Granted Patent B2

US 12,475,545 · App. 18/113,860 · Granted Nov 18, 2025

Inventors: Wei Wang (Beijing, CN); Yizhuo Liu (Beijing, CN)

Assignee: Beijing Baidu Netcom Science Technology Co., Ltd.

G06T7/0002G06T7/90G06V20/49H04N9/64G06T2207/10016G06T2207/10024G06T2207/20021G06T2207/30168

Abstract

Claims (76)

1 . A method for evaluating video quality, comprising:

determining a plurality of video frames containing a target object in a target video;

obtaining at least HSL data of an image area corresponding to the target object in the plurality of video frames;

evaluating quality of the target video according to the HSL data;

associating the plurality of video frames with corresponding HSL data respectively; and

displaying an association relationship in a visualization manner, wherein the visualization manner comprises a data log and/or a grayscale image.

2 . The method of claim 1 , wherein determining the plurality of video frames containing the target object in the target video comprises:

determining a type of the target video according to video contents of the target video;

determining the target object according to the type of the target video; and

determining the plurality of video frames containing the target object from the target video.

3 . The method of claim 2 , wherein determining the plurality of video frames containing the target object from the target video comprises:

determining the plurality of video frames containing the target object from the target video by using an image segmentation technology.

4 . The method of claim 1 , wherein obtaining at least the HSL data of the image area corresponding to the target object in the plurality of video frames comprises:

obtaining at least RGB data of the image area corresponding to the target object in the plurality of video frames;

converting a data format of the RGB data into a preset data format according to a bit depth and/or color depth of the RGB data; and

obtaining the HSL data of the image area corresponding to the target object in the plurality of video frames according to the RGB data after converting the data format.

5 . The method of claim 2 , wherein obtaining at least the HSL data of the image area corresponding to the target object in the plurality of video frames comprises:

obtaining at least RGB data of the image area corresponding to the target object in the plurality of video frames;

converting a data format of the RGB data into a preset data format according to a bit depth and/or color depth of the RGB data; and

obtaining the HSL data of the image area corresponding to the target object in the plurality of video frames according to the RGB data after converting the data format.

6 . The method of claim 3 , wherein obtaining at least the HSL data of the image area corresponding to the target object in the plurality of video frames comprises:

obtaining at least RGB data of the image area corresponding to the target object in the plurality of video frames;

converting a data format of the RGB data into a preset data format according to a bit depth and/or color depth of the RGB data; and

obtaining the HSL data of the image area corresponding to the target object in the plurality of video frames according to the RGB data after converting the data format.

7 . The method of claim 4 , wherein obtaining at least the RGB data of the image area corresponding to the target object in the plurality of video frames comprises:

obtaining at least YUV data of the image area corresponding to the target object in the plurality of video frames; and

obtaining the RGB data of the image area corresponding to the target object in the plurality of video frames according to the YUV data.

8 . The method of claim 5 , wherein obtaining at least the RGB data of the image area corresponding to the target object in the plurality of video frames comprises:

obtaining at least YUV data of the image area corresponding to the target object in the plurality of video frames; and

obtaining the RGB data of the image area corresponding to the target object in the plurality of video frames according to the YUV data.

9 . The method of claim 6 , wherein obtaining at least the RGB data of the image area corresponding to the target object in the plurality of video frames comprises:

obtaining at least YUV data of the image area corresponding to the target object in the plurality of video frames; and

obtaining the RGB data of the image area corresponding to the target object in the plurality of video frames according to the YUV data.

10 . The method of claim 1 , wherein evaluating the quality of the target video according to the HSL data comprises:

obtaining an average value of the HSL data according to a quantity of the plurality of video frames; and

evaluating the quality of the target video according to the average value and a HSL evaluation threshold.

11 . The method of claim 2 , wherein evaluating the quality of the target video according to the HSL data comprises:

obtaining an average value of the HSL data according to a quantity of the plurality of video frames; and

evaluating the quality of the target video according to the average value and a HSL evaluation threshold.

12 . The method of claim 3 , wherein evaluating the quality of the target video according to the HSL data comprises:

obtaining an average value of the HSL data according to a quantity of the plurality of video frames; and

evaluating the quality of the target video according to the average value and a HSL evaluation threshold.

13 . An electronic device, comprising:

at least one processor; and

a memory connected in communication with the at least one processor;

wherein the memory stores an instruction executable by the at least one processor to enable the at least one processor to execute operations, comprising:

determining a plurality of video frames containing a target object in a target video;

obtaining at least HSL data of an image area corresponding to the target object in the plurality of video frames;

evaluating quality of the target video according to the HSL data;

associating the plurality of video frames with corresponding HSL data respectively; and

displaying an association relationship in a visualization manner, wherein the visualization manner comprises a data log and/or a grayscale image.

14 . The electronic device of claim 13 , wherein determining the plurality of video frames containing the target object in the target video comprises:

determining a type of the target video according to video contents of the target video;

determining the target object according to the type of the target video; and

determining the plurality of video frames containing the target object from the target video.

15 . The electronic device of claim 14 , wherein determining the plurality of video frames containing the target object from the target video comprises:

determining the plurality of video frames containing the target object from the target video by using an image segmentation technology.

16 . The electronic device of claim 13 , wherein obtaining at least the HSL data of the image area corresponding to the target object in the plurality of video frames comprises:

obtaining at least RGB data of the image area corresponding to the target object in the plurality of video frames;

converting a data format of the RGB data into a preset data format according to a bit depth and/or color depth of the RGB data; and

obtaining the HSL data of the image area corresponding to the target object in the plurality of video frames according to the RGB data after converting the data format.

17 . The electronic device of claim 13 , wherein evaluating the quality of the target video according to the HSL data comprises:

obtaining an average value of the HSL data according to a quantity of the plurality of video frames; and

evaluating the quality of the target video according to the average value and a HSL evaluation threshold.

18 . A non-transitory computer-readable storage medium storing a computer instruction thereon, wherein the computer instruction is used to cause a computer to execute operations, comprising:

determining a plurality of video frames containing a target object in a target video;

obtaining at least HSL data of an image area corresponding to the target object in the plurality of video frames;

evaluating quality of the target video according to the HSL data;

associating the plurality of video frames with corresponding HSL data respectively; and

displaying an association relationship in a visualization manner, wherein the visualization manner comprises a data log and/or a grayscale image.

19 . The non-transitory computer-readable storage medium of claim 18 , wherein determining the plurality of video frames containing the target object in the target video comprises:

determining a type of the target video according to video contents of the target video;

determining the target object according to the type of the target video; and

determining the plurality of video frames containing the target object from the target video.

20 . The non-transitory computer-readable storage medium of claim 19 , wherein determining the plurality of video frames containing the target object from the target video comprises:

determining the plurality of video frames containing the target object from the target video by using an image segmentation technology.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (29)