# US 2021/0239825 A1 · Object tracking apparatus

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0239825 A1
- Document ID: US20210239825A1
- Status: Published application
- Kind: A1
- Application number: 17/237,593
- Filed: 2021-04-22
- Published: 2021-08-05
- Earliest claimed: 2018-10-24
- Assignees: Denso Corporation
- Applicants: Denso Corporation
- Inventors: Yusuke AKAMINE; Takuya TAKAYAMA; Yasuyuki MIYAKE
- Web page: https://patentgrep.com/patent/US20210239825A1

## CPC

- G01S 13/723: {by using numerical data}
- G01S 7/415: {Identification of targets based on measurements of movement associated with the target}
- G01S 13/52: Discriminating between fixed and moving objects or between objects moving at different speeds
- G01S 13/584: {adapted for simultaneous range and velocity measurements}
- G01S 13/931: of land vehicles
- G01S 15/931: of land vehicles
- G01S 17/931: of land vehicles
- G01S 2013/9323: {Alternative operation using light waves}
- G01S 2013/9324: {Alternative operation using ultrasonic waves}
- 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

## Abstract

An object tracking apparatus generates a plurality of target candidates in which ambiguity in velocity is assumed for an object detected for a first time, calculates a current prediction value of a state quantity of each target candidate from a past estimation value of the state quantity of each target candidate, using one filter among a plurality of filters, and calculates the current estimation value of the state quantity of the target candidate from each of the calculated prediction values and a current observation value that matches each prediction value. The object tracking apparatus deletes the target candidate of which a determined likelihood is less than a preset threshold among the target candidates, and switches a used filter to a filter that has a larger number of state variables among the filters, in response to the target candidate being deleted and the total number of target candidates decreasing.

## Claims

### Claim 1

An object tracking apparatus comprising:
an object detecting unit configured to detect an object that is present in a vicinity of a sensor from sensor information detected by the sensor;
a velocity calculating unit configured to calculate a relative velocity of the object relative to the sensor as one observation value for each object detected by the object detecting unit;
a distance calculating unit configured to calculate a distance from the sensor to the object as one observation value for each object detected by the object detecting unit;
a candidate generating unit configured to generate a plurality of target candidates in which ambiguity in velocity is assumed for an object that is detected for a first time by the object detecting unit;
a filter processing unit configured to
have a plurality of filters of which state variables differs from each other in number,
calculate a current prediction value of a state quantity of each target candidate from a past estimation value of the state quantity of each target candidate, using one filter among the plurality of filters, and
calculate the current estimation value of the state quantity of the target candidate from each of the calculated prediction values and a current observation value that matches each prediction value;
a matching processing unit configured to match each prediction value of the state quantity of the target candidate and the observation value;
a candidate deleting unit configured to
determine a likelihood of each of the plurality of target candidates generated for a single object detected by the object detecting unit being a true target, and
delete a target candidate of which the determined likelihood is less than a preset threshold among the plurality of target candidates, or delete a predetermined number of target candidates in order from the target candidate of which the likelihood is lowest among the plurality of target candidates; and
a filter selecting unit that switches the filter used by the filter processing unit to a filter that has a larger number of state variables among the plurality of filters, in response to the target candidate being deleted by the candidate detecting unit and the total number of target candidates decreasing.

### Claim 2 (depends on 1)

The object tracking apparatus according to claim 1, wherein:
the filter that has fewest state variables among the plurality of filters has state variables that are equal to or less in number than an order of the observation values.

### Claim 3 (depends on 2)

The object tracking apparatus according to claim 2, wherein:
the filter that has most state variables among the plurality of filters has state variables that are greater in number than the order of the observation values.

### Claim 4 (depends on 3)

The object tracking apparatus according to claim 3, wherein:
the filter processing unit is configured to use a filter that has most state variables among the plurality of filters, in response to the target candidates generated for a single object detected by the object detecting unit becoming one.

### Claim 5 (depends on 4)

The object tracking apparatus according to claim 4, further comprising:
an orientation calculating unit configured to calculate an orientation of the object relative to the sensor as one observation value for each object detected by the object detecting unit, wherein
a filter that has fewest state variables among the plurality of filters includes at least one of the distance, the relative velocity, and the orientation of the object among the state variables.

### Claim 6 (depends on 5)

The object tracking apparatus according to claim 5, wherein:
a filter that has most state variables among the plurality of filters includes an X-coordinate value and a Y-coordinate value, and further has either an X-direction velocity and a Y-direction velocity, or a velocity and a velocity direction among the state variables.

### Claim 7 (depends on 6)

The object tracking apparatus according to claim 6, wherein:
the plurality of filters include a Kalman filter.

### Claim 8 (depends on 7)

The object tracking apparatus according to claim 7, wherein:
the candidate deleting unit is configured to determine the likelihood based on a matching-established count between the prediction value of the target candidate and the observation value, and/or a difference between the prediction value and the observation value.

### Claim 9 (depends on 8)

The object tracking apparatus according to claim 8, wherein:
the filter selecting unit is configured to select a filter to be used among the plurality of filters based on a total number of target candidates.

### Claim 10 (depends on 1)

The object tracking apparatus according to claim 1, wherein:
the filter that has most state variables among the plurality of filters has state variables that are greater in number than the order of the observation values.

### Claim 11 (depends on 1)

The object tracking apparatus according to claim 1, wherein:
the filter processing unit is configured to use a filter that has most state variables among the plurality of filters, in response to the target candidates generated for a single object detected by the object detecting unit becoming one.

### Claim 12 (depends on 1)

The object tracking apparatus according to claim 1, further comprising:
an orientation calculating unit configured to calculate an orientation of the object relative to the sensor as one observation value for each object detected by the object detecting unit, wherein
a filter that has fewest state variables among the plurality of filters includes at least one of the distance, the relative velocity, and the orientation of the object among the state variables.

### Claim 13 (depends on 1)

The object tracking apparatus according to claim 1, wherein:
a filter that has most state variables among the plurality of filters includes an X-coordinate value and a Y-coordinate value, and further has either an X-direction velocity and a Y-direction velocity, or a velocity and a velocity direction among the state variables.

### Claim 14 (depends on 1)

The object tracking apparatus according to claim 1, wherein:
the plurality of filters include a Kalman filter.

### Claim 15 (depends on 1)

The object tracking apparatus according to claim 1, wherein:
the candidate deleting unit is configured to determine the likelihood based on a matching-established count between the prediction value of the target candidate and the observation value, and/or a difference between the prediction value and the observation value.

### Claim 16 (depends on 1)

The object tracking apparatus according to claim 1, wherein:
the filter selecting unit is configured to select a filter to be used among the plurality of filters based on a total number of target candidates.
