Object tracking using linear features
First Claim
Patent Images
1. A method of tracking static and dynamic objects within an environment, the method comprising:
- acquiring point sensor data in three dimensions related to the environment, the point sensor data including present point sensor data and previous point sensor data;
identifying present linear features within the present point sensor data;
tracking previous linear features from a previous set of tracked linear features to the present linear features to determine a position of each present linear feature relative to a previous position; and
creating a set of tracked linear features, the set of tracked linear features being used to track static and dynamic objects within the environment,the set of tracked linear features including;
present linear features tracked from previous linear features;
present linear features not tracked from previous linear features; and
untracked previous linear features not tracked to present linear features,the untracked previous linear features being in the previous set of tracked linear features but not identified in the present point sensor data,each linear feature within the set of tracked linear features having a feature probability,feature probabilities of the untracked previous linear features being reduced relative to corresponding previous feature probabilities in the previous set of tracked linear features.
2 Assignments
0 Petitions
Accused Products
Abstract
A method of tracking objects within an environment comprises acquiring sensor data related to the environment, identifying linear features within the sensor data, and determining a set of tracked linear features using the linear features identified within the sensor data and a previous set of tracked linear features, the set of tracked linear features being used to track objects within the environment.
32 Citations
15 Claims
-
1. A method of tracking static and dynamic objects within an environment, the method comprising:
-
acquiring point sensor data in three dimensions related to the environment, the point sensor data including present point sensor data and previous point sensor data; identifying present linear features within the present point sensor data; tracking previous linear features from a previous set of tracked linear features to the present linear features to determine a position of each present linear feature relative to a previous position; and creating a set of tracked linear features, the set of tracked linear features being used to track static and dynamic objects within the environment, the set of tracked linear features including; present linear features tracked from previous linear features; present linear features not tracked from previous linear features; and untracked previous linear features not tracked to present linear features, the untracked previous linear features being in the previous set of tracked linear features but not identified in the present point sensor data, each linear feature within the set of tracked linear features having a feature probability, feature probabilities of the untracked previous linear features being reduced relative to corresponding previous feature probabilities in the previous set of tracked linear features. - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. A method of tracking static and dynamic objects within an environment, the method comprising:
-
acquiring point sensor data in three dimensions related to the environment, the point sensor data including present point sensor data and previous point sensor data; identifying present linear features within the environment using the present point sensor data obtained from the environment; identifying mappings of previous tracked linear features to the present linear features to determine a position of each present linear feature relative to a previous position; determining a feature probability for each present linear feature; and creating a set of present tracked linear features including the present linear features, the set of present tracked linear features further including unmapped previous linear features not mapped to present linear features, the unmapped previous linear features being identified in previous point sensor data but not being identified in the present point sensor data, the feature probability of unmapped previous linear features being reduced, the set of present tracked linear features and mappings being used to track static and dynamic objects within the environment. - View Dependent Claims (8, 9, 10, 11)
-
-
12. A method of tracking static and dynamic objects within an environment, the method comprising:
-
obtaining point sensor data in three dimensions from the environment, the point sensor data including range data; identifying linear features within the environment using the point sensor data; and tracking static and dynamic objects within the environment by tracking the linear features to determine a position of each present linear feature relative to a previous position, wherein the linear features are identified within the point sensor data using a locality-based neighborhood calculation including; determining a normal vector for each point sensor data point using sampled point sensor data around each point sensor data point; and clustering proximate point sensor data points having similar normal vectors, proximate data points being selected using a local distance function, the local distance function extending further in an elongation direction of a pre-existing linear cluster. - View Dependent Claims (13, 14, 15)
-
Specification