Abstract: Embodiments relate to an image processing circuit able to perform image fusion on received images in at least a first mode for fusing demosaiced and downscaled image data, and a second mode for fusing raw image data. Raw image data is received from an image sensor in Bayer RGB format. In the first mode, the raw image data is demosaiced and resampled prior to undergoing image fusion. On the other hand, in the second raw image mode, the image processing circuit performs image fusion on the raw Bayer image data, and demosaics and resamples the generated fused raw Bayer image. This may ensure a cleaner image signal for image fusion, but consumes more memory. The image processing circuit is configured to support both modes of operation, allowing for fused images to be generated to satisfy the requirements of different applications.

Abstract: Embodiments relate to an image processing circuit able to perform image fusion on received images in a first mode for fusing demosaiced and downscaled image data, and a second mode for fusing raw image data. In the first mode, raw image data received from an image sensor is demosaiced and resampled prior to undergoing image fusion. On the other hand, in the second raw image mode, the image processing circuit performs image fusion on the raw image data, and demosaics and resamples the generated fused raw image. The image processing circuit comprises an image fusion circuit that processes images of received image pyramids differently, based on whether the first or second mode is being run. The image fusion circuit further comprises an additional alpha-blending circuit allowing for the image fusion circuit to perform a fusion and an alpha-blending in a single pass through image fusion circuit.

Abstract: Embodiments relate to an image processing circuit able to perform image fusion on received images in at least a first mode for fusing demosaiced and downscaled image data, and a second mode for fusing raw image data. Raw image data is received from an image sensor in Bayer RGB format. In the first mode, the raw image data is demosaiced and resampled prior to undergoing image fusion. On the other hand, in the second raw image mode, the image processing circuit performs image fusion on the raw Bayer image data, and demosaics and resamples the generated fused raw Bayer image. This may ensure a cleaner image signal for image fusion, but consumes more memory. The image processing circuit is configured to support both modes of operation, allowing for fused images to be generated to satisfy the requirements of different applications.

Abstract: Embodiments relate to an image processing circuit comprising a noise reduction circuit configurable to perform bilateral filtering on demosaiced and resampled image data, or on raw image data, based on the operating mode of the image processing circuit. The noise reduction circuit filters received image data based upon directional taps, by selecting, for each pixel, a set of neighbor pixels, and comparing values of the set of neighbor pixels to determine whether the pixel lies on a directional edge. For raw images, the noise reduction circuit selects the set of neighbor pixels to include a plurality of pixels of the same color channel as the pixel, and one or more additional pixels of a different color channel, where color values for the one or more additional pixels are determined by interpolating color values of two or more adjacent pixels of the same color channel as the pixel.

Abstract: Embodiments relate to circuitry for temporal processing and image fusion. An image fusion circuit receives captured images, and generates corresponding image pyramids. The generated image pyramids are raster or tiled processed, and stored in memory. A fusion module receives a first and second image pyramids from the memory, and warps and fuses image pyramids to generate a fused image pyramid, which may be used for further processing, and may also be stored back into the memory. The image fusion circuitry is configurable to operate in a plurality of different configuration modes corresponding to different image fusion applications for fusing image pyramids of received images, including two-frame fusion, temporal filtering, infinite impulse response (IIR) temporal processing, and/or finite impulse response (FIR) temporal processing.

Abstract: Embodiments relate to circuitry for temporal processing and image fusion. An image fusion circuit receives captured images, and generates corresponding image pyramids. The generated image pyramids are raster or tiled processed, and stored in memory. A fusion module receives a first and second image pyramids from the memory, warps the first image pyramid based upon the second image pyramid, and fuses the warped first image pyramid with the second image pyramid to generate a fused image pyramid, which may be used for further processing, and may also be stored back into the memory. Because pyramid generation occurs prior to warping and fusion, and by allowing fused image pyramids to be stored back into memory, the image fusion circuitry is configurable to implement a variety of temporal processing functions involving different image fusion combinations.

