Information Processing Apparatus, Information Processing Method, and Storage Medium

Abstract

The present invention relates to an information processing apparatus, an information processing method, and a storage medium. An apparatus includes: an acquisition unit configured to acquire an image; a first detection unit configured to detect a first region corresponding to a first feature from the image; a second detection unit configured to detect a second region corresponding to a second feature from the image; a measurement unit configured to perform photometry on the first region and the second region; a determination unit configured to determine an exposure based on a weighted average of a first photometry value of the first region acquired by the measurement unit and a second photometry value of the second region acquired by the measurement unit before acquiring the first photometry value; and an output unit configured to output information related to the exposure.

Description

Technical Field

[0001] Aspects of the embodiments relate to an information processing device, an information processing method, and a storage medium. Background Art

[0002] Conventionally, as discussed in Japanese Unexamined Patent Application Publication No. 2015-130615, a technique is known for determining an exposure amount using not only face detection but also human body detection in a backlight environment. Summary of the Invention

[0003] According to an aspect of the embodiments, an information processing device includes: an acquisition unit configured to acquire an image; a first detection unit configured to detect a first region corresponding to a first feature from the image; a second detection unit configured to detect a second region corresponding to a second feature from the image; a measurement unit configured to perform photometry on the first region and the second region; a determination unit configured to determine an exposure based on a weighted average of a first photometry value of the first region acquired by the measurement unit and a second photometry value of the second region acquired by the measurement unit before acquiring the first photometry value; and an output unit configured to output information related to the exposure.

[0004] An information processing method includes: acquiring an image; detecting a first region corresponding to a first feature from the image; detecting a second region corresponding to a second feature from the image; performing photometry on the first region and the second region; determining an exposure based on a weighted average of a first photometry value of the first region acquired in the photometry and a second photometry value of the second region acquired in the photometry before acquiring the first photometry value; and outputting information related to the exposure.

[0005] A non-transitory computer-readable storage medium stores a program for causing a computer to execute the above information processing method.

[0006] Further features of the present disclosure will become apparent from the following description of exemplary embodiments with reference to the accompanying drawings. Brief Description of the Drawings

[0007] Figure 1 is a block diagram showing an example of the configuration of a camera control system according to a first exemplary embodiment of the present invention.

[0008] Figure 2 is a block diagram showing an example of the internal configuration of a surveillance camera according to the first exemplary embodiment.

[0009] Figure 3 is a block diagram showing an example of the internal configuration of a client device as an information processing device according to the first exemplary embodiment.

[0010] Figure 4 is a diagram showing an example of the functional configuration of a client device according to a first exemplary embodiment.

[0011] Figure 5 is a flowchart showing examples of a detection process and an exposure determination process according to a first exemplary embodiment.

[0012] Figure 6A and 6B are diagrams each showing the relationship between a subject detection area and a background area according to a first exemplary embodiment.

[0013] Figures 7A to 7D is a diagram showing the relationship between the average luminance value of a subject and a difference according to a first exemplary embodiment.

[0014] Figures 8A to 8E is a diagram showing the relationship between the average luminance value, a detection score, and a difference of a subject according to a modified example of a first exemplary embodiment. DETAILED DESCRIPTION

[0015] An information processing apparatus according to a first exemplary embodiment will be described below with reference to Figures 1 to 7D One or more functional blocks shown in the drawings to be described below may be implemented by hardware such as an application specific integrated circuit (ASIC) or a programmable logic array (PLA), or may be implemented by a programmable processor such as a central processing unit (CPU) or a microprocessing unit (MPU) that executes software. Alternatively, one or more functional blocks may be implemented by a combination of software and hardware. Therefore, even when different functional blocks are described as the acting body of an operation below, the same hardware may be implemented as the acting body.

