US20200355782A1 - Multi-sensor target tracking using multiple hypothesis testing - Google Patents
Multi-sensor target tracking using multiple hypothesis testing Download PDFInfo
- Publication number
- US20200355782A1 US20200355782A1 US16/812,450 US202016812450A US2020355782A1 US 20200355782 A1 US20200355782 A1 US 20200355782A1 US 202016812450 A US202016812450 A US 202016812450A US 2020355782 A1 US2020355782 A1 US 2020355782A1
- Authority
- US
- United States
- Prior art keywords
- tracks
- measurements
- track
- hypothesis
- collection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
- G01S5/0294—Trajectory determination or predictive filtering, e.g. target tracking or Kalman filtering
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S11/00—Systems for determining distance or velocity not using reflection or reradiation
- G01S11/12—Systems for determining distance or velocity not using reflection or reradiation using electromagnetic waves other than radio waves
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/66—Radar-tracking systems; Analogous systems
- G01S13/72—Radar-tracking systems; Analogous systems for two-dimensional tracking, e.g. combination of angle and range tracking, track-while-scan radar
- G01S13/723—Radar-tracking systems; Analogous systems for two-dimensional tracking, e.g. combination of angle and range tracking, track-while-scan radar by using numerical data
- G01S13/726—Multiple target tracking
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
- G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/66—Sonar tracking systems
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/88—Sonar systems specially adapted for specific applications
- G01S15/93—Sonar systems specially adapted for specific applications for anti-collision purposes
- G01S15/931—Sonar systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/16—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using electromagnetic waves other than radio waves
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/18—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using ultrasonic, sonic, or infrasonic waves
Definitions
- FIG. 3 A decision tree is shown in FIG. 3 .
- the figure shows how the tracks are preserved over multiple scans of measurements
Abstract
The invention is for a multi-sensor multiple hypotheses testing tracking system. The multi-hypothesis testing system associates measurements from multiple sensors with tracks. Measurements are incorporated using a Kalman Filter and the same filters are used to propagate the trajectories of the tracks.
Description
- This application is a continuation of U.S. patent application Ser. No. 16/351,668 filed Mar. 13, 2019, which is a continuation of U.S. patent application Ser. No. 14/835,094 filed on Aug. 25, 2015, now U.S. Pat. No. 10,241,191 issued on Mar. 26, 2019, which claims priority from provisional application U.S. Patent Application Ser. No. 62/041,454 filed on Aug. 25, 2014.
- This invention was partly developed under U.S. Air Force Contracts FA9453-07-M-0110 and FA9453-08-C-0073.
- The present invention relates to the tracking of multiple targets.
- Estimating the position of multiple targets with one or more sensor requires assignment measurements to tracks
- A track is defined as the unique path of a distinct object. In situations where there are a multiple objects, such as for a radar system in a car during rush hour traffic, it is necessary to associate measurements with objects.
- Track Oriented Multiple Hypothesis Testing is a powerful technique for assigning measurements to tracks of objects when the number of objects is unknown or changing. It is absolutely essential for accurate tracking of multiple objects.
- Tracking is based on the formulation of hypotheses. Hypotheses are sets of tracks with consistent data, that is, where no measurements are assigned to more than one track.
- The track-oriented approach recomputes the hypotheses using the newly updated tracks after each scan of data is received. Rather than maintaining, and expanding, hypotheses from scan to scan, the track-oriented approach discards the hypotheses formed on scan $k−1$. The tracks that survive pruning are propagated to the next scan k where new tracks are formed, using the new observations, and reformed into hypotheses. Except for the necessity to delete some tracks based upon low probability, no information is lost because the track scores, that are maintained, contain all the relevant statistical data.
- Hypotheses are sets of tracks with consistent data, that is, where no measurements are assigned to more than one track. The track-oriented approach recomputes the hypotheses using the newly updated tracks after each scan of data is received. Rather than maintaining, and expanding, hypotheses from scan to scan, the track-oriented approach discards the hypotheses formed on scan k−1. The tracks that survive pruning are propagated to the next scan k where new tracks are formed, using the new observations, and reformed into hypotheses. Except for the necessity to delete some tracks based upon low probability, no information is lost because the track scores, that are maintained, contain all the relevant statistical data.
