131 results about "High-dynamic-range video" patented technology

A system and process for generating High Dynamic Range (HDR) video is presented which involves first capturing a video image sequence while varying the exposure so as to alternate between frames having a shorter and longer exposure. The exposure for each frame is set prior to it being captured as a function of the pixel brightness distribution in preceding frames. Next, for each frame of the video, the corresponding pixels between the frame under consideration and both preceding and subsequent frames are identified. For each corresponding pixel set, at least one pixel is identified as representing a trustworthy pixel. The pixel color information associated with the trustworthy pixels is then employed to compute a radiance value for each pixel set to form a radiance map. A tone mapping procedure can then be performed to convert the radiance map into an 8-bit representation of the HDR frame.

A data structure defining a high dynamic range image comprises a tone map having a reduced dynamic range and HDR information. The high dynamic range image can be reconstructed from the tone map and the HDR information. The data structure can be backwards compatible with legacy hardware or software viewers. The data structure may comprise a JFIF file having the tone map encoded as a JPEG image with the HDR information in an application extension or comment field of the JFIF file, or a MPEG file having the tone map encoded as a MPEG image with the HDR information in a video or audio channel of the MPEG file. Apparatus and methods for encoding or decoding the data structure may apply pre- or post correction to compensate for lossy encoding of the high dynamic range information.

Techniques are provided to encode and decode image data comprising a tone mapped (TM) image with HDR reconstruction data in the form of luminance ratios and color residual values. In an example embodiment, luminance ratio values and residual values in color channels of a color space are generated on an individual pixel basis based on a high dynamic range (HDR) image and a derivative tone-mapped (TM) image that comprises one or more color alterations that would not be recoverable from the TM image with a luminance ratio image. The TM image with HDR reconstruction data derived from the luminance ratio values and the color-channel residual values may be outputted in an image file to a downstream device, for example, for decoding, rendering, and / or storing. The image file may be decoded to generate a restored HDR image free of the color alterations.

A device for processing video information has an input unit (112) for receiving the video information having low dynamic range [LDR] video data and / or high dynamic range [HDR] video data, and a video processor (113) for generating a display signal for display in a LDR display mode or HDR display mode. Graphics data is processed for generating an overlay for overlaying the video data. The input unit receives graphics processing control data comprised in the video information, the graphics processing control data including at least one HDR processing instruction for overlaying the graphics data in the HDR display mode. The video processor is constituted for adapting the processing when overlaying the graphics data in dependence on the specific display mode and the HDR processing instruction. Advantageously the source of the video information is enabled to control the processing of graphics in HDR display mode via the HDR processing instruction.

A data structure defining a high dynamic range image comprises a tone map having a reduced dynamic range and HDR information. The high dynamic range image can be reconstructed from the tone map and the HDR information. The data structure can be backwards compatible with legacy hardware or software viewers. The data structure may comprise a JFIF file having the tone map encoded as a JPEG image with the HDR information in an application extension or comment field of the JFIF file, or a MPEG file having the tone map encoded as a MPEG image with the HDR information in a video or audio channel of the MPEG file. Apparatus and methods for encoding or decoding the data structure may apply pre- or post correction to compensate for lossy encoding of the high dynamic range information.

A method and apparatus for encoding high dynamic range video by means of video compression is shown. The method comprises the steps of providing high dynamic range (HDR) tristimulus color data (XYZ) for each frame of the video and threshold versus intensity data for a human observer; constructing a perceptually conservative luminance transformation from continuous luminance data (Y) to discrete values (Lp) using said threshold versus intensity data for the human observer; transforming the HDR tristimulus color data into perceptually linear color data of three color channels (Lp, u′, v′) for obtaining visually lossless compressed frames; estimating motion vector of said consecutive frames of the video and compensating the difference of the tristimulus color data for performing an inter-frame encoding and an inter-frame compression; transforming the compensated differences of the tristimulus color data to frequency space data; quantizing said frequency space data; variable-length encoding of the quantized frequency space data and storing or transmitting a stream of visual data resulting from the encoded quantized frequency space data;