[0016] <Basic Configuration>

[0017] Figure 1 is a block diagram showing an example of the configuration of a camera control system (or a camera system) according to the present exemplary embodiment. Figure 1 The shown camera control system includes a surveillance camera 101, a network 102, a client device 103, an input device 104, and a display device 105. The surveillance camera 101 is capable of performing subject imaging to acquire a moving image and performing image processing. The surveillance camera 101 and the client device 103 are communicably connected to each other via the network 102.

[0018] Figure 2is a block diagram showing an example of the internal configuration of the surveillance camera 101 according to the present exemplary embodiment. The imaging optical system 201 is a group of optical components including a zoom lens, a focusing lens, an anti-shake lens, an aperture, and a shutter, and collects optical information related to a subject.

[0019] The image sensor 202 is a charge accumulation type solid-state image sensor such as a complementary metal oxide semiconductor (CMOS) image sensor or a charge-coupled device (CCD) image sensor, which converts the light flux collected by the imaging optical system 201 into a current value (signal value), and when used in combination with a color filter, serves as an imaging unit for acquiring color information.

[0020] The camera CPU 203 is a control unit for overall controlling the operation of the surveillance camera 101. The camera CPU 203 reads instructions stored in a read-only memory (ROM) 204 or a random access memory (RAM) 205, and performs processing based on the instructions. The imaging system control unit 206 (based on instructions from the camera CPU 203) controls components of the surveillance camera 101 to perform focus control, shutter control, aperture adjustment, etc. for the imaging optical system 201. The communication control unit 207 communicates with the client device 103 to perform control for sending control instructions related to components of the surveillance camera 101 to the camera CPU 203.

[0021] The analog-to-digital (A / D) conversion unit 208 converts the amount of light of the subject detected by the image sensor 202 into a digital signal value. The image processing unit 209 performs image processing on the image data output from the image sensor 202 as a digital signal. The encoder unit 210 is a conversion unit for converting the image data processed by the image processing unit 209 into a file format such as Moving Picture Experts Group (Motion JPEG), H.264, or H.265. The network interface (I / F) 211 is used to communicate with an external device such as the client device 103 via the network 102, and is controlled by the communication control unit 207.

[0022] The network 102 is an Internet Protocol (IP) network that connects the surveillance camera 101 and the client device 103 to each other. The network 102 includes, for example, a plurality of routers, switches, and cables that meet the Ethernet communication standard. In the present exemplary embodiment, the network 102 can be any network through which the surveillance camera 101 and the client device 103 can communicate with each other, and the communication standard, scale, and configuration of the network 102 are not particularly limited. For example, the network 102 can include the Internet, a wired local area network (wired LAN), a wireless LAN, and / or a wide area network (WAN).

[0023] Figure 3 FIG. is a block diagram showing an example of the internal configuration of the client device 103 as an information processing device according to the present exemplary embodiment. The client device 103 includes a client CPU 301, a main storage device 302, an auxiliary storage device 303, an input I / F 304, an output I / F 305, and a network I / F 306. The foregoing components are communicably connected to each other via a system bus.

[0024] The client CPU 301 controls the operation of the client device 103 as a whole. The client CPU 301 may be configured to control the monitoring camera 101 as a whole via the network 102. The main storage device 302 is, for example, a RAM and serves as a temporary data storage area for the client CPU 301. The auxiliary storage device 303 is, for example, a hard disk drive (HDD), a ROM, or a solid state drive (SSD), and stores various programs and various types of setting data. The input I / F 304 is used to receive an input from the input device 104. The output I / F 305 is used to output information to the display device 105. The network I / F 306 is used to communicate with external devices such as the monitoring camera 101 via the network 102.

[0025] The client CPU 301 performs processing based on the programs stored in the auxiliary storage device 303, thereby implementing Figure 4 the functions and processing of the client device 103 shown. Details thereof will be described below.

[0026] Figure 1 The input device 104 shown includes, for example, a mouse and a keyboard. Figure 1 The display device 105 shown is, for example, a monitor and displays an image output from the client device 103. Although the imaging control system according to the present exemplary embodiment includes the client device 103, the input device 104, and the display device 105 as separate devices, the configuration is not limited thereto. For example, the client device 103 and the display device 105 may be integrated, or the input device 104 and the display device 105 may be integrated. Further, the client device 103, the input device 104, and the display device 105 may be integrated.