- Ding, et. al, U.S. Pat. No. 7,626,535, Dec. 1, 2009, “Track Quality Based Multi-Target Tracker,” discloses a track based multi-target tracking system. Their method does not allow for multiple sensors and provides not mechanism for multiple sensors. This application improves on their patent by providing a rigorous method for using mulitple sensors and a more robust tracking algorithm.
- Carson, et. al, U.S. Pat. No. 5,379,044, Jan. 3, 1995, “Efficient Multi-Target Tracking System,” cannot be adapted to multiple-sensors. In addition, this application improves on its processing method by using integer programming which is far more efficient than the disclosed algorithm.
- Miller, U.S. Pat. No. 4,072,943, Feb. 7, 1978, “Multi-Target Tracking” provides no mechanism for associating measurements with multi-targets nor can it be added to the disclosed system.
- The cited patents for tracking targets do not solve the fundamental problem of assigning multiple measurements to multiple objects when the objects are observed by multiple sensors.
- The present invention provides a multiple sensor target tracking system.
- The invention pertains to using track oriented multiple hypothesis testing with multiple sensors.
-
FIG. 1 shows a diagram of the sensing problem; -
FIG. 2 shows a block diagram of the system; -
FIG. 3 shows a decision tree. -
FIG. 4 shows a flow chart; - In the following description, for purposes of explanation, specific numbers, materials and configurations are set forth in order to provide a thorough understanding of the invention. It will be apparent, however, to one having ordinary skill in the art, that the invention may be practiced without these specific details. In some instances, well-known features may be omitted or simplified so as not to obscure the present invention. Furthermore, reference in the specification to “one embodiment” or “an embodiment” means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the invention. The appearances of the phrase “in an embodiment” in various places in the specification are not necessarily all referring to the same embodiment.
- During the course of this description like numbers will be used to identify like elements according to the different views, which illustrate the invention.
- In this disclosure a Measurement is a single measurement taken from a single sensor during a scan. A measurement by itself does not yet imply any association with an object. A Scan is a collection of measurements taken over one time interval. A scan can include measurements from multiple sensors. A Track is a sequence of measurements across multiple scans that are associated with the same object. A Hypothesis is set of compatible tracks.
- An embodiment of the tracking problem that is the subject of this invention is shown in
FIG. 1 . This diagram shows various elements of the tracking problem. - A block diagram of the tracking system is shown in
FIG. 2 . - Before discussing the method of hypothesis formation, it is useful to first consider track formation and how tracks are associated with unique objects.
- New tracks may be formed in one of two ways:
- The new track is based on some existing track, with the addition of a new measurement
- The new track is NOT based on any existing tracks; it is based solely on a single new measurement
- Each track is formed as a sequence of measurements across multiple scans.
- In addition to the raw measurement history, every track also contains a history of state and covariance data that is computed from a Kalman filter.
- When a new measurement is appended to an existing track, we are spawning a new track that includes all of the original track's measurements, plus this new measurement.
- Therefore, the new track is describing the same object as the original track.
- A new measurement can also be used to generate a completely new track that is independent of past measurements.
- When this is done, we are effectively saying that the measurement does not describe any of the objects that are already being tracked. It therefore must correspond to a new/different object.
- In this way, each track is given an object ID to distinguish which object it describes. Within the context of track-tree diagrams, all of the tracks inside the same track-tree have the same object ID. For example, if at some point there are 10 separate track-trees, this means that 10 separate objects are being tracked in the MHT system. When a valid hypothesis is formed, it may turn out that only a few of these objects have compatible tracks.
- In MHT, a valid hypothesis is any compatible set of tracks. In order for two or more tracks to be compatible, they cannot describe the same object, and they cannot share the same measurement at any of the scans. The task in hypothesis formation is to find one or more combinations of tracks that: 1) are compatible, and 2) maximize some performance function.
