on the shallow-layer feature map and the deep-layer feature map based on an attention mechanism, fusing the feature maps of the three levels, and performing linear regression operation to obtain a prediction result of illumination parameters. On the basis of the process, the light source false detection rate can be greatly reduced, the cross-scene generalization ability of the model can be improved, explicit enhancement of a real light source and effective suppression of an error light source are achieved, the prediction result is more accurate, and on the basis of the design, the accuracy of illumination estimation can be improved under limited training samples.

Implementations relate to providing HDR video formats with low dynamic range compatibility. In some implementations, a method includes obtaining a first video including first frames having a first dynamic range and a second video including corresponding second frames having a second dynamic range that is different than the first dynamic range. A recovery map track is generated, including a recovery map frame for each first frame and corresponding second frame, the recovery map frame encoding differences in luminances between portions of the first frame and corresponding second frame. The first video and recovery map track are provided in a video container that is readable to display the first video or to display a derived video based on applying the recovery map track to the first video. The derived video includes derived frames that have a dynamic range different than the first dynamic range.

In some examples, the method for tone mapping a high dynamic range (HDR) image to a lower dynamic range image (TDR) comprises obtaining a luminous intensity image based on the HDR image, processing the luminous intensity image using a feature extractor network, whereby to generate a feature map, processing the feature map using at least one neural network module of multiple neural network modules, obtaining a tone mapping operator based on an output of the at least one neural network module of the multiple neural network modules, and applying the tone mapping operator to the HDR image, whereby to obtain the TDR image, wherein the tone mapping operator comprises a tone mapping curve.

The application relates to a high-dynamic-range seismic imaging profile gain method, device, medium and equipment, wherein the method comprises the following steps: normalizing an original seismic profile according to seismic profile data to form a normalized profile and control the fluctuation range of the data; performing nonlinear color scale mapping on the normalized profile to map high-dynamic-range seismic profile data to a low-dynamic-range; calculating the resolution of the seismic profile data mapped to the low-dynamic-range at different scales to obtain the reference brightness of each point; and performing light-shading-light-increasing mapping on the basis of the reference brightness of each point to increase local details and obtain a final display profile. The application can significantly enhance weak signals while retaining the relative size relationship between signals and the detail information of different scales, and realizes adaptive gain of a high-dynamic-range seismic profile.

An image processing apparatus comprises a receiver (201) for receiving an image signal which comprises at least an encoded image and a target display reference. The target display reference is indicative of a dynamic range of a target display for which the encoded image is encoded. A dynamic range processor (203) generates an output image by applying a dynamic range transform to the encoded image in response to the target display reference. An output (205) then outputs an output image signal comprising the output image, e.g. to a suitable display. The dynamic range transform may furthermore be performed in response to a display dynamic range indication received from a display. The invention may be used to generate an improved High Dynamic Range (HIDR) image from e.g. a Low Dynamic Range (LDR) image, or vice versa.

The invention discloses a cigarette box strip two-dimensional code rendering model construction method for code reading camera response function estimation, and the method comprises the steps: constructing an end-to-end neural network rendering algorithm through employing a cigarette box strip two-dimensional code image sample, recovering a radiation field with a high dynamic range from low-illumination images with different exposures, and estimating a response function of a camera; comprising the following steps: designing a neural radiation field module, and constructing two continuous implicit neural network functions which are respectively used for modeling the density and scene radiance of a radiation field so as to more accurately estimate a camera response function and reflect the real physical characteristics of a camera; a tone mapping module is designed, a high-dynamic-range image is converted into a low-dynamic-range image, the density of a radiation field and scene radiance are combined with tone mapping of image color brightness, comprehensive modeling of the physical imaging process of the camera is achieved, and the generated image is more authentic. The method can adapt to changes of different scenes and lighting conditions, and the practical effect in a specific scene is enhanced.

Global index values for selecting global reshaping functions for an input image are generated using luminance codewords in the input image that have a relatively low dynamic range. Image filtering is applied to the input image to generate a filtered image. Filtered values of the filtered image provide a measure of local brightness levels in the input image. Local index values for selecting particular local reshaping functions for the input image are generated using the global index values and the filtered values of the filtered image. A reshaped image of a relatively high dynamic range is generated by reshaping the input image with the particular local reshaping functions selected using the local index values.

The invention discloses an image reconstruction method and device and electronic equipment, and belongs to the technical field of image processing. The method comprises the steps that an image frame sequence is acquired, and the image frame sequence comprises a first short-exposure low dynamic range (LDR) image, a long-exposure LDR image and a second short-exposure LDR image which are arranged in sequence; determining a bidirectional optical flow between the first short exposure LDR image and the second short exposure LDR image; determining an initialized optical flow corresponding to a first prediction frame insertion image between the first short exposure LDR image and the second short exposure LDR image based on the bidirectional optical flow; refining the initialized optical flow by taking the long-exposure LDR image as a motion alignment target to obtain a target optical flow; determining a frame insertion image based on the target optical flow, the first short exposure LDR image and the second short exposure LDR image; and performing high dynamic range (HDR) image reconstruction based on the long exposure LDR image and the frame insertion image to obtain an HDR image.

