Focus control device, imaging device, focus control method, and storage medium
Through the processor detecting the repetitive areas of the focus object area and the object area in the imaging device, and using the machine learning model for focus control, the problem of insufficient focus control accuracy and speed in the prior art is solved, and fast and high-precision focusing is achieved Effect.
Patent Information
- Application Number
- CN202410573623.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2023-05-12
- Filing Date
- 2024-05-10
- Publication Date
- 2024-11-12
AI Technical Summary
In the prior art, it is difficult to achieve fast and high-precision focusing control of the focus object in focus control, especially in complex environments, the focus control effect of a specific object is not good.
Acquire image signals through the processor, set the focus object area according to user operations, detect the repetitive areas in the area and perform focus control, use machine learning models to detect the object area, and adjust the threshold and search area size according to specific object types to improve focus Accuracy.
It realizes fast and high-precision focusing control of user-specified focus objects, which is suitable for focusing specific objects in complex environments, and improves the stability and efficiency of focus control.
Smart Images

Figure CN118945466A_ABST
Abstract
Description
Technical Field
[0001] The technology of the present invention relates to a focus control device, a camera device, a focus control method and a storage medium. Background Art
[0002] Patent document 1 discloses a control method for an imaging device, which has a signal generating mechanism for obtaining an image signal from an imaging element that captures images via an imaging optical system, and is characterized in that it has: an arbitrary area setting process, which is capable of setting an arbitrary area within the image signal; a focus detection process, which detects a defocus amount from a region obtained by dividing the image signal including the arbitrary area outside the arbitrary area into a plurality of calculation areas; a subject area specifying process, which determines a subject area where a subject is located based on the image signal; and a focus area selection process, which selects a focus area from the arbitrary area and the subject area.
[0003] Patent document 2 discloses an imaging device comprising: an imaging mechanism having imaging pixels arranged in a first area of an imaging area and performing photoelectric conversion on light from a photographic lens to generate an image of a subject, and focus detection pixels arranged in a second area narrower than the first area of the imaging area and receiving light passing through a portion of an exit pupil of the photographic lens; a phase difference detection mechanism for detecting a phase difference between two image signals based on a signal from the focus detection pixels; a subject detection mechanism for detecting a first subject area of a subject based on a signal from the imaging mechanism; and a control mechanism for performing focusing control using a signal from the phase difference detection mechanism in a second subject area that is different from the first subject area detected by the subject detection mechanism and is estimated to be a portion of the subject.
[0004] In Patent Document 3, there are a plurality of AF areas, the defocus amount is detected in each AF area, and in each area of the main range and the outer range, the defocus amount is converted into a lens position corresponding to the distance to create a depth map. If a depth map is created, the nearest area that is larger than the average in the main range by a predetermined value or more is extracted as a crossing candidate. A focus adjustment device is disclosed, which determines an area corresponding to an unwanted object based on the candidate, and controls the focus adjustment based on the distance value corresponding to the area excluding the area corresponding to the unwanted object from the main object area.
[0005] Patent document 4 discloses an imaging device that displays all focus detection areas including the specific subject as being in focus if there is an area including a specific subject in the focus detection area at the determined focus distance within the depth of field.
[0006] Patent Document 1: Japanese Patent Application Publication No. 2022-170554
[0007] Patent Document 2: Japanese Patent Application Publication No. 2013-054256
[0008] Patent Document 3: Japanese Patent Application Publication No. 2022-137760
[0009] Patent Document 4: Japanese Patent Application Publication No. 2013-242407 Summary of the invention
[0010] The technical object of the present invention is to provide a focus control device, an imaging device, a focus control method, and a storage medium that can quickly and accurately perform focus control on an object that a user wants to focus on.
[0011] In order to achieve the above-mentioned purpose, the focus control device of the present invention includes a processor and a memory, the processor obtains an image signal output from a camera element, sets a focus object area within a camera area according to output information from an operating device that receives user operations, and determines a search area according to the focus object area, detects an object area containing a specific object from within the search area, detects an overlapping area where the focus object area overlaps with the object area, and performs focus control according to the image signal within the overlapping area.
[0012] Preferably, the focus target area is composed of a plurality of blocks, and the processor detects one or more blocks overlapping with the object area among the plurality of blocks as the overlapping area.
[0013] Preferably, the processor detects one or more blocks whose overlap ratio with the object region is greater than or equal to a threshold value among the plurality of blocks as the overlap region.
[0014] Preferably, the processor changes the threshold value according to the type of the specific object.
[0015] The processor may also detect, as the overlapping region, a region where the overlapping ratio between the focus target region and the object region is greater than a threshold value.
[0016] Preferably, the processor performs focus control based on the image signal of the focus target area when the repetition rate is less than a threshold value.
[0017] Preferably, the processor determines the search area based on a longer side of the focus object area.
[0018] The focus target area is preferably rectangular.
[0019] Preferably, when the focus target area is not composed of a plurality of blocks, the processor divides the focus target area into blocks of a number corresponding to the type of the specific object.
[0020] Preferably, the processor acquires the defocus amount for non-focus control based on an image signal in an area outside the overlapping area and within the search area.
[0021] Preferably, the processor displays the overlapping region emphatically on the display device by changing a color, a shape, or a line type of a frame of the overlapping region.
[0022] The preferred processor detects the object area by inputting the image signal within the search area into the machine learning completion model.
[0023] Preferably, the processor sets the size of the search area to the predetermined size when the search area determined based on the focus target area is smaller than a predetermined size.
[0024] Preferably, when the detected object region is a specific part, the processor changes the size of the search region according to the type or size of the part.
[0025] An imaging device according to the present invention includes the above-mentioned focus control device, an imaging element, and an operating device.
[0026] The focus control method of the present invention includes the following steps: acquiring an image signal output from a camera element, setting a focus object area within a camera area based on output information from an operating device that receives user operations, and determining a search area based on the focus object area, detecting an object area containing a specific object from within the search area, detecting an overlapping area where the focus object area overlaps with the object area, and performing focus control based on the image signal within the overlapping area.
[0027] The program of the present invention causes a processor to execute processing including the following steps: acquiring an image signal output from an imaging element, setting a focus object area within an imaging area based on output information from an operating device that receives user operations, determining a search area based on the focus object area, detecting an object area containing a specific object from within the search area, detecting an overlapping area where the focus object area overlaps with the object area, and performing focus control based on the image signal within the overlapping area. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] Figure 1 This is a diagram showing an example of the internal structure of the imaging device.
[0029] Figure 2 This is a diagram showing an example of the structure of an imaging pixel.
[0030] Figure 3 It is a diagram showing an example of the structure of a phase difference detection pixel.