[0027] Figure 4 FIG. is a diagram showing an example of the functional configuration of the client device 103 according to the present exemplary embodiment. Figure 4The components shown are the functions of a configuration that can be implemented by the client CPU 301 and are equivalent to the client CPU 301. More specifically, the client CPU 301 of the client device 103 includes an input signal acquisition unit 401, a communication control unit 402, an input image acquisition unit 403, a subject detection unit 404, a photometric value calculation unit 405, an exposure determination unit 406, a detection result storage unit 407, and a display control unit 408. Optionally, the client device 103 may include, independent of the client CPU 301 Figure 4 the components shown.

[0028] The input signal acquisition unit 401 is an input unit that receives the user's input via the input device 104.

[0029] The communication control unit 402 performs control for receiving the image transmitted from the surveillance camera 101 via the network 102. The communication control unit 402 also performs control for transmitting a control instruction to the surveillance camera 101 via the network 102.

[0030] The input image acquisition unit 403 acquires, via the communication control unit 402, the image captured by the surveillance camera 101 as the object image for the subject detection process. The details of the detection process will be described below.

[0031] The subject detection unit 404 performs various types of detections on the image acquired by the input image acquisition unit 403, including face area detection (face detection) and human body area detection (human detection). Although the subject detection unit 404 according to the present exemplary embodiment is configured to select a desired method between face detection and human detection, the configuration is not limited thereto. For example, a configuration capable of detecting a feature area of a part of a person (such as the upper body of a person or a partial area of the face (such as eyes, pupils, nose, or mouth, etc.)) can be selected. In addition, although in the present exemplary embodiment, a person is described as the subject to be detected, a configuration capable of detecting a specific area of a predetermined subject other than a person can be adopted. For example, a configuration capable of detecting a predetermined subject (such as an animal face or a motor vehicle, etc.) preset using the client device 103 can be adopted.

[0032] The photometric value calculation unit 405 calculates the photometric value of the current frame based on the detection result of the current frame obtained from the subject detection unit 404 and the detection result of the previous frame obtained from the detection result storage unit 407.

[0033] The exposure determination unit 406 determines the exposure value at the time of photographing a subject for acquiring an image based on the photometric value calculated by the photometric value calculation unit 405 and a target value. The exposure value determined by the exposure determination unit 406 includes: the exposure value based on the program diagram for exposure control pre-recorded in the client device 103 and the exposure correction value for correcting the exposure value. The communication control unit 402 sends information related to the exposure value determined by the exposure determination unit 406 to the surveillance camera 101 so that exposure control in the surveillance camera 101 is performed. The detailed processing related to the operations of the subject detection unit 404, the photometric value calculation unit 405, and the exposure determination unit 406 will be described below with reference to Figure 5 the flowchart shown in

[0034] <Subject Detection Processing and Exposure Determination Processing>

[0035] Next, the subject detection processing and the exposure determination processing according to the present exemplary embodiment will be described with reference to Figure 5 the flowchart shown in Figure 5 is a flowchart showing an example of the subject detection processing and an example of the exposure determination processing according to the present exemplary embodiment. Assume that: the devices in the imaging system shown in Figure 1 are turned on, and a connection (communication) is established between the surveillance camera 101 and the client device 103. In this state, it is also assumed that subject photographing, image data transmission, and image display on the display device 105 are repeated at a predetermined update interval in the imaging system. In response to an image acquired by subject photographing being input from the surveillance camera 101 via the network 102, the client CPU 301 of the client device 103 starts Figure 5 the flowchart shown in

[0036] First, in step S501, the subject detection unit 404 performs face detection of the subject on the image acquired by the input image acquisition unit 403. A pattern matching method using a pattern (classifier) or a method other than the pattern matching method (such as a subject detection method using the luminance gradient in a local area, etc.) can be used as the method for detecting the face, and the pattern (classifier) is generated using statistical learning. In other words, the detection method is not particularly limited, and various methods such as a detection method based on machine learning and a detection method based on distance information can be adopted.

