Character recognition in air-writing based on network of radars

1. A method for air-writing character recognition, the method comprising:

determining a position of an object in a monitoring space using trilateration by using a plurality of millimeter-wave radars, wherein each millimeter-wave radar of the plurality of millimeter-wave radars has a field of view, and wherein an intersection of the fields of view of the plurality of millimeter-wave radars forms the monitoring space;

tracking the position of the object in the monitoring space over time using the plurality of millimeter-wave radars;

determining a character symbol depicted by the tracked position of the object over time using a neural network (NN); and

providing a signal based on the determined character symbol.

2. The method of claim 1 , wherein determining the character symbol is based on the tracked position of the object over a predetermined fixed time.

3. The method of claim 1 , wherein determining the character symbol is based on the tracked position of the object over a bounded time.

4. The method of claim 3 , further comprising determining the bounded time based on detecting when the object enters and exits the monitoring space.

5. The method of claim 1 , wherein the NN comprises a recurrent NN (RNN).

6. The method of claim 5 , wherein the RNN comprises a long-short term memory (LSTM) network.

7. The method of claim 6 , further comprising:

receiving an unsegmented stream of locations of the object over time; and

using a connectionist temporal classification (CTC) to generate a sequence of character symbols based on the unsegmented stream of locations.

8. The method of claim 1 , wherein the NN comprises a convolutional NN (CNN).

9. The method of claim 1 , wherein the character symbol comprises a number or a Latin character.

10. The method of claim 1 , wherein tracking the position of the object comprises:

determining a trajectory of the object based on multiple determinations of the position of the object over time; and

using a smoothening filter to smooth the determined trajectory.

11. The method of claim 10 , wherein the smoothening filter comprises a Kalman filter.

12. The method of claim 1 , wherein the object comprises a hand of a human.

13. The method of claim 1 , wherein the object comprises a finger of a human.

14. The method of claim 1 , wherein the object comprises a metallic object.

15. The method of claim 1 , wherein three millimeter-wave radars of the plurality of millimeter-wave radars are not situated in a straight line.

16. The method of claim 1 , wherein the monitoring space is located at a distance between 0.3 m and 0.6 m from each millimeter-wave radar of the plurality of millimeter-wave radars.

17. The method of claim 1 , further comprising:

transmitting a chirp towards the monitoring space;

receiving an echo of the chirp from the monitoring space;

generating a beat signal based on the echo of the chirp;

determining a beat frequency based on the beat signal;

determining a first range based on the beat frequency;

determining a beat signal phase based on the first range;

generating a demodulated beat signal based on the determined beat frequency and the determined beat signal phase;

determining a demodulated beat phase based on the demodulated beat signal;

determining a demodulated beat range based on the demodulated beat phase;

determining a fine range estimate based on the demodulated beat range; and

determining the position of the object based on the fine range estimate.

18. An air-writing character recognition system comprising:

a plurality of millimeter-wave radars, wherein each millimeter-wave radar of the plurality of millimeter-wave radars is configured to have a field of view, and wherein an intersection of the fields of view of the plurality of millimeter-wave radars forms a monitoring space; and

a controller configured to:

determine a position of an object in the monitoring space based on outputs of the plurality of millimeter-wave radars by using trilateration,

track the position of the object in the monitoring space over time based on the determined position using the plurality of millimeter-wave radars,

determine a character symbol depicted by the tracked position of the object over time using a neural network (NN), and

provide a signal based on the determined character symbol.

19. The air-writing character recognition system of claim 18 , wherein determining the character symbol is based on the tracked position of the object over a bounded time.

20. The air-writing character recognition system of claim 19 , wherein the controller is further configured to:

generate an unsegmented stream of locations of the object over time; and

use a connectionist temporal classification (CTC) to generate a sequence of character symbols based on the unsegmented stream of locations.

21. The air-writing character recognition system of claim 19 , wherein the controller is configured to track the position of the object by using a Kalman filter.

22. The air-writing character recognition system of claim 19 , wherein the NN comprises a long-short term memory (LSTM) network.

23. A millimeter-wave radar system comprising:

three millimeter-wave radars, each of the three millimeter-wave radars configured to have a field of view, wherein an intersection of the fields of view of each of the three millimeter-wave radars forms a monitoring space; and

a controller configured to:

determine a position of an object in the monitoring space based on output of the three millimeter-wave radars by using trilateration,

determine a trajectory of the object over time based on the determined position of the object,

apply a filter to the determined trajectory to generate a filtered trajectory,

determine a character symbol depicted by the filtered trajectory using a long-short term memory (LSTM), and

provide a signal based on the determined character symbol.