[0031] Figure 4 This is a diagram showing an example of a pixel arrangement of an imaging sensor.
[0032] Figure 5 This is a block diagram showing an example of the functional structure of a processor.
[0033] Figure 6 It is a diagram showing an example of the AF area.
[0034] Figure 7 This is a diagram showing an example of a search area.
[0035] Figure 8 This is a flowchart showing an example of object region detection processing.
[0036] Fig. 9 This is a diagram showing an example of an overlapping region.
[0037] Fig.10 This is a flowchart showing an example of overlapping region detection processing.
[0038] Fig.11 A diagram showing an example of an image displayed on a monitor.
[0039] Fig.12 : is a flowchart showing an example of the focus position detection process.
[0040] Fig.13 This is a flowchart showing the flow of the overall processing executed by the imaging device.
[0041] Fig.14 It is a diagram showing an example of a peripheral area where the defocus amount for non-focus control is obtained.
[0042] Fig.15 This is a diagram showing a process of limiting the size of the search area to a minimum size.
[0043] Fig.16 This is a diagram showing a process of expanding a search area.
[0044] Fig.17 This is a flowchart showing an example of optimization processing of the search area.
[0045] Fig.18 This is a diagram showing an example of an object region when the object is an airplane.
[0046] Fig.19 It is a diagram illustrating the repetition rate of a plurality of object regions.
[0047] Fig. 20 This is a diagram that defines the coordinates of the object area and the AF area.
[0048] Fig.21 This is a flowchart showing an example of processing for determining the positional relationship between the object area and the AF area. DETAILED DESCRIPTION
[0049] An example of an embodiment according to the technology of the present invention will be described with reference to the drawings.
[0050] First, the terms used in the following description are explained.
[0051] In the following description, "IC" is the abbreviation of "Integrated Circuit". "CPU" is the abbreviation of "Central Processing Unit". "ROM" is the abbreviation of "Read Only Memory". "RAM" is the abbreviation of "Random Access Memory". "CMOS" is the abbreviation of "Complementary Metal Oxide Semiconductor".
[0052] “FPGA” is the abbreviation of “Field Programmable Gate Array”. “PLD” is the abbreviation of “Programmable Logic Device”. “ASIC” is the abbreviation of “Application Specific Integrated Circuit”. “OVF” is the abbreviation of “Optical View Finder”. “EVF” is the abbreviation of “Electronic View Finder”. “CNN” is the abbreviation of “Convolutional Neural Network”. “AF” is the abbreviation of “Auto Focus”. “R-CNN” is the abbreviation of “Regions with Convolutional Neural Networks”.
[0053] As one embodiment of the imaging device, a lens-interchangeable digital camera is taken as an example to explain the technology of the present invention. In addition, the technology of the present invention is not limited to the lens-interchangeable type, and can also be applied to a lens-integrated digital camera.
[0054] Figure 1 An example of the structure of the imaging device 10 is shown. The imaging device 10 is a lens-interchangeable digital camera. The imaging device 10 is composed of a main body 11 and an imaging lens 12 that is replaceably mounted on the main body 11. The imaging lens 12 is mounted on the front surface side of the main body 11 via a camera-side mount 11A and a lens-side mount 12A.
[0055] The main body 11 is provided with an operating device 13 including a dial, a release button, a touch panel, etc., and receiving user operations. The operation modes of the imaging device 10 include, for example, a still image capturing mode, a moving image capturing mode, and an image display mode. The operating device 13 is operated by the user when setting the operation mode. Furthermore, the operating device 13 is operated by the user when starting still image capturing or moving image capturing. Furthermore, the operating device 13 is operated by the user when specifying an AF area as a focus object from within the imaging area. In addition, the AF area is an example of a "focus object area" involved in the technology of the present invention.
[0056] In addition, a viewfinder 14 is provided on the main body 11. Here, the viewfinder 14 is a hybrid viewfinder (registered trademark). The so-called hybrid viewfinder refers to a viewfinder that selectively uses an optical viewfinder (hereinafter referred to as "OVF") and an electronic viewfinder (hereinafter referred to as "EVF"), for example. The user can observe an optical image or a live view image of the subject projected by the viewfinder 14 through a viewfinder eyepiece portion (not shown).
[0057] Furthermore, a display 15 is provided on the back side of the main body 11. An image based on an image signal obtained by shooting and various menu screens are displayed on the display 15. The user can also observe a live view image projected by the display 15 instead of the viewfinder 14. In addition, the display 15 is an example of a "display device" involved in the technology of the present invention.
[0058] The body 11 and the imaging lens 12 are electrically connected by contact between an electrical contact 11B provided on the camera-side mount 11A and an electrical contact 12B provided on the lens-side mount 12A.
[0059] The imaging lens 12 includes an objective lens 30, a focusing lens 31, a rear lens 32, and an aperture 33. The components are arranged in order from the objective lens side along the optical axis A of the imaging lens 12 to form the objective lens 30, the aperture 33, the focusing lens 31, and the rear lens 32. The objective lens 30, the focusing lens 31, and the rear lens 32 constitute an imaging optical system. The type, number, and arrangement order of the lenses constituting the imaging optical system are not limited to Figure 1 Example shown.
[0060] Furthermore, the imaging lens 12 includes a lens drive control unit 34. The lens drive control unit 34 is composed of, for example, a CPU, a RAM, and a ROM, etc. The lens drive control unit 34 is electrically connected to a processor 40 in the main body 11 via the electrical contacts 12B and the electrical contacts 11B.
[0061] The lens drive control unit 34 drives the focus lens 31 and the aperture 33 based on the control signal sent from the processor 40. In order to adjust the focus position of the imaging lens 12, the lens drive control unit 34 performs drive control of the focus lens 31 based on the control signal for focus control sent from the processor 40. The processor 40 performs focus position detection by a phase difference method. The focus position is represented by the defocus amount.
[0062] The diaphragm 33 has an opening with a variable opening diameter centered on the optical axis A. To adjust the amount of incident light on the light receiving surface 20A of the imaging sensor 20 , the lens drive control unit 34 controls the drive of the diaphragm 33 based on a diaphragm adjustment control signal sent from the processor 40 .
[0063] Furthermore, the main body 11 includes an imaging sensor 20, a processor 40, and a memory 42. The processor 40 controls the operations of the imaging sensor 20, the memory 42, the operating device 13, the viewfinder 14, and the display 15.
[0064] The processor 40 is composed of, for example, a CPU. In this case, the processor 40 performs various processes based on a program 43 stored in the memory 42. In addition, the processor 40 may be composed of a collection of multiple IC chips. In addition, a machine learning model LM that has been machine trained for object area detection is stored in the memory 42. The processor 40 and the memory 42 constitute a focus control device.
