Information processing device, imaging device, method, program, and storage medium

Abstract

To determine an appropriate parameter in accordance with an area of an image.SOLUTION: An information processing device includes image acquisition means for acquiring an image, first detection means for detecting a specific object from the image, second detection means for detecting a portion of the specific object from the image, exposure determination means for determining a first exposure amount to the specific object detected by the first detection means, and detecting a second exposure amount to the portion of the specific object detected by the second detection means, and parameter determination means for determining a parameter about at least one of the first detection means, the second detection means and the exposure detection means.SELECTED DRAWING: Figure 6

Description

[Technical field]

[0001] The present invention relates to an information processing device, an imaging device, a method, a program, and a storage medium. [Background technology]

[0002] 2. Description of the Related Art Conventionally, there has been known a technique for detecting a face area of ​​a subject from within a captured image, and adjusting pixel values ​​of the captured image based on information relating to the face area (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2005-86682 Summary of the Invention [Problem to be solved by the invention]

[0004] The problem to be solved by the present invention is to determine appropriate parameters depending on the region of an image. [Means for solving the problem]

[0005] The present invention solves the above problems by the following solving means.

[0006] The information processing device according to the present invention comprises: Captured by an imaging device image acquisition means for acquiring an image; a face detection means for detecting a face area from the image; and if the face area is not detected by the face detection means, From the image above human body area Detect human body A detection means; when the face area is detected by the face detection means, determining an exposure compensation amount for a current exposure value of the imaging device based on a difference between an average luminance value of the face area and a target luminance value of the average luminance value of the face area; The above human body By detection means When the human body region is detected, an exposure correction amount for a current exposure value of the imaging device is calculated based on a difference between an average luminance value of the human body region and a target luminance value of the average luminance value of the human body region. an exposure determination means for determining When the face region is detected, a correction parameter is determined for correcting a target luminance value of the face region based on a difference between an average luminance value of the face region and an average luminance value of a background region surrounding the face region, and when the human body region is detected, a correction parameter is determined for correcting a target luminance value of the human body region based on a difference between an average luminance value of the human body region and an average luminance value of a background region surrounding the human body region. Parameter determination means for determining the parameter determination means determines the correction parameter such that, when the face region is detected, an amount of correction by the correction parameter increases as a difference between an average luminance value of the face region and an average luminance value of the background region surrounding the face region increases, and determines the correction parameter such that, when the human body region is detected, an amount of correction by the correction parameter increases as a difference between an average luminance value of the human body region and an average luminance value of the background region surrounding the human body region increases. It is characterized by: [Brief description of the drawings]

[0007] [Figure 1]FIG. 1 is a block diagram showing a configuration of an imaging control system according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a block diagram showing the hardware configuration of the imaging apparatus according to the embodiment. [Diagram 3] FIG. 2 is a block diagram showing a hardware configuration of a client device according to the embodiment. [Figure 4] FIG. 2 is a block diagram showing the functional configuration of a client device proposed in the first embodiment. [Diagram 5] 5 is a flowchart of a process executed by a client device according to the first embodiment. [Figure 6] 5A and 5B are diagrams showing the relationship between a subject detection region and a background region. [Figure 7] FIG. 4 is a diagram showing the relationship of parameters relating to exposure. [Figure 8] FIG. 11 is a block diagram showing the functional configuration of a client device proposed in a second embodiment. [Figure 9] 11 is a flowchart of a process executed by a client device according to a second embodiment. [Figure 10] FIG. 11 is a diagram showing detection parameters of a detection means proposed in the second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0008] (First embodiment) Fig. 1 is a block diagram showing the configuration of an imaging control system according to this embodiment. The imaging system shown in Fig. 1 is composed of a surveillance camera 101 as a device for capturing and processing moving images, a client device 103, an input device 104, and a display device 105, which are connected in a mutually communicable state via an IP network 102.