A system and process for generating High Dynamic Range (HDR) video is presented which involves first capturing a video image sequence while varying the exposure so as to alternate between frames having a shorter and longer exposure. The exposure for each frame is set prior to it being captured as a function of the pixel brightness distribution in preceding frames. Next, for each frame of the video, the corresponding pixels between the frame under consideration and both preceding and subsequent frames are identified. For each corresponding pixel set, at least one pixel is identified as representing a trustworthy pixel. The pixel color information associated with the trustworthy pixels is then employed to compute a radiance value for each pixel set to form a radiance map. A tone mapping procedure can then be performed to convert the radiance map into an 8-bit representation of the HDR frame.

The present invention provides a welding protection helmet with video frequency augmented reality auxiliary operation. The helmet comprises the welding protection helmet, a binocular high dynamic range video camera, a helmet display, a video frequency input-output device, a potable computer, a protective glass, a fan, a mike, a microphone and a respiration device. With the present invention, welding is carried out by observing the video frequency of the helmet display, which avoids the harm caused by watching welding directly or indirectly. At the same time, in the present invention, the augmented reality technology is adopted, which can decrease the welder visual information insufficiency caused by various interferences produced by welding, and additional auxiliary information which is required for welding can also be added into welding at real time to guide welding. The present invention can be applied to the aspects of manual welding, mechanical welding with human participation, etc. and can also be applied to the mechanical processing and manufacturing aspects of cutting, polishing, etc.

An encoder includes a linear offset amplifier, a linear analog to digital converter coupled to the linear offset amplifier, a switched offset amplifier, a switched analog to digital converter coupled to the switched offset amplifier, and a video controller. The video controller is coupled to both the linear and switched analog to digital converters. The video controller is configured to set both gains and offsets of the linear and switched analog to digital converters so that the gain and offset of the linear analog to digital converter is different than the gain and offset of the switched analog to digital converter.

The invention relates to a high dynamic range video imaging system and an image generating method. The system comprises an optical lens, an image processing unit, at least an optical splitter and a plurality of sensitive chips. The optical splitter splits the incident light penetrating through the optical lens into a plurality of beams which enter the plurality of sensitive chips so as to obtain image data with different exposures. The image processing unit fuses the image data to generate high dynamic range images. Each sensitive chip used by the high dynamic range video imaging system fused by the plurality of sensitive chips has same specifications so that synchronization and instantaneity of photographing can be ensured. Meanwhile, the generated video image has obvious advantage in color and luminance uniformities and affluent visual information compared with single exposed image, can effectively solve the problems of underexposure, overexposure and color and luminance non-uniformities in traditional image pickup systems and has great market applicable foreground.

Various embodiments provide tone mapping of images and video from one dynamic range to an available dynamic range of a display device while preserving or enhancing image details. According to one embodiment, an enhanced tone mapping module is configured to decrease a luminance of an image or video from a high dynamic range to a standard dynamic range. Conversely, according to one embodiment, an enhanced inverse tone mapper to increase a luminance of an image or video from a standard dynamic range to a high dynamic range.

A method of producing a compressed video data stream (12) by compressing a stream of relatively high dynamic range video frames (2). A bilateral filter (3) extracts a base frame (4) with luminance information. The base frame (4) and the original frame (2) are used to provide a detail frame (5) with chroma information. A tone mapping operation (6) is selected (7, 11) and applied to the base frame to generate a relatively low dynamic range base frame (8), which is then compressed (9). The detail frame (5) is compressed separately. Final frame data (12) is then created, consisting of the compressed relatively low dynamic range base frame, the compressed detail frame, and stored information in respect of the tone mapping operation that had been applied to the base frame.