[0065] The imaging sensor 20 is, for example, a CMOS image sensor. In the imaging sensor 20, the optical axis A is orthogonal to the light receiving surface 20A, and the optical axis A is arranged to be located at the center of the light receiving surface 20A. Light passing through the imaging lens 12 is incident on the light receiving surface 20A. A plurality of pixels that generate signals by photoelectric conversion are formed on the light receiving surface 20A. The imaging sensor 20 generates an image signal D and outputs it by photoelectrically converting the light incident on each pixel. In addition, the imaging sensor 20 is an example of an "imaging element" involved in the technology of the present invention.
[0066] Furthermore, a color filter array of a Bayer arrangement is arranged on the light receiving surface of the image sensor 20, and any one of the color filters of R (red), G (green), and B (blue) is arranged opposite to each pixel. In addition, some of the plurality of pixels arranged on the light receiving surface of the image sensor 20 may be phase difference detection pixels for detecting a phase difference involved in focus control.
[0067] Figure 2 An example of the structure of the imaging pixel N is shown. Figure 3An example of the structure of phase difference detection pixels P1 and P2 is shown. Phase difference detection pixels P1 and P2 respectively receive one side of the light beam split in the X direction with the main light as the center. Hereinafter, the direction orthogonal to the X direction is referred to as the Y direction. In addition, the X direction corresponds to the horizontal direction, and the Y direction corresponds to the vertical direction.
[0068] like Figure 2 As shown in FIG. 1 , the imaging pixel N includes a photodiode PD as a photoelectric conversion element, a color filter CF, and a microlens ML. The color filter CF is arranged between the photodiode PD and the microlens ML.
[0069] The color filter CF is a filter that transmits light of any one color of R, G, and B. The microlens ML converges the light beam LF incident from the exit pupil EP of the imaging lens 12 at substantially the center of the photodiode PD via the color filter CF.
[0070] like Figure 3 As shown, the phase difference detection pixels P1 and P2 each include a photodiode PD, a light shielding layer SF, and a microlens ML. The microlens ML converges the light beam LF incident from the exit pupil EP of the imaging lens 12 substantially at the center of the photodiode PD, similarly to the imaging pixel N.
[0071] The light shielding layer SF is formed of a metal film or the like, and is disposed between the photodiode PD and the microlens ML. The light shielding layer SF shields a portion of the light beam LF incident on the photodiode PD via the microlens ML.
[0072] In the phase difference detection pixel P1, the light shielding layer SF shields the negative side in the X direction with the center of the photodiode PD as a reference. That is, in the phase difference detection pixel P1, the light shielding layer SF allows the light beam LF from the negative side of the exit pupil EP1 to be incident on the photodiode PD, and shields the light beam LF from the positive side of the exit pupil EP2 in the X direction.
[0073] In the phase difference detection pixel P2, the light shielding layer SF shields the positive side in the X direction with the center of the photodiode PD as a reference. That is, in the phase difference detection pixel P2, the light shielding layer SF allows the light beam LF from the positive side of the exit pupil EP2 to be incident on the photodiode PD, and shields the light beam LF from the negative side of the exit pupil EP1 in the X direction.
[0074] That is, the phase difference detection pixel P1 and the phase difference detection pixel P2 have different light shielding positions in the X direction. The phase difference detection direction by the phase difference detection pixels P1 and P2 is the X direction (ie, the horizontal direction).
[0075] Figure 4An example of a pixel arrangement of the imaging sensor 20 is shown. Figure 4 "R" in _ represents an imaging pixel N provided with a color filter CF of R. "G" represents an imaging pixel N provided with a color filter CF of G. "B" represents an imaging pixel N provided with a color filter CF of B. In addition, the color arrangement of the color filter CF is not limited to the Bayer arrangement, and other color arrangements may be used.
[0076] The row RL including the phase difference detection pixels P1 and P2 is arranged every 10 pixels in the Y direction. In each row RL, a pair of phase difference detection pixels P1 and P2 and one imaging pixel N are repeatedly arranged in the Y direction. In addition, the arrangement pattern of the phase difference detection pixels P1 and P2 is not limited to Figure 4 For example, it may be the example shown in Japanese Patent Application Laid-Open No. 2018-56703. Figure 5 As shown, a pattern is formed in which a plurality of phase difference detection pixels are arranged in one microlens ML.
[0077] Figure 5 FIG. 4 shows an example of the functional structure of the processor 40. The processor 40 executes processing by the program 43 stored in the memory 42, thereby realizing various functional units. Figure 5 As shown, for example, the processor 40 implements a main control unit 50, a camera control unit 51, an image processing unit 52, a display control unit 53, an AF area setting unit 54, a search area determination unit 55, an object area detection unit 56, an overlap area detection unit 57 and a focus position detection unit 58.
[0078] The main control unit 50 controls the overall operation of the imaging device 10 based on output information from the operating device 13. The imaging control unit 51 controls the imaging sensor 20 to execute imaging processing for causing the imaging sensor 20 to perform an imaging operation. The imaging control unit 51 drives the imaging sensor 20 in a still image capturing mode or a moving image capturing mode.
[0079] The imaging sensor 20 outputs an image signal D including an imaging signal SN generated by the imaging pixel N and a phase difference detection signal SP generated by the phase difference detection pixels P1 and P2. The imaging sensor 20 outputs the image signal D to the image processing unit 52. The imaging sensor 20 also outputs the image signal D to the focus position detection unit 58.
[0080] The image processing unit 52 acquires the image signal D output from the imaging sensor 20 , and performs image processing such as demosaicing on the acquired image signal D.
[0081] The display control unit 53 causes the display 15 to display an image represented by the image signal D subjected to image processing by the image processing unit 52. Furthermore, the display control unit 53 causes the display 15 to display a live view image based on the image signal D periodically input from the image processing unit 52 during the still image shooting or the shooting preparation operation before the moving image shooting. Furthermore, the display control unit 53 causes the display 15 to display the AF area RA designated by the user, the overlapping area RD detected by the overlapping area detection unit 57, and the like using the operating device 13. For example, the operating device 13 is a touch panel provided on the display surface of the display 15, and the user can designate the AF area RA by touching the touch panel with a finger.
[0082] The AF area setting unit 54 sets a rectangular AF area RA in the imaging area based on the output information from the operating device 13. For example, the AF area RA is composed of a plurality of blocks. The user can specify the position, number, arrangement direction, etc. of the blocks by operating the operating device 13.
