Device and method for data fusion between heterogeneous sensors
An apparatus and method for data fusion between heterogeneous sensors are disclosed. The method for data fusion between the heterogeneous sensors may include identifying image data and point cloud data for a search area by each of a camera sensor and a LiDAR sensor that are calibrated using a marker board having a hole; recognizing a translation vector determined through calibrating of the camera sensor and the LiDAR sensor; and projecting the point cloud data of the LiDAR sensor onto the image data of the camera sensor using the recognized translation vector to fuse the identified image data and point cloud data.
1. A method for data fusion between calibrated heterogeneous sensors, comprising:
identifying image data and point cloud data for a search area by each of a camera sensor and a LiDAR sensor that are calibrated using a marker board having a hole;
recognizing a translation vector determined through calibrating of the camera sensor and the LiDAR sensor; and
projecting the point cloud data of the LiDAR sensor onto the image data of the camera sensor using the translation vector to fuse the image data and the point cloud data,
wherein the translation vector is determined based on a first distance from the camera sensor to the marker board and a second distance from the LiDAR sensor to the marker board, and
wherein the first and the second distances are determined using a focal length of the camera sensor, a radius of the hole in the marker board, and a radius of the hole recognized through each of the camera sensor and the LiDAR sensor.
2. The method of claim 1 , further comprising evaluating accuracy of a fusion data obtained by fusing of the image data and the point cloud data.
3. The method of claim 2 , wherein evaluating the accuracy comprises evaluating the accuracy of the fusion data based on a correspondence degree between positions of pixels corresponding to a reference area of the image data in the fusion data and positions of points of the point cloud data corresponding to the reference area.
4. The method of claim 2 , wherein evaluating the accuracy comprises evaluating the accuracy of the fusion data by visualizing points of the point cloud data in the fusion data, and by using a correspondence degree between color values of the visualized points and pixel values of the image data which is identified.
5. The method of claim 2 , wherein evaluating the accuracy comprises evaluating the accuracy of the fusion data by determining an estimated distance to a target using points of the point cloud data in the fusion data, which are aligned with pixels corresponding to an image of the target, and by comparing the determined estimated distance with a measured distance to the target measured through an existing target recognition algorithm.
6. An apparatus for data fusion between heterogeneous sensors, comprising:
a processor configured to perform data fusion between a camera sensor and a LiDAR sensor,
wherein the processor is configured to:
identify image data and point cloud data for a search area by each of the camera sensor and the LiDAR sensor that are calibrated using a marker board having a hole;
recognize a translation vector determined through calibrating of the camera sensor and the LiDAR sensor; and
project the point cloud data of the LiDAR sensor onto the image data of the camera sensor using the recognized translation vector to fuse the identified image data and point cloud data,
wherein the translation vector is determined based on a first distance from the camera sensor to the marker board and a second distance from the LiDAR sensor to the marker board, and
wherein the first and the second distances are determined using a focal length of the camera sensor, a radius of the hole in the marker board, and a radius of the hole recognized through each of the camera sensor and the LiDAR sensor.
7. The apparatus of claim 6 , wherein the processor is further configured to evaluate accuracy of fusion data obtained through fusing of the identified image data and point cloud data.
8. The apparatus of claim 7 , wherein the processor is further configured to evaluate the accuracy of the fusion data based on a correspondence degree between positions of pixels corresponding to a reference area of the identified image data in the fusion data and positions of points of the point cloud data corresponding to the reference area.
9. The apparatus of claim 7 , wherein the processor is further configured to evaluate the accuracy of the fusion data by visualizing the points of the point cloud data in the fusion data, and by using a correspondence degree between color values of the visualized points and pixel values of the identified image data.
10. The apparatus of claim 7 , wherein the processor is further configured to evaluate the accuracy of the fusion data by determining an estimated distance to a target using points of the point cloud data in the fusion data, which are aligned with pixels corresponding to an image of the target, and by comparing the determined estimated distance with a measured distance to the target measured through an existing target recognition algorithm.