Abstract: A method of detecting occupants in a vehicle includes detecting an oncoming vehicle and acquiring a plurality of images of occupants in the vehicle in response to detection of the vehicle. The method includes performing automated facial detection on the plurality of images and adding a facial image for each face detected to a gallery of facial images for the occupants of the vehicle. The method includes performing automated facial recognition on the gallery of facial images to group the facial images into groups based on which occupant is in the respective facial images, and counting the final group of unique facial images to determine how many occupants are in the vehicle.

Abstract: A system includes a camera defining an optical axis and a field of view defined about the optical axis. An illuminator is mounted offset from the optical axis and directed to illuminate at least a portion of the field of view, wherein the illuminator is operatively connected to the camera to provide illumination during an image capturing exposure of the camera. An image processer is operatively connected to the camera and includes machine readable instructions configured to receive image data representative of an image captured with the camera, perform facial detection to detect at least one face in the image, perform license plate detection to detect at least one license plate in the image, and to provide a vehicle overview image.

Abstract: A method for facial analytics includes capturing a series of images of individuals from a camera into a circular buffer and selecting a plurality of images from the buffer for analysis in response to a trigger event, wherein the plurality of images are chronologically proximate before and/or after the trigger event in time. The method includes analyzing the plurality of images to determine image quality and selecting one of the plurality of images based on image quality to form a cropped facial image most likely to result in positive facial recognition matching. Methods of signaling to control the pedestrian traffic flow can maximize the individuals' facial alignment to the capturing camera's field of view. Non-relevant facial images associated with individuals outside a given region of interest can be discarded. Facial recognition is run on the resultant cropped facial image. Output can be displayed with information from the facial recognition.

Abstract: A system includes a camera defining an optical axis and a field of view defined about the optical axis. An illuminator is mounted offset from the optical axis and directed to illuminate at least a portion of the field of view, wherein the illuminator is operatively connected to the camera to provide illumination during an image capturing exposure of the camera. An image processer is operatively connected to the camera and includes machine readable instructions configured to receive image data representative of an image captured with the camera, perform facial detection to detect at least one face in the image, perform license plate detection to detect at least one license plate in the image, and to provide a vehicle overview image.

Abstract: A method of navigating an autonomous vehicle includes receiving pulsed illumination from an object in the vehicle environment and decoding the pulsed illumination. The object is identified using the decoded pulsed illumination of the pulsed illumination, and the autonomous vehicle navigated through the vehicle environment based on the identification of the object. Obstacle avoidance methods and navigation systems for autonomous vehicles are also described.

Abstract: A system includes a camera defining an optical axis and a field of view defined about the optical axis. An illuminator is mounted offset from the optical axis and directed to illuminate at least a portion of the field of view, wherein the illuminator is operatively connected to the camera to provide illumination during an image capturing exposure of the camera. An image processer is operatively connected to the camera and includes machine readable instructions configured to receive image data representative of an image captured with the camera, perform facial detection to detect at least one face in the image, perform license plate detection to detect at least one license plate in the image, and to provide a vehicle overview image.

Abstract: A method for facial analytics includes capturing a series of images of individuals from a camera into a circular buffer and selecting a plurality of images from the buffer for analysis in response to a trigger event, wherein the plurality of images are chronologically proximate before and/or after the trigger event in time. The method includes analyzing the plurality of images to determine image quality and selecting one of the plurality of images based on image quality to form a cropped facial image most likely to result in positive facial recognition matching. Methods of signaling to control the pedestrian traffic flow can maximize the individuals' facial alignment to the capturing camera's field of view. Non-relevant facial images associated with individuals outside a given region of interest can be discarded. Facial recognition is run on the resultant cropped facial image. Output can be displayed with information from the facial recognition.

Abstract: A method for facial analytics includes capturing a series of images of individuals from a camera into a circular buffer and selecting a plurality of images from the buffer for analysis in response to a trigger event, wherein the plurality of images are chronologically proximate before and/or after the trigger event in time. The method includes analyzing the plurality of images to determine image quality and selecting one of the plurality of images based on image quality to form a cropped facial image most likely to result in positive facial recognition matching. Methods of signaling to control the pedestrian traffic flow can maximize the individuals' facial alignment to the capturing camera's field of view. Non-relevant facial images associated with individuals outside a given region of interest can be discarded. Facial recognition is run on the resultant cropped facial image. Output can be displayed with information from the facial recognition.

Abstract: A method for facial analytics includes capturing a series of images of individuals from a camera into a circular buffer and selecting a plurality of images from the buffer for analysis in response to a trigger event, wherein the plurality of images are chronologically proximate before and/or after the trigger event in time. The method includes analyzing the plurality of images to determine image quality and selecting one of the plurality of images based on image quality to form a cropped facial image most likely to result in positive facial recognition matching. Methods of signaling to control the pedestrian traffic flow can maximize the individuals' facial alignment to the capturing camera's field of view. Non-relevant facial images associated with individuals outside a given region of interest can be discarded. Facial recognition is run on the resultant cropped facial image. Output can be displayed with information from the facial recognition.