[0083] The search area determination unit 55 determines the search area RB for searching the specific object based on the AF area RA set by the AF area setting unit 54. The search area determination unit 55 determines the search area RB in the imaging area so as to include the AF area RA. For example, the search area determination unit 55 determines the search area RB based on the long side of the AF area RA. The search area RB is rectangular. In addition, the user can specify the type of the specific object to be detected (human face, bird, airplane, car, etc.) using the operating device 13.
[0084] The object region detection unit 56 detects the object region RC containing the specific object from the search region RB determined by the search region determination unit 55. Specifically, the object region detection unit 56 cuts out a portion corresponding to the search region RB from the image represented by the image signal D, and inputs the cut-out image into the machine learning completion model LM, thereby detecting the object region RC. In other words, the object region detection unit 56 detects the object region RC by inputting the image signal D in the search region RB into the machine learning completion model LM. In addition, the object region detection unit 56 may input only the camera signal SN contained in the image signal D in the search region RB into the machine learning completion model LM.
[0085] The overlapping region detecting unit 57 detects an overlapping region RD where the AF region RA overlaps the object region RC. Specifically, the overlapping region detecting unit 57 calculates the overlap ratio with the object region RC for each of the plurality of blocks constituting the AF region RA, and detects one or more blocks having an overlap ratio greater than a threshold value as the overlapping region RD.
[0086] The focus position detection unit 58 obtains the defocus amount for focus control based on the image signal D in the overlapping area RD detected by the overlapping area detection unit 57. Specifically, the focus position detection unit 58 obtains the defocus amount for focus control based on the phase difference detection signal SP included in the image signal D in the overlapping area RD. More specifically, the focus position detection unit 58 calculates the defocus amount by performing a correlation operation based on the phase difference detection signal SP output from the plurality of phase difference detection pixels P1 and the phase difference detection signal SP output from the plurality of phase difference detection pixels P2.
[0087] The main control section 50 drives the focus lens 31 via the lens drive control section 34 based on the defocus amount for focus control acquired by the focus position detection section 58. As a result, the object detected by the object region detection section 56 is in focus.
[0088] Figure 6 An example of the AF area RA is shown. Figure 6 In the example shown, an obstacle OB appears in the image represented by the image signal D, and the user specifies the AF area RA by operating the operating device 13 so as to avoid the obstacle OB. Figure 6 In the example shown, the obstacle OB is a fence extending in the Y direction, and the user specifies the AF area RA having a shape extending in the Y direction.
[0089] And, in Figure 6 In the example shown, the AF area RA is composed of a plurality of rectangular blocks B1 to B5. Each of the plurality of blocks B1 to B5 has the same shape and the same size. Since the number of phase difference detection pixels P1 and P2 included in the block changes, the reliability of the calculated defocus amount varies depending on the shape and size of the block. In this embodiment, since the shape and size of each block are made the same, the variation in the reliability of the defocus amount calculated based on each block can be reduced.
[0090] The user can specify the position of the AF area RA and the number of blocks in the X direction and the Y direction by operating the operating device 13. Thus, the user can set the AF area RA to an appropriate position, shape (for example, aspect ratio) and size so as to avoid the obstacle OB. The AF area setting unit 54 sets the AF area RA in the imaging area based on information such as the position and number of blocks of the AF area RA specified by the user.
[0091] Figure 7 An example of a search area RB is shown. Figure 7As shown in FIG. 5 , when a plurality of blocks B1 to B5 constituting the AF area RA are arranged in the Y direction and the AF area RA extends in the Y direction, the search area determination unit 55 determines the search area RB as a rectangular area whose two sides are connected to both ends of the AF area RA in the Y direction (i.e., the long side direction). That is, the search area determination unit 55 determines the search area RB based on the long side of the AF area RA.
[0092] exist Figure 7 In the example shown, the search region RB is determined to be in contact with the blocks B1 and B5 located at the ends of the AF region RA in the Y direction. The search region RB is a rectangular region having sides parallel to the X direction and sides parallel to the Y direction, and preferably the ratio of the number of pixels in the X direction to the number of pixels in the Y direction is 1:1 (i.e., the aspect ratio is 1:1). This is because the aspect ratio of the image input to the trained model LM is preferably 1:1.
[0093] Figure 8 An example of object region detection processing by the object region detection unit 56 is shown. The trained model LM is composed of a neural network having an input layer, an intermediate layer, and an output layer. The intermediate layer is composed of a plurality of neurons. The number of intermediate layers and the number of neurons in each intermediate layer can be changed appropriately. The trained model LM can be R-CNN.
[0094] The trained model LM is trained by using a plurality of images of a specific object as a teacher data image to detect an object region including the specific object from the image. The trained model LM can be trained by a computer external to the imaging device 10 .
[0095] The object region detection unit 56 inputs an image obtained by cutting out a portion corresponding to the search region RB from the image represented by the image signal D (hereinafter referred to as a cutout image) to the machine learning completed model LM. The machine learning completed model LM detects an object region RC including the specific object OJ from the cutout image, and outputs information indicating the object region RC on the cutout image. The object region detection unit 56 outputs the information indicating the object region RC output from the machine learning completed model LM to the overlapping region detection unit 57.
[0096] Fig. 9 An example of a repeating region RD is shown. Fig. 9 In the example shown, among the multiple blocks B1 to B5 constituting the AF area RA, blocks B2 to B4 overlap with the object area RC. Fig. 9 In the illustrated example, the overlapping region detecting unit 57 detects blocks B2 to B4 as the overlapping region RD.
[0097] Fig.10FIG. 5 shows an example of the overlapping region detection process by the overlapping region detection unit 57. In the overlapping region detection process, first, the overlapping region detection unit 57 selects one block from a plurality of blocks constituting the AF region RA (step S10). Next, the overlapping region detection unit 57 calculates the overlapping ratio between the selected block and the object region RC (step S11). Here, the overlapping ratio refers to the ratio of the object region RC to the overlapping block.
[0098] Next, the repetitive region detection unit 57 determines whether the calculated repetitive ratio is greater than or equal to a threshold value (step S12). When the repetitive ratio is greater than or equal to the threshold value (step S12: Yes), the repetitive region detection unit 57 selects the block as the repetitive region RD (step S13). On the other hand, when the repetitive ratio is less than the threshold value (step S12: No), the repetitive region detection unit 57 transfers the process to step S14.
[0099] In step S14, the overlap region detection unit 57 determines whether it is the final block. If it is not the final block (step S14: No), the overlap region detection unit 57 selects a block for which the overlap ratio has not been calculated from the plurality of blocks constituting the AF area RA (step S15).
[0100] After step S15, the overlapping region detecting unit 57 returns the process to step S11. The overlapping region detecting unit 57 repeats steps S11 to S15, and ends the overlapping region detection process when it is determined in step S14 that the block is the final block. The overlapping region RD includes one or more blocks selected in step S13.