Abstract: Embodiments relate to an image processing circuit that performs machine learning (ML) based noise reduction on image data. The image processing circuit includes a ML based noise reduction circuit that includes a hybrid kernel calculation circuit and a noise filtering circuit coupled to the hybrid kernel calculation circuit. The hybrid kernel calculation circuit generates, for each pixel of an image, a hybrid kernel by combining a ML kernel of each pixel of the image and a bilateral kernel of each pixel of the image. The noise filtering circuit performs, for each pixel of the image, noise filtering of the image using the hybrid kernel for each pixel of the image to generate a de-noised version of the image.

Abstract: Embodiments of the present disclosure relate performing registration of a first image to a second image where the first image is undistorted to linear space before applying a geometric transformation matrix to modify the first image to align with the second image. The geometric transformation matrix may be a linear matrix that causes the undistorted version of the first image to make translation movement, rotational movement or both. The undistorted and modified first image is then reverted back to nonlinear distorted space. Then the reverted first image may be warped to better align with the second image for fusing with the second image. In this way, visual distortions in the fused image such as wobbling may be reduced or eliminated.

Abstract: Embodiments relate to an image processing circuit able to perform image fusion on received images in a first mode for fusing demosaiced and downscaled image data, and a second mode for fusing raw image data. In the first mode, raw image data received from an image sensor is demosaiced and resampled prior to undergoing image fusion. On the other hand, in the second raw image mode, the image processing circuit performs image fusion on the raw image data, and demosaics and resamples the generated fused raw image. The image processing circuit comprises an image fusion circuit that processes images of received image pyramids differently, based on whether the first or second mode is being run. The image fusion circuit further comprises an additional alpha-blending circuit allowing for the image fusion circuit to perform a fusion and an alpha-blending in a single pass through image fusion circuit.

Abstract: Embodiments relate to an image processing circuit able to perform image fusion on received images in at least a first mode for fusing demosaiced and downscaled image data, and a second mode for fusing raw image data. Raw image data is received from an image sensor in Bayer RGB format. In the first mode, the raw image data is demosaiced and resampled prior to undergoing image fusion. On the other hand, in the second raw image mode, the image processing circuit performs image fusion on the raw Bayer image data, and demosaics and resamples the generated fused raw Bayer image. This may ensure a cleaner image signal for image fusion, but consumes more memory. The image processing circuit is configured to support both modes of operation, allowing for fused images to be generated to satisfy the requirements of different applications.

Abstract: Embodiments relate to an image processing circuit comprising a noise reduction circuit configurable to perform bilateral filtering on demosaiced and resampled image data, or on raw image data, based on the operating mode of the image processing circuit. The noise reduction circuit filters received image data based upon directional taps, by selecting, for each pixel, a set of neighbor pixels, and comparing values of the set of neighbor pixels to determine whether the pixel lies on a directional edge. For raw images, the noise reduction circuit selects the set of neighbor pixels to include a plurality of pixels of the same color channel as the pixel, and one or more additional pixels of a different color channel, where color values for the one or more additional pixels are determined by interpolating color values of two or more adjacent pixels of the same color channel as the pixel.

Abstract: Battery thermal preconditioning includes scheduling thermal preconditioning in accordance with user presets, preferences and battery and/or vehicle conditions and profiles. Thermal preconditioning in advance of charging events may optimize charge time, battery health and range. Manual and predictive intelligence methods may be employed to attain and maintain a predetermined range of battery pack temperatures.

Abstract: Embodiments relate to circuitry for warping image pyramids for image fusion. An image fusion circuit receives captured images, and generates image pyramids corresponding to the received images to be used for image fusion. A warping circuit warps the first image pyramid based upon one or more warping parameters to align the first image pyramid to the second image pyramid. The warping circuit is a multi-scale warping circuit configured to warp each level of the first image pyramid, using a first warping engine that warps a base level of the image pyramid, and at least one addition warping engine that warps a plurality of scaled levels of the image pyramid in parallel with the first warping engine.

