JP2020145536A - Video processing device, video processing method, and video processing program - Google Patents

Abstract

To provide a video processing device, a video processing method, and a video processing program that can suppress the loss of image information corresponding to a facial part.SOLUTION: A video processing device 30 includes an image acquisition unit 31, an image detection unit 33, a part brightness value acquisition unit 35, a brightness determination unit 36, and a frame control unit 32. The image acquisition unit 31 acquires an image of the face of an image subject. The image detection unit 33 detects a facial part from the image acquired by the image acquisition unit 31. The part brightness value acquisition unit 35 acquires the brightness value at the facial part detected by the image detection unit 33. The brightness determination unit 36 determines whether the brightness value acquired by the part brightness value acquisition unit 35 is within a predetermined brightness range. The frame control unit 32 generates a frame whose exposure is controlled according to an exposure control value corresponding to the part determined to be out of the brightness range by the brightness determination unit 36.SELECTED DRAWING: Figure 1

Description

The present invention relates to a video processing device, a video processing method, and a video processing program.

For example, in a drive recorder or the like mounted on a vehicle, an image obtained by photographing the outside or the inside of the vehicle is stored in a storage device. When photographing the interior of a vehicle, the state of the interior of the vehicle is memorized as an image, and the image is memorized mainly by the driver.

For example, Patent Document 1 discloses a video processing apparatus including an exposure amount control means, a difference image generation means, and an ambient light change frequency prediction means. The exposure amount control means controls the exposure amount of the image pickup means by at least one of the exposure time and the aperture of the image pickup means. The difference image generation means generates a difference image between an image of a subject taken by the imaging means with the lighting means turned on and an image of the subject taken by the imaging means with the lighting means turned off. The disturbance light change frequency predicting means predicts a vehicle traveling section (a small disturbance light change section) in which the frequency of change of the disturbance light incident on the imaging means is smaller than a predetermined threshold value. The exposure amount control means fixes the exposure amount in the disturbance light change subsection predicted by the disturbance light change frequency prediction means.

Japanese Unexamined Patent Publication No. 2010-252212

The conventional video processing apparatus described in Patent Document 1 functions to prevent blackout and whiteout by predicting the frequency of changes in ambient light. However, when a shadow is partially cast on the face as an image subject due to the influence of ambient light, there is a problem that the image information corresponding to the part of the face in the shadowed portion is lost. there were. For example, if shadows are cast on one of the left and right sides of the face, the image information of either the right eye or the left eye, which is the part of the face, is lost, and the state of the image subject such as the degree of opening and closing of the eyes is analyzed based on the image. It becomes difficult to do.

The present invention has been made in view of such circumstances, and an object of the present invention is a video processing device, a video processing method, and a video processing program capable of suppressing the loss of image information corresponding to a facial portion. Is to provide.

The image processing apparatus according to an aspect of the present invention includes an image acquisition unit that acquires an image of the face of an image to be imaged, an image detection unit that detects a facial portion from the image acquired by the image acquisition unit, and an image detection unit. A brightness value acquisition unit that acquires a brightness value in the face portion detected by the image detection unit, and a brightness determination that determines whether or not the brightness value acquired by the brightness value acquisition unit is within a predetermined brightness range. The unit includes a unit and a frame control unit that generates a frame whose exposure is controlled by an exposure control value corresponding to a portion determined to be out of the luminance range by the luminance determination unit.

Another aspect of the present invention is a video processing method. This image processing method comprises an image acquisition step of acquiring an image of the face of an image to be imaged, an image detection step of detecting a facial portion from the image acquired by the image acquisition step, and the image detection step. A brightness value acquisition step for acquiring the detected brightness value of the face portion, a brightness determination step for determining whether or not the brightness value acquired by the brightness value acquisition step is within a predetermined brightness range, and the brightness It includes a frame control step for generating a frame whose exposure is controlled by an exposure control value corresponding to a portion determined to be out of the luminance range by the determination step.

