# US 12,601,840 B2 · Tuning parameter determination method for tracking an object, a group density-based clustering method, an object tracking method, and an object tracking apparatus using a lidar sensor

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

- Number: US 12,601,840 B2
- Document ID: US12601840B2
- Status: Granted
- Kind: B2
- Application number: 17/396,379
- Filed: 2021-08-06
- Published: 2022-06-09
- Granted: 2026-04-14
- Earliest claimed: 2020-12-03
- Assignees: Hyundai Motor Company; Kia Corporation
- Applicants: Hyundai Motor Company; Kia Corporation
- Inventors: Mu Gwan Jeong; Nam Gyun Kim
- Web page: https://patentgrep.com/patent/US12601840B2

## CPC

- G01S 17/66: Tracking systems using electromagnetic waves other than radio waves
- G01S 7/4802: {using analysis of echo signal for target characterisation; Target signature; Target cross-section}
- G01S 7/4808: {Evaluating distance, position or velocity data}
- G01S 7/486: Receivers
- G01S 17/89: for mapping or imaging
- G01S 17/931: of land vehicles
- G06F 18/22: Matching criteria, e.g. proximity measures
- G06F 18/23: Clustering techniques
- G06V 10/762: using clustering, e.g. of similar faces in social networks
- G06V 10/98: Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns
- G06V 20/58: Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- 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
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

An object-tracking apparatus using a LiDAR sensor of an embodiment includes: a LiDAR sensor configured to acquire a point cloud related to an object; a first clustering unit configured to primarily cluster the point cloud; and a second clustering unit configured to secondarily cluster the result of primary clustering in response to the time taken to perform primary clustering.

## Claims

### Claim 1

An object-tracking method using a LiDAR sensor, the object-tracking method comprising:
acquiring a point cloud related to an object;
performing primary clustering on the point cloud; and
performing secondary clustering on a result of the primary clustering depending on a time taken to perform the primary clustering,
wherein performing the primary clustering comprises:
performing grid-based clustering on the point cloud when an area of a region of the point cloud is greater than a first threshold area;
checking whether the area of the region of the point cloud is greater than a second threshold area that is less than the first threshold area when the area of the region of the point cloud is not greater than the first threshold area;
performing density-based clustering on points of the point cloud when the area of the region of the point cloud is greater than the second threshold area; and
performing group density-based clustering on the points of the point cloud when the area of the region of the point cloud is not greater than the second threshold area.

### Claim 2 (depends on 1)

The object-tracking method according to claim 1, further comprising:
measuring a time taken for the primary clustering,
wherein the secondary clustering is performed depending on the measured time.

### Claim 3 (depends on 2)

The object-tracking method according to claim 2, wherein the performing the secondary clustering comprises:
checking whether the measured time is greater than a first threshold time;
checking whether the number of target clusters obtained during the primary clustering is greater than a second predetermined number when the measured time is not greater than the first threshold time;
performing the grid-based clustering on the points that have undergone the primary clustering when the number of the target clusters is greater than the second predetermined number;
checking whether the measured time is less than a second threshold time when the number of the target clusters is not greater than the second predetermined number;
performing the density-based clustering on the points that have undergone the primary clustering when the measured time is less than the second threshold time; and
performing the group density-based clustering on the points that have undergone the primary clustering when the measured time is not less than the second threshold time.

### Claim 4 (depends on 1)

The object-tracking method according to claim 1, further comprising:
checking whether there is a cluster in which the number of points is not greater than a third predetermined number among clusters that have undergone the primary clustering or the secondary clustering; and
removing a cluster in which the number of points is not greater than the third predetermined number among the clusters that have undergone the primary clustering or the secondary clustering, and removing a cluster in which the number of points is greater than the third predetermined number and in which a similarity with a target cluster is outside of a predetermined range, among the clusters that have undergone the primary clustering or the secondary clustering.

### Claim 5

An object-tracking apparatus comprising:
a LiDAR sensor configured to acquire a point cloud related to an object;
a first clustering unit configured to primarily cluster the point cloud; and
a second clustering unit configured to secondarily cluster a result of primary clustering in response to a time taken to perform the primary clustering,
wherein the first clustering unit comprises:
a first comparison unit configured to compare an area of a region of the point cloud with a first threshold area;
a first grid-based clustering unit configured to perform grid-based clustering on the point cloud in response to a result of comparison by the first comparison unit;
a second comparison unit configured to compare the area of the region of the point cloud with a second threshold area that is less than the first threshold area in response to the result of comparison by the first comparison unit;
a first density-based clustering unit configured to perform density-based clustering on points of the point cloud in response to a result of comparison by the second comparison unit; and
a first group density-based clustering unit configured to perform group density-based clustering on the points of the point cloud in response to the result of comparison by the second comparison unit.

### Claim 6 (depends on 5)

The object-tracking apparatus according to claim 5, further comprising:
a time measurement unit configured to measure the time taken to primarily cluster the point cloud.

### Claim 7 (depends on 6)

The object-tracking apparatus according to claim 6, wherein the second clustering unit comprises:
a third comparison unit configured to compare the measured time with a first threshold time;
a fourth comparison unit configured to compare the number of target clusters obtained by the first clustering unit with a second predetermined number in response to a result of comparison by the third comparison unit;
a second grid-based clustering unit configured to perform grid-based clustering on the points clustered by the first clustering unit in response to a result of comparison by the fourth comparison unit;
a fifth comparison unit configured to compare the measured time with a second threshold time in response to the result of comparison by the fourth comparison unit;
a second density-based clustering unit configured to perform the density-based clustering on the points clustered by the first clustering unit in response to a result of comparison by the fifth comparison unit; and
a second group density-based clustering unit configured to perform the group density-based clustering on the points clustered by the first clustering unit in response to the result of comparison by the fifth comparison unit.

### Claim 8 (depends on 5)

The object-tracking apparatus according to claim 5, further comprising:
a sixth comparison unit configured to compare the number of points included in each of clusters clustered by the first clustering unit or the second clustering unit with a third predetermined number;
a similarity-checking unit configured to check similarity between a cluster, in which the number of points is greater than the third predetermined number among the primarily or secondarily clustered clusters, and a target cluster; and
a cluster-removing unit configured to remove a cluster in which the similarity is outside of a predetermined range or a cluster in which the number of points is not greater than the third predetermined number, in response to a result of comparison by the sixth comparison unit or a result of checking by the similarity-checking unit.