[0101] Fig.11 1 shows an example of an image displayed on the display 15 by the display control unit 53. The main control unit 50 displays the AF area RA and the overlapping area RD in the image represented by the image signal D via the display control unit 53. The main control unit 50 emphasizes the overlapping area RD by changing the color, shape or line type of the frame of the overlapping area RD. Fig.11 In the example shown, the main control unit 50 emphasizes and displays the overlapping region RD by making the frame of the overlapping region RD a thick line and changing the colors of the AF region RA and the overlapping region RD. Alternatively, the overlapping region RD may be displayed without displaying the AF region RA.
[0102] Fig.12 1 shows an example of the focus position detection process by the focus position detection unit 58. In the focus position detection process, first, the focus position detection unit 58 selects one block included in the overlap region RD (step S20). The focus position detection unit 58 calculates the defocus amount of the selected block (step S21). In step S21, the focus position detection unit 58 calculates the defocus amount by performing a correlation operation based on the phase difference detection signal SP included in the image signal D in the block.
[0103] Next, the focus position detection unit 58 determines whether it is the final block (step S22). If it is not the final block (step S22: No), the focus position detection unit 58 selects a block included in the overlap region RD and for which the defocus amount has not yet been calculated (step S23). The focus position detection unit 58 returns the process to step S21 after step S23. The focus position detection unit 58 repeats steps S21 to S23, and in step S22, if it is determined that it is the final block, the process is transferred to step S24.
[0104] In step S24, the focus position detection unit 58 calculates an average value of the plurality of defocus amounts calculated in step S21. Then, the focus position detection unit 58 acquires the calculated average value as the defocus amount for focus control (step S25).
[0105] Fig.13 1 shows the flow of the overall processing executed by the imaging device 10 . Fig.13 An example is shown in which a live view image is displayed during the image capture preparation operation in the still image capture mode.
[0106] First, the main control unit 50 determines whether there is an imaging preparation start command issued by the user operating the operating device 13 (step S30). If there is an imaging preparation start command (step S30: Yes), the main control unit 50 controls the imaging control unit 51 to cause the imaging sensor 20 to perform an imaging operation (step S31).
[0107] The image processing unit 52 acquires the image signal D output from the imaging sensor 20 and performs image processing on the image signal D (step S32 ). The display control unit 53 causes the display 15 to display an image represented by the image signal D subjected to the image processing (step S33 ).
[0108] Next, the main control unit 50 determines whether the user has performed an operation to designate the AF area RA using the operating device 13 (hereinafter referred to as AF area designation operation) (step S34). If there has been no AF area designation operation (step S34: No), the main control unit 50 shifts the process to step S43.
[0109] If the AF area designation operation is performed (step S34: Yes), the AF area setting unit 54 sets the AF area RA in the imaging area based on the output information from the operating device 13 (step S35). The search area determination unit 55 determines the search area RB based on the set AF area RA (step S36).
[0110] Next, the object region detection unit 56 detects the object region RC by performing the above-described object region detection process (step S37 ). The main control unit 50 determines whether the object region RC is detected by the object region detection unit 56 (step S38 ).
[0111] When the object region RC is detected (step S38: Yes), the overlapping region detection unit 57 detects the overlapping region RD by performing the overlapping region detection process (step S39). Then, the focus position detection unit 58 acquires the defocus amount for focus control by performing the focus position detection process (step S40).
[0112] When the object region RC is not detected (step S38: No), the focus position detection unit 58 acquires the defocus amount for focus control from the entire AF area RA (step S41). In addition, when the overlapping region RD is not detected in step S39, the focus position detection unit 58 may acquire the defocus amount for focus control from the entire AF area RA.
[0113] After step S40 or step S41 , the main control unit 50 drives the focus lens 31 according to the acquired defocus amount for focus control (step S42 ).
[0114] Next, the main control unit 50 determines whether there is a camera command issued by the user operating the operating device 13 (step S43). If there is no operation command (step S43: No), the main control unit 50 returns the process to step S31. In step S43, the processes of steps S31 to S43 are repeatedly executed until the main control unit 50 determines that there is a camera command.
[0115] If there is an image capture command (step S43 : Yes), the main control unit 50 causes the image sensor 20 to perform an image capture operation and performs a still image capture process of recording the image signal D image-processed by the image processing unit 52 as a still image in the memory 42 (step S21 ).
[0116] In the technology of the present invention, since the object area detection is performed from the search area RB determined according to the AF area RA specified by the user, the object area RC including the object that the user wants to focus on can be quickly detected. In addition, in the technology of the present invention, since the focus control is performed based on the image signal D in the overlapping area RD where the AF area RA and the object area RC overlap, the focus control can be performed on the object that the user wants to focus on with high precision. That is, according to the technology of the present invention, the focus control can be performed quickly and with high precision on the object that the user wants to focus on.
[0117] [Modifications]
[0118] Various modifications of the above-described embodiment will be described below.
[0119] In the above embodiment, the user can specify the position, number, arrangement direction, etc. of the blocks constituting the AF area RA using the operating device 13, but it is also possible to specify only the position, shape (for example, aspect ratio) and size of the AF area RA. In this way, when the AF area RA specified by the user is not composed of a plurality of blocks, the AF area setting unit 54 can divide the AF area RA specified by the user into a plurality of blocks. In this case, the AF area setting unit 54 preferably sets each block to the same shape and the same size.
[0120] Furthermore, in the case where the AF area RA specified by the user is not composed of a plurality of blocks, the AF area setting unit 54 may divide the AF area RA into a number of blocks corresponding to the type of the specific object to be detected. The depth information required for focus control varies depending on the type of the object. Therefore, in the case where the object is an object that requires more depth information, such as a bird, the number of block divisions is increased. On the other hand, in the case where the object is an object that does not require much depth information, such as a car, the number of block divisions is reduced. The fewer the number of block divisions, the faster the focus control can be performed, and the focus control can be performed with high precision on objects such as cars moving at high speed. In this way, the balance between the accuracy and speed of the focus control can be achieved by adjusting the number of block divisions.
[0121] Furthermore, when the AF area RA designated by the user is not composed of a plurality of blocks, the AF area setting unit 54 may set the AF area RA without dividing it into a plurality of blocks. In this case, the overlapping area detection unit 57 detects an area where the overlapping rate between the AF area RA and the object area RC is greater than a threshold value as the overlapping area RD, and the focus position detection unit 58 obtains the defocus amount for focus control based on the image signal D in the overlapping area RD. In addition, when the overlapping rate between the AF area RA and the object area RC is less than the threshold value, the focus position detection unit 58 may obtain the defocus amount for focus control based on the image signal D of the AF area RA.