According to the present invention, it is possible to suppress the loss of image information corresponding to a facial portion.

It is a block diagram which shows the structure of the driver monitor including the image processing apparatus which concerns on embodiment. FIG. 2A is a schematic diagram for explaining exposure control for the entire face, and FIG. 2B is a schematic diagram for explaining the generated frame. FIG. 3A is a schematic diagram for explaining an example of exposure control for eyes, and FIG. 3B is a schematic diagram for explaining a frame to be generated. FIG. 4A is a schematic diagram for explaining another example of exposure control for the eyes, and FIG. 4B is a schematic diagram for explaining the generated frame. FIG. 5A is a schematic diagram for explaining still another example of exposure control for the eyes, and FIG. 5B is a schematic diagram for explaining the generated frame. It is a flowchart which shows the procedure of the frame generation processing in a video processing apparatus. It is a flowchart which shows the procedure of the calculation process of the exposure control value in a video processing apparatus.

Hereinafter, the present invention will be described with reference to FIGS. 1 to 7 based on a preferred embodiment. The same or equivalent components and members shown in the drawings shall be designated by the same reference numerals, and redundant description will be omitted as appropriate. In addition, some of the members that are not important for explaining the embodiment in each drawing are omitted and displayed.

(Embodiment)
FIG. 1 is a block diagram showing a configuration of a driver monitor 100 including a video processing device 30 according to an embodiment. The driver monitor 100 is mounted on the vehicle and continuously photographs the interior of the vehicle in time. The driver monitor 100 may record the captured image, or may discard it without recording it. The driver monitor 100 is arranged, for example, on a dashboard below the windshield of the vehicle. The image processing device 30 of the driver monitor 100 photographs, for example, a driver in a vehicle as an imaged object, and detects parts such as the face, facial eyes, nose, and mouth of the photographed object.

The image processing device 30 acquires the brightness values for the entire face and each part of the face, and controls the exposure by comparing with the reference brightness value. The image processing device 30 executes exposure control for the entire face, and when the brightness difference from the brightness reference value is large in each part, generates a frame in which the exposure is controlled corresponding to each part. The image processing device 30 controls the frame by sequentially generating a face exposure control frame, a right eye exposure control frame, a left eye exposure control frame, and the like whose exposure is controlled for the entire face, and video data composed of time-series frames. To generate.

In the video data whose exposure is controlled by the video processing device 30, the right eye exposure control frame and the left eye exposure control frame make it easier to discriminate the contours of the left and right eyes, and relate to eye parts such as the degree of opening and closing of the eyes and the inclination of the left and right eyes. It will be suitable for analysis. In the present embodiment, the description of the analysis function related to the eye portion is omitted, but the image processing apparatus 30 may be provided with an analysis function related to the eye portion such as the degree of opening and closing of the eyes and the inclination of the left and right eyes. Further, the eye portion may be analyzed by an external device based on the video data stored or output by the video processing device 30. The analysis function related to the eye portion such as the degree of opening and closing of the eyes and the inclination of the left and right eyes is used, for example, to determine the degree of drowsiness in the imaged object and to determine an emotional state (for example, a normal state or a tense state).

The driver monitor 100 includes an imaging unit 10, a recording unit 20, a video processing device 30, an external input unit 40, an external output unit 41, and the like. The image pickup unit 10 is a camera having a detector such as a CCD, and takes a picture of, for example, a driver in a vehicle as an image subject. The imaging unit 10 appropriately irradiates the imaged object with infrared light so that the imaged object such as a driver can take an image even when it is dark at night. The imaging unit 10 continuously acquires images in time and sends them to the image acquisition unit 31 of the image processing device 30 described later.

The recording unit 20 is, for example, a detachable medium such as an SD card or a USB memory, a hard disk, or the like, and can record and delete the video acquired by the video acquisition unit 31. Hereinafter, the configuration in which the recording unit 20 is provided will be described, but if the driver monitor 100 does not have a portion for recording an image, the recording unit 20 may not be provided. By making the recording unit 20 removable from the driver monitor 100, the recording unit 20 can be removed from the driver monitor 100 and the image can be played back on another PC or the like.

