Apparatus and method for monitoring surrounding environment of vehicle
An apparatus for monitoring the surrounding environment of a vehicle may include a sensor unit including a plurality of detection sensors configured to detect an object outside the vehicle according to frames with a time period; and a controller configured to extract a stationary object among outside objects detected through the sensor unit based on behavior information of the vehicle, map the extracted stationary object to a grid map, add occupancy information to each of grids constituting the grid map, in response to the stationary object being mapped to the grid map, calculate an occupancy probability parameter indicating the probability that the stationary object will be located at each of the grids, from the occupancy information added to the grids within the grid map in a plurality of frames, and monitor the surrounding environment of the vehicle on the basis of the occupancy probability parameter.
1. An apparatus for monitoring a surrounding environment of a vehicle, comprising:
a sensor unit comprising a plurality of detection sensors for detecting objects outside a vehicle according to a frame at a time period; and
a controller configured to;
extract a stationary object from among the objects detected by the sensor unit based on behavior information of the vehicle,
map the stationary object to a grid map,
add occupancy information to each of grids constituting the grid map, in response to the mapping being performed,
calculate an occupancy probability parameter, indicative of a probability that the stationary object is located on each grid, from the occupancy information added to the grid in the grid map in a plurality of frames to be monitored,
monitor the surrounding environment of the vehicle based on the occupancy probability parameter, and
correct a shaded grid, corresponding to a shaded area where the sensor unit is not able to detect an object outside the vehicle, in a differential manner according to the speed of the vehicle,
wherein the controller is further configured to:
correct the shaded grid corresponding to the shaded area where the sensor unit is not able to detect the object outside the vehicle in a K th frame, in a first scheme to receive an occupancy probability parameter of a grid around the shaded grid, in response to the speed of the vehicle being less than a threshold, and
correct the shaded grid from an outermost shaded grid in the first scheme, and
set a highest occupancy probability parameter, from among occupancy probability parameters of grids located within a set range from the shaded grid, as an occupancy probability parameter of the shaded grid from the outermost shaded grid in the first scheme.
2. The apparatus according to claim 1 , wherein the controller is further configured to correct the shaded grid, corresponding to the shaded area where the sensor unit is not able to detect the object outside the vehicle in a K th frame, in a first second scheme to receive an occupancy probability parameter in a (K−1) th frame, in response to the speed of the vehicle being equal to or higher than the threshold.
3. An apparatus for monitoring a surrounding environment of a vehicle, comprising:
a sensor unit comprising a plurality of detection sensors for detecting objects outside a vehicle according to a frame at a time period; and
a controller configured to;
extract a stationary object from among the objects detected by the sensor unit,
map the extracted stationary object to a grid map,
calculate an occupancy probability parameter, indicative of a probability that the stationary object is located on a grid of the grid map, from a result of mapping, and
monitor the surrounding environment of the vehicle by specifying a grid on which the stationary object is located in the grid map, based on the calculated occupancy probability parameter and recognizing a free space around the vehicle using the specified grid,
wherein the controller is further configured to:
determine a peak grid with a maximum occupancy probability parameter among the grids in the grid map, and
determine that the stationary object is located on the peak grid, in response to the occupancy probability parameter of the peak grid being equal to or greater than a threshold value defined for the peak grid, and the peak grid on which the stationary object is determined to be located comprises a plurality of peak grids in relation to the driving of the vehicle,
wherein the controller is further configured to:
map a stationary object corresponding to the peak grid to an azimuth map, the azimuth map having a plurality of azimuth indexes partitioned at equal radial intervals by a set radius and a set angle and sharing coordinates with the grid map, and
recognize an azimuth index, to which no stationary object is mapped, as the free space around the vehicle,
wherein the controller is further configured to correct a third azimuth index to which a stationary object is not mapped to an azimuth index to which a stationary object is mapped when a correction condition is satisfied, in response to the third azimuth index existing adjacent to first and second azimuth indexes to which first and second stationary objects are mapped, respectively, and a third stationary object existing in an area in which the third azimuth index expands radially,
wherein the azimuth indexes on the azimuth map have index flags having sequential values set according to the sequential positions of the respective azimuth indexes,
wherein the controller is further configured to correct the third azimuth index by incorporating the third stationary object into the third azimuth index using longitudinal and transverse coordinates of the first stationary object, longitudinal and transverse coordinates of the second stationary object, and first and second index flags of the respective first and second azimuth indexes, and
wherein the controller is further configured to correct the third azimuth index using Equation below:
Xpos
(
target
3
)
=
Δ
Xpos
_unit
×
(
index
3
-
index
1
)
+
Xpos
(
target
1
)
Ypos
(
target
3
)
=
Δ
Xpos
_unit
×
(
index
3
-
index
1
)
+
Ypos
(
target
1
)
where
Δ
Xpos
_unit
=
Xpos
(
target
2
)
-
Xpos
(
target
1
)
index
2
-
index
1
Δ
Ypos
_unit
=
Ypos
(
target
2
)
-
Ypos
(
target
1
)
index
2
-
index
1
wherein Xpos(target3) and Ypos(target3) are longitudinal and transverse coordinates at a position where the third stationary object is incorporated into the third azimuth index, Xpos(target1) and Ypos(target1) are the longitudinal and transverse coordinates of the first stationary object, Xpos(target2) and Ypos(target2) are the longitudinal and transverse coordinates of the second stationary object, and index1 to index3 are the index flags of the respective first to third azimuth indexes.