A method and apparatus for encoding high dynamic range video by means of video compression is shown. The method comprises the steps of providing high dynamic range (HDR) tristimulus color data (XYZ) for each frame of the video and threshold versus intensity data for a human observer; constructing a perceptually conservative luminance transformation from continuous luminance data (Y) to discrete values (Lp) using said threshold versus intensity data for the human observer; transforming the HDR tristimulus color data into perceptually linear color data of three color channels (Lp, u′, v′) for obtaining visually lossless compressed frames; estimating motion vector of said consecutive frames of the video and compensating the difference of the tristimulus color data for performing an inter-frame encoding and an inter-frame compression; transforming the compensated differences of the tristimulus color data to frequency space data; quantizing said frequency space data; variable-length encoding of the quantized frequency space data and storing or transmitting a stream of visual data resulting from the encoded quantized frequency space data.

A system and process for generating High Dynamic Range (HDR) video is presented which involves first capturing a video image sequence while varying the exposure so as to alternate between frames having a shorter and longer exposure. The exposure for each frame is set prior to it being captured as a function of the pixel brightness distribution in preceding frames. Next, for each frame of the video, the corresponding pixels between the frame under consideration and both preceding and subsequent frames are identified. For each corresponding pixel set, at least one pixel is identified as representing a trustworthy pixel. The pixel color information associated with the trustworthy pixels is then employed to compute a radiance value for each pixel set to form a radiance map. A tone mapping procedure can then be performed to convert the radiance map into an 8-bit representation of the HDR frame.

Techniques are provided to encode and decode image data comprising a tone mapped (TM) image with HDR reconstruction data in the form of luminance ratios and color residual values. In an example embodiment, luminance ratio values and residual values in color channels of a color space are generated on an individual pixel basis based on a high dynamic range (HDR) image and a derivative tone-mapped (TM) image that comprises one or more color alterations that would not be recoverable from the TM image with a luminance ratio image. The TM image with HDR reconstruction data derived from the luminance ratio values and the color-channel residual values may be outputted in an image file to a downstream device, for example, for decoding, rendering, and / or storing. The image file may be decoded to generate a restored HDR image free of the color alterations.

An approach is provided for generating a high dynamic range image from a low dynamic range image. The generation is performed using a mapping relating input data in the form of input sets of image spatial positions and a combination of color coordinates of low dynamic range pixel values associated with the image spatial positions to output data in the form of high dynamic range pixel values. The mapping is generated from a reference low dynamic range image and a corresponding reference high dynamic range image. Thus, a mapping from the low dynamic range image to a high dynamic range image is generated on the basis of corresponding reference images. The approach may be used for prediction of high dynamic range images from low dynamic range images in an encoder and decoder. A residual image may be generated and used to provide improved high dynamic range image quality.

The invention relates to an adaptive format conversion method based on high dynamic range video, comprising: acquiring parameters or user-defined parameters of a terminal display device through EDID (extended display identification data); setting a converter at the terminal display device to perform signal type conversion or video image processing on program signals, or setting an encoder at a server to re-encode the program signals so that the signals adapt to the terminal display device; receiving, by the terminal display device, a video file, or decoding, by the terminal display device, video bit streaming or the video file. The compatibility problem between HDR (high dynamic range) video and / or SDR (standard dynamic range) video program sources of different formats and different display devices is well solved, processing may be performed according to user-defined parameters, the program sources of different formats may also be adaptively displayed on different display devices in optimal state, steps for the display devices to set different parameters according to the different program sources are omitted, and operation is more facilitated for a user.

Techniques are provided to encode and decode image data comprising a tone mapped (TM) image with HDR reconstruction data in the form of luminance ratios and color residual values. In an example embodiment, luminance ratio values and residual values in color channels of a color space are generated on an individual pixel basis based on a high dynamic range (HDR) image and a derivative tone-mapped (TM) image that comprises one or more color alterations that would not be recoverable from the TM image with a luminance ratio image. The TM image with HDR reconstruction data derived from the luminance ratio values and the color-channel residual values may be outputted in an image file to a downstream device, for example, for decoding, rendering, and / or storing. The image file may be decoded to generate a restored HDR image free of the color alterations.

