# US 9,517,768 B2 · Method for object processing and vehicle supporting the same

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

- Number: US 9,517,768 B2
- Document ID: US9517768B2
- Status: Granted
- Kind: B2
- Application number: 14/304,588
- Filed: 2014-06-13
- Published: 2015-06-11
- Granted: 2016-12-13
- Earliest claimed: 2013-12-09
- Assignees: Hyundai Motor Company
- Applicants: Hyundai Motor Company
- Inventors: Young Chul Oh; Myung Seon Heo; Kyung Ho Yoo
- Web page: https://patentgrep.com/patent/US9517768B2

## CPC

- B60W 30/09: Taking automatic action to avoid collision, e.g. braking and steering
- B60W 30/143: {Speed control (B60W30/16 takes precedence)}
- B60W 40/04: Traffic conditions
- G01S 17/89: for mapping or imaging
- G01S 17/931: of land vehicles
- B60W 2050/143: {Alarm means}
- B60W 2554/80: Spatial relation or speed relative to objects
- G06F 18/23: Clustering techniques
- G06V 10/145: Illumination specially adapted for pattern recognition, e.g. using gratings
- 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
- B60W: CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- 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

A vehicle for supporting an object processing includes a lidar sensor configured to collect multi-layer data corresponding to sensor information for a lateral surface for each vertical interval. A controller is configured to classify objects by clustering each layer for the multi-layer data, extract contours and shapes of the objects, and then control a convergence of the objects based on a calculated value of a Mahalanobis distance between the clustered objects, and a method for an object processing.

## Claims

### Claim 1

A vehicle for supporting an object processing, the vehicle comprising:
a lidar sensor configured to collect multi-layer data corresponding to sensor information for a lateral surface for each vertical interval; and
a controller configured to classify objects by clustering each layer for the multi-layer data, extract contours and shapes of the objects and then control a convergence of the objects based on a calculated value of a Mahalanobis distance between the clustered objects,
wherein the controller checks whether or not the objects are overlapped and calculates the Mahalanobis distance in a case in which the objects are overlapped, and
wherein the controller converges two objects used for the Mahalanobis distance calculation in a case in which the Mahalanobis distance is equal to or less than a reference value and classifies the two objects into different objects in a case in which the Mahalanobis distance is larger than the reference value.

### Claim 2 (depends on 1)

The vehicle according to claim 1, wherein the controller selects an object having the largest size among the objects as a reference object and calculates Mahalanobis distances between the reference object and other objects.

### Claim 3 (depends on 1)

The vehicle according to claim 1, wherein the controller performs at least one of a distance calculation between an own vehicle and surrounding geographic features, a speed detection of other vehicles and a distance calculation from another vehicle based on a converged image of the objects.

### Claim 4 (depends on 3)

The vehicle according to claim 3, further comprising a safety service supporter performing at least one of an alarm sound output, a vehicle speed control, and a steering control based on at least one of a distance value and a speed value calculated based on the converged image of the objects.