Abstract: A method for classifying an object in a point cloud includes computing first and second classification statistics for one or more points in the point cloud. Closest matches are determined between the first and second classification statistics and a respective one of a set of first and second classification statistics corresponding to a set of N classes of a respective first and second classifier, to estimate the object is in a respective first and second class. If the first class does not correspond to the second class, a closest fit is performed between the point cloud and model point clouds for only the first and second classes of a third classifier. The object is assigned to the first or second class, based on the closest fit within near real time of receiving the 3D point cloud. A device is operated based on the assigned object class.

Abstract: A method for classifying an object in a point cloud includes computing first and second classification statistics for one or more points in the point cloud. Closest matches are determined between the first and second classification statistics and a respective one of a set of first and second classification statistics corresponding to a set of N classes of a respective first and second classifier, to estimate the object is in a respective first and second class. If the first class does not correspond to the second class, a closest fit is performed between the point cloud and model point clouds for only the first and second classes of a third classifier. The object is assigned to the first or second class, based on the closest fit within near real time of receiving the 3D point cloud. A device is operated based on the assigned object class.

Abstract: A method for classifying an object in a point cloud includes computing first and second classification statistics for one or more points in the point cloud. Closest matches are determined between the first and second classification statistics and a respective one of a set of first and second classification statistics corresponding to a set of N classes of a respective first and second classifier, to estimate the object is in a respective first and second class. If the first class does not correspond to the second class, a closest fit is performed between the point cloud and model point clouds for only the first and second classes of a third classifier. The object is assigned to the first or second class, based on the closest fit within near real time of receiving the 3D point cloud. A device is operated based on the assigned object class.

Abstract: A method for classifying an object in a point cloud includes computing first and second classification statistics for one or more points in the point cloud. Closest matches are determined between the first and second classification statistics and a respective one of a set of first and second classification statistics corresponding to a set of N classes of a respective first and second classifier, to estimate the object is in a respective first and second class. If the first class does not correspond to the second class, a closest fit is performed between the point cloud and model point clouds for only the first and second classes of a third classifier. The object is assigned to the first or second class, based on the closest fit within near real time of receiving the 3D point cloud. A device is operated based on the assigned object class.

Abstract: A method for classifying an object in a point cloud includes computing first and second classification statistics for one or more points in the point cloud. Closest matches are determined between the first and second classification statistics and a respective one of a set of first and second classification statistics corresponding to a set of N classes of a respective first and second classifier, to estimate the object is in a respective first and second class. If the first class does not correspond to the second class, a closest fit is performed between the point cloud and model point clouds for only the first and second classes of a third classifier. The object is assigned to the first or second class, based on the closest fit within near real time of receiving the 3D point cloud. A device is operated based on the assigned object class.

Abstract: A method and apparatus are described including a laser with a plurality of internal or external actuators for affecting an optical frequency of light output by the laser, wherein the plurality of actuators have a corresponding plurality of different frequency response bands for changing optical properties of the laser and a corresponding plurality of actuation ranges of optical frequencies affected. Also included is an optical detector, and a plurality of optical paths configured to direct light output by the laser onto the detector. A laser controller is configured to provide a plurality of inputs to the plurality of actuators based on a detector signal output from the optical detector and the corresponding frequency response bands and actuation ranges.

Abstract: A method and apparatus are described including a laser with a plurality of internal or external actuators for affecting an optical frequency of light output by the laser, wherein the plurality of actuators have a corresponding plurality of different frequency response bands for changing optical properties of the laser and a corresponding plurality of actuation ranges of optical frequencies affected. Also included is an optical detector, and a plurality of optical paths configured to direct light output by the laser onto the detector. A laser controller is configured to provide a plurality of inputs to the plurality of actuators based on a detector signal output from the optical detector and the corresponding frequency response bands and actuation ranges.

Abstract: A method, apparatus and computer-readable storage medium are described for a tunable laser source that produces a desired frequency modulated optical waveform with a precision within 0.01 percent over a bandwidth greater than about 50 gigaHertz. An apparatus includes a tunable laser having one or more drive inputs for affecting an optical frequency of light output by the laser; and an optical detector. Multiple optical paths are configured to direct light output by the laser onto the optical detector. A laser controller is configured to provide to a drive input a loopback signal based on a measured or predetermined difference in optical dispersion among the plurality of optical paths and a detector signal output from the optical detector. In some embodiments, a ranging device includes the tunable laser source.

Abstract: A method, apparatus and computer-readable storage medium are described for a tunable laser source that produces a desired frequency modulated optical waveform with a precision within 0.01 percent over a bandwidth greater than about 50 gigaHertz. An apparatus includes a tunable laser having one or more drive inputs for affecting an optical frequency of light output by the laser; and an optical detector. Multiple optical paths are configured to direct light output by the laser onto the optical detector. A laser controller is configured to provide to a drive input a loopback signal based on a measured or predetermined difference in optical dispersion among the plurality of optical paths and a detector signal output from the optical detector. In some embodiments, a ranging device includes the tunable laser source.