The external input unit 40 acquires vehicle speed information, position information, and the like from an external device. Further, the external output unit 41 outputs the video information or the like processed by the video processing device 30 to the external device. The driver monitor 100 may add speed information, position information, and the like acquired by the external input unit 40 to the video and record or output it to the outside.

The image processing device 30 includes an image acquisition unit 31, a frame control unit 32, an image detection unit 33, a face brightness value acquisition unit 34, a part brightness value acquisition unit 35, a brightness determination unit 36, and an exposure control value calculation unit 37. The video processing device 30 is composed of, for example, a CPU (Central Processing Unit) or the like, and operates according to a computer program to execute processing by each of the above-mentioned parts. The storage unit 30a is composed of a data storage device such as a RAM (Random Access Memory), a flash memory, and a hard disk storage device, and stores a computer program or the like executed by the video processing device 30. Further, the storage unit 30a stores a recognition dictionary for recognizing the face, eyes, and the like of the image subject from the captured image.

The image acquisition unit 31 acquires the image captured by the imaging unit 10 and outputs it to the frame control unit 32. The image acquisition unit 31 may include an imaging unit 10. The frame control unit 32 generates frames in time series based on the video input from the video acquisition unit 31 and outputs the frames to the recording unit 20. The frame control unit 32 controls the exposure of the face and each part of the face such as the eyes, nose, and mouth, and controls the exposure of the entire face, the face exposure control frame, the right eye exposure control frame, and the left eye exposure. Control frames etc. are generated sequentially. The frame control unit 32 outputs the image input from the image acquisition unit 31 to the image detection unit 33, and the image detection unit 33 or the like executes a process for setting the exposure amount. The frame control unit 32 will be described later.

The image detection unit 33 detects the face of the imaged object and each part such as the eyes, nose, and mouth of the face from the image input from the frame control unit 32 based on the recognition dictionary stored in the storage unit 30a. To do. The recognition dictionary stored in the storage unit 30a includes shape data of the face and each part of the face, and the image detection unit 33 extracts the shape pattern appearing in the image and is a recognition dictionary. By collating with the shape data included in, the face and each part of the face are detected. The image detection unit 33 can detect faces, eyes, and the like from images by using known image recognition processing methods that have been developed in various fields.

The face brightness value acquisition unit 34 acquires the brightness value of the face in order to control the exposure of the entire face. The face brightness value acquisition unit 34 calculates the brightness average value in the face detection frame and acquires it as the face brightness value. Here, the face detection frame is a frame including an image of a face portion detected by an image recognition process or the like, and the brightness value of the face is acquired by calculating the brightness average value in the frame. The part brightness value acquisition unit 35 acquires the brightness value of each part in order to control the exposure of each part such as the eyes, nose and mouth of the face. The part brightness value acquisition unit 35 calculates the brightness average value in the eye detection frame, the nose detection frame, and the mouth detection frame, and acquires it as the brightness value of each part. The eye detection frame, nose detection frame, and mouth detection frame are frames including images of each part of the eyes, nose, and mouth detected by image recognition processing or the like, and are included in the frame. The brightness value of each part is acquired by calculating the brightness average value.

The brightness determination unit 36 determines whether or not the brightness value of the face acquired by the face brightness value acquisition unit 34 and the brightness value of each part of the face acquired by the part brightness value acquisition unit 35 are within a predetermined brightness range. To judge. The brightness determination unit 36 calculates the brightness difference between the face brightness value and the face reference brightness value, and determines whether or not the brightness difference is equal to or less than a predetermined threshold value, whereby the face brightness value is predetermined. It is determined whether or not it is within the brightness range. Further, the brightness determination unit 36 calculates the brightness difference between the brightness value of each part of the face and the reference brightness value for each part, and determines whether or not the brightness difference is equal to or less than a predetermined threshold value. It is determined whether or not the brightness value of each part of the face is within a predetermined brightness range. The brightness determination unit 36 outputs the determination result and the brightness difference for the face and each part of the face to the exposure control value calculation unit 37.