- The hypothesis formation step is formulated as an integer program (IP). Each track is given an aggregate score that reflects the component scores attained from each measurement.
- The IP formulation is constructed to select a set of compatible tracks that add to give the highest score.
- Let NT be the total number of tracks currently being maintained, let NO be the number of different objects represented by those tracks, and let NS be the number of scans. Assuming measurements come from a single sensor, then for any given scan, each track can have either a) no measurement or b) a single measurement. Let the score of the measurement for track i at scan j be denoted as s(i,j). The total score for each track is then:
-
- Each track is a collection of measurements that, together, represent the believed state evolution of one object. Therefore, each track has an associated object ID, T(i). Multiple tracks may share the same object ID. These are considered alternative tracks on the same track-tree. Each of these tracks represents a different sequence of measurements that could be used to describe the object. For two tracks to be compatible within a hypothesis, they must meet the following criteria:
- Compatible tracks cannot have the same object ID.
- Compatible tracks cannot share the same measurement.
- At each scan j, a set of NM(j) measurements are taken. Each of these measurements is assigned a unique index. Let m(i,j) denote the measurement index for track i at scan j, where
-
m(i,j)∈{1,2, . . . N M(j)} - Consider two tracks, i≠i
- For the two tracks to be compatible the object IDs must be different and the measurements at each scan must be different.
- This can be written as follows:
-
- Now, let x(i) be a binary decision variable, representing whether track i is selected or not. Also, let the set of tracks whose object ID is p be represented as O(p) The object ID constraints can be written as:
-
- This says that there can be no more than one track with the object ID of p. Applying this constraint for the full list of object IDs ensures that each object is either a) not included in the hypothesis, or b) represented by one track.
- Let R(j,k) represent the set of tracks that have measurement k at scan j.
- The measurement index constraint can be rewritten as:
-
- We can now put the constraints and the objective function together to formulate the IP.
-
- This formulation can also be extended to solve for multiple hypotheses, rather than just one.
- In this case, the solution would provide the “M Best” hypotheses, in descending order of score. This enables tracks to be preserved from alternate hypotheses that may be very close in score to the best.
- To solve for a second hypothesis, we introduce a new set of decision variables, y. This is similar to x but represents an alternative set of tracks to form an alternative hypothesis. The same objective function and constraints are applied to y. In addition, we apply a new constraint which forces the score of $x$ to be higher than the score of $y$. This ensures that the two solutions are different.
-
- where δ>0 is small number. This constraint must be applied to each pair of hypotheses.
- The new IP formulation with two hypotheses becomes:
-
- For M hypotheses, there are M sets of the original constraints, plus M(M−1)/2 new constraints for solution uniqueness. In general, there may not exist M valid hypotheses. Therefore, the problem can be formulated and solved for M=1 first, then M=2, and so on.
- Previously we assumed that all measurements came from a single sensor. We now consider the case where measurements are obtained from multiple sensors.
- There are some important differences in how track formation is carried out when multiple sensors are present.
- With a single sensor, we can add a NULL measurement or a single real measurement at each scan. With multiple sensors, we can add a NULL measurement, a single real measurement, or multiple real measurements at each scan. If multiple measurements are added to a track for a single scan, they must all come from different sensors.
- With a single sensor, if multiple measurements in one scan were within the gate of a track, each spawned a new track with that measurement appended. Now considering multiple sensors, we must check the sensor ID of all the measurements in the gate of a track. If these measurements are from different sensors, then they can all be appended to the same track. However, if any sensor has multiple measurements that are in the gate of a track, then new tracks must be spawned for each of these different combinations of measurements.
- As before, let NT be the total number of tracks currently being maintained, let NO be the number of different objects represented by those tracks, and let NS be the number of scans.
- The track score is still defined according as shown above.
- Now let NQ≥1 be the number of sensors. Then for any given scan, each track can have either a) no measurement or b) as many as NQ measurements.
