Merging intensities in a PHD filter based on a sensor track ID
First Claim
1. A method of tracking multiple objects with a probabilistic hypothesis density filter, the method comprising:
- receiving reflected signals in a first one or more sensors and a second one or more sensors from an object in an environment around a vehicle, wherein the first one or more sensors and the second one or more sensors are onboard the vehicle;
detecting the received reflected signals in the first one or more sensors and the second one or more sensors;
computing a first one or more measurements based on the detected reflected signals in the first one or more sensors;
computing a second one or more measurements based on the detected reflected signals in the second one or more sensors;
generating a first intensity by combining the first one or more measurements, wherein a first set of track identifiers (IDs) includes one or more track IDs provided by the first one or more sensors corresponding to a respective measurement in the first one or more measurements, wherein the first intensity includes a weight, a state mean vector, and a state covariance matrix of statistics of a track of the object at a first time;
generating a second intensity by combining the second one or more measurements, wherein a second set of track IDs includes one or more track IDs provided by the second one or more sensors corresponding to a respective measurement in the second one or more measurements, wherein the second intensity includes a weight, a state mean vector, and a state covariance matrix of statistics of a track of the object at the first time;
comparing the first set of track IDs to the second set of track IDs; and
selectively merging the first intensity with the second intensity based on whether any track IDs in the first set of track IDs match any track IDs in the second set of track IDs.
1 Assignment
0 Petitions
Accused Products
Abstract
In one embodiment, a method of tracking multiple objects with a probabilistic hypothesis density filter is provided. The method includes generating a first intensity by combining a first one or more measurements, wherein a first set of track IDs associated with the first intensity includes track IDs corresponding to respective measurements in the first one or more measurements. A second intensity is generated by combining a second one or more measurements, wherein a second set of track IDs associated with the second intensity includes track IDs corresponding to respective measurements in the second one or more measurements. The first set of track IDs is compared to the second set of track IDs, and the first intensity is selectively merged with the second intensity based on whether any track IDs in the first set of track IDs match any track IDs in the second set of track IDs.
-
Citations
16 Claims
-
1. A method of tracking multiple objects with a probabilistic hypothesis density filter, the method comprising:
-
receiving reflected signals in a first one or more sensors and a second one or more sensors from an object in an environment around a vehicle, wherein the first one or more sensors and the second one or more sensors are onboard the vehicle; detecting the received reflected signals in the first one or more sensors and the second one or more sensors; computing a first one or more measurements based on the detected reflected signals in the first one or more sensors; computing a second one or more measurements based on the detected reflected signals in the second one or more sensors; generating a first intensity by combining the first one or more measurements, wherein a first set of track identifiers (IDs) includes one or more track IDs provided by the first one or more sensors corresponding to a respective measurement in the first one or more measurements, wherein the first intensity includes a weight, a state mean vector, and a state covariance matrix of statistics of a track of the object at a first time; generating a second intensity by combining the second one or more measurements, wherein a second set of track IDs includes one or more track IDs provided by the second one or more sensors corresponding to a respective measurement in the second one or more measurements, wherein the second intensity includes a weight, a state mean vector, and a state covariance matrix of statistics of a track of the object at the first time; comparing the first set of track IDs to the second set of track IDs; and selectively merging the first intensity with the second intensity based on whether any track IDs in the first set of track IDs match any track IDs in the second set of track IDs. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A method of tracking multiple objects with a probabilistic hypothesis density filter, the method comprising:
-
receiving reflected signals in a first one or more sensors and a second one or more sensors from an object in an environment around a vehicle, wherein the first one or more sensors and the second one or more sensors are onboard the vehicle; detecting the received reflected signals in the first one or more sensors and the second one or more sensors; computing a first one or more measurements based on the detected reflected signals in the first one or more sensors; computing a second one or more measurements based on the detected reflected signals in the second one or more sensors; generating a first intensity by combining the first one or more measurements, wherein a first set of track identifiers (IDs) includes one or more track IDs provided by the first one or more sensors corresponding to a respective measurement in the first one or more measurements, wherein the first intensity includes a weight, a state mean vector, and a state covariance matrix of statistics of a track of the object at a first time; generating a second intensity by combining the second one or more measurements, wherein a second set of track IDs includes one or more track IDs provided by the second one or more sensors corresponding to a respective measurement in the second one or more measurements, wherein the second intensity includes a weight, a state mean vector, and a state covariance matrix of statistics of a track of the object at a second time; selectively comparing the first set of track IDs to the second set of track IDs based on whether there are any track IDs in the first set of track IDs and the second set of track IDs that are the same type; and selectively merging the first intensity with the second intensity based on whether any track IDs in the first set of track IDs match any track IDs in the second set of track IDs; wherein selectively comparing includes; if the first set of track IDs includes a first track identifier (ID) that is an international civil aviation organization (ICAO) aircraft address and the second set of track IDs includes a second track ID that is an ICAO aircraft address, then; comparing the first track ID to the second track ID; if the first track ID matches the second track ID, then; computing a statistical distance between the first intensity and the second intensity; and merging the first intensity and the second intensity if the statistical distance is less than a first threshold; if the first set of track IDs includes a first track ID from a first sensor that correlates measurements across time and the second set of track IDs includes a second track ID from the first sensor, then; comparing the first track ID to the second track ID; if the first track ID matches the second track ID, then;
computing a statistical distance between the first intensity and the second intensity; and
merging the first intensity and the second intensity if the statistical distance is less than a second threshold;if either of the first and second set of track IDs do not include a track ID that is an ICAO aircraft address or if either of the first and second set of track IDs do not contain a track ID from the same sensor which correlates measurements across time, then; computing a statistical distance between the first intensity and the second intensity; and merging the first intensity and the second intensity if the statistical distance is less than a third threshold; otherwise, not merging the first intensity and the second intensity. - View Dependent Claims (10, 11, 12, 13, 14)
-
-
15. A tracking system for a vehicle, comprising:
-
one or more processing devices onboard the vehicle; a plurality of sensors onboard the vehicle and operatively coupled to the one or more processing devices; and one or more data storage devices onboard the vehicle and including instructions which, when executed by the one or more processing devices, cause the one or more processing devices to track multiple objects in an environment around the vehicle with a probabilistic hypothesis density filter, wherein the instructions cause the one or more processing devices to perform a method comprising; detecting reflected signals received by a first one or more of the plurality of sensors, and a second one or more of the plurality of sensors, from an object in the environment around the vehicle; computing a first one or more measurements based on the detected reflected signals in the first one or more of the plurality of sensors; computing a second one or more measurements based on the detected reflected signals in the second one or more of the plurality of sensors; generating a first intensity by combining the first one or more measurements, wherein a first set of track identifiers (IDs) includes one or more track IDs provided by the first one or more of the plurality of sensors corresponding to a respective measurement in the first one or more measurements, wherein the first intensity includes a weight, a state mean vector, and a state covariance matrix of statistics of a track of the object at a first time; generating a second intensity by combining the second one or more measurements, wherein a second set of track IDs includes one or more track IDs provided by the second one or more of the plurality of sensors corresponding to a respective measurement in the second one or more measurements, wherein the second intensity includes a weight, a state mean vector, and a state covariance matrix of statistics of a track of the object at the first time; comparing the first set of track IDs to the second set of track IDs; and selectively merging the first intensity with the second intensity based on whether any track IDs in the first set of track IDs match any track IDs in the second set of track IDs. - View Dependent Claims (16)
-
Specification