Vehicle and vehicle position calculation method
View Patent ↗Disclosed are a vehicle and a vehicle position calculation method. The vehicle includes an image sensor. The image may acquire, using the image sensor, a video image of a target vehicle, determine, based on the video image, a set of location points of the target vehicle, project, based on the determined set of location points, first three-dimensional coordinate values of location points corresponding to front and rear wheels of the target vehicle onto a two-dimensional plane by converting the first three-dimensional coordinate values into first two-dimensional coordinate values in the video image, project, based on the determined set of location key points, second three-dimensional coordinate values of location points corresponding to bumpers of the target vehicle onto the two-dimensional plane by converting the second three-dimensional coordinate values into second two-dimensional coordinate values in the video image, and control, based on the three-dimensional coordinate values and the second three-dimensional coordinate values, the host vehicle.
1. A host vehicle comprising:
an image sensor;
one or more processors; and
memory storing instructions that, when executed by the one or more processors, cause the host vehicle to:
acquire, using the image sensor, a video image of a target vehicle;
determine, based on the video image, a set of location points of the target vehicle;
project, based on the determined set of location points, first three-dimensional coordinate values of location points corresponding to front and rear wheels of the target vehicle onto a two-dimensional plane by converting the first three-dimensional coordinate values into first two-dimensional coordinate values in the video image;
project, based on the determined set of location key points, second three-dimensional coordinate values of location points corresponding to bumpers of the target vehicle onto the two-dimensional plane by converting the second three-dimensional coordinate values into second two-dimensional coordinate values in the video image; and
control, based on the first three-dimensional coordinate values and the second three-dimensional coordinate values, the host vehicle.
2. The host vehicle according to claim 1 , wherein the instructions, when executed by the one or more processors, further cause the host vehicle to project the second three-dimensional coordinate values onto the two-dimensional plane by:
calculating the second three-dimensional coordinate values based on a first condition in which the location points corresponding to the bumpers have a common Z value in a three-dimensional coordinate system and based on a second condition in which a line, projected onto the two-dimensional plane, that connects the location points corresponding to the bumpers is perpendicular to a line, projected onto the two-dimensional plane, that connects the front and rear wheels.
3. The host vehicle according to claim 2 , wherein the instructions, when executed by the one or more processors, cause the host vehicle to calculate the second three-dimensional coordinate values of the location points corresponding to the bumpers projected onto the two-dimensional plane by:
representing, in the three-dimensional coordinate system, X and Y coordinate values, of the location points corresponding to the bumpers determined in the video image, as a functional relationship with respect to Z coordinate values;
representing the second three-dimensional coordinate values of the location points corresponding to the bumpers as a functional relationship with respect to height values by applying the first condition to a functional relationship with respect to the Z coordinate values; and
applying the second condition to the functional relationship with respect to the height values.
4. The host vehicle according to claim 1 , wherein the instructions, when executed by the one or more processors, further cause the host vehicle to:
correct positions, in a two-dimensional coordinate system, of the location points corresponding to the bumpers based on a movement amount, in a plurality of consecutive video images, of the set of location points of the target vehicle between a first position of the target vehicle and a second position of the target vehicle.
5. The host vehicle according to claim 1 , wherein the instructions, when executed by the one or more processors, further cause the host vehicle to:
represent a movement amount, in a plurality of consecutive video images, of two-dimensional coordinate values of the set of location points of the target vehicle, between a first position of the target vehicle and a second position of the target vehicle, as a movement amount vector; and
calculate, based on the movement amount vector and a traveling direction vector of the host vehicle, a heading angle of the target vehicle.
6. The host vehicle according to claim 1 , wherein the instructions, when executed by the one or more processors, further cause the host vehicle to:
determine whether the target vehicle is common across a plurality of consecutive video images, based on a movement amount of the location points corresponding to the front and rear wheels of the target vehicle determined in the plurality of consecutive video images.
7. A method comprising:
acquiring, via an image sensor of a host vehicle, a video image of a target vehicle;
determining, based on the video image, a set of location points of the target vehicle;
projecting, based on the determined set of location points, first three-dimensional coordinate values of location points corresponding to front and rear wheels of the target vehicle onto a two-dimensional plane by converting the first three-dimensional coordinate values into first two-dimensional coordinate values in the video image;
projecting, based on the determined set of location points, second three-dimensional coordinate values of location points corresponding to bumpers of the target vehicle onto the two-dimensional plane by converting the second three-dimensional coordinate values into second two-dimensional coordinate values in the video image; and
control, based on the first three-dimensional coordinate values and the second three-dimensional coordinate values, the host vehicle.
8. The method according to claim 7 , wherein the projecting of the second three-dimensional coordinate values onto the two-dimensional plane comprises:
calculating the second three-dimensional coordinate values based on a first condition in which the location points corresponding to the bumpers have a common Z value in a three-dimensional coordinate system and based on a second condition in which a line, projected onto the two-dimensional plane, that connects the location points corresponding to the bumpers is perpendicular to a line, projected onto the two-dimensional plane, that connects the front and rear wheels.
9. The method according to claim 8 , wherein the calculating of the second three-dimensional coordinate values comprises:
representing, in the three-dimensional coordinate system, X and Y coordinate values, of the location points corresponding to the bumpers determined in the video image, as a functional relationship with respect to Z coordinate values;
representing the second three-dimensional coordinate values of the location points corresponding to the bumpers as a functional relationship with respect to height values by applying the first condition to the functional relationship with respect to the Z coordinate values; and
applying the second condition to the functional relationship with respect to the height values.
10. The method according to claim 7 , further comprising:
correcting positions, in a two-dimensional coordinate system, of the location points corresponding to the bumpers based on a movement amount, in a plurality of consecutive video images, of the set of location points of the target vehicle between a first position of the target vehicle and a second position of the target vehicle.
11. The method according to claim 7 , further comprising:
representing a movement amount, in a plurality of consecutive video images, of two-dimensional coordinate values of the set of location points of the target vehicle, between a first position of the target vehicle and a second position of the target vehicle, as a movement amount vector; and
calculating, based on the movement amount vector and a traveling direction vector of the host vehicle, a heading angle of the target vehicle.
12. The method according to claim 7 , further comprising:
determining whether the target vehicle is common across a plurality of consecutive video images, based on a movement amount of the location points corresponding to the front and rear wheels of the target vehicle determined in the plurality of consecutive video images.
13. The method according to claim 12 , wherein the determining whether the target vehicle is common across the plurality of consecutive video images comprises:
determining that the target vehicle is common across the plurality of consecutive video images based on the movement amount of the location points corresponding to the front and rear wheels of the target vehicle being at a minimum among distances among the set of location points.
14. The method according to claim 12 , wherein determining whether the target vehicle is common across the plurality of consecutive video images comprises:
determining that the target vehicle is common across the plurality of consecutive video images based on an overlapping area between a first quadrilateral, formed by the location points corresponding to the front and rear wheels at a first time, and a second quadrilateral, formed by the location points corresponding to the front and rear wheels at a second time, being greater than a threshold value.
15. The method according to claim 12 , further comprising:
determining that the target vehicle is a closest vehicle to the host vehicle.