A method for training an image processing model includes: inputting a low dynamic range image into a first initial image processing model, so that a high dynamic range reconstruction processing is performed on the low dynamic range image to generate a first high dynamic range image; inputting the low dynamic range image into a second initial image processing model to generate a first coefficient; generating a second high dynamic range image according to the first high dynamic range image and the first coefficient; generating a loss function according to data pairs of the second high dynamic range image and a real high dynamic range image, the real high dynamic range image corresponding to the low dynamic range image; and training the first initial image processing model and the second initial image processing model with the loss function.

The application provides an image processing method and device, a computer readable storage medium and an electronic device, relates to the technical field of image processing, and can cut a first image corresponding to a first color depth into a second image corresponding to a second color depth, and normalize the second image into a sample image of the first color depth to simulate a low dynamic range image. Application of such a sample image in model training can facilitate the model to learn the problem of the low dynamic range image, thereby avoiding the model from generating an image with a highlight edge smear problem.

The invention provides an image processing method, a vehicle, electronic equipment and a storage medium. The image processing method comprises the steps that a high-dynamic-range image collected by a camera is acquired, and the high-dynamic-range image is formed by synthesizing a plurality of low-dynamic-range images through the camera; parameters associated with a target low dynamic range image are obtained, and the target low dynamic range image is one of the multiple low dynamic range images; based on the parameter, the target low dynamic range image is restored from the high dynamic range image.

The present invention relates to the field of dynamic vision sensors, and relates in particular to a photosensitive element array for detecting time-related image data. The photosensitive element array is composed of R rows × C columns of units. Each unit comprises: a light sensor having a dynamic range compression characteristic, the light sensor autonomously converting, without any external control, a high-dynamic-range incident light signal into a low-dynamic-range output voltage signal; a plurality of voltage sampling storage units, the stored voltages being obtained by sampling the output voltage signal of the light sensor at different time points; and a voltage readout circuit, configured to read out, simultaneously or in a time-division manner, the voltages in the voltage sampling storage units to the periphery of the photosensitive element array. The present invention further relates to a peripheral readout circuit for the photosensitive element array. The peripheral readout circuit comprises a row scanning and timing control module, C amplifiers, and C analog-to-digital converters capable of sensing field-of-view activity, wherein each analog-to-digital converter adjusts the number of effective conversion cycles in each conversion on the basis of the amplitude of a visual signal sensed by units in a column corresponding to the analog-to-digital converter.

Enhanced eye-tracking techniques for augmented or virtual reality display systems. An example method includes obtaining an image of an eye of a user of a wearable system, the image depicting glints on the eye caused by respective light emitters, wherein the image is a low dynamic range (LDR) image; generating a high dynamic range (HDR) image via computation of a forward pass of a machine learning model using the image; determining location information associated with the glints as depicted in the HDR image, wherein the location information is usable to inform an eye pose of the eye.

The invention relates to a phase adjusting circuit and method and a distance measuring device. The phase adjustment circuit comprises: at least one adjustment unit configured to adjust an input signal according to an initial gain coefficient to generate an adjustment signal; and changing a gain coefficient for adjusting the input signal in response to a gate control signal; wherein when the adjusting unit has different gain coefficients, the cut-off frequencies corresponding to the gain coefficients are the same; and the control unit is coupled with the adjusting unit and is configured to generate the gating control signal to the adjusting unit according to the adjusting signal and a preset signal. By adopting the scheme, the phase delay in the dynamic range can be reduced, and the distance measurement precision is improved.

The invention discloses a video frame insertion method based on event information, and the method comprises the steps: carrying out the linearization of an original color image in a low dynamic range, and mapping the linearized image to a logarithm domain; carrying out eigendecomposition on the linearized image, and obtaining a corresponding reflection image and an intensity image in a logarithm domain; updating the original intensity graph through the event information to obtain a logarithmic intensity graph of the target frame; synthesizing a logarithmic reflection image of the target frame through the new intensity image and the original reflection image; and finally, recovering the reflection image and the intensity image of the logarithm domain into a linear image. According to the method, the original video frame rate can be increased by any multiple times as required, a high-dynamic-range result is obtained, and the overall image effect is improved. Meanwhile, the problem of dependence on the quality and scale of training data in a traditional frame interpolation algorithm is solved, and the influence of space consistency in color images and event information and the shooting frame rate of the training data on a frame interpolation result is reduced.

