Abstract:
A system and method for monitoring vehicle traffic and collecting data indicative of pedestrian right of way violations by vehicles is provided. The system comprises memory and logic for monitoring traffic intersections and recording evidence indicating that vehicles have violated pedestrian right of way. Two sensor modalities collecting video data and radar data of the intersection under observation are employed in one embodiment of the system. The violation evidence can be accessed remotely by a traffic official for issuing of traffic citations.
Abstract:
A system for determining a new orientation and/or position of an object comprises a sky polarimeter configured to record image data of the sky, a signal processing unit, and logic configured to receive and store in memory the image data received from the sky polarimeter. The logic calculates the Stokes parameters (S0, S1, S2,), DoLP, and AoP from the image data, detects obscurants and filters the obscurants (such as clouds and trees) from the image data to produce a filtered image. The logic is further configured to find the Sun and zenith in the filtered image, and to determine the roll, pitch, yaw, latitude and longitude of the object using the filtered image. A method for determining a new position/orientation of an object comprises recording raw image data using a sky polarimeter, calculating S0, S1, S2, DoLP, and AoP from the image data, detecting obscurants and filtering the obscurants from the image data to produce a filtered image, obtaining last known position/orientation data of the object, finding the Sun and zenith in the filtered image, and determining the roll, pitch, yaw, latitude and longitude of the object using the filtered image.
Abstract:
A method for enhancing an image for facial recognition comprises capturing an image of the face with a polarizer and correcting the polarized image for non-uniformity. Stokes Parameters S0, S1, S2 are obtained by weighted subtraction of the polarized image to form Stokes images. DoLP is computed from the Stokes images, and facial recognition algorithms are applied to the DoLP image. A system for enhancing images for facial recognition comprises a polarimeter configured to record polarized image data of a subject's face, a signal processing unit and logic configured to receive and store in memory the image data from the polarimeter, calculate Stokes parameters from the image data, and compute a DoLP image from the Stokes parameters.
Abstract:
A method for detecting the presence of foreign fluids on surface comprises estimating an expected polarization response for a foreign fluid desired to be detected. Oil from an oil spill is one such foreign fluid. A polarimeter records raw image data of a surface (e.g., the surface of water) to obtain polarized images of the surface. IR and polarization data products are computed from the polarized images. The IR and polarization data products are converted to multi-dimensional data set to form multi-dimensional imagery. Contrast algorithms are applied to the multi-dimensional imagery to form enhanced contrast images, from which foreign fluids can be automatically detected.
Abstract:
In a method of determining the position of an object, raw image data of the sky is recorded using a celestial imaging unit. The last known position, orientation, date, and time data of the object are obtained, and the position of a celestial body is measured. A latitude and longitude of the object is determined by matching the measured celestial body position to the expected celestial body position based on the input parameters. A system for determining a new position of an object comprises a celestial imaging unit configured to record image data of the sky, a signal processing unit, and a signal processing unit configured to receive and store in memory the image data received from the celestial imaging unit. The signal processing unit filters the image to find the positions of celestial objects in the sky. The signal processing unit is further configured to use roll and pitch from an IMU, and date and time from a clock to determine the object's position (latitude and longitude).
Abstract:
A system and method for monitoring vehicle traffic and collecting data indicative of pedestrian right of way violations by vehicles is provided. The system comprises memory and logic for monitoring traffic intersections and recording evidence indicating that vehicles have violated pedestrian right of way. Two sensor modalities collecting video data and radar data of the intersection under observation are employed in one embodiment of the system. The violation evidence can be accessed remotely by a traffic official for issuing of traffic citations.
Abstract:
A method for detecting and tracking aerial objects and vehicles comprises recording raw image data using a polarimeter to obtain polarized images of the sky. The images are then corrected for non-uniformity, optical distortion, and registration. IR and polarization data products are computed, and the resultant data products are converted to a multi-dimensional data set for exploitation. Contrast enhancement algorithms are applied to the multi-dimensional imagery to form enhanced object images. The enhanced object images may then be displayed to a user, and/or an annunciator may announce the presence of an object.
Abstract:
A method using Infrared Imaging Polarimetry for detecting the presence of foreign fluids on water comprises estimating an expected polarization response for a foreign fluid desired to be detected. Oil from an oil spill is one such foreign fluid. An optimal position of a polarimeter to take images of the water's surface is determined from the expected polarization response. The polarimeter is positioned at the optimal position and records raw image data of the water's surface to obtain polarized images of the area. The polarized images are corrected, and IR and polarization data products are computed. The IR and polarization data products are converted to multi-dimensional data set to form multi-dimensional imagery. Contrast algorithms are applied to the multi-dimensional imagery to form enhanced contrast images, from which foreign fluids can be automatically detected.
Abstract:
A method using Long Wave Infrared Imaging Polarimetry for improved mapping and perception of a roadway or path and for perceiving or detecting obstacles comprises recording raw image data using a polarimeter to obtain polarized images of the roadway or area. The images are then corrected for non-uniformity, optical distortion, and registration. IR and polarization data products are computed, and the resultant data products are converted to a multi-dimensional data set for exploitation. Contrast enhancement algorithms are applied to the multi-dimensional imagery to form enhanced object images. The enhanced object images may then be displayed to a user, and/or an annunciator may announce the presence of an object. Further, the vehicle may take evasive action based upon the presence of an object in the roadway.
Abstract:
A method for enhancing an image for facial recognition comprises capturing an image of the face with a polarizer and correcting the polarized image for non-uniformity. Stokes Parameters S0, S1, S2 are obtained by weighted subtraction of the polarized image to form Stokes images. DoLP is computed from the Stokes images, and facial recognition algorithms are applied to the DoLP image. A system for enhancing images for facial recognition comprises a polarimeter configured to record polarized image data of a subject's face, a signal processing unit and logic configured to receive and store in memory the image data from the polarimeter, calculate Stokes parameters from the image data, and compute a DoLP image from the Stokes parameters.