Device and method for estimating distance based on object detection
A device for estimating a distance based on object detection and a method thereof are provided. The device for estimating a distance based on object detection according to an embodiment of the present disclosure includes a fusion sensor including a first sensor configured to detect positions of a plurality of objects in front of a host vehicle and a second sensor configured to capture a front image of the host vehicle, and a controller communicatively connected to the fusion sensor and configured to recognize all radar tracks corresponding to distances detected by the first sensor and all vision tracks corresponding to distances detected by the second sensor, assign adjacent vision tracks for each of the radar tracks to one cluster, and correct distances of all the vision tracks assigned to the corresponding cluster based on the closest vision track from the radar track for each cluster.
1. A device for estimating a distance based on object detection, the device comprising:
a fusion sensor including a first sensor configured to detect positions of a plurality of objects in front of a host vehicle and a second sensor configured to capture a front image of the host vehicle; and
a controller communicatively connected to the fusion sensor and configured to:
recognize radar tracks corresponding to distances detected by the first sensor and vision tracks corresponding to distances detected by the second sensor,
assign, among all of the recognized vision tracks, adjacent vision tracks to each of the radar tracks to one cluster, and
update the distance of each of the vision tracks assigned to the corresponding cluster based on the closest vision track from the corresponding radar track for each cluster by multiplying a correction factor to the distance of each of the vision tracks assigned to the corresponding cluster,
wherein the correction factor for each cluster is a ratio of a distance from the host vehicle to the corresponding radar track to a distance from the host vehicle to the closest vision track of the corresponding cluster.
2. The device of claim 1 , wherein the first sensor is a radar sensor or a lidar sensor, and the second sensor is an image sensor.
3. The device of claim 1 , wherein the controller is configured to recognize the closest radar track for each of the vision tracks and assign each vision track to the corresponding cluster having the closest radar track.
4. The device of claim 1 , wherein the controller is configured to:
recognize and tag the closest vision track from the radar track for each cluster,
determine the ratio of the distance from the host vehicle to the radar track to the distance from the host vehicle to the tagged vision track for each cluster, and
multiply the ratio to the distance of each of the vision tracks assigned to the corresponding cluster.
5. The device of claim 4 , wherein the controller is configured to determine the number of the clusters and determine the number of objects in each cluster.
6. A method of estimating a distance based on object detection, the method comprising:
detecting, by a first sensor, positions of a plurality of objects in front of a host vehicle;
capturing, by a second sensor, a front image of the host vehicle;
recognizing, by a controller, radar tracks corresponding to distances detected by the first sensor and vision tracks corresponding to distances detected by the second sensor based on data detected by a fusion sensor including the first sensor and the second sensor;
assigning, by the controller, among all of the recognized vision tracks, adjacent vision tracks to each of the radar tracks to one cluster, the controller being communicatively connected to the fusion sensor; and
updating, by the controller, the distance of each of the vision tracks assigned to the corresponding cluster based on the closest vision track from the corresponding radar track for each cluster, by multiplying a correction factor to the distance of each of the vision tracks assigned to the corresponding cluster, wherein the correction factor for each cluster is a ratio of a distance from the host vehicle to the corresponding radar track to a distance from the host vehicle to the closest vision track of the corresponding cluster; and
predicting, by the controller, a time until the host vehicle collides with each object based on the updated distances.
7. The method of claim 6 , wherein the first sensor is a radar sensor or a lidar sensor, and the second sensor is an image sensor.
8. The method of claim 6 , wherein the assigning operation includes recognizing the closest radar track for each of the vision tracks and assigning each vision track to the corresponding cluster having the closest radar track.
9. The method of claim 6 , wherein the updating operation includes:
recognizing and tagging the closest vision track from the radar track for each cluster;
determining the ratio of the distance from the host vehicle to the radar track to the distance from the host vehicle to the tagged vision track; and
multiplying the ratio to the distance of each of the vision tracks assigned to the corresponding cluster.
10. The method of claim 6 , further comprising:
after the assigning the adjacent vision tracks, determining, by the controller, the number of the clusters; and
determining, by the controller, the number of objects in each cluster.
11. A vehicle comprising:
a fusion sensor including a first sensor configured to detect positions of a plurality of objects in front of a host vehicle and a second sensor configured to capture a front image of the host vehicle; and
a controller communicatively connected to the fusion sensor and configured to:
recognize radar tracks corresponding to distances detected by the first sensor and vision tracks corresponding to distances detected by the second sensor,
assign, among all of the recognized vision tracks, adjacent vision tracks to each of the radar tracks to one cluster, and
update the distance of each of the vision tracks assigned to the corresponding cluster based on the closest vision track from the corresponding radar track for each cluster by multiplying a correction factor to the distance of each of the vision tracks assigned to the corresponding cluster,
wherein the correction factor for each cluster is a ratio of a distance from the host vehicle to the corresponding radar track to a distance from the host vehicle to the closest vision track of the corresponding cluster.
12. The vehicle of claim 11 , wherein the first sensor is a radar sensor or a lidar sensor, and the second sensor is an image sensor.
13. The vehicle of claim 11 , wherein the controller is configured to recognize the closest radar track for each of the vision tracks and assign each vision track to the corresponding cluster having the closest radar track.
14. The vehicle of claim 11 , wherein the controller is configured to:
recognize and tag the closest vision track from the radar track for each cluster,
determine the ratio of the distance from the host vehicle to the radar track to the distance from the host vehicle to the tagged vision track for each cluster, and
multiply the ratio to the distance of each of the vision tracks assigned to the corresponding cluster.
15. The vehicle of claim 14 , wherein the controller is configured to determine the number of the clusters and determine the number of objects in each cluster.