Multi-surface model-based tracking

A vehicle mounted system for detecting a vehicle, the system comprising:na controller including a processor, a computer readable media in communication with the processor, and an input/output interface, the processor configured to:nreceive images from a camera mounted on a moving first vehicle,identify a surface of a second vehicle located around the first vehicle based on the images by: detecting motion in the images,nextracting features from the images based on the detected motion,generating a surface based on the extracted features, andcomparing the surface to a side surface of at least one vehicle model;generate a three-dimensional model associated with the second vehicle, the three-dimensional model including a first plane and a second plane approximately perpendicular to the first plane, wherein the first plane is associated with the identified surface of the second vehicle, andtrack a position of the second vehicle using the three-dimensional model after the identified surface falls at least partially outside of a field-of-view of the camera by:nreceiving updated images from the camera,extracting features from the updated images,determining if the extracted features fit the first plane of the three-dimensional model,when the extracted features do not fit the first plane of the three-dimensional model, determining if the extracted features fit the second plane of the three-dimensional model, andwhen the extracted features fit the second plane of the three-dimensional model, updating the three-dimensional model based on the extracted features, andwherein the controller is further configured to perform at least one automatic vehicle control operation based on the tracked position of the second vehicle.

A method for detecting and avoiding collision with a vehicle, the method comprising:nreceiving, at at least one controller, images from at least one camera mounted on a first vehicle;identifying, by the at least one controller, a surface of a second vehicle located around the first vehicle based on the images by:ndetecting motion in the images,extracting features from the images based on the detected motion,generating a surface based on the extracted features, andcomparing the surface to a side surface of at least one vehicle model;generating, by the at least one controller, a three-dimensional model representing the second vehicle, the three-dimensional model including a first plane and a second plane approximately perpendicular to the first plane, wherein the first plane represents the identified surface of the second vehicle;determining, by the at least one controller, a position of the second vehicle using the model and updated data from the at least one camera after the identified surface of the second vehicle falls at least partially outside of a field-of-view of the at least one camera, andperforming, by the at least one controller, at least one automatic vehicle control operation based on the tracked position of the second vehicle.

A method for detecting a vehicle, the method comprising:nreceiving images from a camera mounted on a moving first vehicle;detecting a surface of a second vehicle located around the first vehicle based on the images;generating, by a controller, a three-dimensional model representing the second vehicle, the three-dimensional model including a first plane and a second plane approximately perpendicular to the first plane, wherein the first plane represents the identified surface of the second vehicle;determining a position of the second vehicle using the model after the identified surface of the second vehicle falls at least partially outside of a field-of-view of the camera, wherein determining the position of the second vehicle includes:nreceiving updated images from the camera;extracting features from the updated images;determining if the extracted features fit the first plane of the three-dimensional model;when the extracted features do not fit the first plane of the three-dimensional model, determining if the extracted features fit the second plane of the three-dimensional model; andwhen the extracted features fit the second plane of the three-dimensional model, updating the three-dimensional model based on the extracted features, andperforming at least one automatic vehicle control operation based on the tracked position of the second vehicle.