The exposure control value calculation unit 37 calculates the exposure control value when the brightness value is out of the predetermined brightness range in the determination result input from the brightness determination unit 36. When the brightness value of the face and each part of the face is higher than the corresponding reference brightness value, the exposure control value calculation unit 37 calculates the exposure control value in order to increase the shutter speed and decrease the gain. Further, the exposure control value calculation unit 37 calculates the exposure control value in order to slow down the shutter speed and increase the gain when the brightness value of the face and each part of the face is lower than the corresponding reference brightness value. .. The exposure control value calculation unit 37 outputs the exposure control value calculated for the face and each part of the face to the frame control unit 32, and the frame control unit 32 outputs the exposure control value to the imaging unit 10 to control the exposure. Perform value-based control.

The frame control unit 32 sets the frame configuration based on the exposure control value for the face and each part of the face input from the exposure control value calculation unit 37. FIG. 2A is a schematic diagram for explaining exposure control for the entire face, and FIG. 2B is a schematic diagram for explaining the generated frame. In the example shown in FIG. 2A, the image of the entire face before exposure control is dark, and the brightness value of the face is lower than the reference brightness value and is out of the predetermined brightness range. The frame control unit 32 controls the exposure in the imaging unit 10 based on the exposure control value calculated by the exposure control value calculation unit 37 in order to control the exposure corresponding to the entire face. In this case, the frame control unit 32 controls the image pickup unit 10 by an exposure control value that slows down the shutter speed and raises the gain. The exposure control by the frame control unit 32 is not always completed by one control, and may be, for example, a control in which the gain is gradually increased until the brightness value becomes appropriate for the blackened image. .. Further, regarding the video acquired as a moving image, the frame control unit 32 reuses the exposure control value in the previously acquired frame in the frame acquired in chronological order by using the exposure control value in the current frame as well. , It may be operated to reduce the number of trials of exposure control. The frame control unit 32 executes exposure control processing such as stepwise exposure control and reuse of exposure control values not only in exposure control for the entire face but also in exposure control for each part of the face described later. You may. In addition to the specific description below, the stepwise exposure control and the reuse of the exposure control value will be omitted for the sake of brevity.

The brightness value of the entire face is appropriate for the image taken after the exposure control. As shown in FIG. 2B, the frame control unit 32 generates an image taken after the exposure control as a face exposure control frame in chronological order and outputs the image to the recording unit 20.

The frame control unit 32 generates an exposure-controlled frame corresponding to each portion based on the brightness value of each portion of the face in the face exposure control frame. Hereinafter, an example in which the right eye and the left eye are used as facial parts will be described, but the same applies to the nose, mouth, and the like. FIG. 3A is a schematic diagram for explaining an example of exposure control for eyes, and FIG. 3B is a schematic diagram for explaining a frame to be generated. In the example shown in FIG. 3A, the brightness value of the right eye is lower than the reference brightness value and is outside the predetermined brightness range, and the brightness value of the left eye is within the brightness range. The frame control unit 32 controls the exposure in the imaging unit 10 based on the exposure control value calculated by the exposure control value calculation unit 37 in order to control the exposure corresponding to the right eye. The exposure control value output from the exposure control value calculation unit 37 to the imaging unit 10 slows the shutter speed and increases the gain.

The brightness value of the image taken after the exposure control is appropriate for the right eye. As shown in FIG. 3B, the frame control unit 32 generates an image captured after exposure control as a right eye exposure control frame in chronological order. That is, the frame control unit 32 generates a frame for the captured image with a frame configuration that generates a right eye exposure control frame after the face exposure control frame.

