Abstract: A system for optical alignment and calibration of an infrared camera lens, including: a lens support mechanism configured to adjust a position of an infrared camera lens relative to a camera body; at least one collimator configured to output infrared rays, wherein the at least one collimator is positioned such that the output infrared rays converge on an infrared sensor within the camera body through the infrared camera lens; and at least one curing catalyst configured to cure an adhesive placed on the infrared camera lens when an ideal lens position is determined.

Abstract: A system and method for correcting oversaturated pixels in far-infrared (FIR) images captured by a shutterless FIR camera. The method includes identifying oversaturated pixels based on a pixel value analysis of an input image; creating an oversaturated pixel mask of the input image, where the oversaturated pixel mask includes the identified oversaturated pixels and excludes pixels not identified as oversaturated pixels; and correcting the oversaturated pixels of the current image using the oversaturated pixel mask, based on a scene-based nonuniformity correction (SBNC).

Abstract: A method and apparatus for correcting nonuniformity noise in thermal images. The method comprises receiving a current image being part of a stream of thermal images; concatenating the current image from the stream of thermal images with hidden state images; processing, by a first convolutional neural network, the concatenated image to extract a number of feature channels; generating based on the feature channels at least a first multiplicative mask; processing, by a second convolutional neural network, a masked concatenated image to compute a weighting parameter, wherein the masked concatenated image is resulted by applying the first multiplicative mask on the concatenated image; and simulating, using the weighting parameter, an infinite impulse response (IIR)-style updating scheme to estimate the nonuniformity noise in the current image.

Abstract: A method and apparatus for correcting nonuniformity noise in thermal images. The method comprises receiving a current image being part of a stream of thermal images; concatenating the current image from the stream of thermal images with hidden state images; processing, by a first convolutional neural network, the concatenated image to extract a number of feature channels; generating based on the feature channels at least a first multiplicative mask; processing, by a second convolutional neural network, a masked concatenated image to compute a weighting parameter, wherein the masked concatenated image is resulted by applying the first multiplicative mask on the concatenated image; and simulating, using the weighting parameter, an infinite impulse response (IIR)-style updating scheme to estimate the nonuniformity noise in the current image.

Abstract: A shutterless far-infrared (FIR) camera for advanced driver assistance systems, including at least one optical unit including at least one lens; an FIR sensor coupled to the optical unit and configured to capture FIR images; and an integrated circuit (IC) configured to process the captured FIR images to output an enhanced thermal video stream, wherein the IC further includes: a processing circuitry; and a memory containing instructions that, when executed by the processing circuitry, configure the processing circuitry to perform image corrections including at least a shutterless correction.

Abstract: A camera mounting system and a method for processing images are disclosed. The system includes an external component configured to capture thermal images, and an internal component configured to receive the thermal images. The thermal images are wirelessly transmitted by the external component, the external component is coupled to the internal component via a glass, and the internal component is further configured to wirelessly power the external component.

Abstract: A system and method for correcting nonuniformity in far-infrared (FIR) images captured by a shutterless FIR camera. The method includes determining a noise of a current image based on updating a noise estimate of a previous image with a noise estimate of a current image; determining a weight mask matrix of the current image, where the weight matrix includes high values corresponding to pixels of the current image in which noise estimation is facilitated, and low values corresponding to pixels of the current image in which noise estimation is inhibited; applying the weight mask matrix to the current image; and correcting the nonuniformity of the current image incrementally based on the determined noise of current image and the applied weight mask matrix.

Abstract: An infrared camera assembly for a vehicle. The assembly includes: a vehicle component having a front surface; a shutterless far-infrared (FIR) camera mounted within the vehicle component, wherein the shutterless FIR camera is utilized to output at least one thermal video stream processed by the autonomous vehicle system; and a protective window disposed on at least a portion of the front surface of the vehicle component, where the protective window is positioned to be aligned with a lens of the FIR camera, so as to allow the shutterless FIR camera to capture images therethrough.

Abstract: A camera apparatus. The camera apparatus includes a housing having a front end and a back end; a lens, wherein the lens is disposed in the front end of the housing; and a thermal core, wherein the thermal core is disposed between the lens and the back end of the housing, the thermal core further comprising: at least one substrate; at least one thermally conductive member configured to remove heat from the thermal core; and an infrared imager affixed to one of the at least one substrate, the infrared imager configured to capture an infrared video stream.

Abstract: A system and method for correcting fixed pattern noise in far-infrared (FIR) images captured by a shutterless FIR camera. The method includes: determining a drift coefficient based on previously determined calibration values and high pass filter values applied to an input FIR image captured by the shutterless FIR camera; smoothing the drift coefficient based, in part, on previously computed drift coefficient values; and removing noise from the input image based on the smoothed drift coefficient value.