The invention discloses a high-dynamic range video processing method which comprises the following steps: detecting brightness values and contrast ratios of different scenes of a standard dynamic range (SDR) video so as to obtain a corresponding gamma value of each scene, further calculating according to the gamma values so as to obtain parameters for reverse tone mapping, and performing final conversion, so as to obtain high-dynamic range (HDR) video data. The method has the beneficial effects that the method is automatically applicable to most videos of different styles and different scenes, influence of brightness / contrast ratios in different scenes and areas in different conversion processes is taken into account, creation intentions of original content makers can be maintained in final conversion results to a very large extent, and very good image attractiveness and fidelity can be represented.

The invention provides a method for synthesizing a ghost-reduced high-dynamic-range (HDR) video based on a block matching dynamic estimation algorithm. The method comprises the following steps: block matching: selecting a reference frame and a current frame from an input picture sequence, performing gray-scale processing, and calculating a motion vector of the current frame through an ARPS3 block matching algorithm; detection and calibration of motion areas: detecting respective motion areas of the current frame and the reference frame through the calculated motion vector, combining the motion areas of specific images, and marking on a binary bitmap; and synthesis of a ghost-reduced HDR image: improving a weight map obtained by calculation according to an Exposure Fusion algorithm by the obtained binary bitmap, and fusing images needing to be fused under the guidance of the improved weight map in order to obtain a final HDR image, namely, video frames. According to the HDR video synthesis method, ghost areas are detected through motion estimation, and ghosts are reduced through a fusion algorithm to synthesize the HDR video frames.

Approaches are described for tone-mapping an image frame in a sequence of image frames. A tone-mapping pipeline applies a spatiotemporal filter to each pixel of the image frame, based on a forward optical flow and a backward optical flow, to produce a base layer image. The tone-mapping pipeline applies a temporal filter to each pixel of the image frame, based on the forward and backward optical flows, to produce a temporally filtered frame. The tone-mapping pipeline produces a detail layer image based on the base layer image and the temporally filtered frame. The tone-mapping pipeline produces a detail layer image based on the base layer image and the temporally filtered frame. The tone-mapping pipeline applies a tone curve to the base and detail layer images to produce a tone-mapped base and detail layer image, respectively, and combines the tone-mapped base and detail layer images to produce a tone-mapped image frame.

The present invention provides a generative adversarial network-based high dynamic range inverse tone mapping method and system. The method includes the following steps that: an original high dynamicrange video is read, and the original high dynamic range video is cut and converted into data sets which can be used for training and are corresponding to a standard dynamic range and a high dynamic range respectively; a generative adversarial network is established based on a convolutional neural network and a hopping type connection is established, and standard dynamic range images are convertedinto high dynamic range images, namely inverse tone mapping is performed; and the entire generative adversarial network is continuously optimized according to a set comprehensive objective function,and a finally obtained network can complete mapping from the standard dynamic range to the high dynamic range. With the method of the invention adopted, the problems such as non-linearity insufficiency and complicated parameter adjustment of an existing non-learning method can be solved; the one-dimensional characteristic and gradient characteristic of the high dynamic range images are considered,so that inverse dynamic mapping of the high dynamic range can be better realized.

A high dynamic range (HDR) video can be compressed using inter-frame or intra-frame compression. The compression results in multiple encoded macroblocks and associated residual images. The residual images can be lossy compressed by mapping floating point image data values of the residual image from a light linear space to a perceptually linear space using a first non-linear mapping function. A value in the light linear space is proportionate to the power of a light source, and a value in the perceptually linear space is proportionate to a visual perceived brightness. Floating point discrete cosine transform (DCT) frequency coefficients of the floating point image data values of the residual image are determined. The floating point DCT frequency coefficients are quantized. The quantized floating point DCT frequency coefficients are compressed. The compression of the quantized floating point DCT frequency coefficients is lossless. The compressed quantized floating point DCT frequency coefficients are stored.

