Abstract: An image sensor includes: a pixel array including a plurality of sensing pixels each configured to convert a received light signal into an electrical signal; a readout circuit configured to convert the electrical signals into image data and output the image data; and a bad pixel correction circuit configured to: input, to a neural network, first input data comprising a first cluster bad pixel of the image data in a first direction to generate a first corrected pixel data, and flip second input data comprising a second cluster bad pixel of the image data in a second direction to generate third input data, and input, to the neural network, the third input data to generate a second corrected pixel data.

Abstract: A method of operating a dynamic vision sensor system includes: obtaining event signals from a plurality of dynamic vision sensor pixels over a predetermined time period, wherein the event signals correspond to a measured change in light; obtaining original image data based on the event signals output by the plurality of DVS pixels and including a plurality of image pixels, wherein the plurality of image pixels respectively correspond to the plurality of dynamic vision sensor pixels; obtaining binary image data by binarizing pixel values of the plurality of image pixels; defining a plurality of pixel groups from the plurality of image pixels in the binary image data; and selecting a plurality of effective groups from among the plurality of pixel groups that represent the movement of an object.

Abstract: An image signal processor, an image sensor, and an operating method of the image sensor are provided. The image sensor may include a pixel array including a plurality of sensing pixels each configured to convert a received light signal into an electrical signal, a readout circuit configured to convert the electrical signals into image data and output the image data, and an image signal processor configured to correct bad pixels occurring in a first pixel group of the image data, based on a neural network, encode position information representing a position of at least one bad pixel of the bad pixels to generate position data, and provide the position data to a first middle layer of a plurality of layers included in the neural network.

Abstract: An image sensor includes: a pixel array including a plurality of sensing pixels each configured to convert a received light signal into an electrical signal; a readout circuit configured to convert the electrical signals into image data and output the image data; and a bad pixel correction circuit configured to: input, to a neural network, first input data comprising a first cluster bad pixel of the image data in a first direction to generate a first corrected pixel data, and flip second input data comprising a second cluster bad pixel of the image data in a second direction to generate third input data, and input, to the neural network, the third input data to generate a second corrected pixel data.

Abstract: A method of processing image data includes: receiving image data from a color filter array including N×N same color pixels; converting first pixel data in an N×N array into second pixel data in an (N?L)×(N?M) array, wherein the first pixel data is output from the N×N same color pixels; and generating third pixel data in the N×N array by performing reconstruction on the second pixel data, wherein each of “L” and “M” is a natural number that is greater than or equal to 1 and less than N, and “N” is a natural number that is greater than or equal to 2.

Abstract: A method of operating a dynamic vision sensor system includes: obtaining event signals from a plurality of dynamic vision sensor pixels over a predetermined time period, wherein the event signals correspond to a measured change in light; obtaining original image data based on the event signals output by the plurality of DVS pixels and including a plurality of image pixels, wherein the plurality of image pixels respectively correspond to the plurality of dynamic vision sensor pixels; obtaining binary image data by binarizing pixel values of the plurality of image pixels; defining a plurality of pixel groups from the plurality of image pixels in the binary image data; and selecting a plurality of effective groups from among the plurality of pixel groups that represent the movement of an object.

Abstract: Disclosed is a method of detecting obstacle around a vehicle. The method of detecting an obstacle around a vehicle, includes: acquiring an image of the obstacle around the vehicle using a monocular camera; creating, by a controller, a distance based cost map, a color based cost map and an edge based cost map from the image; and integrating, by the controller, the distance based cost map, the color based cost map, and the edge based cost map to create a final cost map, and estimating, by the controller, a height of the obstacle from the final cost map.

Abstract: Disclosed is a method of detecting obstacle around a vehicle. The method of detecting an obstacle around a vehicle, includes: acquiring an image of the obstacle around the vehicle using a monocular camera; creating, by a controller, a distance based cost map, a color based cost map and an edge based cost map from the image; and integrating, by the controller, the distance based cost map, the color based cost map, and the edge based cost map to create a final cost map, and estimating, by the controller, a height of the obstacle from the final cost map.