Abstract: A method of enhancing an image includes constructing an input histogram corresponding to an input image received at a focal plane array, the input histogram representing a pixel intensity distribution corresponding to the input image and performing an analytical operation on the input histogram to produce a modified cumulative distribution, wherein the analytical operation is a function of camera temperature. The input image is transformed using the modified cumulative distribution to produce an enhanced output image corresponding to the input image, wherein at least a portion of the input image is enhanced in the output image. In addition to or in lieu of the non-linear operation, the binning edges of the input histogram can be adjusted based on at least one of camera temperature and sensitivity state to construct an adjusted cumulative distribution.

Abstract: A method of detecting occupants in a vehicle includes detecting an oncoming vehicle and acquiring a plurality of images of occupants in the vehicle in response to detection of the vehicle. The method includes performing automated facial detection on the plurality of images and adding a facial image for each face detected to a gallery of facial images for the occupants of the vehicle. The method includes performing automated facial recognition on the gallery of facial images to group the facial images into groups based on which occupant is in the respective facial images, and counting the final group of unique facial images to determine how many occupants are in the vehicle.

Abstract: A method of controlling FPA system stabilization includes calculating FPA adjustments as a function of FPA temperature and adjusting a TEC set point to assist the FPA adjustments in attaining a predetermined level of FPA performance. Adjusting the TEC set point can include adjusting the TEC set point as a function of at least one of ambient temperature, FPA temperature, or disparity between the predetermined level of FPA performance and a level of FPA performance obtainable by calculating the FPA adjustments as a function of FPA temperature alone without adjusting the TEC set point.

Abstract: A laser designator pulse detector includes an InGaAs photodetector configured to convert laser signals into electrical signals. A Read Out Integrated Circuit (ROIC) is operatively connected to the InGaAs photodetector to condition electrical signals from the InGaAs photodetector. The ROIC can be operatively connected to a peripheral device including one or more modules configured to process signals from the ROIC and provide pulse detection, decoding, and tracking. In another aspect, a laser designator pulse detector includes a two-dimensional array of photodetectors configured to convert laser signals into electrical signals. A ROTC as described above is operatively connected to the two-dimensional array of photodetectors.

Abstract: An imaging method includes receiving electromagnetic radiation at a focal plane array of a handheld device. The electromagnetic radiation is processed within the handheld device, and visible images are displayed on the handheld device. The displayed visible images are indicative of a scene, and include a designator and a designator identifier when a high frequency laser pulse is in the scene. The designator and designator identifier represent the high frequency pulsed electromagnetic radiation received by the focal plane array when a high frequency pulse is present in the scene.

Abstract: A pulse repetition frequency detector, tracker, and decoder includes a two-dimensional InGaAs FPA of photodetectors configured to convert laser signals into electrical signals. A ROIC is operatively connected to the InGaAs FPA to condition electrical signals from the InGaAs FPA. A module is operatively connected to the ROIC to decode pulsed codes in the conditioned electrical signals and to provide output for tracking decoded laser spots in two-dimensional space. In another aspect, an imaging device includes an imager with an imaging FPA operatively connected to a first ROIC for imaging. A pulse repetition frequency detector, tracker, and decoder including a second ROIC as described above, is operatively connected to the first ROIC. The first and second ROICs are operatively connected to correlate the position of decoded laser spots in images from the imaging FPA.

Abstract: A method of identifying at least one target includes receiving a series of images over time of pulsed energy reflected from the at least one target, each image including a plurality of pulses related to different first and second pulse codes, detecting the pulses in an image of the received images, and outputting pulse detection information including XY coordinates and arrival time information associated with the respective detected pulses. The method further includes associating the pulse detection information with the first and second pulse codes based on the arrival time information, and generating output position information for the at least one target in space that indicates output positions for the at least one target based on the XY coordinates and being associated with the corresponding first and second pulse codes.

Abstract: A method of threat detection includes illuminating a scene with short-wavelength infrared (SWIR) illumination and receiving a return of the SWIR illumination reflected back from the scene. The method includes analyzing the return of the SWIR illumination to detect presence of man-made optics in the scene. Illuminating, receiving, and analyzing can be performed by a device, e.g., a rifle-mounted laser device.

Abstract: A method of navigating an autonomous vehicle includes receiving pulsed illumination from an object in the vehicle environment and decoding the pulsed illumination. The object is identified using the decoded pulsed illumination of the pulsed illumination, and the autonomous vehicle navigated through the vehicle environment based on the identification of the object. Obstacle avoidance methods and navigation systems for autonomous vehicles are also described.

Abstract: A method of enhancing an image includes constructing an input histogram corresponding to an input image received at a focal plane array, the input histogram representing a pixel intensity distribution corresponding to the input image and performing an analytical operation on the input histogram to produce a modified cumulative distribution, wherein the analytical operation is a function of camera temperature. The input image is transformed using the modified cumulative distribution to produce an enhanced output image corresponding to the input image, wherein at least a portion of the input image is enhanced in the output image. In addition to or in lieu of the non-linear operation, the binning edges of the input histogram can be adjusted based on at least one of camera temperature and sensitivity state to construct an adjusted cumulative distribution.

Abstract: A method of threat detection includes illuminating a scene with short-wavelength infrared (SWIR) illumination and receiving a return of the SWIR illumination reflected back from the scene. The method includes analyzing the return of the SWIR illumination to detect presence of man-made optics in the scene. Illuminating, receiving, and analyzing can be performed by a device, e.g., a rifle-mounted laser device.