[0037] Next, in step S502, it is determined whether a face is detected in the face detection performed in step S501. In the case where no face is detected (No in step S502), the process proceeds to step S508. On the other hand, in the case where at least one face is detected (Yes in step S502), the process proceeds to step S503.

[0038] In step S503, the photometric value calculation unit 405 calculates the average luminance value Iface of the face region of the face determined to be detected in step S502 based on the detection result obtained from the subject detection unit 404. More specifically, the photometric value calculation unit 405 applies information related to the number of detected faces, the positions of the detected faces, and the sizes of the detected faces obtained from the subject detection unit 404 to the following formula (1).

[0039]

[0040] In formula (1), I(x, y) represents the luminance value at the two-dimensional coordinate position (x, y) in the horizontal direction (x-axis direction) and the vertical direction (y-axis direction) in the image. f represents the number of detected faces. (v, h) represents the center coordinates of the region where the subject is detected. k represents the size of the region where the subject is detected in the horizontal direction. l represents the size of the region where the subject is detected in the vertical direction. t represents the time of the frame in which the subject is detected. In step S510, in the same manner as step S503, information related to the number of detected humans, the positions of the detected humans, and the sizes of the detected humans is applied to the following formula (2) to calculate the average luminance value of the human region.

[0041]

[0042] In formula (2), g represents the number of detected humans, and the other symbols are the same as those in formula (1). Next, in step S504, the photometric value calculation unit 405 calculates the photometric value E(t) in the current frame (at time t) based on the average luminance value Iface of the face region calculated in step S503 and the detection result of the previous frame. For example, the average luminance value Iface of the face region in the current frame and the weighted average of the average luminance values of the face region and the human region in the previous frame immediately preceding the current frame are calculated using the following formulas (3) and (4) to obtain the photometric value E(t).

[0043]

[0044]

[0045] In Formulas (3) and (4), n represents the number of previous frames used for calculating the weighted average. In the proposed method, the number of previous frames n is set to 1 or more. For example, when the number of previous frames n is 10, the weighted average of the average luminance values of the current frame and the ten frames immediately preceding the current frame is calculated. In addition, α and β respectively represent the weight parameters for the average luminance value of the face region and the average luminance value of the human body region used for calculating the weighted average. The values of the weight parameters α and β can be changed according to the environment in which the subject is detected, the application purpose of the subsequent authentication process, and the accuracy of the detection process performed by the subject detection unit 404. The following will refer to Figures 6A to 7D Describe the specific method of setting the parameters α and β and the effects of the parameters α and β. The method of calculating the photometric value based on the detection results of the current frame and the previous frame is not limited to the method using Formulas (3) and (4). For example, a calculation method using statistical values such as arithmetic mean, harmonic mean, or geometric mean can be adopted, and this statistical value takes into account the influence of multiple frames in the time direction.

[0046] Next, in step S505, as shown in the following Formula (5), the difference ΔDiff between the target value Itarget of the subject area and the photometric value E(t) calculated in step S504 is calculated.

[0047] ΔDiff = I target -E(t) (5)

[0048] In Formula (5), the target value Itarget of the subject area can be preset by the user or can be a fixed value preset in the hardware.

[0049] Next, in step S506, based on the difference ΔDiff calculated in step S505, a predetermined threshold Th, and the current exposure value EVcurrent, the exposure correction amount EVcorrection is determined. For example, the exposure correction amount EVcorrection is represented by the following Formula (6).

