Clear path detection using an example-based approach

A method for detecting a clear path of travel for a vehicle using a current image generated by a camera, the method comprising:

• determining a human-defined exemplary clear path for each of a plurality of sample images, the human-defined exemplary clear path determined during an off-line training process;
• during the off-line training process, identifying features as corresponding to one of the clear path and an obstacle within each of the plurality of sample images;
• storing the identified features within each of the plurality of sample images in a refined database;
• monitoring the current image generated by the camera;
• identifying features within the current image;
• matching the current image to at least one of the sample images based upon the identified features within the current image and the identified features within the plurality of sample images;
• determining a clear path for the current image of travel based upon the matching and the exemplary clear path for each of the matched sample images;
• utilizing the clear path of travel to navigate the vehicle;
• determining a feature value for each of the plurality of sample images based upon the identified features within each of the sample images;
• and
• determining a feature value for the current image based upon the identified features within the current image;
• wherein matching the current image to at least one of the sample images based upon the identified features within the current image and the identified features within the plurality of sample images comprises
• comparing the feature value for the current image to the feature value for each of the plurality of sample images, and
• selecting a predetermined number of matched sample images having feature values in nearest spatial proximity to the feature value of the current image.

A method for detecting a clear path of travel for a vehicle using a current image generated by a camera, the method comprising:

• defining an-exemplary clear path for each of a plurality of sample images;
• identifying features within each of the plurality of sample images;
• monitoring the current image generated by the camera;
• identifying features within the current image;
• matching the current image to at least one of the sample images based upon the identified features within the current image and the identified features within the plurality of sample images;
• determining a clear path of travel based upon the matching and the exemplary clear path for each of the matched sample images;
• utilizing the clear path of travel to navigate the vehicle;
• determining a feature value for each of the plurality of sample images based upon the identified features within each of the sample images;
• and
• determining a feature value for the current image based upon the identified features within the current image;
• wherein matching the current image to at least one of the sample images based upon the identified features within the current image and the identified features within the plurality of sample images comprises
• comparing the feature value for the current image to the feature value for each of the plurality of sample images, and
• selecting a predetermined number of matched sample images having feature values in nearest spatial proximity to the feature value of the current image, wherein spatial proximity between the feature value of a sample image and the feature value of the current image is given by:
• DF
• =
• ∑
• i
• =
• 1
• N
• ⁢
• f
• i
• q
• ⁡
• (
• f
• i
• q
• -
• f
• i
• d
• )
• 2
• where
• DF represents the spatial proximity,
• N represents a number of feature values,
• fid represents the feature value of a candidate sample image, and
• fiq resents the feature value of the current image.

A method for detecting a clear path of travel for a vehicle using a current image area generated by a camera, the method comprising:

• determining a human-defined exemplary clear path for each of a plurality of sample image areas, the human-defined exemplary clear path determined during an off-line training process;
• during the off-line training process, identifying features as corresponding to one of the clear path and an obstacle within each of the plurality of sample image areas, comprising
• convoluting selected patches corresponding to the human-defined exemplary clear path within each sample image area to obtain a plurality of filter responses for each selected patch using a filter bank,
• summing absolute responses for each filter,
• applying area normalization to compensate for different image areas within each sample image area by dividing the image area of each selected patch, and
• forming a predetermined dimensional feature vector associated with each selected patch based on the applied area normalization;
• storing the identified features within each of the plurality of sample images areas in a refined database;
• monitoring the current image area generated by the camera;
• identifying features within the current image area;
• comparing the identified features within the current image area to the identified features within each of the plurality of sample images areas stored in the refined database;
• selecting one or more candidate sample images areas from the plurality of sample images areas, each candidate sample image area having identified features that match the identified features within the current image area;
• matching the current image area the one or more candidate sample image areas based upon the identified features within the current image area and the identified features within the one or more candidate sample image areas;
• determining a clear path of travel for the current image area based upon the matching and the exemplary clear path for each of the one or more candidate sample image areas;
• and
• utilizing the clear path of travel to navigate the vehicle.

A method for detecting a clear path of travel for a vehicle using a current image area generated by a camera, the method comprising:

• determining a human-defined exemplary clear path for each of a plurality of sample image areas, the human-defined exemplary clear path determined during an off-line training process;
• during the off-line training process, identifying features as corresponding to one of the clear path and an obstacle within each of the plurality of sample image areas;
• storing the identified features within each of the plurality of sample images in a refined database;
• monitoring the current image area generated by the camera;
• identifying features within the current image area;
• matching the current image area to at least one of the sample image areas based upon the identified features within the current image area and the identified features within the plurality of sample image areas;
• determining a clear path for the current image of travel based upon the matching and the exemplary clear path for each of the matched sample image areas;
• utilizing the clear path of travel to navigate the vehicle;
• determining a feature value for each of the plurality of sample image areas based upon the identified features within each of the sample image areas;
• and
• determining a feature value for the current image area based upon the identified features within the current image area;
• wherein matching the current image area to at least one of the sample image areas based upon the identified features within the current image area and the identified features within the plurality of sample image areas comprises
• comparing the feature value for the current image area to the feature value for each of the plurality of sample image areas, and
• selecting a predetermined number of matched sample image areas having feature values in nearest spatial proximity to the feature value of the current image area.