Granted Patent B2

US 10,573,346 · App. 16/001,221 · Granted Feb 25, 2020

Abstract

Claims (45)

1. A case video processing apparatus, comprising:

a processor; and

a memory,

wherein, in cooperation with the memory, the processor:

processes video data including a first frame and a second frame, the second frame being subsequent to the first frame,

detects a first face region of a person included in an image of the first frame of the video data, and displays the detected first face region as a region to be masked,

determines that a first instruction that selects a target not to be masked has been input on the displayed first face region,

excludes the first face region selected by the first instruction from targets to be masked and registers the first face region in the memory as a region not to be masked,

outputs the first frame of the video data, wherein masking processing is not performed on the first face region of the person included in the image of the first frame of the video data based on the first instruction,

detects a second face region of a person included in an image of the second frame of the video data,

determines whether the detected second face region of the person included in the image of the second frame of the video data conforms to the first face region of the person included in the image of the first frame of the video data which has been registered as the region not to be masked,

includes the detected second face region of the person included in the image of the second frame of the video data in targets to be masked, when the detected second face region of the person included in the image of the second subsequent frame of the video data is not determined to conform to the first face region of the person included in the image of the first frame of the video data which has been registered as the region not to be masked,

determines that a second instruction that selects a target to be masked has been input on the displayed second face region, after the detected second face region of the person included in the image of the second subsequent frame of the video data is determined to conform to the first face region of the person included in the image of the first frame of the video data which has been registered as the region not to be masked, and

outputs the second frame of the video data, wherein the masking processing is performed on the second face region of the person included in the image of the first frame of the video data based on the second instruction.

2. The case video processing apparatus of claim 1 ,

wherein the processor generates a to-be-masked frame with respect to the detected first face region and displays the generated to-be-masked frame in association with the first face region.

3. The case video processing apparatus of claim 1 , wherein the processor:

detects a third face region included in the image for each of a plurality of frames of the video data,

searches for the region to be masked which is registered in a previous frame, and tracks the region to be masked, and

determines whether characteristic data of a face in the detected face region is consistent with characteristic data of a face registered in the memory, and excludes the detected third face region from the targets to be masked, as a region not to be masked, in a case where the characteristic data of the face in the detected face region is consistent with the characteristic data of the face registered in the memory.

4. The case video processing apparatus of claim 1 , wherein the processor registers coordinate data of the first face region which is set to be the target not to be masked, in the memory.

5. The case video processing apparatus of claim 1 , further comprising the processor in cooperation with the memory:

for a frame different from a frame in which the masking process is performed, determining whether a third instruction that selects a target not to be masked has been input on a displayed third face region in the frame different from the frame in which the masking process is performed; and

excluding the third face region selected by the third second instruction from targets to be masked.

6. A case video processing method of performing image processing of video data related to a case by including a processor and a memory, the method comprising:

processing video data including a first frame and a second frame, the second frame being subsequent to the first frame;

detecting a first face region of a person included in an image of the first frame of the video data;

displaying the detected first face region as a region to be masked;

determining that a first instruction that selects a target not to be masked has been input with respect to the displayed first face region;

excluding the first face region selected by the first instruction from targets to be masked;

registering the first face region as a region not to be masked in the memory;

outputting the first frame of the video data, wherein masking processing is not performed on the first face region of the person included in the image of the first frame of the video data based on the first instruction;

detecting a second face region of a person included in an image of the second frame of the video data,

determining whether the detected second face region of the person included in the image of the second frame of the video data conforms to the first face region of the person included in the image of the first frame of the video data which his been registered as the person not to be masked,

including the detected second face region of the person included in the image of the second frame of the video data in targets to be masked, when the detected second face region of the person included in the image of the second subsequent frame of the video data is not determined to conform to the first face region of the person included in the image of the first frame of the video data which has been registered as the region not to be masked,

determining that a second instruction that selects a target to be masked has been input on the displayed second face region, after the detected second face region of the person included in the image of the second subsequent frame of the video data is determined to conform to the first face region of the person included in the image of the first frame of the video data which has been registered as the region not to be masked, and

outputting the second frame of the video data, wherein the masking processing is performed on the second face region of the person included in the image of the first frame of the video data based on the second instruction.

7. The case video processing method of claim 6 , further comprising:

detecting a third face region included in an image for each of a plurality of frames of the video data;

searching for the region to be masked which is registered in a previous frame, and tracking the region to be masked; and

determining whether characteristic data of a face in the detected third face region is consistent with characteristic data of a face registered in the memory, and

excluding the detected third face region from the targets to be masked, as a region not to be masked, in a case where a result of the determining is that the characteristic data of the face in the detected face region is consistent with the characteristic data of the face registered in the memory.

8. The case video processing method of claim 6 , further comprising:

for a frame different from a frame in which the masking process is performed, determining whether a third second instruction that selects a target not to be masked has been input on a displayed third face region; and

excluding the third face region selected by the third instruction from targets to be masked.

Assignments (7)