Abstract: A system and method for image stream synchronization for an FIR camera. The method includes applying an initial correction to a received image stream; splitting the corrected image stream into a first image stream and at least a second image stream; enhancing the first image stream by at least one image enhancing process; buffering the second image stream until a synchronization signal is received; and synchronizing the first image stream and second image stream, such that the output of the enhanced first image stream and the buffered second image stream match.

Abstract: A camera apparatus. The camera apparatus includes a housing having a front end and a back end; a lens, wherein the lens is disposed in the front end of the housing; and a thermal core, wherein the thermal core is disposed between the lens and the back end of the housing, the thermal core further comprising: at least one substrate; at least one thermally conductive member configured to remove heat from the thermal core; and an infrared imager affixed to one of the at least one substrate, the infrared imager configured to capture an infrared video stream.

Abstract: A method and apparatus for correcting nonuniformity noise in thermal images. The method comprises receiving a current image being part of a stream of thermal images; concatenating the current image from the stream of thermal images with hidden state images; processing, by a first convolutional neural network, the concatenated image to extract a number of feature channels; generating based on the feature channels at least a first multiplicative mask; processing, by a second convolutional neural network, a masked concatenated image to compute a weighting parameter, wherein the masked concatenated image is resulted by applying the first multiplicative mask on the concatenated image; and simulating, using the weighting parameter, an infinite impulse response (IIR)-style updating scheme to estimate the nonuniformity noise in the current image.

Abstract: An infrared camera assembly for a vehicle. The assembly includes: a vehicle component having a front surface; a shutterless far-infrared (FIR) camera mounted within the vehicle component, wherein the shutterless FIR camera is utilized to output at least one thermal video stream processed by the autonomous vehicle system; and a protective window disposed on at least a portion of the front surface of the vehicle component, where the protective window is positioned to be aligned with a lens of the FIR camera, so as to allow the shutterless FIR camera to capture images therethrough.

Abstract: A window for resistive heating and a camera apparatus including a window for resistive heating. The window includes a transparent member having an outer edge, wherein the transparent member is made of a first material, wherein the first material is a low conductivity material; and at least one set of two conductive pads disposed on the outer edge of the transparent member and electrically coupled to at least one source of electricity, wherein each conductive pad is made of a second material, wherein matter disposed on the transparent member is removed via resistive heating when electricity is conducted from the at least one source through the at least one set of two conductive pads and the transparent member.

Abstract: A system and method for correcting oversaturated pixels in far-infrared (FIR) images captured by a shutterless FIR camera. The method includes identifying oversaturated pixels based on a pixel value analysis of an input image; creating an oversaturated pixel mask of the input image, where the oversaturated pixel mask includes the identified oversaturated pixels and excludes pixels not identified as oversaturated pixels; and correcting the oversaturated pixels of the current image using the oversaturated pixel mask, based on a scene-based nonuniformity correction (SBNC).

Abstract: A camera apparatus. The camera apparatus includes a housing having a front end and a back end; a lens, wherein the lens is disposed in the front end of the housing; and a thermal core, wherein the thermal core is disposed between the lens and the back end of the housing, the thermal core further including: an electrical component; at least one substrate electrically connected to the electrical component; and an infrared imager configured to capture an infrared video stream, wherein the infrared imager is affixed to one of the at least one substrate.

Abstract: A system and method for correcting nonuniformity in far-infrared (FIR) images captured by a shutterless FIR camera. The method includes determining a noise of a current image based on updating a noise estimate of a previous image with a noise estimate of a current image; determining a weight mask matrix of the current image, where the weight matrix includes high values corresponding to pixels of the current image in which noise estimation is facilitated, and low values corresponding to pixels of the current image in which noise estimation is inhibited; applying the weight mask matrix to the current image; and correcting the nonuniformity of the current image incrementally based on the determined noise of current image and the applied weight mask matrix.

Abstract: A system and method for correcting fixed pattern noise in far-infrared (FIR) images captured by a shutterless FIR camera. The method includes: determining a drift coefficient based on previously determined calibration values and high pass filter values applied to an input FIR image captured by the shutterless FIR camera; smoothing the drift coefficient based, in part, on previously computed drift coefficient values; and removing noise from the input image based on the smoothed drift coefficient value.

Abstract: A shutterless far-infrared (FIR) camera for advanced driver assistance systems, including at least one optical unit including at least one lens; an FIR sensor coupled to the optical unit and configured to capture FIR images; and an integrated circuit (IC) configured to process the captured FIR images to output an enhanced thermal video stream, wherein the IC further includes: a processing circuitry; and a memory containing instructions that, when executed by the processing circuitry, configure the processing circuitry to perform image corrections including at least a shutterless correction.