FIG. 4A is a schematic diagram for explaining another example of exposure control for the eyes, and FIG. 4B is a schematic diagram for explaining the generated frame. In the example shown in FIG. 4A, the brightness value of the right eye is lower than the reference brightness value and is out of the predetermined brightness range, and the brightness value of the left eye is higher than the reference brightness value and is out of the brightness range. The frame control unit 32 controls the exposure corresponding to the right eye, and subsequently controls the exposure corresponding to the left eye.

In the image captured after the exposure control, the brightness value of the right eye is appropriate in the right eye exposure control frame, and the brightness value of the left eye is appropriate in the left eye exposure control frame. As shown in FIG. 4B, the frame control unit 32 generates images taken after exposure control as a right-eye exposure control frame and a left-eye exposure control frame in chronological order. That is, the frame control unit 32 generates a frame for the captured image with a frame configuration that generates a right eye exposure control frame and a left eye exposure control frame after the face exposure control frame.

FIG. 5A is a schematic diagram for explaining still another example of exposure control for the eyes, and FIG. 5B is a schematic diagram for explaining the generated frame. In the example shown in FIG. 5A, the brightness values of both the left and right eyes are lower than the reference brightness value and are out of the predetermined brightness range. The frame control unit 32 needs to control the exposure corresponding to both the left and right eyes. In this case, for example, the exposure control value may be calculated so that the average value of the brightness values of the left eye and the right eye approaches the reference brightness value, but the method is not limited to this method. The brightness value of the image taken after the exposure control is appropriate for both eyes.

As shown in FIG. 5B, the frame control unit 32 generates images taken after exposure control as binocular exposure control frames in chronological order. That is, the frame control unit 32 generates a frame for the captured image with a frame configuration that generates a binocular exposure control frame after the face exposure control frame.

Next, the operation of the video processing device 30 will be described based on the frame generation process. FIG. 6 is a flowchart showing a procedure of frame generation processing in the video processing device 30. It is assumed that the image processing device 30 acquires an image and obtains a detection frame for the face and each part of the face. The face brightness value acquisition unit 34 of the image processing device 30 acquires the face brightness value from the input image (S1). The brightness determination unit 36 determines whether or not the brightness value of the face is within a predetermined brightness range (S2). When the determination result in step S2 is negative and the brightness value of the face is out of the predetermined brightness range (S2: NO), the exposure control value calculation unit 37 executes the calculation process of the exposure control value for the face (S3). .. The process of calculating the exposure control value will be described later. The frame control unit 32 controls the exposure of the imaging unit 10 based on the exposure control value for the face calculated by the exposure control value calculation unit 37 to generate a face exposure control frame (S4), returns to step S1 and repeats the process. ..

When the brightness value of the face is within the predetermined brightness range in the determination result in step S2 (S2: YES), the currently generated frame is recorded in the recording unit 20 as the face exposure control frame (S5). Further, the current exposure control value is stored in the storage unit 30a as the exposure control value for the face (S6). Next, the portion brightness value acquisition unit 35 acquires the brightness value of each portion of the face (S7).

The brightness determination unit 36 determines whether or not there is a portion in which the brightness value of each portion of the face is within the predetermined luminance range (S8), and when there is a portion within the predetermined luminance range (S8: YES), the current frame is recorded in the recording unit 20 as an exposure control frame for each part of the portion within the brightness range (S9). Further, the current exposure control value is stored in the storage unit 30a as an exposure control value for a portion within the brightness range (S10). After the step S10 and when the determination result is no in step S8 (S8: NO), the frame control unit 32 determines whether or not the exposure control frame has been recorded for all the parts (S11).

