Image processing apparatus
An image processing apparatus is configured to detect an external situation of a vehicle based on image information acquired by a detection unit mounted on the vehicle. The image processing apparatus includes a microprocessor configured to perform: extracting feature points of an object included in the image information, selecting feature points to be used for processing from a plurality of feature points, dividing the image information into a plurality of regions, and adjusting the number of feature points to be selected in each of the plurality of regions based on distances to objects included in the plurality of regions.
1 . An image processing apparatus configured to detect an external situation of a vehicle based on image information acquired by a detection unit mounted on the vehicle, the image processing apparatus comprising
a microprocessor configured to perform:
extracting feature points of an object included in the image information;
selecting feature points to be used for processing from a plurality of the feature points;
dividing the image information into a plurality of regions; and
adjusting a number of feature points to be selected in each of the plurality of regions based on distances to objects included in the plurality of regions, wherein
the microprocessor is configured to perform:
the adjusting including:
calculating a distance to the object based on the image information;
calculating an average distance from a position of the vehicle to the plurality of feature points for each of the plurality of regions based on a result of the calculating the distance;
adjusting the number of feature points so as to reduce the number of feature points in an area where the average distance is longer; and
adjusting the number of feature points so as to increase the number of feature points on an object determined in advance, regardless of the average distance for each of the plurality of regions from the position of the vehicle to the plurality of feature points.
2 . The image processing apparatus according to claim 1 , wherein
the microprocessor is configured to perform:
the adjusting including performing adjustment so as to leave feature points on an object from which more feature points have been extracted.
3 . The image processing apparatus according to claim 1 , wherein
the microprocessor is configured to perform:
the adjusting including calculating a median value of distance from the position of the vehicle to the plurality of feature points for each of the plurality of regions based on a result of the calculating the distance, and adjusting the number of feature points so as to reduce the number of feature points in an area where the median value is larger.
4 . The image processing apparatus according to claim 1 , wherein
the microprocessor is configured to perform:
setting a stationary object included in the image information as an extraction target of feature points and excluding a moving object from the extraction target.
5 . The image processing apparatus according to claim 1 further comprising
a memory coupled to the microprocessor, wherein
the memory stores a plurality of frames of the image information in units of frames, and
the microprocessor is configured to further perform:
searching for a set of identical feature points commonly included in the image information of the plurality of frames stored in the memory; and
performing estimation of the position of the vehicle based on the set of identical feature points.
6 . An image processing apparatus configured to detect an external situation of a vehicle based on image information acquired by a detection unit mounted on the vehicle, the image processing apparatus comprising
a microprocessor configured to perform:
extracting feature points of an object included in the image information;
selecting feature points to be used for processing from a plurality of the feature points;
dividing the image information into a plurality of regions; and
adjusting a number of feature points to be selected in each of the plurality of regions based on distances to objects included in the plurality of regions, and
a memory coupled to the microprocessor, wherein the memory stores a plurality of frames of the image information in units of frames, wherein
the microprocessor is configured to further perform:
searching for a set of identical feature points commonly included in the image information of the plurality of frames stored in the memory;
performing estimation of a position of the vehicle based on the set of identical feature points; and
interrupting the estimation of the position of the vehicle when a reliability of the position estimated in the estimation decreases by a predetermined number of times or more.
7 . The image processing apparatus according to claim 6 , wherein
the microprocessor is configured to perform:
interrupting the estimation of the position of the vehicle according to a situation of the vehicle.
8 . An image processing apparatus configured to detect an external situation of a vehicle based on image information acquired by a detection unit mounted on the vehicle, the image processing apparatus comprising
a microprocessor configured to perform:
extracting feature points of an object included in the image information;
selecting feature points to be used for processing from a plurality of the feature points;
dividing the image information into a plurality of regions; and
adjusting a number of feature points to be selected in each of the plurality of regions based on distances to objects included in the plurality of regions, wherein
the microprocessor is configured to further perform:
calculating three-dimensional positions of identical feature points commonly included in the image information of a plurality of frames for each of a plurality of different feature points; and
performing map generation and estimation of a position of the vehicle based on the three-dimensional positions of the plurality of different feature points, wherein
the adjusting includes calculating an average distance from the position of the vehicle to the plurality of feature points for each of the plurality of regions based on results of the map generation and the estimation of the position of the vehicle, and adjusting the number of feature points so as to reduce the number of feature points in a region where the average distance is longer.