4. The apparatus according to claim 3 , wherein, in response to the distances from the vehicle to the first to third stationary objects being defined as first to third distances, respectively, the correction condition comprise any one or any combination of i) a condition in which the difference between the first and second distances is less than a reference value, ii) a condition in which the third azimuth index is located between the first and second azimuth indexes, iii) a condition in which the difference between the first and third distances is greater than a reference value and the difference between the second and third distances is greater than a reference value, and iv) a condition in which the third distance is greater than the first and second distances.
5. An apparatus for monitoring a surrounding environment of a vehicle, comprising:
a sensor unit comprising a plurality of detection sensors for detecting objects outside a vehicle according to a frame at a time period; and
a controller configured to;
extract a stationary object from among the objects detected by the sensor unit,
map the extracted stationary object to a grid map,
calculate an occupancy probability parameter, indicative of a probability that the stationary object is located on a grid of the grid map, from a result of mapping,
monitor the surrounding environment of the vehicle by specifying a grid on which the stationary object is located in the grid map, based on the calculated occupancy probability parameter,
apply a clustering algorithm to the specified grid to create one or more clusters composed of a plurality of grids having a same characteristic, and to
extract an edge grid of each of the created one or more clusters to monitor a continuous structure around the vehicle.
6. The apparatus according to claim 5 , wherein the controller is further configured to:
determine a peak grid with a maximum occupancy probability parameter among the plurality of grids in the grid map, and to
determine that the stationary object is located on the peak grid, in response to the occupancy probability parameter of the peak grid being equal to or greater than a threshold value defined for the peak grid, and the peak grid on which the stationary object is determined to be located comprises a plurality of peak grids in relation to the driving of the vehicle.
7. The apparatus according to claim 6 , wherein the controller is further configured to use a density based spatial clustering of applications with noise (DBSCAN) algorithm as the clustering algorithm to create one or more clusters.
8. The apparatus according to claim 7 , wherein the clustering criterion of the DBSCAN algorithm corresponds to a distance between the peak grids where the stationary object is determined to be located.
9. The apparatus according to claim 5 , wherein the controller is further configured to extract grids in which a peak grid does not exist in an immediately adjacent grid, as edge grid of the cluster, from among the grids constituting the cluster.
10. The apparatus according to claim 9 , wherein the controller is further configured to determine nearest edge grids, which are at positions closest to the vehicle, among the extracted edge grids, and to determine the nearest edge grids as grids on which continuous structures around the vehicle are located, in response to the determined nearest edge grids being continuously arranged.
11. The apparatus according to claim 10 , wherein the grid map has a longitudinal axis, a transverse axis, and an index set with respect to the vehicle; and
wherein when the nearest edge grids of the cluster are determined, the controller is further configured to determine the nearest edge grids of the cluster in a variable manner depending on a quadrant in which that cluster exists from among first to fourth quadrants partitioned in the grid map with respect to the vehicle.
12. The apparatus according to claim 11 , wherein the controller is further configured to:
determine, as a nearest edge grid, a grid with minimum longitudinal and minimum transverse coordinates of an index among the edge grids of the cluster, in response to the cluster existing in the first quadrant;
determine, as a nearest edge grid, a grid with maximum longitudinal and minimum transverse coordinates of an index among the edge grids of the cluster, in response to the cluster existing in the second quadrant;
determine, as a nearest edge grid, a grid with maximum longitudinal and maximum transverse coordinates of an index among the edge grids of the cluster, in response to the cluster existing in the third quadrant; and
determine, as a nearest edge grid, a grid with minimum longitudinal and maximum transverse coordinates of an index among the edge grids of the cluster, in response to the cluster existing in the fourth quadrant.