If the result is negative in step S11 (S11: NO), the exposure control frame is not recorded in the frame control unit 32 because there is a portion where the exposure control is still insufficient, and the brightness value is the brightness. Executes the calculation process of the exposure control value for the part outside the range. The exposure control value calculation process in step S12 is equivalent to the process in step S3. The frame control unit 32 controls the exposure of the imaging unit 10 based on the exposure control value calculated by the exposure control value calculation unit 37, generates an exposure control frame for a portion whose brightness value is outside the brightness range (S13), and steps. The process returns to S7 and the process is repeated. In step S11, if it is a determination result that the exposure control frame has been recorded for all the parts (S11: YES), the process ends.

By the above processing, for example, a right eye exposure control frame corresponding to the right eye, a left eye exposure control frame corresponding to the left eye, a nose exposure control frame, and a mouth exposure control frame are sequentially generated and recorded in the recording unit 20. The image processing device 30 can suppress the loss of image information corresponding to each part of the face or face by generating a face exposure control frame corresponding to the face and an exposure control frame corresponding to each part of the face. , It is possible to suppress overexposure and underexposure in the frame.

FIG. 7 is a flowchart showing a procedure for calculating the exposure control value in the video processing device 30. The exposure control value calculation process according to FIG. 7 is used for calculating the face exposure control value in step S3 of FIG. 6 and calculating the exposure control value for a portion whose brightness value is outside the predetermined brightness range in step S12 of FIG. .. The exposure control value calculation unit 37 acquires the previous exposure control value (S21) and determines whether or not the brightness value is higher than the predetermined brightness range (S22). When the luminance value is higher than the predetermined luminance range (S22: YES), the exposure control value calculation unit 37 lowers the gain of the exposure control value so that the luminance value becomes lower (S23), and ends the process. In addition to lowering the gain of the exposure control value, the exposure control value calculation unit 37 may increase the shutter speed or use these in combination.

When it is determined in step S22 that the luminance value is not higher than the predetermined luminance range (S22: NO), the exposure control value calculation unit 37 determines whether or not the luminance value is lower than the predetermined luminance range (S22: NO). S24), if it is low (S24: YES), the gain of the exposure control value is increased so that the luminance value is high (S25), and the process is terminated. Further, when it is determined in step S24 that the luminance value is not lower than the predetermined luminance range (S24: NO), the process ends without changing the exposure control value. The exposure control value calculation unit 37 may increase the gain of the exposure control value, slow down the shutter speed, or use these in combination. In the processing procedure shown in FIG. 6, when the luminance value is within the predetermined luminance range, the process does not shift to the exposure control value calculation process, but when the luminance value is within the predetermined luminance range. It is not necessary to change the exposure control value.

The image processing device 30 identifies each part of the face on the left, right, top, bottom, or part of the face, for example, a shadow is generated on the right half of the face to make it darker, or conversely, light is emitted to make the face brighter. When it is difficult, an exposure control frame corresponding to each part is generated. By generating the exposure control frame corresponding to the right eye and the left eye, the image processing device 30 can enhance the distinctiveness of the left and right eyes even when light and darkness occurs on the left and right or top and bottom of the face. Based on each frame generated by the image processing device 30, for example, in the analysis of the eye portion, the contour of the eye is image-recognized, and the degree of opening and closing of the eye is calculated based on the contour.

Further, the frame control unit 32 does not need to generate the exposure control frames individually for the parts having the same exposure control values, and may combine them into one exposure control frame. When there are a plurality of parts within a predetermined brightness range in one exposure control frame, the frame control unit 32 does not need to generate a new frame individually for each part, and summarizes them. By processing the video, the load of video processing and the amount of video data can be reduced.

Further, the frame control unit 32 does not generate an exposure control frame for each part when an appropriate image in which all parts are within a predetermined brightness range is obtained from the exposure control frame of the entire face. It is possible to reduce the load of video processing and the amount of video data.

Further, the frame control unit 32 may add information on the exposure control value and information for identifying each part of the face or the face subject to the exposure control to each exposure control frame, and these information may be added. It may be recorded in the recording unit 20 including the eye portion and used for analysis of the eye portion and the like.