[0009] FIG. 2 is a block diagram showing the internal configuration of the surveillance camera 101 in this embodiment. The imaging optical system 201 is composed of a zoom lens, a focus lens, a blur correction lens, an aperture, and a shutter, and collects optical information of a subject. The imaging element unit 202 is an element that converts optical information collected by the optical unit 201 into a current value, and acquires color information by combining with a color filter or the like. In addition, the imaging sensor is capable of setting an arbitrary exposure time for all pixels. The CPU 203 is involved in all processing of each component, sequentially reads and interprets instructions stored in a ROM (Read Only Memory) 204 and a RAM (Random Access Memory) 205, and executes processing according to the results. In addition, the control system control unit 206 controls the optical unit 201 according to instructions from the CPU 203, such as adjusting the focus, opening the shutter, and adjusting the aperture. The control unit 207 controls according to instructions from the client device 102. The A / D conversion unit 208 converts the amount of light of the subject detected by the optical unit 102 into a digital signal value. The image processing unit 209 performs image processing on the image data of the digital signal. An encoder unit 210 converts the image data processed by the image processing unit 209 into a file format such as Motion JPEG, H264, H265, etc. A network I / F 211 is an interface used for communication with an external device such as a client device 103 via the network 102.

[0010] The network 102 is a network that connects the surveillance camera 101 and the client device 103. The network is composed of a plurality of routers, switches, cables, etc. that satisfy a communication standard such as Ethernet (registered trademark). In this embodiment, the network 102 may be any network that can perform communication between the imaging device 101 and the client device 103, and the communication standard, scale, and configuration are not important. For example, the network 102 may be composed of the Internet, a wired LAN (Local Area Network), a wireless LAN (Wireless LAN), a WAN (Wide Area Network), etc.

[0011] 3 is a block diagram showing an example of the internal configuration of the client device 103 of this embodiment. The client device 103 includes a 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. Each element is connected to each other via a system bus so as to be able to communicate with each other.

[0012] The CPU 301 is a central processing unit that controls the operation of the client device 103. The main memory device 302 is a memory device such as a RAM that functions as a temporary storage location for data of the CPU 301. The auxiliary memory device 302 is a memory device such as a HDD, a ROM, or an SSD that stores various programs, various setting data, and the like. The input I / F 304 is an interface used when accepting input from the input device 104, etc. The output I / F 305 is an interface used to output information to the display device 105, etc. The network I / F 306 is an interface used for communication with external devices such as the imaging device 101 via the network 102.

[0013] The CPU 301 executes processes based on the programs stored in the auxiliary storage device 303, thereby implementing the functions and processes of the client device 103 shown in FIG.

[0014] The input device 104 is an input device configured with a mouse, a keyboard, and the like. The display device 105 is a display device such as a monitor that displays an image output by the client device 103. In this embodiment, the client device 103, the input device 104, and the display device 105 are each independent devices. However, 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. Also, the client device 103, the input device 104, and the display device 105 may be integrated.

[0015] 4 is a diagram showing an example of the functional configuration of the client device 103. The client device 103 includes an input information acquisition unit 401, a communication control unit 402, an input image acquisition unit 403, a subject detection unit 404, an image information calculation unit 405, a detection parameter determination unit 406, an exposure determination unit 407, and a display control unit 408.

[0016] The input information acquisition unit 401 accepts input from a user via the input device 104. The communication control unit 402 receives an image transmitted from the surveillance camera 101 via the network 102. The communication control unit 402 also transmits a control command to the imaging device 101 via the network 102. The input image acquisition unit 403 acquires an image captured by the imaging device 101 via the communication control unit 402 as an image to be subjected to subject detection processing. The subject detection unit 404 executes face detection and human body detection processing for detecting an area including a face (part of a specific object) and a human body (specific object) on the image acquired by the input image acquisition unit 403. Here, the subject detection unit 404 in this embodiment performs two types of detection processing, face detection and human body detection, but is not limited thereto. For example, a means for detecting the upper body or a part of a face such as the eyes, nose, and mouth can be adopted. The image information calculation unit 405 calculates the average brightness value of the subject (face, human body) region, the background around the subject, and the region including the subject's clothes based on the detection result obtained from the subject detection unit 404. The parameter determination unit 406 determines the target value of exposure related to each detection means based on the average brightness value of the subject region, the background around the subject, and the region including the subject's clothes obtained from the image information calculation unit 405. The exposure determination unit 407 determines the exposure level (exposure amount) based on the target value of exposure obtained from the parameter determination unit 406, transmits the above-mentioned exposure level (exposure amount) to the surveillance camera 101 from the communication control unit 402, and correction is performed via the control unit 207. A detailed process flow related to the subject detection unit 404, the image information calculation unit 405, the detection parameter determination unit 406, and the exposure determination unit 407 will be described later with reference to the flowchart of FIG. 5. The display control unit 408 outputs the captured image reflecting the exposure correction determined by the exposure determination unit 407 to the display device 105 according to an instruction from the CPU 301.

