초록 ▼

A method for providing a forward collision warning using a camera mountable in a motor vehicle. The method acquires multiple image frames at known time intervals. A patch may be selected in at least one of the image frames. Optical flow may be tracked between the image frames of multiple image point

A method for providing a forward collision warning using a camera mountable in a motor vehicle. The method acquires multiple image frames at known time intervals. A patch may be selected in at least one of the image frames. Optical flow may be tracked between the image frames of multiple image points of the patch. Based on the fit of the image points to a model, a time-to collision (TTC) may be determined if a collision is expected. The image points may be fit to a road surface model and a portion of the image points is modeled to be imaged from a road surface. A collision is not expected based on the fir of the image points to the road surface model.

대표청구항 ▼

1. A method for providing a forward collision warning or control signal using a camera mountable in a motor vehicle, the method comprising: acquiring a plurality of image frames at known time intervals;selecting a patch in at least one of the image frames;tracking optical flow between the image fram

1. A method for providing a forward collision warning or control signal using a camera mountable in a motor vehicle, the method comprising: acquiring a plurality of image frames at known time intervals;selecting a patch in at least one of the image frames;tracking optical flow between the image frames of a plurality of image points of said patch to produce a tracked optical flow;for a plurality of models selected from the group consisting of: (i) a road surface model wherein a portion of the image points is modeled to be imaged from a road surface (ii) vertical surface model wherein a portion of the image points is modeled to be imaged from a substantially vertical object and (iii) a mixed model wherein a first portion of the image points is modeled to be imaged from a road surface and a second portion of the image points is modeled to be imaged from a substantially vertical object, fitting the tracked optical flow of at least a portion of the image points to produce a plurality of fits to the models;using at least a portion of the image points, scoring the fits of the tracked optical flow to the respective models to produce respective scores; anddetermining if a collision is expected and a time-to-collision by selecting the model with a score which corresponds to a best fit of the image points to the tracked optical flow. 2. The method of claim 1, further comprising: determining that a collision is not expected based on the best fit of the image points to the tracked optical flow corresponding to the road surface model. 3. The method of claim 1, further comprising: determining that a collision is expected based on the best fit of the image points to the tracked optical flow corresponding to the vertical surface model or the mixed model. 4. The method of claim 3, further comprising: detecting in the patch a candidate image of a pedestrian; andverifying the candidate image as an image of an upright pedestrian and not an object in the road surface when the best fit model is the vertical surface model. 5. The method of claim 3, further comprising: detecting in the image frames a vertical line, wherein said patch is selected to include said vertical line;verifying the vertical line as an image of a vertical object and not of an object in the road surface when the best fit model is the vertical surface model. 6. The method of claim of claim 1, further comprising: issuing a warning based on said time-to-collision being less than a threshold. 7. A system comprising: a camera; anda processor mountable in a motor vehicle; wherein the system is configured to provide a forward collision warning or control signal,wherein the processor is configured to acquire a plurality of image frames at known time intervals;wherein the processor is configured to select a patch in at least one of the image frames;wherein the processor is configured to track optical flow between the image frames of a plurality of image points of said patch for a plurality of models selected from the group consisting of: (i) a road surface model wherein a portion of the image points is modeled to be imaged from a road surface (ii) vertical surface model wherein a portion of the image points is modeled to be imaged from a substantially vertical object and (iii) a mixed model wherein a first portion of the image points is modeled to be imaged from a road surface and a second portion of the image points is modeled to be imaged from a substantially vertical object;wherein the processor is configured to fit the tracked optical flow of at least a portion of the image points to produce a plurality of fits to the models;wherein the processor is configured to use at least a portion of the image points and score the fits of the tracked optical flow to the respective models to produce respective scores; andwherein the processor is configured to use at least a portion of the image points, determine if a collision is expected and determine the time-to-collision by selecting the model with the score which corresponds to a best fit of the image points to the tracked optical flow. 8. The system of claim 7, wherein the processor is configured to fit the image points to a road surface model; wherein the processor is configured to determine a collision is not expected based on the fit of the image points to the road surface model. 9. A method of providing a forward collision warning or control signal using a camera and a processor mountable in a motor vehicle, the method comprising: acquiring a plurality of image frames at known time intervals;selecting a patch in an image frame corresponding to where the motor vehicle will be in a predetermined time interval;tracking optical flow between the image frames of a plurality of image points of said patch to produce a tracked optical flow;for a plurality of models selected from the group consisting of: (i) a road surface model wherein a portion of the image points is modeled to be imaged from a road surface (ii) vertical surface model wherein a portion of the image points is modeled to be imaged from a substantially vertical object and (iii) a mixed model wherein a first portion of the image points is modeled to be imaged from a road surface and a second portion of the image points is modeled to be imaged from a substantially vertical object, fitting the tracked optical flow of at least a portion of the image points to produce a plurality of fits to the models;using at least a portion of the image points, scoring the fits of the tracked optical flow to the respective models to produce respective scores; anddetermining if a collision is expected and a time-to-collision by selecting the model with a score which corresponds to a best fit of the image points to the tracked optical flow. 10. The method of claim of claim 9, further comprising: determining if an object as imaged in said patch includes a substantially vertical portion. 11. The method of claim 9, further comprising: fitting the image points to a road surface model; anddetermining a collision is not expected based on the best fit of the image points to the road surface model. 12. The method of claim 9, further comprising: issuing a forward collision warning when the best fit model is a vertical surface model or a mixed model. 13. A system for providing a forward collision warning or control signal in a motor vehicle, the system comprising: a camera mountable in the motor vehicle, said camera operable to acquire a plurality of image frames at known time intervals;a processor configured to select a patch in an image frame corresponding to where the motor vehicle will be in a predetermined time interval; wherein the processor is configured to track optical flow between the image frames of a plurality of image points of said patch to produce a tracked optical flow, for a plurality of models selected from the group consisting of: (i) a road surface model wherein a portion of the image points is modeled to be imaged from a road surface (ii) vertical surface model wherein a portion of the image points is modeled to be imaged from a substantially vertical object and (iii) a mixed model wherein a first portion of the image points is modeled to be imaged from a road surface and a second portion of the image points is modeled to be imaged from a substantially vertical object,wherein the processor is configured to fit the tracked optical flow of at least a portion of the image points to produce a plurality of fits to the models;wherein the processor is configured to use at least a portion of the image points, to score the fits of the tracked optical flow to the respective models to produce respective score; andwherein the processor is configured to determine if a collision is expected and to determine a time-to-collision by selecting the model with a score which corresponds to a best fit of the image points to the tracked optical flow. 14. The system of claim 13, wherein the processor is further configured to determine if said object as imaged in said patch includes a substantially vertical portion when the best fit of the image points to the tracked optical flow is of the vertical surface model or the mixed model. 15. The system of claim 13, wherein the processor is configured to issue a forward collision warning based on the TTC being less than a threshold. 16. The method of claim 9, further comprising: inputting or computing from the image frames a yaw rate of the motor vehicle; anddynamically shifting the patch laterally over the image frames based on the yaw rate of the motor vehicle. 17. The method of claim 4, further comprising: verifying the candidate image as an object in the road surface and a collision is not expected when the best fit model is the road surface model.