The frame control unit 32 may handle each part independently, or may treat the corresponding parts as one set. The frame control unit 32 may have the left and right eyes as a set related to the eyes, for example. In this case, the frame control unit 32 differs between the left eye exposure control group that controls the exposure of the left eye, the right eye exposure control group that controls the exposure of the right eye, the binocular exposure control group that uses the same exposure control value for both eyes, and the left and right exposure control frames. Divide into asymmetric binocular exposure control groups that use exposure control values. The frame control unit 32 can simplify the exposure control process by tracing the exposure control value for each group.

(Modification example)
In the above-described embodiment, an example in which the reference luminance value is preset for each part such as the face, eyes, nose, and mouth has been described, but the individual difference of the image subject and the influence of the surrounding light environment may be affected. It may be changed dynamically to eliminate it. In addition, the reference brightness value is dynamically set based on the average value of the face angle within a certain period based on the state where the face angle (roll, pitch, yaw angle) is 0 deg and faces the front. You may do so.

In the above-described embodiment, the face brightness value acquisition unit 34 and the part brightness value acquisition unit 35 of the image processing device 30 acquire the brightness average value in the detection frame of the face and each part, but for example, the portion within the detection frame. By changing the weighting, it is possible to improve the distinctiveness of the facial part. In addition, the face brightness value acquisition unit 34 and the portion brightness value acquisition unit 35 may acquire the brightness value excluding the portion that is locally shining due to reflection such as eyeglasses.

In the above-described embodiment, the eyes, nose, mouth, and the like are exemplified as the respective parts of the face, but other parts such as the eyebrows, cheeks, forehead, chin, and ears may be the target parts for exposure control.

Next, the features of the video processing device 30, the video processing method, and the video processing program according to the above-described embodiment will be described.
The image processing device 30 according to the embodiment includes an image acquisition unit 31, an image detection unit 33, a portion brightness value acquisition unit 35 as a brightness value acquisition unit, a brightness determination unit 36, and a frame control unit 32. The image acquisition unit 31 acquires an image of the face of the image subject. The image detection unit 33 detects a facial portion from the image acquired by the image acquisition unit 31. The part brightness value acquisition unit 35 acquires the brightness value of the face part detected by the image detection unit 33. The brightness determination unit 36 determines whether or not the brightness value acquired by the part brightness value acquisition unit 35 is within a predetermined brightness range. The frame control unit 32 generates a frame whose exposure is controlled by the exposure control value corresponding to the portion determined to be out of the brightness range by the brightness determination unit 36. As a result, the image processing device 30 can suppress the loss of image information corresponding to each part of the face, and can suppress overexposure and underexposure in the frame.

Further, there are a plurality of facial parts whose exposure is controlled by the frame control unit 32. The frame control unit 32 does not generate a new exposure-controlled frame for one or more portions of the exposure-controlled frame whose brightness value is determined by the brightness determination unit 36 to be within a predetermined brightness range. As a result, the video processing device 30 can reduce the amount of video data and the like.

Further, the part brightness value acquisition unit 35 weights and acquires the brightness value in the detection frame corresponding to the face part. As a result, the image processing device 30 can enhance the distinctiveness of the facial part.

Further, the facial part has a right eye part and a left eye part, and the frame control unit 32 generates a frame whose exposure is controlled for at least one of the right eye part and the left eye part. As a result, the image processing device 30 can improve the distinctiveness of the left and right eyes when light and darkness occurs on the left and right or top and bottom of the face.

The video processing method according to the embodiment includes a video acquisition step, a video detection step, a brightness value acquisition step, a brightness determination step, and a frame control step. The image acquisition step acquires an image of the face of the image subject. The image detection step detects a facial part from the image acquired by the image acquisition step. The brightness value acquisition step acquires the brightness value of the face portion detected by the image detection step. The brightness determination step determines whether or not the brightness value acquired by the brightness value acquisition step is within a predetermined brightness range. The frame control step generates a frame whose exposure is controlled by the exposure control value corresponding to the portion determined to be out of the luminance range by the luminance determination step. According to this image processing method, it is possible to suppress the loss of image information corresponding to each part of the face, and it is possible to suppress overexposure and underexposure in the frame.

