Vehicle radar control

1. A method for controlling a radar system of a vehicle, the radar system having a plurality of transmitters and a plurality of receivers, the method comprising the steps of:

transmitting, via the plurality of transmitters, a first plurality of radar signals from the vehicle;

receiving, via the plurality of receivers, a second plurality of radar signals pertaining to an object that is in proximity to a roadway on which the vehicle is travelling, the second plurality of radar signals directed from the object after the first plurality of radar signals contact the object;

determining, via a processor, a location of the object with respect to the vehicle based on the second plurality of radar signals;

determining, via the processor, an azimuth angle for the object with respect to the vehicle based on the second plurality of radar signals;

determining, via the processor, an elevation angle for the object with respect to the vehicle based on the second plurality of radar signals;

determining, via the processor, a range for the object with respect to the vehicle based on the second plurality of radar signals;

generating, via the processor, a plurality of feature vectors based on the second plurality of radar signals, the location, the azimuth angle, the elevation angle, and the range;

generating, via the processor, a three dimensional representation of the object using the plurality of feature vectors via association of the second plurality of radar signals to a three dimensional array, the three dimensional representation comprising a union of the plurality of feature vectors over the three dimensional array, wherein the three dimensional array is constructed such that the three dimensional array has a first dimension based on the azimuth angle, a second dimension based on the elevation angle, a third dimension based on the range, and a center that is based on the location of the object;

extracting features from the second plurality of radar signals using the three dimensional representation of the object; and

classifying, via the processor, the object based on the feature extraction.

2. The method of claim 1 , further comprising:

classifying the object based upon the three dimensional representation and a learned dictionary model.

3. The method of claim 1 , further comprising:

classifying the object based upon the three dimensional representation and a circular regression model.

4. A radar control system for a vehicle, the radar control system comprising:

one or more transmitters configured to transmit transmitted radar signals from the vehicle;

a plurality of receivers configured to receive return radar signals after the transmitted radar signals are deflected from an object proximate the vehicle; and

a processor coupled to the plurality of receiver and configured to:

determine a location of the object with respect to the vehicle based on the return radar signals;

determine an azimuth angle for the object with respect to the vehicle based on the return radar signals;

determine an elevation angle for the object with respect to the vehicle based on the return radar signals;

determine a range for the object with respect to the vehicle based on the return radar signals;

generate a plurality of feature vectors based on the return radar signals, the location, the azimuth angle, the elevation angle, and the range;

generate a three dimensional representation of the object using the plurality of feature vectors via association of the return radar signals to a three dimensional array, the three dimensional representation comprising a union of the plurality of feature vectors over the three dimensional array, wherein the three dimensional array is constructed such that the three dimensional array has a first dimension based on the azimuth angle, a second dimension based on the elevation angle, a third dimension based on the range, and a center that is based on the location of the object;

extract features from the return radar signals using the three dimensional representation of the object; and

classify the object based on the compressive sensing feature extraction.

5. The radar control system of claim 4 , wherein the processor is further configured to classify the object based upon the three dimensional representation and a learned dictionary model.

6. The radar control system of claim 4 , wherein the processor is further configured to classify the object based upon the three dimensional representation and a circular regression model.

7. A computer system for a radar system of a vehicle, the radar system having a plurality of transmitters and a plurality of receivers, the computer system comprising:

a non-transitory, computer readable storage medium storing a program, the program configured to:

transmit, via the plurality of transmitters, a first plurality of radar signals from the vehicle;

receive, via the plurality of receivers, a second plurality of radar signals pertaining to an object that is in proximity to a roadway on which the vehicle is travelling, the second plurality of radar signals directed from the object after the first plurality of radar signals contact the object;

determine a location of the object with respect to the vehicle based on the second plurality of radar signals;

determine an azimuth angle for the object with respect to the vehicle based on the second plurality of radar signals;