[0017] Hereinafter, the detection process, parameter determination process, and exposure determination process of the subject according to this embodiment will be described with reference to the flowchart shown in FIG. 5. FIG. 5 is a flowchart for illustratively explaining the detection process and exposure determination process according to the first embodiment of the present invention. Note that in the imaging system shown in FIG. 1, it is assumed that the power of each device is turned on and a connection (communication) between the surveillance camera 101 and the client device 103 is established. In this state, it is assumed that the imaging system repeats imaging of the subject, transmission of image data, and image display on the display device at a predetermined update period. It is assumed that the flowchart shown in FIG. 5 is started in response to input of an image obtained by imaging the subject by the client CPU 301 of the client device 103 from the surveillance camera 101 via the network 102.

[0018] First, in step S501, the subject detection unit 404 performs face detection processing on the input image. As a method for face detection, a pattern (classifier) ​​created using statistical learning may be used as a pattern matching method, or a method other than pattern matching may be used to perform subject detection using a brightness gradient in a local region. In other words, the detection method is not limited to this, and various methods such as detection based on machine learning and detection based on distance information may be adopted.

[0019] In step S502, it is determined whether a face area is detected in the image in the face detection process executed in step S501. If no face area is detected, the process proceeds to step S506, and if at least one face area is detected, the process proceeds to step S503.

[0020] In step S503, the image information calculation unit 405 calculates the average luminance value of the face region and the average luminance value of the background region around the face region based on the face detection result obtained from the subject detection unit 404. Specifically, the image information calculation unit 405 applies information on the number of faces detected, the detection positions, and the detection size to the following formula (1) to calculate the average luminance value Iface of the face region.

[0021]

number

[0022] Here, I(x, y) represents the luminance value of the two-dimensional coordinate position (x, y) in the horizontal direction (x-axis direction) and the vertical direction (y-axis direction) in the image. Also, f represents the number of detected faces, (v, h) represents the center coordinates where the face is detected, and k and l represent the detection size of the subject in the horizontal direction and the vertical direction, respectively. The average luminance value Iback of the background region can be calculated by applying a process similar to that of formula (1) to a wider area centered on the center coordinates of the face detection, as shown by the dotted line area in FIG. 6, excluding the area corresponding to the face. In this embodiment, the average luminance of the background region is calculated based on the center coordinates of the face detection, but this is not limited to this. For example, a method of identifying the background region in the image using a histogram of the entire image or feature extraction processing using machine learning and calculating the average luminance of the corresponding area may be used.

[0023] Next, in step S504, the parameter determination unit 406 determines a target value of exposure for the face region based on the average luminance value obtained from the image information calculation unit 405. For example, when the luminance value of the background region is large compared to the average luminance value of the face region, as shown in FIG. 6, it is highly likely that the scene is a backlit scene occurring at the entrance or exit of a building or a stadium. In the case of a backlit scene as shown in FIG. 6, pixels with a large luminance value that should be determined as background are mistakenly included in the face detection region detected by the subject detection unit 404 as a face (shaded area in FIG. 6). Therefore, it is considered that the average luminance value of the face region calculated by the image information calculation unit 405 is calculated to be higher than expected due to the influence of the mistakenly included pixels of the background region. Therefore, in order to eliminate the influence of the background luminance included in the face detection region, the parameter determination unit 406 in this embodiment applies information on the average luminance values ​​of the face detection region and the background region to the following formulas (2), (3), and (4). As a result, the target luminance value I'Face Target of the face region is determined.

