HD color video using monochromatic CMOS image sensors integrated in a 3D package is provided. An example 3DIC package for color video includes a beam splitter to partition received light of an image stream into multiple light outputs. Multiple monochromatic CMOS image sensors are each coupled to one of the multiple light outputs to sense a monochromatic image stream at a respective component wavelength of the received light. Each monochromatic CMOS image sensor is specially constructed, doped, controlled, and tuned to its respective wavelength of light. A parallel processing integrator or interposer chip heterogeneously combines the respective monochromatic image streams into a full-spectrum color video stream, including parallel processing of an infrared or ultraviolet stream. The parallel processing of the monochromatic image streams provides reconstruction to HD or 4K HD color video at low light levels. Parallel processing to one interposer chip also enhances speed, spatial resolution, sensitivity, low light performance, and color reconstruction.

HD color video using monochromatic CMOS image sensors integrated in a 3D package is provided. An example 3DIC package for color video includes a beam splitter to partition received light of an image stream into multiple light outputs. Multiple monochromatic CMOS image sensors are each coupled to one of the multiple light outputs to sense a monochromatic image stream at a respective component wavelength of the received light. Each monochromatic CMOS image sensor is specially constructed, doped, controlled, and tuned to its respective wavelength of light. A parallel processing integrator or interposer chip heterogeneously combines the respective monochromatic image streams into a full-spectrum color video stream, including parallel processing of an infrared or ultraviolet stream. The parallel processing of the monochromatic image streams provides reconstruction to HD or 4K HD color video at low light levels. Parallel processing to one interposer chip also enhances speed, spatial resolution, sensitivity, low light performance, and color reconstruction.

A video processing system includes a computing platform having a hardware processor and a memory storing a software code including a convolutional neural network (CNN). The hardware processor executes the software code to receive video data including a key video frame in color and a video sequence in gray scale, determine a first estimated colorization for each frame of the video sequence except the key video frame based on a colorization of a previous frame, and determine a second estimated colorization for each frame of the video sequence except the key video frame based on the key video frame in color. For each frame of the video sequence except the key video frame, the software code further blends the first estimated colorization with the second estimated colorization using a color fusion stage of the CNN to produce a colorized video sequence corresponding to the video sequence in gray scale.

A video processing system includes a computing platform having a hardware processor and a memory storing a software code including a convolutional neural network (CNN). The hardware processor executes the software code to receive video data including a key video frame in color and a video sequence in gray scale, determine a first estimated colorization for each frame of the video sequence except the key video frame based on a colorization of a previous frame, and determine a second estimated colorization for each frame of the video sequence except the key video frame based on the key video frame in color. For each frame of the video sequence except the key video frame, the software code further blends the first estimated colorization with the second estimated colorization using a color fusion stage of the CNN to produce a colorized video sequence corresponding to the video sequence in gray scale.

An imager captures images of a living subject including a near-infrared image, an infrared image, or both. A processor is connected to the imager and an output device. The processor is configured to generate output images of vasculature of the living subject from the images captured by the imager, include in the output images a range of discrete scale comparator objects of different sizes, and provide the output images to the output device for display to a user.

An imager captures images of a living subject including a near-infrared image, an infrared image, or both. A processor is connected to the imager and an output device. The processor is configured to generate output images of vasculature of the living subject from the images captured by the imager, include in the output images a range of discrete scale comparator objects of different sizes, and provide the output images to the output device for display to a user.

A video processing system includes a computing platform having a hardware processor and a memory storing a software code including a convolutional neural network (CNN). The hardware processor executes the software code to receive video data including a key video frame in color and a video sequence in gray scale, determine a first estimated colorization for each frame of the video sequence except the key video frame based on a colorization of a previous frame, and determine a second estimated colorization for each frame of the video sequence except the key video frame based on the key video frame in color. For each frame of the video sequence except the key video frame, the software code further blends the first estimated colorization with the second estimated colorization using a color fusion stage of the CNN to produce a colorized video sequence corresponding to the video sequence in gray scale.

A video processing system includes a computing platform having a hardware processor and a memory storing a software code including a convolutional neural network (CNN). The hardware processor executes the software code to receive video data including a key video frame in color and a video sequence in gray scale, determine a first estimated colorization for each frame of the video sequence except the key video frame based on a colorization of a previous frame, and determine a second estimated colorization for each frame of the video sequence except the key video frame based on the key video frame in color. For each frame of the video sequence except the key video frame, the software code further blends the first estimated colorization with the second estimated colorization using a color fusion stage of the CNN to produce a colorized video sequence corresponding to the video sequence in gray scale.

An imaging system includes an array of photodetectors configured to produce an array of intensity values corresponding to light intensity at the photodetectors. The imaging system can include a display for display images acquired with the array of photodetectors, after some image and display processing. The image and display processing components of the imaging system produce an array of display-formatted pixels for display on the imaging system display. The display-formatted pixels include at least a first plurality of pixels formatted for display using a first lookup table and a second plurality of pixels formatted for display using a second lookup table. Threshold criteria for choosing which pixels belong to which plurality are determined from analysis of a scene indicated by a user as a background scene. Once the threshold criteria are determined from the background the criteria are applied to pixels in subsequent image frames, and the pixels that meet the criteria are displayed in at least one color table LUT and the pixels that do not are displayed in a at least one different color table LUT. In a particular embodiment. The criteria may be above or below the max scene value (or temperature) from the background scene and pixels below the criteria may be displayed in a monochrome or non-vivid color table and pixels above the criteria are displayed in a vivid color table.

An imaging system includes an array of photodetectors configured to produce an array of intensity values corresponding to light intensity at the photodetectors. The imaging system can include a display for display images acquired with the array of photodetectors, after some image and display processing. The image and display processing components of the imaging system produce an array of display-formatted pixels for display on the imaging system display. The display-formatted pixels include at least a first plurality of pixels formatted for display using a first lookup table and a second plurality of pixels formatted for display using a second lookup table. Threshold criteria for choosing which pixels belong to which plurality are determined from analysis of a scene indicated by a user as a background scene. Once the threshold criteria are determined from the background the criteria are applied to pixels in subsequent image frames, and the pixels that meet the criteria are displayed in at least one color table LUT and the pixels that do not are displayed in a at least one different color table LUT. In a particular embodiment. The criteria may be above or below the max scene value (or temperature) from the background scene and pixels below the criteria may be displayed in a monochrome or non-vivid color table and pixels above the criteria are displayed in a vivid color table.