Artificial intelligence based image data processing method and image processing device

1. An image data processing method comprising:

receiving, from an image sensor, frame image data of a frame at a first resolution;

reducing a resolution of the frame image data to a second resolution;

performing an artificial intelligence (AI) based image recognition on the frame image data at the second resolution to determine one or more regions of interest (ROI) and a priority level of each of the one or more ROIs, wherein the one or more ROIs include a first ROI at a first priority level and a second ROI at a second priority level lower than the first priority level;

extracting portions of the frame image data corresponding to the one or more ROIs;

modifying a resolution of the portions of the frame image data corresponding to the one or more ROIs based on the priority level of each of the one or more ROIs;

maintaining a resolution of a portion of the frame image data corresponding to the first ROI at the first resolution;

reducing a resolution of a portion of the frame image data corresponding to the second ROI to a third resolution lower than the first resolution and higher than the second resolution; and

combining the resolution-modified portions of the frame image data corresponding to the one or more ROIs with the frame image data at the second resolution to generate output frame image data.

2. The method of claim 1 , further comprising modifying at least one of brightness and contrast of the portions of the frame image data corresponding to the one or more ROIs, wherein the portions of the frame image data corresponding to the one or more ROIs of which at least one of brightness and contrast has been modified are combined with the frame image data at the second resolution to generate the output frame image data.

3. The method of claim 1 , wherein the modifying resolution of the portions of the frame image data corresponding to the one or more ROIs comprises:

reducing a resolution of a portion of the frame image data corresponding to the first ROI to a third resolution lower than the first resolution and higher than the second resolution; and

reducing a resolution of a portion of the frame image data corresponding to the second ROI to a fourth resolution lower than the third resolution and higher than the second resolution.

4. The method of claim 1 , wherein the image sensor is mounted on a vehicle or robot, and the one or more ROIs corresponds to one or more regions including at least one of a human face, a traffic sign, and a license plate.

5. The method of claim 1 , wherein the frame image data of the frame is received from the image sensor through a first data communication link of a first bandwidth, and the output frame image data is output through a second data communication link of a second bandwidth lower than the first bandwidth.

6. The method of claim 5 , wherein the first data communication link comprises a wired data communication link, including no wireless communication link, and the second data communication link comprises a wireless data communication link.

7. The method of claim 1 , further comprising transmitting an image data signal containing the output frame image data, wherein the output frame image data in the image data signal includes a sequence of blocks of row data corresponding to a plurality of rows of the image sensor, and each block of row data includes image data at the second resolution and image data corresponding to the one or more ROIs.

8. The method of claim 1 , further comprising transmitting an image data signal containing the output frame image data, wherein the output frame image data in the image data signal includes a first sequence of blocks of row data corresponding to a plurality of rows of the image sensor and a second sequence of blocks of row data corresponding to the plurality of rows; and

the first sequence of blocks of row data including image data of each of the rows at the second resolution, and the second sequence of blocks of row data including image data of each of the rows corresponding to the one or more ROIs.

9. The method of claim 1 , further comprising receiving an external ROI request; and

extracting one or more portions of the frame image data based on the external ROI request.

10. An image data processing device comprising:

a first resolution modification circuit configured to receive, from an image sensor, frame image data at a first resolution, and reduce a resolution of the frame image data to a second resolution;

a feature detection circuit configured to perform an artificial intelligence (AI) based image recognition on the frame image data at the second resolution to determine one or more regions of interest (ROI) and a priority level of each of the one or more ROIs, wherein the one or more ROIs includes a first ROI at a first priority level and a second ROI at a second priority level lower than the first priority level;

a second resolution modification circuit configured to extract portions of the frame image data corresponding to the one or more ROIs, and modify a resolution of the portions of the frame image data corresponding to the one or more ROIs based on the priority level of each of the one or more ROIs;

wherein the second resolution modification unit circuit is configured to maintain a resolution of a portion of the frame image data corresponding to the first ROI at the first resolution, and reduce a resolution of a portion of the frame image data corresponding to the second ROI to a third resolution lower than the first resolution and higher than the second resolution; and

a data combination circuit configured to combine the resolution-modified portions of the frame image data corresponding to the one or more ROIs with the frame image data at the second resolution to generate output frame image data.

11. The image data processing device of claim 10 , further comprising a pre-processing circuit configured to modify at least one of brightness and contrast of the portions of the frame image data corresponding to the one or more ROIs, wherein the data combination circuit combines the portions of the frame image data corresponding to the one or more ROIs of which at least one of brightness and contrast has been modified with the frame image data at the second resolution to generate the output frame image data.

12. The image data processing device of claim 10 , wherein the second resolution modification circuit is configured to reduce a resolution of a portion of the frame image data corresponding to the first ROI to a third resolution lower than the first resolution and higher than the second resolution, and reduce a resolution of a portion of the frame image data corresponding to the second ROI to a fourth resolution lower than the third resolution and higher than the second resolution.

13. The image data processing device of claim 10 , wherein the image data processing device is mountable on a vehicle or robot, and the one or more ROIs corresponds to one or more regions including at least one of a human face, a traffic sign, and a license plate.

14. The image data processing device of claim 10 , wherein the first resolution modification circuit receives the frame image data from the image sensor through a first data communication link of a first bandwidth, and the data combination circuit is configured to output the output frame image data through a second data communication link of a second bandwidth lower than the first bandwidth.

15. The image data processing device of claim 14 , wherein the first data communication link comprises a wired data communication link, including no wireless communication link, and the second data communication link comprises a wireless data communication link.

16. The image data processing device of claim 10 , wherein the data combination circuit is further configured to transmit an image data signal containing the output frame image data, wherein the output frame image data in the image data signal includes a sequence of blocks of row data corresponding to a plurality of rows of the image sensor, and each block of row data includes image data at the second resolution and image data corresponding to the one or more ROIs.

17. The image data processing device of claim 10 , wherein the data combination circuit is further configured to transmit an image data signal containing the output frame image data, wherein the output frame image data in the image data signal includes a first sequence of blocks of row data corresponding to a plurality of rows of the image sensor and a second sequence of blocks of row data corresponding to the plurality of rows; and

the first sequence of blocks of row data including image data of each of the rows at the second resolution, and the second sequence of blocks of row data including image data of each of the rows corresponding to the one or more ROIs.

18. The image sensor of claim 10 , wherein the second resolution modification circuit is configured to receive an external ROI request; and

extract one or more portions of the frame image data based on the external ROI request.