[0122] In the above-mentioned embodiment, the focus position detection unit 58 obtains the average value of the defocus amount of each block included in the repeated area RD as the defocus amount for focus control. Alternatively, the focus position detection unit 58 can obtain a weighted average value of the defocus amount of each block by taking the repetition rate with the object area RC of each block as a weight as the defocus amount for focus control. For example, the greater the repetition rate, the greater the weight. Furthermore, the weighted average value of the defocus amount of each block by taking the type of the part of the object located in each block as a weight can be used as the defocus amount for focus control. For example, the more important the part is as the focus object, the greater the weight.
[0123] In the above embodiment, the focus position detection unit 58 obtains the defocus amount for focus control from the overlap region RD, but the defocus amount for non-focus control may be obtained based on the image signal D of the area outside the overlap region RD and within the search area RB (hereinafter referred to as the peripheral area). Fig.14 As shown, the focus position detection unit 58 divides the peripheral area RE into blocks and obtains the defocus amount for non-focus control as the defocus amount calculated from each block. Each block of the peripheral area RE is preferably the same shape and size as each block of the AF area RA. In addition, the defocus amount for non-focus control is a defocus amount for reference rather than focus control.
[0124] In this way, in addition to the defocus amount for focus control, by obtaining the defocus amount for non-focus control from the peripheral area RE, when a specific object invades the search area RB from outside the search area RB, the focus position can be predicted in a short time and focus control can be performed more quickly.
[0125] In the above embodiment, the search area determination unit 55 determines the search area RB based on the long side of the AF area RA. Fig.15 As shown in (A), when the set AF area RA is small, the search area RB becomes smaller. If the search area RB is too small, the object area RC may not be detected by the object area detection unit 56. Fig.15 As shown in (B), the search area determination unit 55 determines the search area RB based on the long side of the AF area RA, so that Fig.15 As shown in (A), when the search area RB determined based on the AF area RA is smaller than a predetermined size, it is preferable to set the size of the search area RB to the predetermined size. Fig.15 (B) shows the search area RB expanded to a predetermined size. For example, the predetermined size is the minimum image size that can be input to the trained model LM. For example, the predetermined size is an image size of 320 pixels × 320 pixels in the X direction and the Y direction. For example, when the AF area RA is 200 pixels × 100 pixels, the search area determination unit 55 sets the search area RB to 320 pixels × 320 pixels.
[0126] Furthermore, when the size of the search region RB determined by the search region determination unit 55 is smaller than a predetermined size (e.g., 320 pixels×320 pixels), the object region detection unit 56 may enlarge the cutout image cutout from the search region RB to a minimum size and input the image to the trained model LM. Furthermore, a lower limit of the size of the enlarged cutout image may be specified. For example, the lower limit of the size of the enlarged cutout image may be set to 200 pixels×200 pixels.
[0127] Furthermore, the AF area RA may be set as a plurality of blocks discretely in the imaging area. In this case, the search area determination unit 55 determines a search area RB for each block. When the search areas RB of each block are close to each other, the search area determination unit 55 may integrate the plurality of search areas RB into one search area RB.
[0128] Furthermore, the search region determination unit 55 can optimize the size of the search region RB using the past detection history of the object region RC based on the object region detection unit 56. Even if the object region RC is detected, in the case where the size of the object OJ included in the object region RC is too small relative to the search region RB, the detection performance is reduced and the detection is likely to become unstable. Furthermore, even when the object OJ is so large as to exceed the search region RB, the detection performance is reduced and the detection becomes unstable.
[0129] For example, Fig.16 As shown in FIG. 1 , when the object OJ included in the object region RC is a human pupil, a face larger than the eye may be beyond the search region RB, and detection becomes unstable. In this case, the search region determination unit 55 preferably expands the search region RB in a manner including the face when determining the search region RB next time. In this way, the search region determination unit 55 changes the size of the search region RB according to the type or size of the specific part when the detected object region RC is the specific part.
[0130] Fig.17 An example of optimization processing of the search region RB by the search region determination unit 55 is shown. In the optimization processing, first, the search region determination unit 55 determines whether the detection of the object region RC by the object region detection unit 56 is unstable (step S50). For example, when the object OJ is too small or too large relative to the search region RB, it is determined that the detection is unstable. When the detection is unstable (step S50: No), the search region determination unit 55 ends the optimization processing.
[0131] When the detection is unstable (step S50: yes), the search area determination unit 55 determines whether the object OJ included in the object region RC is the smallest part (step S51). The smallest part is the smallest part in the object OJ (for example, the pupil of a person). When the object OJ is the smallest part (step S51: yes), the search area determination unit 55 determines whether the smallest part is larger than A% of the search area RB (step S52). When the smallest part is larger than A% of the search area RB, the search area determination unit 55 expands the search area RB (step S53) and ends the optimization process. Furthermore, the search area determination unit 55 ends the optimization process when the smallest part is not larger than A% of the search area RB.
[0132] When the object OJ is not the smallest part (step S51: No), the search area determination unit 55 determines whether the object OJ is the largest part (step S54). The largest part is the largest part in the object OJ (for example, the body of a bird). When the object OJ is the largest part (step S54: Yes), the search area determination unit 55 determines whether the largest part is smaller than B% of the search area RB (step S55). When the largest part is smaller than B% of the search area RB, the search area determination unit 55 reduces the search area RB (step S56) and ends the optimization process. Furthermore, the search area determination unit 55 ends the optimization process when the largest part is not smaller than B% of the search area RB.
[0133] Furthermore, the search region determination unit 55 determines the expansion rate and reduction rate of the search region RB based on the detection stability (for example, the detection success rate of 4 successful detections in the past 10 frames) and the history of the size of the object OJ relative to the search region RB.
[0134] According to the above optimization processing, for example, the human pupil is detected as the smallest part, and when the smallest part is about 30% of the size of the search area RB, the human head is about 10 times the size of the pupil, so the search area RB is expanded to about 10 times the size of the pupil.
[0135] Furthermore, according to the above-mentioned optimization processing, for example, the body of a bird is detected as the largest part. When the largest part is about 5% of the size of the search area RB, the detection is unstable because the size of the largest part is too small, and therefore the search area RB is reduced so that the largest part becomes about 10% of the search area RB.
[0136] In the above embodiment, the repetitive region detecting unit 57 detects one or more blocks with a repetitive rate greater than a threshold as the repetitive region RD. The repetitive region detecting unit 57 may change the threshold according to the type of object. Fig.18 As shown, when the object OJ is an airplane, since there are many blanks in the object region RC where the object OJ does not exist, it is preferable to increase the threshold. As a result, only blocks with a high overlap rate with the object OJ are detected as the overlap region RD, thereby improving the accuracy of focus control.