- The following criteria must be met for two tracks to be compatible:
- Compatible tracks cannot have the same object ID.
- Compatible tracks cannot share the same measurement from the same sensor.
- The object ID constraints remain the same.
- Previously, we defined R(j,k) as the set of tracks that have measurement $k$ at scan j. We now introduce multiple sensors. Let R*(j,k,q) be the set of tracks that have measurement k from sensor q at scan j.
- The measurement index constraint can now be written as:
-
- The contents of the set R* for each (j,k,q) triple are a set of incompatible tracks.
- Track pruning is carried out on an intermittent basis. Nominally, a set frequency can be used throughout the process—for example, prune tracks once every 5 scans. Another option is to conduct the pruning step when the number of tracks exceeds a set threshold. In any case, the purpose of track pruning is to delete the tracks that we think are wrong, and keep only those that we think may be correct.
- We employ a pruning method in which the following tracks are preserved:
- Tracks with the “N” highest scores
- Tracks that are included in the “M best” hypotheses
- Tracks that have both 1) the object ID and 2) the first “P” measurements found in the “M best” hypotheses.
- We use the results of hypothesis formation to guide track pruning. The parameters N, M, P can be tuned to improve performance. The objective with pruning is to reduce the number of tracks as much as possible, while not removing any tracks that should be part of the actual true hypothesis.
- The second item listed above is to preserve all tracks included in the “M best” hypotheses. Each of these is a full path through a track-tree, which is clear. The third item listed above is similar, but less constrained. Consider one of the tracks in the “M best” hypotheses. We will preserve this full track. In addition, we will preserve all tracks that stem from scan “P” of this track.
-
FIG. 3 provides an example of which tracks in a track-tree might be preserved. The diagram shows 17 different tracks over 5 scans. The green track represents one of the tracks found in the set of “M best” hypotheses, from the hypothesis formation step. This track would be preserved. The orange tracks all stem from the node in this track atscan 2. These would be preserved if we set P=2 from the description above. - A decision tree is shown in
FIG. 3 . The figure shows how the tracks are preserved over multiple scans of measurements - A flow chart is shown in
FIG. 4 . - Multiple sensors generate measurements. Each sensor may generate multiple measurements.
- An object can only have one measurement per sensor. All measurements create a new track. The covariances are used to determine if a measurement should be associated with an existing track or multiple existing tracks.
- Hypotheses are formed.
- Hypotheses are pruned. Ideally only one hypothesis remains. Tracks that are not part of a retained hypothesis are removed.
- Measurements are incorporated.
- Tracks are propagated
- Updated covariances are made available.
- Estimated states are output.
- Although the invention herein has been described with reference to particular embodiments, it is to be understood that these embodiments are merely illustrative of the principles and applications of the present invention. It is therefore to be understood that numerous modifications may be made to the illustrative embodiments and that other arrangements may be devised without departing from the spirit and scope of the present invention as defined by the appended claims.
Claims (10)
1. A system for tracking a plurality of moving vehicles that reduces a number of computations required, the system comprising:
a plurality of sensors that form a plurality of scans by measuring positions of the plurality of moving vehicles over a plurality of time intervals, wherein each of the plurality of scans is a collection of measurements from the plurality of sensors taken in a particular time interval; and
a processor that is communicatively coupled to the plurality of sensors; wherein the processor:
receives, from the plurality of sensors, a first collection of measurements of a first scan measured during a first time interval, wherein each measurement of the first collection of measurements is a single measurement from one of the plurality of sensors,
generates a first group of tracks using a dynamic state transition model, wherein the first group of tracks includes a track for each of the first collection of measurements;
forms a first hypothesis for the first group of tracks, wherein the first hypothesis is a set of compatible tracks, wherein two or more tracks are compatible if each track describes a different target and do not share an identical measurement from any of the plurality of scans;
removes one or more particular tracks from the first group of tracks that are not included in the first hypothesis to form a first pruned group by assigning a score to each track group;
predicts using a Kalman filter, expected positions of each of the plurality of moving vehicles based on the first pruned group;
updates the dynamic state transition model to form an updated dynamic transition model based on a plurality of covariances calculated for the first pruned group,
receives, from the plurality of sensors, a second collection of measurements from a second scan during a second time interval,
forms a second hypothesis based on the updated dynamic transition model, and
tracks the plurality of moving vehicles based on the second hypothesis.
