Method and system for spatial modeling of an interior of a vehicle

Patent metadata

Field	Value
Publication number	US-10422874-B2
Application number	US-201815952855-A
Country	US
Kind code	B2
Filing date	Apr 13, 2018
Priority date	Apr 20, 2017
Publication date	Sep 24, 2019
Grant date	Sep 24, 2019

Abstract

A method is described for spatial modelling of an interior of a vehicle. The method includes transmitting a wireless signal, from each of multiple transmitters, each transmitter having a known location in the vehicle, receiving, by multiple receivers, multiple reflection signals having been reflected in the interior of the vehicle, each receiver having a known location in the vehicle. The method also includes, for the received reflection signals, determining a source data set by determining multipath propagation components, Doppler shifts, phase shifts and time differences of the received reflection signals, and determining a spatial model of at least a portion of the vehicle interior by applying a computer vision algorithm on the source data set. A system is also described for performing the method.

First claim

What is claimed is:

1. A method for spatial modelling of an interior of a vehicle, the method comprising:
transmitting a wireless signal from each of a plurality of transmitters, each transmitter having a known location in the vehicle;
receiving, by a plurality of receivers, a plurality of reflection signals having been reflected in the interior of the vehicle, each receiver having a known location in the vehicle;
for the received reflection signals, determining a source data set by determining multipath propagation components, Doppler shifts, phase shifts and time differences of the received reflection signals, wherein the source data set comprises the determined multipath propagation components, Doppler shifts, phase shifts, and time differences of the received reflection signals; and
determining a spatial model of at least a portion of the vehicle interior by applying a computer vision algorithm on the source data set.

2. The method according to claim 1 wherein applying the computer vision algorithm comprises performing generalized cross correlation with phase transform, GCC-PHAT.

3. The method according to claim 1 further comprising explicitly tracking the multi-path components.

4. The method according to claim 1 further comprising identifying and categorizing objects in the vehicle.

5. The method according to claim 1 wherein applying a computer vision algorithm comprises employing a neural network for analyzing the source data set.

6. The method according to claim 5 further comprising identifying locations of vehicle occupants.

7. The method according to claim 1 wherein the transmitted signals are audio signals having a frequency in the range of 20-30 kHz or in the range of 40-50 kHz.

8. The method according to claim 1 wherein the transmitted signals are radio signals having a frequency of 2.5 GHz or 5 GHz.

9. The method according to claim 1 wherein transmitting a wireless signal comprises transmitting a plurality of separate signals having different properties.

10. The method according to claim 1 wherein the transmitters comprise speakers of a vehicle entertainment system.

11. The method according to claim 1 further comprising determining a temperature and airflow properties in the vehicle, and wherein the spatial model is determined based on the determined temperature and airflow properties.

12. The method according to claim 1 further comprising identifying an object by comparing the determined spatial model with a predetermined spatial model of an empty vehicle.

13. A system for spatial modelling of an interior of a vehicle, the system comprising:
a plurality of transmitters for arrangement at known locations within the vehicle, each transmitter configured to transmit a wireless signal;
a plurality of receivers for arrangement at known locations within the vehicle, each receiver configured to receive a plurality of reflection signals reflected in the interior of the vehicle;
a spatial modelling control unit connectable to the transmitters and the receivers and configured to (i) for the received reflection signals, determine a source data set by determining multipath propagation components, Doppler shifts, phase shifts and time differences of the received reflection signals, wherein the source data set comprises the determined multipath propagation components, Doppler shifts, phase shifts, and time differences of the received reflection signals, and (ii) determine a spatial model of at least a portion of the vehicle interior by applying a computer vision algorithm on the source data set.

14. The system according to claim 13 wherein the transmitters comprise speakers of an entertainment system of the vehicle or ultrasonic transmitters.

15. The system according to claim 13 wherein the transmitters comprise a WiFi transmitter and receiver of the vehicle.

Assignees

• Volvo Car Corp

Inventors

• Fekete Robert

Classifications

• G01S13/87

  Combinations of radar systems, e.g. primary radar and secondary radar · CPC title

• G01S13/56

  for presence detection {(presence detection using near field arrangements G01V3/00, e.g. G01V3/08, G01V3/12; burglar, theft or intruder alarms with electrical actuation G08B13/22 - G08B13/26)} · CPC title

• G01S15/87

  Combinations of sonar systems · CPC title

• G06T17/00

  Three-dimensional [3D] modelling for computer graphics · CPC title

• G06N3/02

  Neural networks · CPC title