Abstract: Methods, apparatuses and systems may provide for operating a machine learning device by obtaining training image data, conducting an offline prediction analysis of the training image data with respect to one or more real-time parameters of an image capture device, and generating one or more parameter detection models based on the offline prediction analysis. Additionally, methods, apparatuses and systems may provide for operating the image capture device by obtaining a candidate image associated with the image capture device, determining that the candidate image corresponds to a particular type of scene represented in a parameter prediction model, and adjusting one or more real-time parameters of the image capture device based at least in part on one or more parameter values associated with the particular type of scene.

Abstract: Techniques related to generating downscaled image or image frame data in a luma chroma separated color space for an image or video pipeline architecture are discussed. Such techniques may include converting input image data to the luma chroma separated color space based on adaptive color coefficients determined based on an illumination indicator associated with the input image data and storing downscaled color converted image data to an input image buffer of the image or video pipeline.

Abstract: Methods, apparatuses and systems may provide for operating a machine learning device by obtaining training image data, conducting an offline prediction analysis of the training image data with respect to one or more real-time parameters of an image capture device, and generating one or more parameter detection models based on the offline prediction analysis. Additionally, methods, apparatuses and systems may provide for operating the image capture device by obtaining a candidate image associated with the image capture device, determining that the candidate image corresponds to a particular type of scene represented in a parameter prediction model, and adjusting one or more real-time parameters of the image capture device based at least in part on one or more parameter values associated with the particular type of scene.

Abstract: Techniques related to generating downscaled image or image frame data in a luma chroma separated color space for an image or video pipeline architecture are discussed. Such techniques may include converting input image data to the luma chroma separated color space based on adaptive color coefficients determined based on an illumination indicator associated with the input image data and storing downscaled color converted image data to an input image buffer of the image or video pipeline.

Abstract: In one example embodiment, a method includes determining at least one of integral column sums and integral row sums for pixels of an image and determining at least one of a column-wise sum of pixel values and a row-wise sum of pixel values associated with an area within the image based on at least one of the determined integral column sums and the determined integral row sums corresponding to a plurality of the pixels forming the area.

Abstract: An image processing method includes: receiving image data of a Bayer format comprising red color information, green color information, and blue color information, generating image data of a modified Bayer format by combining the green color information with the red color information and combining the green color information with the blue color information while downscaling the image data of the Bayer format to a target resolution, denoising the image data of the modified Bayer format, and generating RGB image data by demosaicing the denoised image data of the modified Bayer format.

Abstract: In at least one example embodiment, a method of determining motion in an image includes acquiring pixel data from a plurality of pixels in an image sensor, the plurality of pixels having respective response ranges, the response range of at least a first pixel of the pixels including a linear response range and a logarithmic response range, the plurality of pixels configured to produce pixel data according to light of the image in a scene and the response ranges and determining the motion based on the pixel data generated across the response ranges including the logarithmic response range of the at least first pixel.

Abstract: High quality upscaling and denoising are required in mobile imaging devices that do not contain high quality lenses. Such is also required in order to scale up standard-definition video content for display in high-definition television screens. The disclosed method uses contextual information obtained during upscaling and/or denoising of frames. Relevant correspondences between patches within a frame and between frames, are detected, managed and exploited. The correspondence information is simultaneously used and updated while video frames are being processed. Two approaches may be used: 1. keeping, searching for and updating a database of useful patches, by adding frequently visible similar patches, aggregating high-frequency, low-noise information associated with the similar patches, and removing less-observed patches; 2.

Abstract: In one example embodiment, a method includes determining at least one of integral column sums and integral row sums for pixels of an image and determining at least one of a column-wise sum of pixel values and a row-wise sum of pixel values associated with an area within the image based on at least one of the determined integral column sums and the determined integral row sums corresponding to a plurality of the pixels forming the area.

Abstract: In at least one example embodiment, a method of determining motion in an image includes acquiring pixel data from a plurality of pixels in an image sensor, the plurality of pixels having respective response ranges, the response range of at least a first pixel of the pixels including a linear response range and a logarithmic response range, the plurality of pixels configured to produce pixel data according to light of the image in a scene and the response ranges and determining the motion based on the pixel data generated across the response ranges including the logarithmic response range of the at least first pixel.

Abstract: An image capture device can include an analysis unit that can be configured to determine a refined light model that models a light source based on first and second image signals sampled with first and second exposure times, respectively, and corresponding to first and second rows of pixels. A compensation unit can be coupled to the analysis unit, and can be configured to generate an output image signal by compensating the first and second image signals and the second image signal using compensation gains associated with the refined light model.

