Provided are an image composition apparatus for composing color images with black-and-white images including infrared components, and an image composition method thereof. The image composition method includes generating a first image signal with color information and a second image signal including infrared components without color information, dividing the first image signal into a brightness signal and a color signal, composing the brightness signal of the first image signal with a brightness signal of the second image signal to generate a composed brightness signal, and composing the composed brightness signal with the color signal of the first image signal to generate a color image.

Input video signals characterized by a source electro-optical transfer function (EOTF) are to be blended and displayed on a target display with a target EOTF which is different than the source EOTF. Given an input set of blending parameters, an output set of blending parameters is generated as follows. The input blending parameters are scaled by video signal metrics computed in the target EOTF to generate scaled blending parameters. The scaled blended parameters are mapped back to the source EOTF space to generate mapped blending parameters. Finally the mapped blending parameters are normalized to generate the output blending parameters. An output blended image is generating by blending the input video signals using the output blending parameters. Examples of generating the video signal metrics are also provided.

Input video signals characterized by a source electro-optical transfer function (EOTF) are to be blended and displayed on a target display with a target EOTF which is different than the source EOTF. Given an input set of blending parameters, an output set of blending parameters is generated as follows. The input blending parameters are scaled by video signal metrics computed in the target EOTF to generate scaled blending parameters. The scaled blended parameters are mapped back to the source EOTF space to generate mapped blending parameters. Finally the mapped blending parameters are normalized to generate the output blending parameters. An output blended image is generating by blending the input video signals using the output blending parameters. Examples of generating the video signal metrics are also provided.

An image processing method is provided. The image processing method includes the following steps: blending a plurality of exposure frames captured by one or more image capturing devices using a plurality of exposure times to generate a real-time image; analyzing one or more regions of interest (ROIs) of the real-time image according to ROI information about the one or more ROIs of the real-time image, and accordingly generating an analysis result; and utilizing an image processor for referring to the analysis result to locally adjust image data within the one or more ROIs of the real-time image to generate an adjusted real-time image in real time.

A system, method, and computer program product are provided for rendering a combined image. In use, two or more source images including at least one strobe image and at least one ambient image are loaded. A pixel-level correction is estimated for at least one of the two or more source images based on a pixel level correction function. At least one pixel of the two or more source images is color-corrected based on the pixel-level correction. A first blend weight associated with the two or more source images is initialized, and a first combined image from the two or more source images is rendered based on the color-correction and the first blend weight. Additional systems, methods, and computer program products are also presented.

A system, method, and computer program product are provided for rendering a combined image. In use, two or more source images including at least one strobe image and at least one ambient image are loaded. A pixel-level correction is estimated for at least one of the two or more source images based on a pixel level correction function. At least one pixel of the two or more source images is color-corrected based on the pixel-level correction. A first blend weight associated with the two or more source images is initialized, and a first combined image from the two or more source images is rendered based on the color-correction and the first blend weight. Additional systems, methods, and computer program products are also presented.

A system, method, and computer program product are provided for rendering a combined image. In use, two or more source images including at least one strobe image and at least one ambient image are loaded. A pixel-level correction is estimated for at least one of the two or more source images based on a pixel level correction function. At least one pixel of the two or more source images is color-corrected based on the pixel-level correction. A first blend weight associated with the two or more source images is initialized, and a first combined image from the two or more source images is rendered based on the color-correction and the first blend weight. Additional systems, methods, and computer program products are also presented.

A system, method, and computer program product are provided for rendering a combined image. In use, two or more source images including at least one strobe image and at least one ambient image are loaded. A pixel-level correction is estimated for at least one of the two or more source images based on a pixel level correction function. At least one pixel of the two or more source images is color-corrected based on the pixel-level correction. A first blend weight associated with the two or more source images is initialized, and a first combined image from the two or more source images is rendered based on the color-correction and the first blend weight. Additional systems, methods, and computer program products are also presented.

The invention provides an autonomous vehicle with a video camera that merges images taken a different light levels by replacing saturated parts of an image with corresponding parts of a lower-light image to stream a video with a dynamic range that extends to include very low-light and very intensely lit parts of a scene. The high dynamic range (HDR) camera streams the HDR video to a HDR system in real time—as the vehicle operates. As pixel values are provided by the camera's image sensors, those values are streamed directly through a pipeline processing operation and on to the HDR system without any requirement to wait and collect entire images, or frames, before using the video information.

The invention provides an autonomous vehicle with a video camera that merges images taken a different light levels by replacing saturated parts of an image with corresponding parts of a lower-light image to stream a video with a dynamic range that extends to include very low-light and very intensely lit parts of a scene. The high dynamic range (HDR) camera streams the HDR video to a HDR system in real time—as the vehicle operates. As pixel values are provided by the camera's image sensors, those values are streamed directly through a pipeline processing operation and on to the HDR system without any requirement to wait and collect entire images, or frames, before using the video information.