[0024]

number

[0025]

number

[0026]

number

[0027] Here, I Face Target indicates a target luminance value of a reference face region, and may be a value preset by a user or a unique value preset on hardware. The parameter αFace is a coefficient that influences the degree of correction according to the difference in the average luminance value between the face region and the background region, centered on the target luminance value of the reference face region. Furthermore, formula (3) is a calculation formula for the parameter α, and formula (4) indicates the difference in average luminance between the background region and the face region. THFaceMax and THFaceMin included in formula (3) adjust the extent to which the difference between the average luminance value of the face region and the average luminance value of the background region is allowed. Furthermore, αFaceMax and αFaceMin are parameters that adjust the extent to which the target luminance value of the reference face region is corrected. FIG. 7 is a graph showing the relationship between the parameters included in formula (3). As shown in FIG. 7, in an area where the luminance difference between the face region and the background region is small (within the threshold value THFace), the influence of the background region erroneously included when calculating the average luminance value of the face region is considered to be minor, and the correction parameter α is set to 0 (no correction is applied). On the other hand, in areas with large luminance differences, taking into consideration that the influence of the background area on the average luminance value of the face area, the correction amount α is set large and added to the reference target value IFace Target. By carrying out the above processing, it becomes possible to set an appropriate target value for the face area even in a scene where the face is crushed in black in a backlit environment or where the surroundings are dark but the face is blown out.

[0028] Next, in step S505, the exposure determination unit 407 calculates the difference value between the average luminance value Iface of the face area obtained from the image information calculation unit 405 and the target luminance value I'Face Target of the face area obtained from the parameter determination unit 406, as shown in equation (4).

[0029]

number

[0030] Next, the exposure correction amount EVcorrection is determined based on the calculated difference value ΔDiff, a predetermined threshold Th, and an exposure value EVcurrent related to the current exposure. For example, the correction amount EVcorrection is determined as shown in equation (5). Note that EVcurrent is an EV value converted into APEX based on the subject luminance value (BV value), and is set based on a program diagram related to exposure control that is stored in advance in the client device 103.

[0031]

number

[0032] Here, the parameter β is a coefficient that affects the degree (speed) of correction when correcting the exposure to the underexposure side or overexposure side with the current exposure value EVcurrent as the center. By setting the value of the parameter β to a large value, the processing speed (or time) related to reaching the target value becomes high, but when an erroneous determination occurs in the detection result or when the detection of the subject is unstable, the brightness of the entire screen changes sharply. On the other hand, when the value of the parameter β is set to a small value, the processing speed (or time) related to reaching the target exposure becomes slow, but it becomes robust against erroneous detection and shooting conditions. This parameter β is set as a correction value of the exposure for the current exposure value EVcurrent when the difference ΔDiff calculated in step S507 is equal to or greater than the set threshold value Th. The above is the process when at least one or more face areas are detected in this embodiment.

[0033] Next, a process according to this embodiment when a face area is not detected will be described. If a face area is not detected in the process of step S502, then in step S506, subject detection unit 404 performs a human body detection process on the input image.

[0034] In step S507, it is determined whether or not a human body region has been detected in the image based on the result of the human body detection executed in step S506. If at least one human body region has been detected, the process proceeds to step S508, and if no human body region has been detected, the process proceeds to step S511. If the process proceeds to step S511 (i.e., if no face region or human body region is detected), no exposure correction based on the subject detection result is performed, as described in steps 511 to S512.

[0035] The processing in steps S508 to S510 is executed based on substantially the same arithmetic expressions as those in steps S503 to S505 described above, except that the average luminance value of the human body region is calculated and exposure is determined, and therefore detailed description thereof will be omitted. When determining the target value of exposure for the human body region in step S509, as shown in Figs. 6(a) and 6(b), the ratio of the background region included in the human body region is large compared to the ratio of the background region included in the face detection region. Therefore, it is necessary to set the correction amount to a large value with respect to the reference target value. Therefore, it is desirable to set the parameter αbody corresponding to human body detection, which is applied to equation (2) in step S509, to a large value compared to the parameter αface corresponding to face detection.

[0036] The parameters included in the formulas (2) and (3) used in determining the target exposure values ​​corresponding to the respective detection means described in the present embodiment may be preset values, or may be configured to be set to values ​​manually selected by the user via the input device 104.