2. The system of claim 1 , wherein the plurality of sensors includes a camera.
3. The system of claim 1 , wherein the plurality of sensors includes a radar device.
4. The system of claim 1 , wherein the plurality of sensors includes a range finder.
5. The system of claim 1 , wherein the plurality of sensors is an acoustic range finder.
6. The system of claim 1 , wherein the Kalman filter is an unscented Kalman filter.
7. The system of claim 1 , wherein the Kalman filter is any combination of a Kalman filter, an unscented Kalman filter, and an extended Kalman filter.
8. A method for tracking a plurality of moving vehicles that reduces a required number of computations, the method comprising:
receiving, from a plurality of sensors, a first collection of measurements of a first scan measured during a first time interval, wherein the plurality of sensors form a plurality of scans by measuring positions of the plurality of moving vehicles over a plurality of time intervals, wherein each of the plurality of scans is a collection of measurements from the plurality of sensors taken in a particular time interval;
generating a first group of tracks using a dynamic state transition model, wherein the first group of tracks includes a track for each of the first collection of measurements;
forming a first hypothesis for the first group of tracks, wherein the first hypothesis is a set of compatible tracks, and two or more tracks are compatible if each track describes a different target and do not share an identical measurement from any of the plurality of scans;
removing one or more particular tracks from the first group of tracks that are not included in the first hypothesis to form a first pruned group by assigning a score to each track;
predicting, using a Kalman filter, expected positions of each of the plurality of moving vehicles based on the first pruned group;
updating the dynamic state transition model to form an updated dynamic transition model based on a plurality of covariances calculated for the first pruned group;
receiving, from the plurality of sensors, a second collection of measurements from a second scan during a second time interval;
forming a second hypothesis based on the updated dynamic transition model; and
tracking the plurality of moving vehicles based on the second hypothesis.
9. The method of claim 8 , wherein the second hypothesis is formed by appending one of the second collection of measurements to an existing track in the first pruned group by generating a new track that includes at least one of the first collection of measurements associated with the existing track on a condition that the one of the second collection of measurements describes an object described by the existing track.
10. The method of claim 8 , wherein the second hypothesis is formed by generating a new track, independent of all of first collection of measurements, using one of the second collection of measurements on a condition that the one of the second collection of measurements does not describe an object described by any existing track in the first hypothesis.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US16/812,450 US20200355782A1 (en) | 2014-08-25 | 2020-03-09 | Multi-sensor target tracking using multiple hypothesis testing |
Applications Claiming Priority (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US201462041454P | 2014-08-25 | 2014-08-25 | |
US14/835,094 US10241191B2 (en) | 2014-08-25 | 2015-08-25 | Multi-sensor target tracking using multiple hypothesis testing |
US16/351,668 US10585163B2 (en) | 2014-08-25 | 2019-03-13 | Multi-sensor target tracking using multiple hypothesis testing |
US16/812,450 US20200355782A1 (en) | 2014-08-25 | 2020-03-09 | Multi-sensor target tracking using multiple hypothesis testing |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/351,668 Continuation US10585163B2 (en) | 2014-08-25 | 2019-03-13 | Multi-sensor target tracking using multiple hypothesis testing |
