Method and system for classification of an object in a point cloud data set
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.
1. A light detection and ranging (LIDAR) sensor system for a vehicle, comprising:
a sensor configured to:
transmit a transmit beam, the transmit beam having at least one of a frequency or a phase that is modulated over time;
receive a return beam from reflection or scattering of the transmit beam by an object; and
output a data signal comprising at least one point cloud data point representing the object; and
one or more processors configured to:
determine at least one feature variable based on the at least one point cloud data point;
determine a first classification statistic based on the at least one feature variable;
determine a second classification statistic based on the at least one feature variable; and
determine an object class corresponding to the object based on the first classification statistic and the second classification statistic.
2. The LIDAR sensor system of claim 1 , wherein the sensor comprises:
a laser source configured to output a carrier wave;
a modulator configured to modulate the carrier wave to provide the carrier wave as the transmit beam; and
one or more scanning optics configured to transmit the transmit beam.
3. The LIDAR sensor system of claim 2 , wherein the modulator is configured to modulate the at least one of the phase or the frequency by applying modulation to a current driving the laser source.
4. The LIDAR sensor system of claim 2 , wherein the modulator is an electro-optic modulator.
5. The LIDAR sensor system of claim 2 , wherein the modulator is an acoustic-optic modulator.
6. The LIDAR sensor system of claim 1 , wherein the transmit beam is a chirp signal.
7. The LIDAR sensor system of claim 1 , wherein the sensor is further configured to output the data signal as a three-dimensional (3D) point cloud comprising the at least one point cloud data point.
8. The LIDAR sensor system of claim 7 , wherein the sensor is configured to output the 3D point cloud for use as training data.
9. The LIDAR sensor system of claim 1 , wherein the one or more processors are configured to determine the object class from a predetermined number of object classes.
10. The LIDAR sensor system of claim 1 , wherein the one or more processors are configured to determine the object class from a vehicle class and a roadside structure class.
11. An autonomous vehicle control system, comprising:
one or more processors configured to:
receive a data signal comprising at least one point cloud data point representing an object;
determine at least one feature variable based on the at least one point cloud data point;
determine a first classification statistic based on the at least one feature variable;
determine a second classification statistic based on the at least one feature variable;
determine an object class corresponding to the object based on the first classification statistic and the second classification statistic; and
generate a control signal to control operation of an autonomous vehicle based on the determined object class.
12. The autonomous vehicle control system of claim 11 , wherein the data signal comprises a three-dimensional (3D) point cloud comprising the at least one point cloud data point.
13. The autonomous vehicle control system of claim 11 , wherein the one or more processors are configured to determine the object class from a predetermined number of object classes.
14. The autonomous vehicle control system of claim 11 , wherein the one or more processors are configured to determine the object class from a vehicle class and a roadside structure class.
15. A LIDAR sensor system for a vehicle, comprising:
a laser source configured to generate a carrier wave having at least one of a frequency or a phase that is modulated over time;
an optic configured to output the carrier wave as a transmit signal;
one or more detectors configured to detect a return signal from reflection or scattering of the transmit signal by an object; and
one or more processors configured to:
determine a 3D point cloud representative of the object based on the return signal;
determine at least one feature variable based on the 3D point cloud;
determine a first classification statistic based on the at least one feature variable;
determine a second classification statistic based on the at least one feature variable; and
determine an object class corresponding to the object based on the first classification statistic and the second classification statistic.
16. The LIDAR sensor system of claim 15 , further comprising a modulator configured to modulate the carrier wave to provide the carrier wave as the transmit beam.
17. The LIDAR sensor system of claim 16 , wherein the modulator is configured to modulate the at least one of the phase or the frequency by changing a current driving the laser source.
18. The LIDAR sensor system of claim 16 , wherein the modulator is an electro-optic modulator.
19. The LIDAR sensor system of claim 16 , wherein the modulator is an acoustic-optic modulator.
20. The LIDAR sensor system of claim 15 , wherein the one or more processors are configured to determine the object class from a vehicle class and a roadside structure class.