[0037] As described above, the imaging system of this embodiment can determine the target exposure value based on the average brightness value of the subject area and the background area, taking into consideration the proportion of erroneous detection areas that occur depending on the means of subject detection. Therefore, with the imaging system of this embodiment, the amount of exposure correction can be determined depending on the detection accuracy of the multiple detection means and the shooting environment, and it is possible to set the brightness of the subject's face and human body according to the user's intention.

[0038] Second Embodiment In this embodiment, a configuration is described in which parameters related to exposure and detection of the first detection means and the second detection means are set based on shooting information related to an input image, and exposure is determined based on the detection result of the subject using the parameters. Note that the configurations of the surveillance camera 101, network 102, client device 103, input device 104, and display device 105 that constitute the imaging system according to this embodiment are the same as those of the first embodiment, so their explanations are omitted.

[0039] 8 is a diagram showing an example of the functional configuration of the client device 103 according to this embodiment. The client device 103 includes an input information acquisition unit 801, a communication control unit 802, an input image acquisition unit 803, a subject detection unit 804, a shooting information acquisition unit 805, a detection parameter determination unit 806, an exposure determination unit 807, and a display control unit 808.

[0040] Hereinafter, the parameter determination process, subject detection process, and exposure determination process according to this embodiment will be described with reference to the flowchart shown in Fig. 9. Note that the start timing of the processes is the same as in the first embodiment, so a description thereof will be omitted.

[0041] First, in step S901, the shooting information acquisition unit 805 acquires shooting information of an input image. For example, as the shooting information, the exposure setting value of the surveillance camera 101 is acquired. In this embodiment, a configuration capable of acquiring three items of camera information of the surveillance camera 101, namely, shutter speed, aperture, and gain, will be described, but the present invention is not limited thereto.

[0042] In addition, the detection parameters related to the detection by the face detection means and human body detection means in this embodiment refer to the maximum and minimum detection sizes, maximum detection numbers, etc. of face detection and human body detection, as shown in Fig. 10(a). Here, Fig. 10(a) shows the reference default parameter values ​​for each detection parameter. Note that the reference parameter setting values ​​may be preset values, or may be configured to set values ​​manually selected by the user via the input device 104.

[0043] Returning to FIG. 9, in step S902, the parameter determination unit 806 determines detection parameters related to the detection of the face detection means and the human body detection means based on the exposure setting value obtained from the shooting information acquisition unit 805. For example, when the shutter speed is slow, as shown in FIG. 10(b), it is highly likely that the face of a moving subject existing in the screen will be photographed with fine structures such as the eyes, nose, and mouth blurred, making it difficult to detect the face. Therefore, the parameter determination unit 806 in this embodiment determines parameters so that when the shutter speed is slow, human body detection processing is executed with higher priority than face detection. Specifically, for face detection, the maximum detection size is set smaller than the default setting (50→10), the minimum detection size value is set larger (4→8), and the maximum detection number is set smaller (50→5). On the other hand, for human body detection, the maximum detection size value is set larger than the default setting (50→80), the minimum detection size value is set smaller (4→2), and the maximum detection number is set larger (50→80). For other exposure settings, for example, when the aperture value is large, the depth of field is deep and the range in which the facial structure is in focus is wide. Therefore, in such a case, a parameter value that places a higher weight on face detection processing is set compared to the default value. Also, when the gain value is large, the random noise generated in the screen increases, and the fine structure of the subject becomes obscured by the noise. Therefore, in such a case, a parameter value that places a lower weight on face detection processing and a higher weight on human body detection processing is set compared to the default value.

[0044] Next, in step S 903 , the subject detection unit 804 executes face detection processing based on the detection parameters for face detection determined by the parameter determination unit 806 .

[0045] In step S904, it is determined whether or not a face has been detected in the image based on the result of the face detection executed in step S903. If at least one face area has been detected, the process proceeds to step S905, and if no face area has been detected, the process proceeds to step S907.

[0046] The processes in steps S905 and S906 are 、 Detailed description will be omitted since the processing is executed based on substantially the same calculation formula as the processing in steps S503 and S505 in the above-described embodiment 1. The above is the processing in this embodiment when at least one face area is detected.

[0047] In step S 907 , the subject detection unit 804 executes a human body detection process based on the detection parameters of the human body detection means determined by the parameter determination unit 806 .

