PROCEEDABLE DIRECTION DETECTION APPARATUS AND PROCEEDABLE DIRECTION DETECTION METHOD

• US 20200133283A1
• Filed: 10/17/2019
• Published: 04/30/2020
• Est. Priority Date: 10/25/2018
• Status: Active Grant

• Current Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Original Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Inventors: Hirano, Kota, Hashimoto, Daisuke, Takeyasu, Satoshi
• Granted Patent: US 11,335,099 B2
• Time in Patent Office: Days
• CPC Class Codes: G05D 1/0214 in accordance with safety or protection criteria, e.g. avoiding hazardous areas monitoring the location of vehicles within a certain area, e.g. forbidden or allowed areas, in traffic control systems for road vehicles G08G1/13
• CPC Class Codes: G05D 1/0221 involving a learning process
• CPC Class Codes: G06F 18/2415 based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
• CPC Class Codes: G06V 20/584 of vehicle lights or traffic lights
• CPC Class Codes: G06V 20/588 Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road

Abstract

A proceedable direction detection apparatus includes a processor. The processor inputs an image acquired from an image capturing unit mounted on a vehicle into a classifier that is pre-trained to output a proceedable certainty degree indicating a proceedable probability of each relative bearing with respect to a predetermined direction relative to a vehicle based on a display status of a traffic signal in the image. The processor calculates, using the classifier, the proceedable certainty degree of each relative bearing based on the display status of the traffic signal in the image. The processor determines the direction in which the vehicle can proceed based on a proceedable certainty degree of each relative bearing.

Claims

1. A proceedable direction detection apparatus comprising a processor, wherein the processor is configured to:

input an image acquired from an image capturing unit mounted on a vehicle into a classifier that is pre-trained to output a proceedable certainty degree indicating a proceedable probability of each relative bearing with respect to a predetermined direction relative to a vehicle based on a display status of a traffic signal in the image;

calculate, using the classifier, the proceedable certainty degree of each relative bearing based on the display status of the traffic signal in the image; and

determine a proceedable direction of the vehicle based on the proceedable certainty degree of each relative bearing.

2. The proceedable direction detection apparatus according to claim 1, wherein:

the classifier is pre-trained to calculate the proceedable certainty degree of each relative bearing based on a display characteristic of the traffic signal for each region; and

the processor is configured to input, into the classifier, information indicating a region in which the vehicle is located, together with the image.

3. The proceedable direction detection apparatus according to claim 1, wherein:

the processor is configured to, when the traffic signal has a plurality of traffic lights, calculate the proceedable certainty degree of each relative bearing for each of the lit traffic lights among the plurality of traffic lights; and

the processor is configured to set, as the proceedable direction of the vehicle, a relative bearing in which the proceedable certainty degree that is equal to or higher than a predetermined threshold value is calculated for each of the lit traffic lights.

4. A proceedable direction detection method executed using a processor, the method comprising:

inputting, by the processor, an image acquired from an image capturing unit mounted on a vehicle into a classifier that is pre-trained to output a proceedable certainty degree indicating a proceedable probability of each relative bearing with respect to a predetermined direction relative to a vehicle based on a display status of a traffic signal in the image;

calculating, by the processor, the proceedable certainty degree of each relative bearing based on the display status of the traffic signal in the image, using the classifier; and

determining, by the processor, a proceedable direction of the vehicle based on the proceedable certainty degree of each relative bearing.