The video processing program according to the embodiment causes a computer to execute a video acquisition step, a video detection step, a brightness value acquisition step, a brightness determination step, and a frame control step. The image acquisition step acquires an image of the face of the image subject. The image detection step detects a facial part from the image acquired by the image acquisition step. The brightness value acquisition step acquires the brightness value of the face portion detected by the image detection step. The brightness determination step determines whether or not the brightness value acquired by the brightness value acquisition step is within a predetermined brightness range. The frame control step generates a frame whose exposure is controlled by the exposure control value corresponding to the portion determined to be out of the luminance range by the luminance determination step. According to this image processing method, it is possible to suppress the loss of image information corresponding to each part of the face, and it is possible to suppress overexposure and underexposure in the frame.

The above description has been made based on the embodiment of the present invention. It will be appreciated by those skilled in the art that these embodiments are exemplary and that various modifications and modifications are possible within the claims of the invention, and that such modifications and modifications are also within the claims of the present invention. It is about to be done. Therefore, the descriptions and drawings herein should be treated as exemplary rather than limiting.

30 Video processing device, 31 Video acquisition unit, 32 Frame control unit,
33 Image detection unit, 35 Part brightness value acquisition unit (luminance value acquisition unit),
36 Brightness determination unit.

Claims (7)

An image acquisition unit that acquires an image of the face of the image subject,
An image detection unit that detects a facial part from the image acquired by the image acquisition unit,
A luminance value acquisition unit that acquires a luminance value in the face portion detected by the image detection unit, and a luminance value acquisition unit.
A luminance determination unit that determines whether or not the luminance value acquired by the luminance value acquisition unit is within a predetermined luminance range, and a luminance determination unit.
A frame control unit that generates a frame whose exposure is controlled by an exposure control value corresponding to a portion determined to be out of the brightness range by the brightness determination unit.
A video processing device characterized by being equipped with. The frame control unit does not generate a new exposure-controlled frame for one or more parts of the exposure-controlled frame whose brightness value is determined by the brightness determination unit to be within a predetermined brightness range. The video processing apparatus according to claim 1. The video processing apparatus according to claim 1 or 2, wherein the brightness value acquisition unit acquires an averaged brightness value in a detection frame corresponding to the face portion. The video processing device according to any one of claims 1 to 3, wherein the luminance value acquisition unit acquires the luminance value by weighting within the detection frame corresponding to the facial portion. The facial part has a right eye part and a left eye part.
The video processing apparatus according to any one of claims 1 to 4, wherein the frame control unit generates a frame whose exposure is controlled for at least one of a right eye portion and a left eye portion. An image acquisition step to acquire an image of the face of the image subject,
An image detection step for detecting a facial part from the image acquired by the image acquisition step,
A luminance value acquisition step for acquiring a luminance value in the face portion detected by the image detection step, and a luminance value acquisition step.
A luminance determination step for determining whether or not the luminance value acquired by the luminance value acquisition step is within a predetermined luminance range, and a luminance determination step.
A frame control step that generates a frame whose exposure is controlled by an exposure control value corresponding to a portion determined to be out of the brightness range by the brightness determination step.
A video processing method characterized by comprising. An image acquisition step to acquire an image of the face of the image subject,
An image detection step for detecting a facial part from the image acquired by the image acquisition step,
A luminance value acquisition step for acquiring a luminance value in the face portion detected by the image detection step, and a luminance value acquisition step.
A luminance determination step for determining whether or not the luminance value acquired by the luminance value acquisition step is within a predetermined luminance range, and a luminance determination step.
A frame control step that generates a frame whose exposure is controlled by an exposure control value corresponding to a portion determined to be out of the brightness range by the brightness determination step.
A video processing program characterized by having a computer execute.

Images