Abstract: Embodiments relate to circuitry for warping image pyramids for image fusion. An image fusion circuit receives captured images, and generates image pyramids corresponding to the received images to be used for image fusion. A warping circuit warps the first image pyramid based upon one or more warping parameters to align the first image pyramid to the second image pyramid. The warping circuit is a multi-scale warping circuit configured to warp each level of the first image pyramid, using a first warping engine that warps a base level of the image pyramid, and at least one addition warping engine that warps a plurality of scaled levels of the image pyramid in parallel with the first warping engine.

Abstract: Embodiments relate to circuitry for temporal processing and image fusion. An image fusion circuit receives captured images, and generates corresponding image pyramids. The generated image pyramids are raster or tiled processed, and stored in memory. A fusion module receives a first and second image pyramids from the memory, warps the first image pyramid based upon the second image pyramid, and fuses the warped first image pyramid with the second image pyramid to generate a fused image pyramid, which may be used for further processing, and may also be stored back into the memory. Because pyramid generation occurs prior to warping and fusion, and by allowing fused image pyramids to be stored back into memory, the image fusion circuitry is configurable to implement a variety of temporal processing functions involving different image fusion combinations.

Abstract: Embodiments relate to circuitry for temporal processing and image fusion. An image fusion circuit receives captured images, and generates corresponding image pyramids. The generated image pyramids are raster or tiled processed, and stored in memory. A fusion module receives a first and second image pyramids from the memory, and warps and fuses image pyramids to generate a fused image pyramid, which may be used for further processing, and may also be stored back into the memory. The image fusion circuitry is configurable to operate in a plurality of different configuration modes corresponding to different image fusion applications for fusing image pyramids of received images, including two-frame fusion, temporal filtering, infinite impulse response (IIR) temporal processing, and/or finite impulse response (FIR) temporal processing.

Abstract: A feature extractor determines reference feature locations from a portion of a reference image and corresponding feature locations from a portion of a warp image. A transform module determines a homography transform function that transforms versions of the corresponding feature locations to the reference feature locations. The homography transform function has an error below a threshold level, where the error represents a difference between the transformed corresponding feature locations and the reference feature locations. The local transform module generates transform parameters by processing the homography transform function. A warper circuit warps the portion of the warp image by at least applying the transform parameters to generate a portion of a warped image.

Abstract: A feature extractor determines reference feature locations from a portion of a reference image and corresponding feature locations from a portion of a warp image. A transform module determines a homography transform function that transforms versions of the corresponding feature locations to the reference feature locations. The homography transform function has an error below a threshold level, where the error represents a difference between the transformed corresponding feature locations and the reference feature locations. The local transform module generates transform parameters by processing the homography transform function. A warper circuit warps the portion of the warp image by at least applying the transform parameters to generate a portion of a warped image.

Abstract: Embodiments relate to fusion processing between two images captured with two different exposure times to generate a fused image with a higher dynamic range. An unscaled single color version of a first image is blended with another unscaled single color version of a second image to generate an unscaled single color version of the fused image. A downscaled multi-color version of the first image is blended with a downscaled multi-color version of the second image to generate a downscaled multi-color version of the fused image of a plurality of downscaled versions of the fused image. A first downscaled multi-color version of the fused image is generated by upscaling and accumulating the plurality of downscaled versions of the fused image. The first downscaled multi-color version of the fused image has a pixel resolution lower than a pixel resolution of the unscaled single color version of the fused image.

Abstract: Embodiments relate to biasing an image noise filter to reduce edge and texture blurring of image data. Pixel values used to determine photometric coefficients for a bilateral filter are modified by offset values. The offset value for a pixel value is determined by applying a high pass filter to the pixel (referred to as the center pixel) and neighboring pixels of the center pixel. By adding the offset value to the center pixel value, the pixel value difference between the neighboring pixels and the center pixel becomes smaller for pixels on the same side of an edge as the center pixel. Thus, pixels on the same side of the edge get more weight in the bilateral noise filter. Conversely, pixels on the opposite side of the edge as the center pixel get less weight in the bilateral filter. As a result, the biased bilateral filter reduces blurring of edges and increases preservation of texture in the image data.