[0050]

[0051] In Equation (6), the parameter γ represents the exposure correction value, and this exposure correction value affects the correction for shifting the current exposure value EVcurrent to the underexposure side or overexposure side when the difference ΔDiff calculated in step S505 does not satisfy a predetermined threshold Th. For example, as shown in the last branch of Equation (6), when the difference ΔDiff between the photometric value E(t) and the target value Itarget is greater than the threshold Th (Th < ΔDiff), it is determined that the average luminance of the subject area in this state is on the underexposure side. Then, the current exposure value EVcurrent is corrected to increase (+γ) so that the luminance of the subject area is controlled to be closer to the target value Itarget. Therefore, in order to perform exposure correction stably in the time direction, it is important that the difference ΔDiff calculated using Equation (5) gradually changes in the time direction.

[0052] Next, a specific method for setting the parameters α and β in Equations (3) and (4) and its effects will be described. Generally, as Figure 6A and 6B show, compared with the detection result of the face area, the detection result of the human body area erroneously includes many pixels that are assumed to be the background area (as shown by the hatched area in Figure 6B ). For example, when a subject is detected at the entrance or exit of a building or stadium as shown in Figure 6A and 6B , due to the pixels of the erroneously included background area, the average luminance value of the human body area may be calculated to be greater than the expected value. Figure 7A and 7B each show how the average luminance value of the subject changes over time when a subject is detected in a backlight scene as shown in Figure 6A and 6B . Figure 7C and 7D each show how the difference ΔDiff changes over time when a subject is detected in a backlight scene as shown in Figure 6A and 6B . As time passes, face detection is performed on multiple frames, and exposure correction is performed so that the current exposure value EVcurrent increases toward the target value Itarget. However, in the case where, for example, the orientation of the face changes or the face area is shaded, there is a moment when human body detection is performed instead of face detection, and as shown by times T1, T2, T3, and T4 in Figure 7A and 7B , the average luminance value of the subject temporarily becomes high.

[0053] In this case, in a conventional method that does not consider the detection results of previous frames, the photometric value E(t) temporarily becomes greater than the target value Itarget, making it difficult to stably calculate the exposure correction amount EVcorrection in the time direction. As used herein, the term "conventional method" refers to a method in which the number n of previous frames is set to 0 in formulas (3) and (4). Therefore, there may be moments when the subject area suddenly brightens or darkens over time. In contrast, in the method proposed according to this exemplary embodiment, the photometric value E(t) is calculated considering the subject detection results on multiple previous frames, such that the photometric value E(t) is smooth in the time direction (as indicated by the dashed line shown in Figure 7B ).

[0054] As a result, the exposure fluctuation in the time direction is stabilized. As used herein, the term "proposed method" refers to a method in which the number n of previous frames is 1 or more and is substituted into formulas (3) and (4). In addition, as described above, the average luminance value of the human body area may generally be affected by the background area compared to the average luminance value of the face area. Considering this, the weight parameters α and β in formula (4) are set to satisfy the relationship α > β. This achieves exposure control that focuses on more accurate detection processing. The relationship between the weight parameters α and β is not limited to the relationship that focuses on the accuracy of the detection processing. For example, in the case of counting the number of people in a subsequent authentication process, the weight parameters α and β can be set to satisfy the relationship α < β that focuses on the human body detection processing. Additionally, in the case where the accuracy of the human body detection processing and the accuracy of the face detection processing are equivalent and comparable, the weight parameters α and β can be set to satisfy the relationship α = β. Furthermore, although exposure fluctuations occurring according to the type of detection processing are described as a problem with reference to Figures 7A to 7D , the problems applicable to the proposed method are not limited to this. The proposed method is also applicable to problems caused by, for example, false detections, thereby achieving stable exposure.

[0055] Return Figure 5 , in step S507, the average luminance value calculated in step S503 or S510 and the information related to the subject detection method are stored in the detection result storage unit 407. The above is the description of the processing performed according to this exemplary embodiment in the case where at least one face area is detected.