Abstract: A digital image stabilization method includes taking N frames of a target image with an exposure of T, dividing each of the N frames into predetermined blocks, and selecting a reference frame from among the N frames by setting one of the blocks in each of the N frames as a reference region and comparing reference regions of the respective N frames with one another. The method further includes estimating a motion vector of each of the remaining frames based on a reference region of the reference frame, and generating a result frame by combining a weighted frame, which is obtained by mapping a weight calculated based on the estimated motion vector to each block, and a color component frame.

Abstract: A denoising apparatus comprising an image input unit which receives pixel data including color information of pixels included in a correction target image, a denoising unit which denoises the pixel data by a weight based averaging method, wherein the weight is set to a maximum value when a difference value between a correction target block and a comparison target block in the correction target image is zero, decreases linearly to zero as the difference value increases until it reaches a threshold value, and is set to zero when the difference value is greater than or equal to the threshold value, and an image output unit which outputs the pixel data processed by the denoising unit. The denoising unit assigns a corrected weight value to at least a guaranteed number of comparison target blocks for an impulse block, where an impulse block is a correction target block for which the number of non-zero weight valued comparison target blocks is less than a predetermined guaranteed number.

Abstract: An image capture device can include an analysis unit that can be configured to determine a refined light model that models a light source based on first and second image signals sampled with first and second exposure times, respectively, and corresponding to first and second rows of pixels. A compensation unit can be coupled to the analysis unit, and can be configured to generate an output image signal by compensating the first and second image signals and the second image signal using compensation gains associated with the refined light model.

Abstract: High quality upscaling and denoising are required in mobile imaging devices that do not contain high quality lenses. Such is also required in order to scale up standard-definition video content for display in high-definition television screens. The disclosed method uses contextual information obtained during upscaling and/or denoising of frames. Relevant correspondences between patches within a frame and between frames, are detected, managed and exploited. The correspondence information is simultaneously used and updated while video frames are being processed. Two approaches may be used: 1. keeping, searching for and updating a database of useful patches, by adding frequently visible similar patches, aggregating high-frequency, low-noise information associated with the similar patches, and removing less-observed patches; 2.

Abstract: A digital image stabilization method includes taking N frames of a target image with an exposure of T, dividing each of the N frames into predetermined blocks, and selecting a reference frame from among the N frames by setting one of the blocks in each of the N frames as a reference region and comparing reference regions of the respective N frames with one another. The method further includes estimating a motion vector of each of the remaining frames based on a reference region of the reference frame, and generating a result frame by combining a weighted frame, which is obtained by mapping a weight calculated based on the estimated motion vector to each block, and a color component frame.

Abstract: An image processing method includes: receiving image data of a Bayer format comprising red color information, green color information, and blue color information, generating image data of a modified Bayer format by combining the green color information with the red color information and combining the green color information with the blue color information while downscaling the image data of the Bayer format to a target resolution, denoising the image data of the modified Bayer format, and generating RGB image data by demosaicing the denoised image data of the modified Bayer format.

Abstract: A method of detecting a target in an image. The method includes receiving an image; generating a plurality of scaled-down images based on the received image; generating integral column images of each of the plurality of scaled images by calculating integral values of pixels column by column; selecting and classifying a plurality of windows of the integral column images according to a feature arithmetic operation based on a recursive column calculation; and detecting the target on the basis of the classification results for the plurality of windows.

Abstract: A denoising apparatus comprising an image input unit which receives pixel data including color information of pixels included in a correction target image, a denoising unit which denoises the pixel data by a weight based averaging method, wherein the weight is set to a maximum value when a difference value between a correction target block and a comparison target block in the correction target image is zero, decreases linearly to zero as the difference value increases until it reaches a threshold value, and is set to zero when the difference value is greater than or equal to the threshold value, and an image output unit which outputs the pixel data processed by the denoising unit. The denoising unit assigns a corrected weight value to at least a guaranteed number of comparison target blocks for an impulse block, where an impulse block is a correction target block for which the number of non-zero weight valued comparison target blocks is less than a predetermined guaranteed number.

Abstract: In a method for rectifying rolling shutter effects, a horizontal translation and a vertical translation of a second image relative to a first image are estimated, and the estimated horizontal and vertical translations are filtered using a Kalman filter. Rolling shutter distortion of the second image is rectified according to the filtered horizontal and vertical translations.