[0048] Next, in step S908, it is determined whether or not a human body region has been detected in the image based on the result of the human body detection executed in step S907. If at least one human body region has been detected, the process proceeds to step S909, and if no human body region has been detected, the process proceeds to step S912. If the process proceeds to step S912 (i.e., if no face region or human body region is detected), no exposure correction is performed based on the subject detection result. Note that the processes in steps S909 and S910 are 、 Since this is executed based on substantially the same calculation formula as in steps S508 and S510 described above, a detailed description thereof will be omitted.

[0049] As described above, in the imaging system according to this embodiment, parameters related to detection by the first detection means and the second detection means can be set based on the shooting information obtained from the shooting information acquisition unit 805. This makes it possible to perform subject detection with higher accuracy.

[0050] In this embodiment, the maximum and minimum detection sizes and the maximum number of detections of face detection and human body detection are used as parameters related to detection by the first detection means and the second detection means. However, the embodiment of the present invention is not limited to this. For example, a configuration using detection speed, detection accuracy, and execution frequency of detection processing (detection processing) may be used.

[0051] In the present embodiment, the parameter setting unit 806 sets the detection parameters for each detection unit based on the exposure setting value at the time of shooting as the predetermined shooting information. However, the embodiment of the present invention is not limited to this. For example, the detection parameters may be set based on information related to AF (AUTO FOCUS) processing related to focus adjustment, information related to white balance, imaging information such as distance information of the subject, and the number of controlled cameras.

[0052] Furthermore, in the above-described embodiment, the client device 103 automatically sets the parameters related to the above-described subject detection and exposure in response to acquiring an image input from the surveillance camera 101, but the present invention is not limited to this. For example, the parameters may be set in response to a manual operation input by a user. In addition, the subject detection process may be executed at a period longer than the exposure update period in the exposure control, or may be executed in response to a manual operation by a user, the start of imaging (recording), a zoom operation, panning, tilting, or the like, to a change in the angle of view.

[0053] In the above-described embodiment, the client device 103 is an information processing device such as a PC, and the imaging system is assumed to have the surveillance camera 101 and the client device 103 connected by wire or wirelessly, but the present invention is not limited to this. For example, the imaging device such as the surveillance camera 101 may itself function as an information processing device equivalent to the client device 103, and the imaging device may include the input device 104 and the display device 105. Also, the imaging device such as the surveillance camera 101 may perform some of the operations performed by the client device 103 described above.

[0054] In the above embodiment, a so-called lens-integrated imaging device in which the imaging optical system 201 is integrally formed with the surveillance camera 101 has been described as an example of an imaging device for implementing the present invention, but the present invention is not limited to this. For example, a so-called lens-interchangeable imaging device in which the surveillance camera 101 and a lens unit equipped with the imaging optical system 201 are separately provided may also be used as an imaging device for implementing the present invention.

[0055] In the above-described embodiment, a surveillance camera is assumed as an example of an imaging device for implementing the present invention, but the present invention is not limited thereto. For example, imaging devices other than surveillance cameras, such as portable devices and wearable terminals, such as digital cameras, digital video cameras, and smartphones, may be used. Furthermore, in the above-described embodiment, an electronic device such as a PC is assumed as an example of the client device 103, which is an information processing device for implementing the present invention, but the present invention is not limited thereto. For example, the client device 103 may be configured to use other electronic devices, such as a smartphone or a tablet terminal.

[0056] In the embodiment described above, the client CPU 301 of the client device 103 executes the functions illustrated in FIG. 4. However, the client device 103 may have each of these functions as a means separate from the client CPU 301.

[0057] (Other embodiments) The present invention can also be realized by a process in which a program for implementing one or more of the functions of the above-described embodiments is supplied to a system or device via a network or a storage medium, and one or more processors in a computer of the system or device read and execute the program. The present invention can also be realized by a circuit (e.g., ASIC) that implements one or more of the functions.

[0058] Although the embodiments of the present invention have been described above, the present invention is not limited to these embodiments, and various modifications and changes are possible within the scope of the gist of the present invention.