[0056] Next, the processing performed according to this exemplary embodiment in the case where no face area is detected will be described. In the case where no face area is detected in step S502 (No in step S502), then in step S508, the subject detection unit 404 performs human body detection of the subject on the image acquired by the input image acquisition unit 403.

[0057] Next, in step S509, based on the result of the human body detection performed in step S508, it is determined whether a human body region is detected from the image. In the case where at least one human body region is detected (Yes in step S509), the process proceeds to step S510. On the other hand, in the case where no human body region is detected (No in step S509), the process proceeds to step S514. In the case where the process proceeds to step S514 (that is, in the case where neither a face region nor a human body region is detected), exposure correction based on the subject detection result is not performed. In addition to calculating the average luminance value of the human body region to determine the exposure, the processing in steps S510 to S513 is performed using an arithmetic formula that is substantially the same as the arithmetic formula used in steps S503 to S506 described above, and thus the detailed description of steps S510 to S513 will be omitted.

[0058] As described above, the imaging system according to the present exemplary embodiment calculates the photometric value E(t) based on the subject detection results of (one or more) previous frames in addition to the subject detection result of the current frame, and sets the most suitable exposure for the subject in the image. Therefore, the imaging system according to the present exemplary embodiment reduces exposure fluctuations caused by changes in the detection process, and stably performs the most suitable exposure control for the subject. In addition, since the weight is variably controlled for each detection process, exposure control that is not affected by processes with low detection accuracy and is also robust to randomly occurring false detections is achieved.

[0059] Next, a second exemplary embodiment will be described. A case of calculating the photometric value E(t) based on the detection score calculated by the detection unit will be described with reference to Figures 8A to 8E and formula (7) as a modification of the above exemplary embodiment. As used herein, the term "detection score" refers to an evaluation value indicating the reliability degree of the detection result of the detection unit. More specifically, the larger the value of the detection score, the higher the possibility that a detection object exists in the set detection region. The smaller the value of the detection score, the higher the possibility that no detection object exists in the set detection region (that is, the possibility of false detection). Although, for convenience, a value normalized within a value range between a minimum value of 0 and a maximum value of 100 is used to describe the detection score according to this modification, the detection score is not limited thereto.

[0060] Figure 8A and 8B each show how the average luminance value of the subject changes over time, Figure 8C shows the detection score, and Figure 8D and 8E each show how the difference ΔDiff changes over time. Over time, subject detection is performed on many frames, and as inFigure 8A and 8B false detections with low detection scores occur at random timings shown by times T1, T2, T3, T4, T5, and T6 in 8B . The false detections generally refer to regions where no subject exists, such that the average luminance value calculated based on the false detections is significantly different from the average luminance value of the subject. Therefore, in cases where false detections occur frequently, exposure fluctuations occur using conventional methods, and even the above-proposed method using weighted averaging is affected to some extent (refer to Figure 8A ). Thus, in this modification example, for example, the detection score is used to calculate the photometric value E(t) as shown in the following formula (7). Figure 8A )

[0061]

[0062] In formula (7), Score(t) represents the detection score value at time t. Figure 8B The dashed line in the figure shown in Figure 8B indicates an example of the photometric value E(t) calculated in the case of applying formula (7). Considering the detection score enables calculation of the photometric value E(t) without being affected by the average luminance value of frames in which false detections may have been made. As a result, from the comparison between Figure 8A and 8B , it can be clearly seen that, compared with the proposed method that does not consider the detection score, the proposed method that considers the detection score can capture the subject at a luminance closer to the target value for a longer time. In addition, the number n of previous frames used for weighted averaging can be changed according to the value of the detection score. For example, in cases where the value of the detection score has been continuously low for a predetermined period, the value of the number n of previous frames used for weighted averaging is increased to reduce the influence on the photometric value E(t). On the other hand, in cases where the value of the detection score has been continuously high, the value of the number n of previous frames is decreased to calculate the photometric value E(t) with high accuracy while suppressing the calculation amount. The parameter Score(t) used in formula (7) is not limited to the detection score and can be replaced by information related to detection accuracy (such as the amount of noise included in the video image, the Q value for determining the quality of the video image, and camera setting conditions, etc.). Figure 8A and 8B

[0063] With the above configuration, optimal exposure control is stably performed on the main subject that the user intends to capture.

