Object detection system
An object detection system includes a lidar-unit and a controller. The controller defines an occupancy-grid that segregates the field-of-view into columns, determine a first-occupancy-status of a column based on first-cloud-points detected by the lidar-unit in the column by a first-scan, determine a second-occupancy-status of the column based second-cloud-points detected in the column by a second-scan, determine a first-number of the first-cloud-points and a second-number of the second-cloud-points, and determine a dynamic-status of the column only if the column is classified as occupied by either the first-occupancy-status or the second-occupancy-status. The dynamic-status of the column is determined to be moving when a count-difference between the first-number and the second-number is greater than a difference-threshold, and the dynamic-status of the column is determined to be static when the count-difference is not greater than the difference-threshold and a registration-factor that aligns the first-cloud-points to the second-cloud-points is less than a registration-threshold.
1. An object detection system that determines a dynamic-status of an object proximate to an automated-vehicle, said system comprising:
a lidar-unit used to detect cloud-points in a field-of-view of the lidar-unit proximate to a host-vehicle; and
a controller in communication with the lidar-unit, said controller configured to
define an occupancy-grid that segregates the field-of-view into an array of columns,
determine a first-occupancy-status of a column based on a first-height of first-cloud-points detected in the column by a first-scan taken by the lidar-unit at a first-time, wherein the first-occupancy-status is determined to be occupied when the first-height is greater that a height-threshold,
determine a second-occupancy-status of the column based on a second-height of second-cloud-points detected in the column by a second-scan taken by the lidar-unit at a second-time subsequent to the first-time, wherein the second-occupancy-status is determined to be occupied when the second-height is greater than the height-threshold,
determine a first-number of the first-cloud-points detected in the column by the first-scan,
determine a second-number of the second-cloud-points detected in the column by the second-scan,
determine a dynamic-status of the column only if the column is classified as occupied by either the first-occupancy-status or the second-occupancy-status, wherein
the dynamic-status of the column is determined to be moving when a count-difference between the first-number and the second-number is greater than a difference-threshold, and
the dynamic-status of the column is determined to be static when the count-difference is not greater than the difference-threshold and a registration-factor that aligns the first-cloud-points to the second-cloud-points is less than a registration-threshold.
2. The system in accordance with claim 1 , wherein the controller is configured to
align the second-scan to the first-scan based on movement of the host-vehicle between the first-time and the second-time.
3. The system in accordance with claim 1 , wherein the column is associated with an adjacent-column to form a cluster when both the column and the adjacent-column are classified as occupied, and the dynamic-status of the cluster is determined to be moving when a majority of the columns that form the cluster are classified as moving.
4. The system in accordance with claim 1 , wherein the system includes a camera-unit that renders a first-image at the first-time and a second-image at a second-time, wherein the first-image and the second-image are aligned with the field-of-view of the lidar-unit, and the controller is further configured to determine the registration-factor of the column based on the first-cloud-points, the second-cloud-points, the first-image, and the second-image.
5. The system in accordance with claim 1 , wherein the system includes a camera-unit that renders a first-image at the first-time and a second-image at a second-time, wherein the first-image and the second-image are aligned with the field-of-view of the lidar-unit, and the controller is configured to determine the registration-factor of the column based on the first-image and the second-image when the first-number and the second-number are both less than a count-threshold.
6. The system in accordance with claim 1 , wherein the system includes a radar-unit that detects a first-target-group at the first-time and a second-target-group at the second-time, wherein the first-target-group and the second-target-group are aligned with the field-of-view of the lidar-unit, and the dynamic-status of the column is determined based on tracking of a target in the first-target-group and the second-target-group that is closest to a center-line of the column when the first-number and the second-number are both less than a count-threshold.
7. The system in accordance with claim 1 , wherein the system includes a radar-unit that indicates a radar-detection and is aligned with the lidar-unit, and the controller is further configured to determine the dynamic-status of the occupied columns in the first scan by defining a circle around a radar-detection and labeling all columns inside the circle with the dynamic information of the radar-detection.
8. The system in accordance with claim 1 , wherein each column is divided into a plurality of vertical cells.
9. The system in accordance with claim 8 , wherein each cell has an area of 0.2 square meters on one side.