Abstract: Systems and methods for image processing, and specifically for color reconstruction of an output signal from a multispectral imaging sensor (MIS), are described. Embodiments of the present disclosure receive image sensor data from an image sensor of a camera device; apply a non-linear color space mapping to the image sensor data using a neural network to obtain image data, wherein the non-linear color space mapping comprises a non-negative homogeneous function; and store the image data in a memory of the camera device.

Abstract: An image processing unit includes an imaging sensor having a pixel array, a memory storing an artificial neural network (ANN), and an image signal processor configured to operate the ANN on an image output by the imaging sensor to predict an error value of a pixel of the image and correct the pixel using the predicted error value.

Abstract: Systems and methods for image processing, and specifically for color reconstruction of an output signal from a multispectral imaging sensor (MIS), are described. Embodiments of the present disclosure receive image sensor data from an image sensor of a camera device; apply a non-linear color space mapping to the image sensor data using a neural network to obtain image data, wherein the non-linear color space mapping comprises a non-negative homogeneous function; and store the image data in a memory of the camera device.

Abstract: A method of fusing frame based image sensors (FBIS) images with dynamic vision sensor (DVS) event data includes concatenating a plurality of image tensors into a single image input tensor; concatenating a plurality of event tensors into a single event input tensor; concatenating the event input tensor and the image input tensor wherein a single input tensor containing data from both the image input tensor and the event input tensor is generated; processing the single input tensor with a fully convolutional neural network (FCNN), wherein in a contracting path of the FCNN, a number of channels is increased, and in an expansion path of the FCNN, the number of channels is decreased; and combining channels wherein an output image tensor is generated with a reduced number of channels.

Abstract: A method of fusing frame based image sensors (FBIS) images with dynamic vision sensor (DVS) event data includes concatenating a plurality of image tensors into a single image input tensor; concatenating a plurality of event tensors into a single event input tensor; concatenating the event input tensor and the image input tensor wherein a single input tensor containing data from both the image input tensor and the event input tensor is generated; processing the single input tensor with a fully convolutional neural network (FCNN), wherein in a contracting path of the FCNN, a number of channels is increased, and in an expansion path of the FCNN, the number of channels is decreased; and combining channels wherein an output image tensor is generated with a reduced number of channels.