[0064] Although the lens integrated imaging device formed by integrating the imaging optical system 201 and the surveillance camera 101 has been described as an example of the imaging device according to the above exemplary embodiment, the imaging device according to the exemplary embodiment is not limited thereto. For example, a lens interchangeable imaging device in which the surveillance camera 101 and the lens unit including the imaging optical system 201 are separately provided may be employed.

[0065] ​In addition, a computer program (software) for implementing the functions according to the above-described exemplary embodiments to partially or fully control the exemplary embodiments of the present invention can be supplied to the imaging device or the information processing device via a network or various storage media. Then, a computer (or a CPU, MPU, etc.) of the imaging device or the information processing device can read the program and execute the read program. In this case, the program and the storage medium storing the program constitute the exemplary embodiments of the present invention.

[0066] Other Embodiments

[0067] Embodiments of the present invention can also be implemented by the following method, that is, a software (program) that executes the functions of the above-described embodiments is provided to a system or a device via a network or various storage media, and a method in which a computer or a central processing unit (CPU) or a microprocessing unit (MPU) of the system or the device reads and executes the program.

[0068] Although the present invention has been described with reference to the exemplary embodiments, it should be understood that the present invention is not limited to the disclosed exemplary embodiments. The scope of the appended claims should be given the broadest interpretation to cover all such modifications and equivalent structures and functions.

Claims

1. An information processing device, comprising: An acquisition unit configured to acquire an image; A first detection unit configured to detect, from the image, a first region of a subject corresponding to a first feature; A second detection unit configured to detect, from the image, a second region of the subject corresponding to a second feature; A measurement unit configured to perform photometry on the first region and the second region; A determination unit configured to determine an exposure based on a weighted average of a first photometry value of the first region obtained by the measurement unit and a second photometry value of the second region obtained by the measurement unit before obtaining the first photometry value; And An output unit configured to output information related to the exposure.

2. The information processing device according to claim 1, wherein, The weight for the first photometry value is greater than the weight for the second photometry value.

3. The information processing device according to claim 1, wherein, The area of the first region is smaller than the area of the second region.

4. The information processing device according to claim 1, wherein, The determination unit calculates the weighted average of the first photometry value and the second photometry value based on a first score indicating the reliability degree of the detected first region and a second score indicating the reliability degree of the detected second region.

5. The information processing device according to claim 1, wherein, The first detection unit detects a face region as the first region.

6. The information processing device according to claim 1, wherein, The second detection unit detects a human body region as the second region.

7. An information processing method, comprising: Acquire an image; Detect, from the image, a first region of a subject corresponding to a first feature; Detect, from the image, a second region of the subject corresponding to a second feature; Perform photometry on the first region and the second region; Determine an exposure based on a weighted average of a first photometry value of the first region obtained in the photometry and a second photometry value of the second region obtained in the photometry before obtaining the first photometry value; And Output information related to the exposure.

8. The information processing method according to claim 7, wherein, The weight for the first photometry value is greater than the weight for the second photometry value.

9. The information processing method according to claim 7, wherein, The area of the first region is smaller than the area of the second region.

10. The information processing method according to claim 7, wherein, The determination calculates the weighted average of the first photometry value and the second photometry value based on a first score indicating the reliability degree of the first region and a second score indicating the reliability degree of the second region.

11. The information processing method according to claim 7, wherein, Detect a face region as the first region.

12. The information processing method according to claim 7, wherein, Detect a human body region as the second region.

13. A non-transitory computer-readable storage medium storing a program for causing a computer to execute the information processing method according to any one of claims 7 to 12.

14. A computer program product comprising a program for causing a computer to execute the information processing method according to any one of claims 7 to 12.

Images