LIDAR GROUND PLANE DETECTION USING PROJECTED AND FILTERED DATA
A system includes one or more processors configured to receive data point information captured using a lidar device, project the data point information onto a horizontal plane perspective, filter the projected data point information, determine a ground plane among one or more planes identified using the filtered projected data point information, and provide a parameter associated with the determined ground plane for configuring the lidar device. The system also includes a memory coupled with at least a portion of the one or more processors.
1 . A system, comprising:
one or more processors configured to:
receive data point information captured using a lidar device;
project the data point information onto a horizontal plane perspective;
filter the projected data point information;
determine a ground plane among one or more planes identified using the filtered projected data point information; and
provide a parameter associated with the determined ground plane for configuring the lidar device; and
a memory coupled with at least a portion of the one or more processors.
2 . The system of claim 1 , wherein the received data point information is collected during a first scan frame of the lidar device.
3 . The system of claim 2 , wherein the parameter associated with the determined ground plane is utilized to configure the lidar device for a second scan frame subsequent to the first scan frame.
4 . The system of claim 1 , wherein the received data point information is collected during a window of a scan frame of the lidar device that is shorter in time than the scan frame.
5 . The system of claim 1 , wherein the one or more processors are configured to project the data point information onto the horizontal plane perspective including by being configured to project a collection of points from a three-dimensional space.
6 . The system of claim 1 , wherein the one or more processors are configured to filter the projected data point information including by being configured to determine co-linearity of different data points of the projected data point information.
7 . The system of claim 1 , wherein the one or more processors are configured to determine the ground plane including by being configured to perform a planarity check of an initial plane.
8 . The system of claim 7 , wherein the one or more processors are configured to determine the ground plane including by being further configured to perform planarity checks of multiple sub-planes of the initial plane.
9 . The system of claim 8 , wherein the one or more processors are configured to determine the ground plane including by being further configured to perform planarity checks of multiple smaller sub-planes of the sub-planes of the initial plane.
10 . The system of claim 1 , wherein the one or more processors are configured to determine the ground plane including by being configured to perform a planarity check multiple times and iteratively on successively smaller sub-regions of an initial candidate ground plane.
11 . The system of claim 10 , wherein the one or more processors are configured to perform the planarity check including by being configured to determine a covariance matrix.
12 . The system of claim 11 , wherein the covariance matrix is a 3×3 matrix.
13 . The system of claim 11 , wherein the one or more processors are configured to determine the covariance matrix including by being configured to determine a summed area table based on areas of the successively smaller sub-regions of the initial candidate ground plane.
14 . The system of claim 11 , wherein the one or more processors are configured to perform the planarity check including by being further configured to determine eigenvalues of the covariance matrix.
15 . The system of claim 14 , wherein the one or more processors are configured to perform the planarity check including by being further configured to determine a ratio of a first eigenvalue of the determined eigenvalues to a second eigenvalue of the determined eigenvalues.
16 . The system of claim 15 , wherein the first eigenvalue is smaller than all other eigenvalues of the determined eigenvalues.
17 . The system of claim 15 , wherein the one or more processors are configured to perform the planarity check including by being further configured to compare the ratio with a specified threshold.
18 . The system of claim 1 , wherein the provided parameter is utilized by the lidar device to adjust a scan angle of the lidar device.
19 . A method, comprising:
receiving data point information captured using a lidar device;
projecting the data point information onto a horizontal plane perspective;
filtering the projected data point information;
determining a ground plane among one or more planes identified using the filtered projected data point information; and
providing a parameter associated with the determined ground plane for configuring the lidar device.
20 . A computer program product embodied in a non-transitory computer readable medium and comprising computer instructions for:
receiving data point information captured using a lidar device;
projecting the data point information onto a horizontal plane perspective;
filtering the projected data point information;
determining a ground plane among one or more planes identified using the filtered projected data point information; and
providing a parameter associated with the determined ground plane for configuring the lidar device.