determine an elevation angle for the object with respect to the vehicle based on the second plurality of radar signals;

determine a range for the object with respect to the vehicle based on the second plurality of radar signals;

generate a plurality of feature vectors based on the second plurality of radar signals, the location, the azimuth angle, the elevation angle, and the range;

generate a three dimensional representation of the object using the plurality of feature vectors via association of the second plurality of radar signals to a three dimensional array, the three dimensional representation comprising a union of the plurality of feature vectors over the three dimensional array, wherein the three dimensional array is constructed such that the three dimensional array has a first dimension based on the azimuth angle, a second dimension based on the elevation angle, a third dimension based on the range, and a center that is based on the location of the object;

extract features from the second plurality of radar signals using the three dimensional representation of the object; and

classify the object based on the compressive sensing feature extraction.

8. The computer system of claim 7 , wherein the program is further configured to classify the object based upon the three dimensional representation and a learned dictionary model.

9. The computer system of claim 7 , wherein the program is further configured to classify the object based upon the three dimensional representation and a circular regression model.

10. The method of claim 1 , wherein the step of extracting the features comprises extracting the features from the second plurality of radar signals using the three dimensional representation of the object by performing, via the processor, compressive sensing feature extraction.

11. The method of claim 1 , wherein:

the step of extracting the features comprises extracting the features utilizing a radar signal decomposition dictionary in which radar signals are expressed in a compacted manner, utilizing smart feature extraction.

12. The method of claim 1 , wherein:

the step of extracting the features comprises extracting the features utilizing a signal processing technique for acquiring and reconstructing radar signals by finding solutions to undetermined linear systems.

13. The method of claim 11 , wherein

the step of extracting the features comprises extracting the features utilizing the signal processing technique for acquiring and reconstructing radar signals by finding the solutions to undetermined linear systems using a least squares mathematical technique.

14. The method of claim 1 , wherein the step of classifying the object comprises:

performing a training stage prior to a current vehicle ignition cycle, during which a dictionary is built per object class category;

storing the dictionary in a memory; and

classifying the object during the current ignition cycle based on a comparison of results of the feature extraction with the dictionary.

15. The method of claim 14 , further comprising:

merging each class dictionary for each class together, generating a merged dictionary;

subsequently, decomposing each signal into the merged dictionary;

building energy signatures using components of the energy signatures that comprise a sum of absolute decomposition coefficients per each class, the energy signatures included in the merged dictionary;

storing the merged dictionary in the memory; and

classifying the object during the current ignition cycle based on a comparison of results of the feature extraction with the merged dictionary.

16. The method of claim 14 , further comprising:

utilizing dictionary learning for the dictionary based on a temporal gradient that captures a Doppler frequency shift with respect to the second plurality of radar signals that are deflected from the object.

17. The method of claim 16 , wherein a time interval for the Doppler frequency shift is proportional to relative changes in the object's position with respect to the vehicle.

18. The method of claim 14 , further comprising:

reducing a data dimensionality of possible directions of motion for the object, using the dictionary.

19. The method of claim 18 , further comprising:

estimating a direction of motion for the object in two stages, namely:

a first phase, in which a plurality of dictionaries are generated using training data, prior to the current ignition cycle; and

a second phase, in which radar measurements of the second plurality of radar signals that are dependent upon the direction of motion of the object are decomposed, using the plurality of dictionaries.

20. The method of claim 19 , wherein:

in the first phase, the plurality of dictionaries are generated using a training data set that includes radar echoes received from spatial cells of interest when observing the object moving in particular directions, along with an additive noise vector that models additive noise, and utilizing Micro-Doppler signatures for different objects, and wherein each measurement is represented as a combination of selected basic directions of motion of the object, while corresponding decomposition coefficients are used as features for inclusion in the dictionary; and

in the second phase, a classification is generated for the object using the three dimensional representation, including Micro-Doppler signatures thereof, in comparison with the plurality of dictionaries.