The model training method, the illumination determination method, the device and the program product provided by the present disclosure relate to the technical field of image processing, and include the following steps: acquiring low dynamic range images of a preset environment acquired based on different exposure values and actual illumination values of the preset environment when the low dynamic range images are acquired; and training a preset model according to each low dynamic range image and the actual illumination value corresponding to the low dynamic range image to obtain an illumination prediction model. In the model training method, the illumination determination method, the device and the program product provided by the present disclosure, a predicted illumination value can be obtained according to the acquired low dynamic range image in a store, data does not need to be collected by a dedicated person, and the brightness of a lighting lamp in the store can be adjusted in real time according to the predicted illumination value.

The invention discloses a simulation-based high dynamic range image synthesis method, which comprises the following steps of: generating low dynamic range images with different exposure degrees based on a CARLA simulator, and synthesizing a plurality of low dynamic range images into a high dynamic range image by using a multi-exposure fusion algorithm, thereby constructing a large-scale automatic driving high dynamic range simulation data set. According to the invention, through a multi-exposure fusion algorithm, low-dynamic-range images of multiple exposures are concisely and efficiently fused, a high-quality high-dynamic-range image which retains details of a dark part and a bright part at the same time is obtained, and the synthesis speed is relatively high. The method supports the synthesis of a large-scale automatic driving high-dynamic range policy data set, and is used for the research of related tasks.

A high dynamic range (HDR) depth buffer is received at a remote computer. The HDR depth buffer is formed into a plurality of tiles. For each tile, a respective maximum and minimum value of the HDR depth buffer in a region greater than a width of the respective tile is determined. An initial pair of piecewise bilinear bounding functions for the HDR depth buffer is determined using the determined maximum and minimum depth values. For each tile, the initial pair of piecewise bilinear bounding functions is iteratively adjusted to move the respective minimum and maximum depth value of each tile closer to the HDR depth buffer, wherein no adjacent tile is adjusted in the same iteration. Using the adjusted pair of piecewise bilinear bounding functions, a low dynamic range (LDR) depth buffer and tile data are generated and encoded using a video encoder and a lossless compressor respectively.

The invention discloses an array and difference beam co-excitation optimization method and system based on unit dynamic range ratio constraint and a storage medium, and mainly solves the problem that an array and difference beam directional diagram cannot be optimized in a complex application scene and the dynamic range ratio cannot be reduced at the same time in the prior art. The implementation scheme comprises the following steps: determining an antenna optimization index; optimizing the planar array antenna and the difference beam directional diagram by adopting a convex optimization algorithm, and solving the planar array antenna and the difference beam directional diagram to obtain an initial sum beam complex excitation coefficient meeting a constraint condition; adding a unit dynamic range ratio constraint in a planar array antenna and difference beam directional diagram optimization problem, and converting the directional diagram optimization problem after adding the unit dynamic range ratio constraint into a series of convex optimization sub-problems; iteratively solving the convex optimization sub-problem by using a solver to obtain an optimal sum beam excitation coefficient; and synthesizing a sum and difference beam directional diagram of the array according to the optimal sum beam excitation coefficient. According to the invention, the sum-difference beam synthesis with a small dynamic range ratio can be effectively realized while the radiation performance constraint is satisfied, and the method can be used for a monopulse radar system with a cover.

The invention provides a method for capturing an image in video recording, electronic equipment and a readable medium. The method comprises the steps that a video interface of a camera application is displayed, the dynamic range of an image displayed by the video interface is larger than a first value, the first value indicates that the image displayed by the video interface is a non-low-dynamic-range image, and the image displayed by the video interface is stored in a cache region; and in response to a snapshot instruction in the video, taking an image corresponding to the snapshot moment in the cache region as a snapshot image. The cache region stores the image displayed by the video recording interface, that is, the image collected by the camera is stored in the cache region, the image is greater than the first value, and the first value indicates that the image is a non-low dynamic range image, which indicates that the camera outputs a high dynamic range image, and the video recording interface belongs to an HDR video recording interface. Under the condition that the snapshot instruction is formed in the video, the image corresponding to the snapshot moment in the cache region is taken as the snapshot image, and the snapshot moment is the moment corresponding to the snapshot instruction, so that the ZSL requirement of image snapshot is ensured.

Generating a High Dynamic Range (HDR) panoramic image, comprising: accessing a field of view (FoV) image 302 that has a field of view less than 360 degrees and has Low Dynamic Range (LDR) values; gene

An ultrasonic image dynamic range compression processing method relates to the technical field of image processing, and comprises the following steps: acquiring high dynamic range original A-Scan data, and converting the data into two-dimensional matrix data; preprocessing the two-dimensional matrix data to obtain standard input data; performing nonlinear brightness adjustment on the standard input data by adopting a Gamma correction algorithm, preliminarily compressing the dynamic range of the image, and generating a compressed image after global brightness adjustment; based on a Retinex algorithm, decomposing the compressed image after global brightness adjustment, introducing a contrast enhancement factor and an adaptive nonlinear offset factor, and calculating an enhanced compressed image in a low dynamic range; the method can maintain the definition of the processed image.