Abstract: A vision first light detection and ranging (LIDAR) system captures an image including a targeted object and uses the image to determine a predicted location of the targeted object. Based on the predicted location, the vision first LIDAR system directs a tracking beam onto the targeted object and detects a portion of the tracking beam reflected by the targeted object. The vision first LIDAR system includes an image sensor to capture the image for predicting the location of the targeted object and includes a distance sensor to determine a distance to the targeted object using the tracking beam.
Type:
Grant
Filed:
July 16, 2020
Date of Patent:
September 3, 2024
Assignee:
CRAZING LAB, INC.
Inventors:
Sang-Pyo Kim, SeongYoon Cho, Jae Young Lee
Abstract: A vision based light detection and ranging (LIDAR) system captures images including a targeted object and identifies the targeted object using an object recognition model. To identify the targeted object, the vision based LIDAR system determines a type of object and pixel locations or a boundary box associated with the targeted object. Based on the identification, the vision based LIDAR system directs a tracking beam onto one or more spots on the targeted object and detects distances to the one or more spots. The vision based LIDAR system updates the identification of the targeted object based on the one or more determined distances.
Abstract: A vision based light detection and ranging (LIDAR) system detects motion of a targeted object using a dynamic vision sensor to locate and track the targeted object. The dynamic vision sensor identifies activity events associated with the motion of the targeted object based on changes in brightness detected at pixels of the dynamic vision sensor. Based on the identified events, the vision based LIDAR system predicts a location of the targeted object and directs a tracking beam onto one or more spots on the targeted object and determines distances to the one or more spots to track the motion of the targeted object in three dimensions.
Abstract: A vision based light detection and ranging (LIDAR) system detects motion of a targeted object using a dynamic vision sensor to locate and track the targeted object. The dynamic vision sensor identifies activity events associated with the motion of the targeted object based on changes in brightness detected at pixels of the dynamic vision sensor. Based on the identified events, the vision based LIDAR system predicts a location of the targeted object and directs a tracking beam onto one or more spots on the targeted object and determines distances to the one or more spots to track the motion of the targeted object in three dimensions.