Method and apparatus for detecting light source of vehicle

• US 10,839,235 B2
• Filed: 04/24/2018
• Issued: 11/17/2020
• Est. Priority Date: 05/09/2012
• Status: Active Grant

• Current Assignee: DENSO Corporation
• Original Assignee: DENSO Corporation
• Inventors: Sato, Hironori, Morishita, Taiji
• Primary Examiner(s): Moyer, Andrew M
• Assistant Examiner(s): Rosario, Dennis
• Application Number:
  US15/960,856
• Publication Number:
  US 20180239974A1
• Time in Patent Office: 938 Days
• CPC Class Codes: B60Q 1/1423 Automatic dimming circuits, i.e. switching between high beam and low beam due to change of ambient light or light level in road traffic
• CPC Class Codes: B60Q 2300/41 preceding vehicle
• CPC Class Codes: G01J 3/46 Measurement of colour; Colour measuring devices, e.g. colorimeters measuring colour temperature G01J5/60
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/20076 Probabilistic image processing
• CPC Class Codes: G06T 2207/30252 Vehicle exterior; Vicinity of vehicle
• CPC Class Codes: G06V 20/584 of vehicle lights or traffic lights

Abstract

In a light control system, a captured image of a cruising direction of a vehicle is acquired, and a light source is extracted from the captured image. A probability for estimating a light source to be a vehicle light source originating from a vehicle is calculated based on light source parameters for differentiating the light source. A dark section that is darker than the periphery and is present below the light source in the captured image is extracted. The probability is set to be higher for the light source of which the dark section is extracted. The light source having a probability that is a reference value set in advance or higher is estimated to be a light source of another vehicle. When the dark section that is detected as a shadow of a vehicle is detected, the probability of the light source being a vehicle light source is set to be high.

Claims

1. An apparatus that is mounted in an own vehicle and detects a light source of an additional vehicle, the apparatus comprising:

a processor,

wherein the processor is configured to;

acquire a captured image of a field of view in a cruising direction of the own vehicle;

extract a light source candidate in the captured image;

calculate a probability of the light source candidate being a vehicle light source originated from an additional vehicle based on light source parameters;

correct the probability of the light source candidate being the vehicle light source from the originally calculated probability to a higher corrected probability in response to a dark section in the captured image being located within a predetermined distance below the light source candidate, the dark section being darker than a periphery of the additional vehicle in the captured image;

estimate the light source candidate to be the light source of the additional vehicle based on the higher corrected probability; and

remove the light source candidate from being a candidate for the vehicle light source in response to the dark section being located outside the predetermined distance below the light source candidate.

2. The apparatus according to claim 1, wherein the processor is configured to further:

extract, in the captured image, a similar-color light area that is present below the light source candidate and has a color that is similar to the color of the light source candidate; and

correct the probability of the light source candidate being the vehicle light source, below which the similar-color light area is present, from the originally calculated probability to the higher corrected probability in response to the dark section being located within the predetermined distance below the light source candidate.

3. The apparatus according to claim 2, wherein the processor is configured to:

correct the probability of the light source candidate being the vehicle light source based on a distance from the light source candidate to the similar-color light area.

4. The apparatus according to claim 1, wherein:

the processor is configured to;

extract, in the captured image, a plurality of light source candidates;

extract, in the captured image, a tail light source candidate that indicates a light source having a color that is similar to the color of a taillight, from the light source candidates;

extract, in the captured image, a bright section that indicates an area located on a left or right side of the tail light source candidate that is brighter than the periphery of the tail light source candidate; and

correct the probability of the tail light source candidate with the bright section being located on the left or right side of the tail light source candidate being the vehicle light source from the originally calculated probability to the higher corrected probability.

5. The apparatus according to claim 2, wherein the processor is configured to:

extract, in the captured image, a plurality of light source candidates;

extract, in the captured image, a tail light source candidate that indicates a light source having a color that is similar to the color of a taillight, from the light source candidates;

extract, in the captured image, a bright section that indicates an area located on a left or right side of the tail light source candidate that is brighter than the periphery of the tail light source candidate; and

correct the probability of the tail light source candidate with the bright section being located on the left or right side of the tail light source candidate being the vehicle light source from the originally calculated probability to the higher corrected probability.

6. The apparatus according to claim 3, wherein the processor is configured to:

extract, in the captured image, a plurality of light source candidates;

extract, in the captured image, a tail light source candidate that indicates a light source having a color that is similar to the color of a taillight, from the light source candidates;

extract, in the captured image, a bright section that indicates an area located on a left or right side of the tail light source candidate that is brighter than the periphery of the tail light source candidate; and

correct the probability of the tail light source candidate with the bright section being located on the left or right side of the tail light source candidate being the vehicle light source from the originally calculated probability to the higher corrected probability.

7. A vehicle light source detection apparatus that is an apparatus that is mounted in an own vehicle and detects a light source of an additional vehicle, the vehicle light source detection apparatus comprising:

a processor,

wherein the processor is configured to;

acquire a captured image of a field of view in a cruising direction of the own vehicle;

extract a light source candidate in the captured image;

calculate a probability of the light source candidate being a vehicle light source originated from an additional vehicle based on light source parameters;

extract, in the captured image, a similar-color light area that is present below the light source candidate and has a color that is similar to the color of the light source candidate;

correct the probability of the light source candidate being the vehicle light source, below which the similar-color light area is present, from the originally calculated probability to a higher corrected probability; and

remove the light source candidate from being a candidate for the vehicle light source in response to a dark section in the captured image being located outside a predetermined distance below the light source candidate, the dark section being darker than a periphery of the additional vehicle in the captured image.

8. A method of detecting a light source of an additional vehicle, the method comprising:

acquiring a captured image of a field of view in a cruising direction of an own vehicle;

extracting a light source candidate in the captured image;

calculating a probability of the light source candidate being a vehicle light source originated from an additional vehicle based on light source parameters;

correcting the probability of the light source candidate from the originally calculated probability to a higher corrected probability in response to a dark section in the captured image is located within a predetermined distance below the light source candidate, the dark section being darker than a periphery of the additional vehicle in the captured image;

estimating the light source candidate to be the light source of the additional vehicle based on the higher corrected probability; and

removing the light source candidate from being a candidate for the vehicle light source when the dark section is located outside the predetermined distance below the light source candidate.

9. A non-transitory computer readable program medium, the program providing a computer with instructions including:

acquiring a captured image of a field of view in a cruising direction of an own vehicle;

extracting a light source candidate in the captured image;

calculating a probability of the light source candidate being a vehicle light source originated from an additional vehicle based on light source parameters;

correcting the probability of the light source candidate being the vehicle light source from the originally calculated probability to a higher corrected probability when a dark section in the captured image is located within a predetermined distance below the light source candidate, the dark section being darker than a periphery of the additional vehicle in the captured image;

estimating the light source candidate to be the light source of the additional vehicle based on the higher corrected probability; and

removing the light source candidate from being a candidate for the vehicle light source when the dark section is located outside the predetermined distance below the light source candidate.