[0137] Furthermore, in the above embodiment, the ratio of the object region RC to the block is defined as the repetition rate, but the ratio of the AF region RA to the object region RC may also be defined as the repetition rate. Fig.19As shown, when a plurality of object regions RC1 to RC3 are detected by the object region detection unit 56, the repetition rates of the object regions RC1 to RC3 are different from each other. The object region RC1 is a region including the pupil of the bird. Since the object region RC1 is completely included in the AF region RA, the repetition rate is high. The object region RC2 is a region including the face of the bird. Since only a portion of the object region RC2 overlaps with the AF region RA, the repetition rate is low. The object region RC3 is a region including the body of the bird. Since only a portion of the object region RC3 overlaps with the AF region RA, the repetition rate is low.
[0138] like Fig. 20 As shown in FIG. 1 , by setting the coordinates of the object area RC and the AF area RA, and according to Fig.21 By making a judgment according to the flowchart, the positional relationship between the object area RC and the AF area RA can be obtained.
[0139] like Fig. 20 As shown in FIG. 1 , the minimum coordinate and the maximum coordinate of the object region RC in the X direction are respectively set to Cxmin and Cxmax. Furthermore, the minimum coordinate and the maximum coordinate of the object region RC in the Y direction are respectively set to Cymin and Cymax. Furthermore, the minimum coordinate and the maximum coordinate of the AF region RA in the X direction are respectively set to Axmin and Axmax. Furthermore, the minimum coordinate and the maximum coordinate of the AF region RA in the Y direction are respectively set to Aymin and Aymax.
[0140] exist Fig.21 In the flowchart shown, first, it is determined whether condition 1 is satisfied (step S60). When condition 1 is satisfied (step S60: Yes), it is determined that the object region RC is included in the AF region RA (step S61). When condition 1 is not satisfied (step S60: No), it is determined whether condition 2 is satisfied (step S62). When condition 2 is satisfied (step S62: Yes), it is determined that the AF region RA is included in the object region RC (step S63). When condition 2 is not satisfied (step S62: No), it is determined whether condition 3 is satisfied (step S64). When condition 3 is satisfied (step S64: Yes), it is determined that the object region RC partially overlaps with the AF region RA (step S65). When condition 3 is not satisfied (step S64: No), it is determined that the object region RC does not overlap with the AF region RA (step S66).
[0141] The overlap region detection unit 57 preferably reduces the threshold when it is determined that the object region RC partially overlaps with the AF region RA and that the object region RC includes a highly important portion such as the pupil. Also, the overlap region detection unit 57 preferably reduces the threshold when it is determined that the object region RC partially overlaps with the AF region RA and that the object region RC includes the entire object such as the body.
[0142] Furthermore, in the above-mentioned embodiment, the display control unit 53 displays an image on the display 15, but the viewfinder 14 may be used to display an image instead of the display 15 or together with the display 15. In this case, the focus control device may be configured so that the user can specify the AF area RA via the line of sight input device. The viewfinder 14 is an example of the "display device" involved in the technology of the present invention. The line of sight input device is an example of the "operation camera device" involved in the technology of the present invention.
[0143] Furthermore, the technology of the present invention is not limited to digital cameras, but can also be applied to electronic devices such as smartphones and tablet terminals that have a camera function.
[0144] In the above-mentioned embodiment, as the hardware structure of the control unit, the processor 40 is used as an example, and various processors shown below can be used. Among the above-mentioned various processors, in addition to the CPU which is a common processor that functions by executing software (program), there are also processors such as FPGA whose circuit structure can be changed after manufacturing. FPGA includes a dedicated circuit, which is a processor having a circuit structure specially designed to execute specific processing such as PLD or ASIC.
[0145] The control unit may be composed of one of these various processors, or may be composed of a combination of two or more processors of the same type or different types (for example, a combination of multiple FPGAs or a combination of a CPU and an FPGA). Furthermore, multiple control units may be composed of one processor.
[0146] There are multiple examples of multiple control units composed of one processor. In the first example, as represented by computers such as clients and servers, there is a method in which one processor is composed of a combination of one or more CPUs and software, and the processor functions as multiple control units. In the second example, as represented by a system on chip (System On Chip: SOC), a processor that implements the functions of the entire system including multiple control units by one IC chip is used. In this way, the control unit can use one or more of the above-mentioned various processors to form a hardware structure.
[0147] Furthermore, as the hardware configuration of these various processors, more specifically, a circuit combining circuit elements such as semiconductor elements can be used.
[0148] Also, the program may be stored in a storage medium that is non-temporarily readable by a computer.
[0149] The records and illustrations shown above are detailed descriptions of the parts involved in the technology of the present invention, and are only an example of the technology of the present invention. For example, the description of the above-mentioned structure, function, action and effect is a description of an example of the structure, function, action and effect of the parts involved in the technology of the present invention. Therefore, without departing from the scope of the main purpose of the technology of the present invention, it is of course possible to delete unnecessary parts of the records and illustrations shown above, or add new elements, or replace them. In addition, in order to avoid complexity and facilitate understanding of the parts involved in the technology of the present invention, in the records and illustrations shown above, on the basis of being able to implement the technology of the present invention, descriptions related to technical common sense that does not need to be specifically explained are omitted.
[0150] All documents, patent applications, and technical specifications described in this specification are incorporated herein by reference in the same manner as if each document, patent application, and technical specification was specifically and individually described as being incorporated by reference.
[0151] Through the above description, the following techniques can be mastered.
[0152] [Additional item 1]
[0153] A focus control device comprises a processor and a memory.
[0154] The processor performs the following processing:
[0155] Acquire an image signal output from an imaging element,
[0156] The focus target area is set in the imaging area based on output information from the operating device that receives the user's operation.
[0157] and determining a search area according to the focus object area,
[0158] Detecting an object region including a specific object from within the search region,
[0159] detecting an overlapping area where the focus object area overlaps with the object area,
[0160] Focus control is performed based on the image signal in the overlapping area.
[0161] [Supplementary Item 2]
[0162] The focus control device according to supplementary item 1, wherein:
[0163] The focus object area is composed of a plurality of blocks.
[0164] The processor detects one or more blocks overlapping with the object region among the plurality of blocks as the overlapping region.
[0165] [Supplementary item 3]
[0166] The focus control device according to supplementary item 2, wherein:
[0167] The processor detects, as the overlapping region, one or more blocks of the plurality of blocks whose overlap ratio with the object region is greater than or equal to a threshold.