Publications (1)
Publication Number | Publication Date |
---|---|
US20200355782A1 true US20200355782A1 (en) | 2020-11-12 |
Family
ID=55348151
Family Applications (3)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US14/835,094 Active 2036-08-07 US10241191B2 (en) | 2014-08-25 | 2015-08-25 | Multi-sensor target tracking using multiple hypothesis testing |
US16/351,668 Active US10585163B2 (en) | 2014-08-25 | 2019-03-13 | Multi-sensor target tracking using multiple hypothesis testing |
US16/812,450 Abandoned US20200355782A1 (en) | 2014-08-25 | 2020-03-09 | Multi-sensor target tracking using multiple hypothesis testing |
Family Applications Before (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US14/835,094 Active 2036-08-07 US10241191B2 (en) | 2014-08-25 | 2015-08-25 | Multi-sensor target tracking using multiple hypothesis testing |
US16/351,668 Active US10585163B2 (en) | 2014-08-25 | 2019-03-13 | Multi-sensor target tracking using multiple hypothesis testing |
Country Status (1)
Country | Link |
---|---|
US (3) | US10241191B2 (en) |
Families Citing this family (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102016218093A1 (en) * | 2016-09-21 | 2018-03-22 | Robert Bosch Gmbh | Operating method for an ultrasonic sensor system, control device, ultrasonic sensor system and vehicle |
DE102016218064A1 (en) * | 2016-09-21 | 2018-03-22 | Robert Bosch Gmbh | Operating method for an ultrasonic sensor system, control device, ultrasonic sensor system and vehicle |
CN106709938B (en) * | 2016-11-18 | 2019-10-18 | 电子科技大学 | Based on the multi-target tracking method for improving TLD |
US10564276B2 (en) * | 2017-03-02 | 2020-02-18 | GM Global Technology Operations LLC | Adaptive process noise description for improved kalman filter target tracking |
US10421452B2 (en) * | 2017-03-06 | 2019-09-24 | GM Global Technology Operations LLC | Soft track maintenance |
CN106874701B (en) * | 2017-04-10 | 2019-01-08 | 哈尔滨工业大学 | A kind of multi-model maneuvering target tracking filtering method being limited based on models switching number |
US11022511B2 (en) | 2018-04-18 | 2021-06-01 | Aron Kain | Sensor commonality platform using multi-discipline adaptable sensors for customizable applications |
JP7060441B2 (en) * | 2018-05-10 | 2022-04-26 | 株式会社デンソーテン | Radar device and target detection method |
CN108646739A (en) * | 2018-05-14 | 2018-10-12 | 北京智行者科技有限公司 | A kind of sensor information fusion method |
CN109358316B (en) * | 2018-11-05 | 2022-04-22 | 南开大学 | Line laser global positioning method based on structural unit coding and multi-hypothesis tracking |
JP7313299B2 (en) | 2020-02-25 | 2023-07-24 | 三菱電機株式会社 | Information processing device, information processing method, and information processing program |
CN111812638B (en) * | 2020-07-17 | 2022-07-29 | 北京理工大学 | IMM-MHT multi-target tracking method |
US20220065587A1 (en) * | 2020-08-31 | 2022-03-03 | Raytheon Company | System and method of hypersonic object tracking |
CN113281744B (en) * | 2021-03-11 | 2023-03-21 | 中南大学 | Time sequence InSAR method based on hypothesis test and self-adaptive deformation model |
CN113109761B (en) * | 2021-04-13 | 2023-04-07 | 北京工业大学 | Trajectory-oriented calculation time reduction method based on multi-hypothesis tracking algorithm |
CN112990124B (en) * | 2021-04-26 | 2021-08-06 | 湖北亿咖通科技有限公司 | Vehicle tracking method and device, electronic equipment and storage medium |
Family Cites Families (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4072943A (en) | 1975-04-14 | 1978-02-07 | Rca Corporation | Multi-target tracker |
US5379044A (en) | 1993-12-23 | 1995-01-03 | Hughes Aircraft Company | Efficient multi-target tracking method |
EP1610152B1 (en) * | 2004-05-28 | 2017-05-03 | Saab Ab | Tracking of a moving object for a self-defence system |
US8089393B2 (en) * | 2006-06-13 | 2012-01-03 | Bae Systems Plc | Relating target tracking |
