Object detection device, object detection system, and object detection method

1. An object detection device, comprising:

a communication device configured to perform a first operation for acquirin measurement records of one or more radars,

a processor configured to perform a second operation for detecting an object based on the measurement records of the one or more radars,

wherein the processor is configured to:

acquire settings data for one or more radar grids for measurement, the settings data including location data of cells in the one or more radar grids, each radar grid being set for a measurement area of a corresponding one of the one or more radars and consisting of a plurality of radar cells;

performing clustering operations to define a processing grid, the processing grid being set based on the measurement area of each radar grid and consisting of a plurality of processing cells;

calculate, for each processing cell, one or more likelihood values associated with measurements of one or more radar cells overlapped with the processing cell based on distances between the processing cell and the one or more radar cells, wherein each likelihood value is determined such that a maximum value is a center point of each of the one or more radar cells and the likelihood value decreases with a distance from the center point of each of the one or more radar cells;

calculate a grid value of each of the processing cells based on the one or more likelihood values; and

perform a clustering operation on each processing cell based on at least one of (i) distances between the processing cell and one or more different processing cells, or (ii) the grid value of the processing cell and grid values of the one or more different processing cells.

2. The object detection device according to claim 1 , wherein the processor is further configured such that, when a plurality of likelihood values are calculated for a processing cell based on the distances between the processing cell and the one or more radar cells, the processor calculates the maximum value of the one or more likelihood values as the grid value of the processing cell.

3. The object detection device according to claim 1 , wherein the processor is further configured such that, when a plurality of likelihood values are calculated, for a processing cell, based on the distances between the processing cell and the one or more radar cells, the processor calculates a sum of the one or more likelihood values as the grid value of the processing cell.

4. The object detection device according to claim 1 , wherein the processor is further configured to calculate the one or more likelihood values associated with the measurements of the one or more radar cells overlapped with the processing cell based on radar reflection intensity measurements associated with the respective radar cells.

5. The object detection device according to claim 1 , wherein the processor is further configured to calculate the one or more likelihood values associated with the measurements of the one or more radar cells overlapped with the processing cell based on radar Doppler velocities associated with the respective radar cells.

6. The object detection device according to claim 1 , wherein the processor is further configured to perform the clustering operation based on a difference between two grid values of a pair of processing cells to be subjected to the clustering operation.

7. The object detection device according to claim 1 , wherein a distance between the processing cell and each radar cell of the one or more radar cells overlapped with the processing cell is between centers of the radar cell and the processing cell.

8. The object detection device according to claim 1 , wherein each radar grid is formed based on polar coordinates, and wherein the processing grid is formed based on orthogonal coordinates.

9. An object detection system comprising:

the object detection device according to claim 1 ; and

the one or more radars.

10. The object detection system according to claim 9 , wherein the one or more radars are installed on roads.

11. The object detection system according to claim 9 , wherein the one or more radars consist of a plurality of radars arranged side by side so as to have a same reference emission direction, and

wherein the plurality of processing cells forming the processing grid increase in size with distance from the one or more radars in the measurement area of each radar grid.

12. An object detection method performed by an object detection device, the object detection device including a communication device configured to perform a first operation for acquiring measurement records of one or more radars and a processor configured to perform a second operation for detecting an object based on the measurement records of the one or more radars, the object detection method comprising:

acquiring settings data for one or more radar grids for measurement, the settings data including location data of cells in the one or more radar grids, each radar grid being set for a measurement area of a corresponding one of the one or more radars and consisting of a plurality of radar cells;

performing clustering operations to define a processing grid, the processing grid being set based on the measurement area of each radar grid and consisting of a plurality of processing cells;

calculating, for each processing cell, one or more likelihood values associated with measurements of one or more radar cells overlapped with the processing cell based on distances between the processing cell and the one or more radar cells, wherein each likelihood value is determined such that a maximum value is a center point of each of the one or more radar cells and the likelihood value decreases with a distance from the center point of each of the one or more radar cells:

calculating a grid value of each of the processing cells based on the one or more likelihood values; and

performing a clustering operation on each processing cell based on at least one of (i) distances between the processing cell and one or more different processing cells, or (ii) the grid value of the processing cell and grid values of the one or more different processing cells.