The invention provides a multi-exposure high-dynamic range inverse tone mapping model construction method and device. The multi-exposure high-dynamic range inverse tone mapping model construction method comprises the following steps: intercepting a high dynamic range image from an original high dynamic range video, converting the standard dynamic range images into standard dynamic range images, adjusting exposure time to generate multi-exposure standard dynamic range images, and forming a supervised data set by the standard dynamic range images with different exposures and a high dynamic rangeimage with the same normal exposure to serve as a training data set; establishing a generative adversarial network based on a convolutional neural network and skip connection; and establishing a target loss function integrated by the image content features, the intrinsic features and the perception features for the generative adversarial network, and continuously training and optimizing by adopting the training data set to obtain a final model. According to the multi-exposure high-dynamic range inverse tone mapping model construction method, the brightness of the overexposure or underexposureimage can be adjusted, and the effect of the generated high-dynamic-range image is improved, and the brightness characteristic and the chrominance characteristic of the high-dynamic-range image are considered, and inverse tone mapping of the high dynamic range is better achieved.

A user interactive video tone mapping method is provided that can be used for the tone reproduction of high dynamic range (HDR) content on low dynamic range (LDR) displays. The method comprises the steps of selecting a frame of a video sequence; providing a user interface for a user to manually apply scribble marks to the frame; manually applying N scribble marks to the frame, N being a whole number of value 1 or in greater; and tone mapping the video sequence responsive to the scribble marks.

A tone mapping graphical user interface is provided that allows a video engineer to process a video using a set of tools for changing high dynamic range data into lower dynamic range data.

The invention discloses a coding method for a high dynamic range (HDR) image compatible with a low dynamic range (LDR). The method includes 1 converting an original HDR image into an LDR image through tone mapping conversion; 2 re-reading the LDR image obtained through the tone mapping conversion and conducting reverse tone mapping to obtain a processed HDR image; 3 converting the original HDR image and the processed HDR image from the RGB (red, green and blue) format into the YCbCr format respectively; 4 calculating the YCbCr component difference between the original HDR image converted into the YCbCr format and the processed HDR image to obtain redundancy information and conducting image compression on the redundancy information; 5 utilizing the compressed redundancy information as an application mark and storing the information into the LDR image obtained through the tone mapping conversion. By means of the method, the redundancy information is utilized as the application mark of the LDR image obtained through the tone mapping conversion and is stored, the information of the original HDR image is reflected truly, the HDR image can be normally displayed on an LDR display, and the effect that the HDR is compatible with the LDR can be achieved. A decoding method for the image is further disclosed.

A method is provided for reconstructing a high dynamic range (HDR) video from a low dynamic range (LDR) video. The LDR video is captured with dynamic exposure values by a regular camera device to store as an LDR video file. An exposure setting sequence and an LDR video frame sequence are retrieved from the LDR video file, where the exposure setting sequence corresponds to the LDR video frame sequence. The LDR video frame sequence is aligned to generate a compensated frame sequence to merge with the LDR video frame sequence, so as to generate an HDR frame sequence and reconstruct the HDR video.

The invention discloses a high dynamic range video recording method and a device based on Bayer color filtering array. The method comprises steps of performing exposure according to different odd-even double list configuration sensitizing time, obtaining an image frame of different odd-even double list exposure values, decomposing the image frame into an underexposure frame and an overexposure image frame, wherein the underexposure double lists and the deficiency double lists in the underexposure frame are arranged at interval in series and the overexposure double lists and the deficiency double lists are arranged at interval in series in the overexposure image, obtaining underexposure image frame according to the underexposure and the pixel value of the overexposure double-list pixel point and pixel recovery values missing the double list pixel points in the overexposure image frame as the pixel value of the corresponding pixel point on a red-green-blue channel, and merging the overexposure image frame and the underexposure frame according to the pixel value of the pixel point on the red-green-blue channel to obtain a high dynamic range frame according. Through the above steps, the invention can overcome the problem of high speed motion fuzziness and reduce the frame efficiency of high speed continuous shooting.