Object tracking using sensor fusion within a probabilistic framework

Patent metadata

Field	Value
Publication number	US-10160448-B2
Application number	US-201615346210-A
Country	US
Kind code	B2
Filing date	Nov 8, 2016
Priority date	Nov 8, 2016
Publication date	Dec 25, 2018
Grant date	Dec 25, 2018

Abstract

A controller receives outputs form a plurality of sensors such as a camera, LIDAR sensor, RADAR sensor, and ultrasound sensor. Sensor outputs corresponding to an object are assigned to a tracklet. Subsequent outputs by any of the sensors corresponding to that object are also assigned to the tracklet. A trajectory of the object is calculated from the sensor outputs assigned to the tracklet, such as by means of Kalman filtering. For each sensor output assigned to the tracklet, a probability is updated, such as using a Bayesian probability update. When the probability meets a threshold condition, the object is determined to be present and an alert is generated or autonomous obstacle avoidance is performed with respect to an expected location of the object.

First claim

The invention claimed is:

1. A method comprising performing, by a vehicle controller:
providing a plurality of sensors in data communication with the vehicle controller;
receiving, from the plurality of sensors, a plurality of sensor outputs;
detecting a first feature in a first output of the plurality of outputs received from a first sensor of the plurality of sensors;
creating a tracklet corresponding to the first feature, the tracklet having a location and a trajectory determined according to the first output;
detecting a second feature in a second output of the plurality of outputs received from a second sensor of the plurality of sensors;
(a) determining that a second location of the second feature determined according to the second output corresponds to the location and the trajectory of the tracklet;
in response to (a) updating the location and the trajectory of the tracklet according to the second output and increasing a probability associated with the tracklet according to the second output;
detecting a third feature in a third output of the plurality of outputs received from the first sensor of the plurality of sensors after receiving the first output from the first sensor;
(b) determining that a third location of the third feature determined according to the third output corresponds to the location and the trajectory of the tracklet;
in response to (b) updating the location and the trajectory of the tracklet according to the third output and increasing the probability associated with the tracklet according to the third output;
determining that the probability is sufficiently high to perform collision avoidance with respect to the tracklet; and
actuating at least one of a steering actuator, an accelerator actuator, and a brake actuator effective to avoid the object in response to determining that the probability is sufficiently high to perform collision avoidance with respect to the tracklet.

2. The method of claim 1 , wherein the plurality of different sensing modalities include at least two of a two-dimensional camera image, radio distancing and ranging (RADAR), light distancing and ranging (LIDAR), and ultrasound.

3. The method of claim 1 , further comprising determining the trajectory for the tracklet by performing Kalman filtering with respect to the first feature, second feature, and third feature.

4. The method of claim 1 , wherein increasing the probability associated with the tracklet comprises performing a Bayesian probability update for the first feature, the second feature, and the third feature.

5. The method of claim 1 , further comprising:
creating the tracklet in response to detecting a minimum number of contiguous sensor outputs of the plurality of sensor outputs indicating presence of an object.

6. The method of claim 1 , further comprising:
creating the tracklet in response to both of (a) detecting a minimum number of contiguous sensor outputs of the plurality of sensor outputs indicating presence of an object and (b) the minimum number of contiguous sensor outputs indicating movement of the object that is consistent with expected object behavior.

7. A system comprising:
a plurality of sensors having a plurality of sensing modalities;
a vehicle controller operably coupled to the plurality of sensors, the vehicle controller programmed to—
receive, from the plurality of sensors, a plurality of sensor outputs;
detect a first feature in a first output of the plurality of outputs received from a first sensor of the plurality of sensors;
create a tracklet corresponding to the first feature, the tracklet having a location and a trajectory determined according to the first output;
detect a second feature in a second output of the plurality of outputs received from a second sensor of the plurality of sensors;
if (a) a second location of the second feature determined according to the second output corresponds to the location and the trajectory of the tracklet, update the location and the trajectory of the tracklet according to the second output and increase a probability associated with the tracklet according to the second output;
detect a third feature in a third output of the plurality of outputs received from the first sensor of the plurality of sensors after receiving the first output from the first sensor;
if (b) a third location of the third feature determined according to the third output corresponds to the location and the trajectory of the tracklet, update the location and the trajectory of the tracklet according to the third output and increase the probability associated with the tracklet according to the third output;
and
if the probability associated with the tracklet meets a threshold condition, determine that an object is present.

8. The system of claim 7 , wherein the plurality of sensors include at least two of a two-dimensional camera, a radio distancing and ranging (RADAR) sensor, a light distancing and ranging (LIDAR) sensor, and an ultrasonic sensor.

9. The system of claim 7 , wherein the vehicle controller is further programmed to determine the trajectory for the tracklet by performing Kalman filtering with respect to features assigned to the tracklet.

10. The system of claim 7 , wherein the vehicle controller is further programmed to update the probability by performing a Bayesian probability update for the first feature, the second feature, and the third feature assigned to the tracklet.

11. The system of claim 7 , wherein the vehicle controller is further programmed to create the tracklet in response to detecting a minimum number of contiguous sensor outputs of the plurality of sensor outputs indicating presence of an object.

12. The system of claim 7 , wherein the vehicle controller is further programmed to create the tracklet in response to both of (a) detecting a minimum number of contiguous sensor outputs of the plurality of sensor outputs indicating presence of the object and (b) the minimum number of contiguous sensor outputs indicating movement of the object that is consistent with expected object behavior.

13. The system of claim 7 , wherein the vehicle controller is further programmed to, if the probability meets the threshold condition, actuate at least one of a steering actuator, an accelerator actuator, and a brake actuator effective to avoid the object.

Assignees

• Ford Global Tech Llc

Inventors

• Liu Dongran
• Kadetotad Sneha
• Castro Marcos Paul Gerardo
• Jain Jinesh J

Classifications

• G06F18/253

  of extracted features · CPC title

• B60W10/20

  including control of steering systems · CPC title

• B60W10/06

  including control of combustion engines · CPC title

• B60W2420/54

  Audio sensitive means, e.g. ultrasound · CPC title

• B60W30/0956 Primary

  the prediction being responsive to traffic or environmental parameters · CPC title