Trailer striking area prediction using camera monitoring system
A camera monitoring system (CMS) for a vehicle, including a CMS controller including a memory and a processor, the CMS controller being connected to a plurality of cameras disposed about a vehicle and configured to receive a video feed from each of the cameras in the plurality of cameras, the CMS controller including at least one side camera configured to define a rear side view and at least one rear camera configured to generate a rear facing view, the memory storing a trailer end detection module configured to identify a trailer end within at least one image generated by the plurality of cameras, and the memory further storing a trailer striking area prediction module configured to define a striking area geometry using a set of predicted future positions of prediction points in a prediction set, the prediction points being defined along an edge of the trailer.
1. A camera monitoring system (CMS) for a vehicle, comprising:
a CMS controller including a memory and a processor;
the CMS controller being connected to a plurality of cameras disposed about a vehicle and configured to receive a video feed from each of the cameras in the plurality of cameras, the CMS controller including at least one side camera configured to define a rear side view and at least one rear camera configured to generate a rear facing view;
the memory storing a trailer end detection module configured to identify a trailer end of a trailer within at least one image generated by the plurality of cameras; and
the memory further storing a trailer striking area prediction module configured to define a striking area geometry using a set of predicted future positions of prediction points in a prediction set, the prediction points being defined along an edge of the trailer,
wherein the striking area prediction module defines the striking area geometry by:
identifying a current location (t 0 ) of a set of prediction points of the trailer along an inside edge of the trailer and store the current location (t 0 ) of the set of prediction points in a prediction set;
identifying a first predicted future position of each prediction point at a time t 1 based on a set of parameters including at least a trailer angle of the vehicle, a steering angle of the vehicle and the current location (t 0 ) of the corresponding prediction point and storing the first future prediction point (t 1 ) in the prediction set;
identifying at least one additional predicted future position of each prediction point at a time (tn) based on a second set of parameters including at least the trailer angle of the vehicle, the steering angle of the vehicle, and the location at a previous time (tn−1) of the corresponding prediction point; and
converting each location in the prediction set from a three dimensional real world position to a two dimensional position within a rear view display image, generate a geometry including each two dimensional position, and causing the CMS to display the geometry over an image on the rear view display image as an overlay.
2. The CMS of claim 1 , wherein the CMS is configured to iterate the process defined in the trailer striking area prediction module over the course of a turning operation.
3. The CMS of claim 1 , wherein the memory further including a collision alert module configured to cause the controller to identify at least one object within an image, compare a location of the object within the image to the geometry, and output a collision warning in response to the object overlapping with the geometry.
4. The CMS of claim 1 , wherein the set of parameters includes at least a trailer angle of the vehicle, a steering angle of the vehicle, the current location (t 0 ) of the corresponding prediction point, rate of change of trailer angle, vehicle speed, and yawrate.
5. The CMS of claim 1 , wherein the first predicted position of each prediction point at the time t 1 and of each additional predicted future position is determined by applying the set of parameters to a kinematic model.
6. A method for displaying a potential striking area of a trailer to a vehicle operator, the method comprising:
predicting a striking area of a trailer by defining a striking area geometry using a set of predicted future positions of prediction points in a prediction set, the prediction points being defined along an edge of the trailer, wherein predicting a striking area of a trailer by defining a striking area geometry using a set of predicted future positions of prediction points in a prediction set comprises:
identifying a current location (t 0 ) of a set of prediction points of the trailer along an inside edge of the trailer and store the current location (t 0 ) of the set of prediction points in a prediction set;
identifying a first predicted future position of each prediction point at a time t 1 based on a set of parameters including at least a trailer angle of the vehicle, a steering angle of the vehicle and the current location (t 0 ) of the corresponding prediction point and storing the first future prediction point (t 1 ) in the prediction set; and
identifying at least one additional predicted future position of each prediction point at a time (tn) based on a second set of parameters including at least the trailer angle of the vehicle, the steering angle of the vehicle, and the location at a previous time (tn−1) of the corresponding prediction point;
converting the geometry to a two dimensional overlay; and
applying the two dimensional overlay to a rear view display during a turning operation.
7. The method of claim 6 , further comprising iterating the process over the course of the turning operation.
8. The method of claim 6 , wherein the set of parameters includes at least a trailer angle of the vehicle, a steering angle of the vehicle, the current location (t 0 ) of the corresponding prediction point, rate of change of trailer angle, vehicle speed, and yawrate.
9. The method of claim 6 , wherein the first predicted position of each prediction point at the time t 1 and of each additional predicted future position is determined by applying the set of parameters to a kinematic model.