Driving assistance apparatus and image processing method

1. A driving assistance apparatus comprising:

an image sensor; and

a processor configured to identify a specific color area in a peripheral image captured by the image sensor as a first candidate area, identify an area including a specific shape in the first candidate area as a second candidate area, and identify an area of a traffic sign in the second candidate area,

wherein the processor is configured to:

identify the second candidate area as a plurality of first blocks based on a first direction, and acquire first pixel information based on a pixel value included in each of the plurality of first blocks,

identify the second candidate area as a plurality of second blocks based on a second direction, and acquire second pixel information based on a pixel value included in each of the plurality of second blocks, and

identify an area of the traffic sign based on the first pixel information and the second pixel information,

wherein the first pixel information includes a difference value between an average value of pixels included in each of the plurality of first blocks, and an average value of pixels included in adjacent first blocks, and

wherein the second pixel information includes a difference value between an average value of pixels included in each of the plurality of second blocks, and an average value of pixels included in adjacent second blocks.

2. The apparatus of claim 1 , wherein the processor is configured to apply the first pixel information and the second pixel information to a training model to identify the area of the traffic sign, and

wherein the training model is configured to identify a plurality of sample traffic sign images as a plurality of blocks, and learn and obtain pixel information based on pixel values included in each of the plurality of blocks.

3. A driving assistance apparatus comprising:

an image sensor;

at least one among an illuminance sensor and a rain sensor; and

a processor configured to identify a specific color area in a peripheral image captured by the image sensor as a first candidate area, identify an area including a specific shape in the first candidate area as a second candidate area, and identify an area of a traffic sign in the second candidate area,

wherein the processor is configured to:

identify red (R) color, green (G) color, and blue (B) color included in the peripheral image, and

identify an area in which a pixel value of the R color is equal to or greater than a predetermined multiple of pixel values of the G color and the B color as the first candidate area, and

wherein the multiple is updated based on at least one of illuminance measured by the illuminance sensor or rainfall measured by the rain sensor.

4. The apparatus of claim 1 , wherein the processor is configured to, based on the first candidate area being identified, acquire a binary image including only the first candidate area among the peripheral image, and

identify the second candidate area based on the acquired binary image.

5. The apparatus of claim 1 , further comprising:

a storage configured to store reference shape information of a traffic sign,

based on the reference shape information being identified in the first candidate area, identifying the first candidate area as the second candidate area.

6. The apparatus of claim 1 , further comprising:

a display,

wherein the processor is configured to control the display to identify and provide at least one of a type or an instruction content of the traffic sign in the identified traffic sign area, and

based on at least one of the type or the instruction content of the traffic sign, control the vehicle.

7. A method of image processing comprising:

acquiring a peripheral image of a vehicle through an image sensor;

identifying a first candidate area based on color information included in the acquired peripheral image;

identifying a second candidate area based on shape information included in the first candidate area; and

identifying the second candidate area as a plurality of blocks, and identifying an area of traffic sign based on pixel values included in each of the plurality of blocks,

wherein the identifying the traffic sign area comprises:

identifying the second candidate area as a plurality of first blocks based on a first direction, and acquiring first pixel information based on a pixel value included in each of the plurality of first blocks,

identifying the second candidate area as a plurality of second blocks based on a second direction, and acquiring second pixel information based on a pixel value included in each of the plurality of second blocks, and

identifying an area of the traffic sign based on the first pixel information and the second pixel information,

wherein the first pixel information includes a difference value between an average value of pixels included in each of the plurality of first blocks, and an average value of pixels included in adjacent first blocks, and

wherein the second pixel information includes a difference value between an average value of pixels included in each of the plurality of second blocks, and an average value of pixels included in adjacent second blocks.

8. The method of claim 7 , wherein the identifying the traffic sign area comprises applying the first pixel information and the second pixel information to a training model to identify the area of the traffic sign, and

wherein the training model is configured to identify a plurality of sample traffic sign images as a plurality of blocks, and learn and obtain pixel information based on pixel values included in each of the plurality of blocks.

9. The method of claim 7 , wherein the identifying the first candidate area comprises:

identifying red (R) color, green (G) color, and blue (B) color included in the peripheral image, and

identifying an area in which a pixel value of the R color is equal to or greater than a predetermined multiple of pixel values of the G color and the B color as the first candidate area.

10. The method of claim 9 , wherein the multiple is updated based on at least one of illuminance or rainfall.