SYSTEM AND METHOD FOR OBJECT MOTION DETECTION BASED ON MULTIPLE 3D WARPING AND VEHICLE EQUIPPED WITH SUCH SYSTEM

• US 20100183192A1
• Filed: 12/30/2009
• Published: 07/22/2010
• Est. Priority Date: 01/16/2009
• Status: Active Grant

• Current Assignee: Honda Research Institute Europe GmbH (Honda Motor Company)
• Original Assignee: Honda Research Institute Europe GmbH (Honda Motor Company)
• Inventors: MICHALKE, Thomas, KASTNER, Robert, FRITSCH, Jannik
• Granted Patent: US 8,233,660 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06T 7/254 involving subtraction of images

Abstract

The present invention relates to a technique for detecting dynamic (i.e., moving) objects using sensor signals with 3D information and can be deployed e.g. in driver assistance systems.

Claims

1. A method for detecting dynamic objects in a scene representation of a driver assistance system for a vehicle, comprising the steps of:

Supplying signals from internal and external sensors of a vehicle, wherein at least one external sensor is a 3D sensor,

generation of a scene model in 3D world coordinates based on the supplied external sensor signals,

predicting the scene model in 3D world coordinates taking into account the measured ego-motion of the vehicle,

comparing the predicted scene model with a scene model in 3D world coordinates based on external sensor signals in order to detect the location of dynamic objects in the scene representation as well as their motion parameters, respectively, expressed in 3D world coordinates, and

storing the detected dynamic objects and their motion parameters.

2. The method according to claim 1, wherein the step of predicting the scene model in 3D world coordinates taking into account the measured ego-motion of the vehicle uses information gained from sensors for the longitudinal velocity and yaw rate of the vehicle.

3. The method according to claim 1, wherein the step of predicting the scene model in 3D world coordinates taking into account the measured ego motion of the vehicle comprises one or more of the following steps:

a) Iconic 3D warping directly on the 3D world coordinates computed the sensor signals,

b) use of top-down knowledge of scene knowledge, wherein known static objects are handled independently,

c) region-based 3D warping that allows the inclusion of scene knowledge in form of environmental models and plane models in order to decrease noise in the sensor signals, and/or.

d) Using an environmental envelope for the planes of interest to reduce the complexity of the 3D warping procedure.

4. The method according to claim 1, wherein information from a 3D depth sensor such as a rotating laser scanner is used to generate the external sensor signals.

5. The method according to claim 1, wherein information from a 2D depth sensor such as a Photonic Mixer Device is used to generate the sensor signals.

6. The method according to claim 1, wherein information from a 1D depth sensor such as a laser scanner is used to generate 3D data.

7. The method according to claim 1, wherein information from a satellite-based navigation system is used to generate 3D data and/or for generating environmental information.

8. A driver assistance computing unit, designed to carry out a method according to claim 1.

9. A vehicle being equipped with a driver assistance computing unit according to claim 7.

10. A computer program product, implementing a method according to claim 1 when run on a computing unit.

12. The system according to claim 10, wherein the sensors comprise video cameras.

13. The system according to claim 10, wherein the driver assistance action is an emission of a warning message.

11. A driver assistance system with a model generation apparatus, the model generation apparatus comprising:

at least one 3D sensor for supplying signals to the driver assistance system, —

computing means for generating a 3D world model based on the signals of the at least one 3D sensor and means for detecting dynamic objects based on the sensor signals in the 3D world,

storing means for storing the detected dynamic objects and their motion parameters,

means for determining whether to carry out an driver assistance action based on the detected dynamic objects, and

means for carrying out a driver assistance action.