Object recognition device and object recognition method

Patent metadata

Field	Value
Publication number	US-11921191-B2
Application number	US-202117202975-A
Country	US
Kind code	B2
Filing date	Mar 16, 2021
Priority date	Apr 2, 2020
Publication date	Mar 5, 2024
Grant date	Mar 5, 2024

Abstract

The object recognition device includes at least one sensor, a data reception unit, and a setting unit. The sensor detects an object present in a detectable range and transmits object data including a plurality of physical quantities indicating a state of the object. The data reception unit receives the object data from the sensor. The setting unit generates prediction data which predicts current object data based on at least a part of past object data received by the data reception unit and a motion model in the object, and sets a association possible region for determining a association between the prediction data and the current object data based on a plurality of physical-quantity delay times each corresponding to each of the plurality of physical quantities included in the prediction data.

First claim

What is claimed is:

1. An object recognition device, comprising:
at least one sensor configured to detect an object present in a detectable range and to transmit object data including a plurality of physical quantities indicating a state of the object;
a data reception unit configured to receive the object data from the at least one sensor; and
a setting unit configured to generate prediction data which predicts current object data based on at least a part of past object data received by the data reception unit and a motion model in the object and to set a association possible region for determining a association between the prediction data and the current object data based on the prediction data and a plurality of physical-quantity delay times each corresponding to each of the plurality of physical quantities.

2. The object recognition device according to claim 1 , wherein the plurality of physical-quantity delay times are fixed values determined in advance.

3. The object recognition device according to claim 1 , wherein the at least one sensor is configured to transmit, along with the object data, the plurality of physical-quantity delay times corresponding to the at least one sensor.

4. The object recognition device according to claim 1 , wherein the plurality of physical quantities include a longitudinal position and a longitudinal speed in the object.

5. The object recognition device according to claim 1 , wherein the plurality of physical quantities include a lateral position and a lateral speed in the object.

6. The object recognition device according to claim 1 , wherein the setting unit is configured to correct a center point of the association possible region, to thereby set the association possible region.

7. The object recognition device according to claim 1 , wherein the setting unit is configured to correct a size of the association possible region, to thereby set the association possible region.

8. The object recognition device according to claim 1 , wherein the setting unit is configured to correct a center point of the association possible region and a size of the association possible region, to thereby set the association possible region.

9. An object recognition device, comprising:
at least one sensor configured to detect an object present in a detectable range and to transmit object data including a plurality of physical quantities indicating a state of the object;
an ego vehicle travel scene obtaining unit configured to detect a current ego vehicle travel scene in a vehicle in which the object recognition device is installed and to transmit ego vehicle travel scene data corresponding to the current ego vehicle travel scene;
a data reception unit configured to receive the object data when the object data is transmitted from the at least one sensor and to receive the ego vehicle travel scene data when the ego vehicle travel scene data is transmitted from the ego vehicle travel scene obtaining unit;
a physical-quantity delay time estimation unit configured to estimate, based on the ego vehicle travel scene data, at least one of a plurality of physical-quantity delay times each corresponding to each of the plurality of physical quantities included in the object data; and
a setting unit configured to generate prediction data which predicts current object data based on at least a part of past object data received by the data reception unit and a motion model in the object and to set a association possible region for determining a association between the prediction data and the current object data based on the prediction data and the plurality of physical-quantity delay times.

10. The object recognition device according to claim 9 , wherein the physical-quantity delay time estimation unit is configured to estimate a plurality of current physical-quantity delay times based on scenes stored in advance, a plurality of physical-quantity delay times stored in advance based on the scenes, and the current ego vehicle travel scene.

11. An object recognition method, comprising:
at least one step of detecting an object present in a detectable range and transmitting object data including a plurality of physical quantities indicating a state of the object;
a step of receiving the object data transmitted in the at least one step of transmitting object data; and
a step of generating prediction data which predicts current object data based on at least a part of past object data received in the step of receiving the object data and a motion model in the object and setting a association possible region for determining a association between the prediction data and the current object data based on a plurality of physical-quantity delay times each corresponding to each of the plurality of physical quantities included in the prediction data.

Assignees

• Mitsubishi Electric Corp
• Mazda Motor

Inventors

• Akiyama Tomohiro
• Moritani Takayuki

Classifications

• G01S13/862 Primary

  Combination of radar systems with sonar systems · CPC title

• B60W40/12

  related to parameters of the vehicle itself {, e.g. tyre models} · CPC title

• G06V20/58

  Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads · CPC title

• B60W2520/105

  Longitudinal acceleration · CPC title

• B60W2520/12

  Lateral speed · CPC title