Claims

1. An image acquisition means for acquiring an image captured by an imaging device; a face detection means for detecting a face area from the image; a human body detection means for detecting a human body area from the image when the face detection means does not detect the face area; when the face area is detected by the face detection means, determining an exposure compensation amount for a current exposure value of the imaging device based on a difference between an average luminance value of the face area and a target luminance value of the average luminance value of the face area; an exposure determination means for determining, when the human body region is detected by the human body detection means, an exposure correction amount for a current exposure value of the imaging device based on a difference between an average luminance value of the human body region and a target luminance value of the average luminance value of the human body region; when the face region is detected, determining a correction parameter for correcting a target luminance value of the face region based on a difference between an average luminance value of the face region and an average luminance value of a background region surrounding the face region; a parameter determining means for determining, when the human body region is detected, a correction parameter for correcting a target luminance value of the human body region based on a difference between an average luminance value of the human body region and an average luminance value of a background region surrounding the human body region; The parameter determination means determining the correction parameter such that, when the face region is detected, an amount of correction by the correction parameter increases as a difference between an average luminance value of the face region and an average luminance value of the background region surrounding the face region increases; An information processing device characterized in that, when the human body region is detected, the correction parameter is determined so that the amount of correction by the correction parameter becomes larger when the difference between the average luminance value of the human body region and the average luminance value of the background region surrounding the human body region becomes larger.

2. An imaging apparatus comprising the information processing apparatus according to claim 1 .

3. An image acquisition step of acquiring an image captured by an imaging device; a face detection step of detecting a face region from the image; a human body detection step of detecting a human body area from the image when the face area is not detected by the face detection step; determining an exposure compensation amount for a current exposure value of the imaging device based on a difference between an average luminance value of the face area and a target luminance value of the average luminance value of the face area when the face area is detected by the face detection step; an exposure determination step of determining, when the human body region is detected by the human body detection step, an exposure correction amount for a current exposure value of the imaging device based on a difference between an average luminance value of the human body region and a target luminance value of the average luminance value of the human body region; when the face region is detected, determining a correction parameter for correcting a target luminance value of the face region based on a difference between an average luminance value of the face region and an average luminance value of a background region surrounding the face region; a parameter determining step of determining, when the human body region is detected, a correction parameter for correcting a target luminance value of the human body region based on a difference between an average luminance value of the human body region and an average luminance value of a background region surrounding the human body region; The parameter determination step includes: determining the correction parameter such that, when the face region is detected, an amount of correction by the correction parameter increases as a difference between an average luminance value of the face region and an average luminance value of the background region surrounding the face region increases; A method characterized by determining the correction parameters such that, when the human body region is detected, the amount of correction by the correction parameters increases as the difference between the average luminance value of the human body region and the average luminance value of the background region surrounding the human body region increases.

4. A program for causing a computer to execute a method, the method comprising: An image acquisition step of acquiring an image captured by an imaging device; a face detection step of detecting a face region from the image; a human body detection step of detecting a human body area from the image when the face area is not detected by the face detection step; determining an exposure compensation amount for a current exposure value of the imaging device based on a difference between an average luminance value of the face area and a target luminance value of the average luminance value of the face area when the face area is detected by the face detection step; an exposure determination step of determining, when the human body region is detected by the human body detection step, an exposure correction amount for a current exposure value of the imaging device based on a difference between an average luminance value of the human body region and a target luminance value of the average luminance value of the human body region; when the face region is detected, determining a correction parameter for correcting a target luminance value of the face region based on a difference between an average luminance value of the face region and an average luminance value of a background region surrounding the face region; a parameter determining step of determining, when the human body region is detected, a correction parameter for correcting a target luminance value of the human body region based on a difference between an average luminance value of the human body region and an average luminance value of a background region surrounding the human body region; The parameter determination step includes: determining the correction parameter such that, when the face region is detected, an amount of correction by the correction parameter increases as a difference between an average luminance value of the face region and an average luminance value of the background region surrounding the face region increases; A program characterized by determining the correction parameters so that, when the human body region is detected, the amount of correction by the correction parameters increases as the difference between the average luminance value of the human body region and the average luminance value of the background region surrounding the human body region increases.

5. A computer-readable storage medium storing the program according to claim 4.

Images