[0168] [Supplementary Item 4]
[0169] The focus control device according to supplementary item 3, wherein:
[0170] The processor changes the threshold value according to the type of the specific object.
[0171] [Supplementary Item 5]
[0172] The focus control device according to supplementary item 1, wherein:
[0173] The processor detects, as the overlapping region, a region in which the overlapping rate between the focus target region and the object region is greater than a threshold value.
[0174] [Supplementary Item 6]
[0175] The focus control device according to supplementary item 5, wherein:
[0176] The processor performs focus control according to the image signal of the focus object area when the repetition rate is less than a threshold value.
[0177] [Supplementary Item 7]
[0178] A focus control device according to any one of supplementary items 1 to 6, wherein:
[0179] The processor determines the search area according to a long side of the focus object area.
[0180] [Supplementary Item 8]
[0181] The focus control device according to supplementary item 7, wherein:
[0182] The focus object area is a rectangle.
[0183] [Supplementary Item 9]
[0184] A focus control device according to any one of supplementary items 1 to 4, wherein:
[0185] The processor divides the focus target area into blocks of a number corresponding to the type of the specific object when the focus target area is not composed of a plurality of blocks.
[0186] [Supplementary Item 10]
[0187] A focus control device according to any one of supplementary items 1 to 9, wherein:
[0188] The processor acquires a defocus amount for non-focus control based on the image signal in an area outside the overlapping area and within the search area.
[0189] [Supplementary Note 11]
[0190] A focus control device according to any one of supplementary items 1 to 10, wherein:
[0191] The processor emphatically displays the repeated region on the display device by changing a color, a shape, or a line type of a frame of the repeated region.
[0192] [Supplementary Item 12]
[0193] A focus control device according to any one of supplementary items 1 to 11, wherein:
[0194] The processor detects the object region by inputting an image signal within the search region into a machine learning completion model.
[0195] [Supplementary Item 13]
[0196] A focus control device according to any one of Notes 1 to 12, wherein:
[0197] The processor sets the size of the search area to the prescribed size when the search area determined based on the focus target area is smaller than a prescribed size.
[0198] [Supplementary Item 14]
[0199] A focus control device according to any one of supplementary items 1 to 13, wherein:
[0200] When the detected object region is a specific part, the processor changes the size of the search region according to the type or size of the part.
[0201] [Supplementary Item 15]
[0202] A camera device comprising:
[0203] A focus control device as described in any one of Supplementary items 1 to 14;
[0204] The imaging element; and
[0205] The operating device.
[0206] Explanation of symbols
[0207] 10-camera device, 11-main body, 11A-camera side mount, 11B-electrical contact, 12-camera lens, 12A-lens side mount, 12B-electrical contact, 13-operating device, 14-viewfinder, 15-display, 20-camera sensor, 20A-light receiving surface, 30-objective lens, 31-focusing lens, 32-rear lens, 34-lens drive control unit, 40-processor, 42-memory, 43-program, 50-main control unit, 51-camera control unit, 52-image processing unit, 53-display control unit, 54-area setting unit, 55-search area determination unit, 56-object area detection unit Measurement unit, 57-repeated area detection unit, 58-focus position detection unit, A-optical axis, B1~B5-blocks, CF-color filter, D-image signal, EP, EP1, EP2-exit pupil, LF-light beam, LM-trained model, ML-microlens, N-camera pixel, OB-obstacle, OJ-object, P1, P2-phase difference detection pixel, PD-photodiode, RA-AF area, RB-search area, RC, RC1~RC3-object area, RD-repeated area, RE-peripheral area, RL-row, SF-light shielding layer, SN-camera signal, SP-phase difference detection signal.
Claims
1. A focus control device comprising a processor and a memory, The processor performs the following processing: Acquire an image signal output from an imaging element, The focus target area is set in the imaging area based on output information from the operating device that receives the user's operation. Determine a search area according to the focus object area, Detecting an object region including a specific object from within the search region, detecting an overlapping area where the focus object area overlaps with the object area, Focus control is performed based on the image signal in the overlapping area.
2. The focus control device according to claim 1, wherein: The focus object area is composed of a plurality of blocks. The processor detects one or more blocks overlapping with the object region among the plurality of blocks as the overlapping region.
3. The focus control device according to claim 2, wherein: The processor detects, as the overlapping region, one or more blocks of the plurality of blocks whose overlap ratio with the object region is greater than or equal to a threshold.
4. The focus control device according to claim 3, wherein: The processor changes the threshold value according to the type of the specific object.
5. The focus control device according to claim 1, wherein: The processor detects, as the overlapping region, a region in which the overlapping rate between the focus target region and the object region is greater than a threshold value.
6. The focus control device according to claim 5, wherein: The processor performs focus control according to the image signal of the focus object area when the repetition rate is less than a threshold value.
7. The focus control device according to claim 1, wherein: The processor determines the search area according to a long side of the focus object area.
8. The focus control device according to claim 7, wherein: The focus object area is a rectangle.
9. The focus control device according to claim 2, wherein: The processor divides the focus target area into blocks of a number corresponding to the type of the specific object when the focus target area is not composed of a plurality of blocks.
10. The focus control device according to claim 1, wherein: The processor acquires a defocus amount for non-focus control based on the image signal in an area outside the overlapping area and within the search area.
11. The focus control device according to claim 1, wherein: The processor emphatically displays the repeated region on the display device by changing a color, a shape, or a line type of a frame of the repeated region.
12. The focus control device according to claim 1, wherein: The processor detects the object region by inputting an image signal within the search region into a machine learning completion model.
13. The focus control device according to claim 1, wherein: The processor sets the size of the search area to the prescribed size when the search area determined based on the focus target area is smaller than a prescribed size.
14. The focus control device according to claim 1, wherein: When the detected object region is a specific part, the processor changes the size of the search region according to the type or size of the part.
15. A camera device comprising: The focus control device according to any one of claims 1 to 14; The imaging element; and The operating device.
16. A focusing control method, comprising the steps of: Acquire an image signal output from an imaging element, The focus target area is set in the imaging area based on output information from the operating device that receives the user's operation. Determine a search area according to the focus object area, Detecting an object region including a specific object from within the search region, detecting an overlapping area where the focus object area overlaps with the object area, Focus control is performed based on the image signal in the overlapping area.
17. A computer-readable storage medium storing a program that causes a processor to execute a process including the following steps: Acquire an image signal output from an imaging element, The focus target area is set in the imaging area based on output information from the operating device that receives the user's operation. Determine a search area according to the focus object area, Detecting an object region including a specific object from within the search region, detecting an overlapping area where the focus object area overlaps with the object area, Focus control is performed based on the image signal in the overlapping area.