US7626535B2 (en) | 2006-11-09 | 2009-12-01 | Raytheon Company | Track quality based multi-target tracker |
DE102006057276B4 (en) * | 2006-12-05 | 2023-09-28 | Robert Bosch Gmbh | Method and device for object tracking in a driver assistance system of a motor vehicle |
US8027741B2 (en) * | 2008-05-29 | 2011-09-27 | The United States Of America As Represented By The Secretary Of The Navy | System and method of improved kalman filtering for estimating the state of a dynamic system |
BRPI0916647B1 (en) * | 2008-07-30 | 2019-10-29 | Bae Systems Plc | method for estimating states of a plurality of targets tracked by a plurality of sensors, sensor, and computer readable storage medium |
GB201004232D0 (en) * | 2010-03-15 | 2010-04-28 | Bae Systems Plc | Target tracking |
US8805648B2 (en) * | 2011-10-05 | 2014-08-12 | Ats Group (Ip Holdings) Limited | Data fusion in high computational load environments |
EP2799902A1 (en) * | 2013-04-30 | 2014-11-05 | Baselabs GmbH | Method and apparatus for the tracking of multiple objects |
US9612316B1 (en) * | 2014-07-31 | 2017-04-04 | Sandia Corporation | Correlation and 3D-tracking of objects by pointing sensors |
-
2015
- 2015-08-25 US US14/835,094 patent/US10241191B2/en active Active
-
2019
- 2019-03-13 US US16/351,668 patent/US10585163B2/en active Active
-
2020
- 2020-03-09 US US16/812,450 patent/US20200355782A1/en not_active Abandoned
Also Published As
Publication number | Publication date |
---|---|
US10241191B2 (en) | 2019-03-26 |
US20190212412A1 (en) | 2019-07-11 |
US10585163B2 (en) | 2020-03-10 |
US20160054430A1 (en) | 2016-02-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20200355782A1 (en) | Multi-sensor target tracking using multiple hypothesis testing | |
ES2334983T3 (en) | SYSTEM AND METHOD FOR ASSOCIATION OF MEASUREMENT DOMAIN DATA IN APPLICATIONS OF PASSIVE COHERENT LOCATION. | |
US8970429B2 (en) | Systems and methods for tracking targets by a through-the-wall radar using multiple hypothesis tracking | |
KR102168288B1 (en) | System and method for tracking multiple object using multi-LiDAR | |
JP2016075905A5 (en) | ||
US20160033276A1 (en) | Merging intensities in a phd filter based on a sensor track id | |
Leung et al. | Multifeature-based importance weighting for the PHD SLAM filter | |
US11668857B2 (en) | Device, method and computer program product for validating data provided by a rain sensor | |
Chen et al. | Multitarget multisensor tracking | |
Park et al. | Measuring intersection performance from bluetooth-based data utilized for travel time data collection | |
Qu et al. | Source localization by TDOA with random sensor position errors—part II: mobile sensors | |
CN102592038A (en) | DS-based data association method for multi-target tracking of wireless sensor network | |
Wang et al. | Robust exploration with multiple hypothesis data association | |
Wieneke et al. | The PMHT: Solutions to some of its problems | |
US10705182B2 (en) | Wideband ranging system | |
Chhetri et al. | Efficient search strategies for non-myopic sensor scheduling in target tracking | |
Janapati et al. | Indoor localization of cooperative WSN using PSO assisted AKF with optimum references | |
US5469374A (en) | Automatic data segmentation module for target motion analysis applications | |
Poston | Toward tracking multiple building occupants by footstep vibrations | |
US9851437B2 (en) | Adjusting weight of intensity in a PHD filter based on sensor track ID | |
CN113687347B (en) | Track cluster data processing method, system and readable storage medium | |
Zhang et al. | A new path optimization method in dynamic adverse weathers | |
Paluszek et al. | Multiple Hypothesis Testing | |
EP4166983A1 (en) | System and methods and computer program products for central, cluster aided multi-hypothesis tracking which may include bias correction | |
Chuong et al. | Range Estimation of Radar Targets Using a Temporal Convolutional Network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |