TWI845126B - Image processing method and image capturing system for multiple facing directions - Google Patents

Abstract

An image processing method and an image capturing system for multiple facing directions are provided. In the method, a first image and a second image are obtained, and the first image and the second image are obtained by capturing toward different facing directions through two image-capturing apparatuses. A first body shape parameter of a first object in the first image is generated, and the second body shape parameter of a second object in the second image is generated. The reference body shape parameter is determined according to the first body shape parameter and the second body shape parameter. The body shape size of the first object and/or the second object in the belonging image is adjusted according to the reference body shape parameter. Accordingly, the view and interaction experiences could be enhanced.

Description

Multi-faceted image processing method and image capturing system

The present invention relates to an image processing technology, and in particular to a multi-faceted image processing method and an image capturing system.

Traditional photography can only shoot horizontally. Therefore, the following effects may occur: (1) Because horizontal shooting cannot capture the entire vertical view of the space, the user or product may only be half-body in the frame, so the picture cannot show the full body shape. In particular, application scenarios for people walking or displaying tall large products (such as floor lamps, bookcases or cars) will be limited. (2) Horizontal shooting cannot shoot the product from a top-down or bottom-up angle, and can only use a perspective perspective to understand the product structure. Therefore, when it is necessary to discuss from a frontal or non-stereoscopic perspective, the lecturer cannot accurately explain the details of the product. For example, circuit board discussions, note annotations during video teaching, or textbook explanations.

In view of this, the present invention provides a multi-faceted image processing method and an image capturing system, which can adjust the shape of an object to a suitable size.

The multi-faceted image processing method of the embodiment of the present invention includes (but is not limited to) the following steps: obtaining a first image and a second image, wherein the first image and the second image are respectively obtained by two image capture devices shooting in different directions. Generating a first body shape parameter of a first object in the first image, and generating a second body shape parameter of a second object in the second image. Determining a reference body shape parameter based on the first body shape parameter and the second body shape parameter. Adjusting the body size of the first object and/or the second object in the corresponding image based on the reference body shape parameter.

The multi-directional image capturing system of the embodiment of the present invention includes (but is not limited to) two image capturing devices and an image processing device. These image capturing devices respectively face different directions (orientations) to capture and respectively obtain a first image and a second image. The image processing device is coupled to those image capturing devices. The image processing device is used to generate a first body shape parameter of a first object in the first image, generate a second body shape parameter of a second object in the second image, determine a reference body shape parameter based on the first body shape parameter and the second body shape parameter, and adjust the body size of the first object and/or the second object in the corresponding image based on the reference body shape parameter.

Based on the above, according to the multi-faceted image processing method and image capturing system of the embodiment of the present invention, the objects captured by multiple image capturing devices can be adjusted to a suitable size, thereby understanding the details of the object and improving the viewing and interactive experience.

In order to make the above features and advantages of the present invention more clearly understood, embodiments are specifically cited below and described in detail with reference to the accompanying drawings.

FIG1 is a block diagram of an image capturing system 10 according to an embodiment of the present invention. Referring to FIG1 , the image capturing system 10 includes (but is not limited to) two or more image capturing devices 110 and an image processing device 120.

The image capture device 110 may be a camera, a camcorder, a monitor, a smart phone, or a circuit with an image capture function, and is used to capture images within a specified field of view (FOV).

In one embodiment, the multiple image capture devices 110 shoot in different orientations/directions. For example, the first image capture device 110 shoots toward the north, the second image capture device 110 shoots toward the east, the third image capture device 110 shoots toward the south, and the fourth image capture device 110 shoots toward the west. However, the orientations of the multiple image capture devices 110 may vary, and the user may change them according to actual needs.

FIG2 is a block diagram of an image processing device 120 according to an embodiment of the present invention. Referring to FIG2 , the image processing device 120 includes (but is not limited to) a communication transceiver 121 , a memory 122 , and a processor 123 .

The communication transceiver 121 can support communication transceiver circuits such as Bluetooth, Wi-Fi, USB, mobile network, optical network or other communication technologies. In one embodiment, the communication transceiver 121 is used to receive signals from an external device or transmit signals to an external device. For example, the communication transceiver 121 receives images captured by the image capture device 110. For another example, the communication transceiver 121 transmits instructions to the image capture device 110, and executes a shooting operation or parameter adjustment accordingly.

The memory 122 may be any type of fixed or removable random access memory (RAM), read only memory (ROM), flash memory, traditional hard disk drive (HDD), solid-state drive (SSD), or similar components. In one embodiment, the memory 122 is used to store program code, software modules, configurations, data (e.g., images, parameters, etc.) or files, and its embodiments will be described in detail later.

The processor 123 is coupled to the communication transceiver 121 and the memory 122. The processor 123 may be a central processing unit (CPU), a graphic processing unit (GPU), or other programmable general-purpose or special-purpose microprocessor, digital signal processor (DSP), programmable controller, field programmable gate array (FPGA), application-specific integrated circuit (ASIC), neural network accelerator or other similar components or a combination of the above components. In one embodiment, the processor 123 is used to execute all or part of the operations of the image processing device 120, and can load and execute various program codes, software modules, files and data stored in the memory 122, and execute the image processing method of the embodiment of the present invention accordingly. In some embodiments, the functions of the processor 123 can be implemented through software or chips.

In some embodiments, the image capture device 110 and the image processing device 120 may be integrated into independent devices.

For example, FIG3A is a three-dimensional diagram of an image capturing system 10 at a first height according to an embodiment of the present invention. Referring to FIG3A , the main body 130 of the image capturing system 10 is rotatably disposed on a bracket 135. When the main body 130 is in an upright state, the image capturing device 110 is located above the main body 130 and faces different directions. That is, the image is captured in a horizontal direction.

FIG. 3B is a partial enlarged view of the image capturing system 10 according to an embodiment of the present invention (corresponding to the dotted frame of FIG. 3A ). Referring to FIG. 3A and FIG. 3B , the bracket 135 includes a short arm 131 and a protrusion 132 (constituting a fixing member), and the protrusion 132 may be made of a metal material having elasticity. As shown in FIG. 3A , it is assumed that the bracket 135 is provided with three through holes 133. The through holes 133 allow the protrusion 132 to extend out. FIG. 3A shows that the protrusion 132 extends out of the through hole 133 located at the bottom, so that the main body 130 is located at a first height. When the height of the main body 130 needs to be adjusted, force may be applied to the protrusion 132 to bend the protrusion 132 toward the main body 130. Taking FIG. 3B as an example, applying force to the right on the protrusion 132 can cause the protrusion 132 to bend to the right. Then, the body 130 slides up/down to the desired height, and the protrusion 132 enters the through hole 133 of the bracket 135, so that the structure of the through hole 133 clamps the protrusion 132, thereby achieving the purpose of fixing the body 130 at a specific height. For example, FIG. 3C is a three-dimensional diagram of an image capture system at a second height according to an embodiment of the present invention. Referring to FIG. 3C, it is assumed that the protrusion 132 extends out of the through hole 133 located in the middle, so that the body 130 is located at the second height.

FIG4A is a side view of the image capturing system 10 at a first height H11 according to an embodiment of the present invention. Referring to FIG4A , the right figure is a perspective view of the left figure, and the bracket 135 in the right figure is indicated by a dotted line to clearly show the position of the body 130. The protrusion 132 is located at the bottom through hole 133, and the body 130 has a first height H11.

FIG4B is a side view of the image capturing system 10 at a second height H12 according to an embodiment of the present invention. Referring to FIG4B , the protrusion 132 is located in the middle through hole 133, and the body 130 has a second height H12.

FIG4C is a side view of the image capturing system 10 at a third height H13 according to an embodiment of the present invention. Referring to FIG4C , the protrusion 132 is located at the uppermost through hole 133, and the body 130 has a third height H13.

Fig. 5 is a three-dimensional diagram of a rotating image capturing system 10 according to an embodiment of the present invention. Referring to Fig. 5, the body 130 rotates around the protrusion 132. When the body 130 is lying flat, the image capturing device 110 captures images in a vertical direction.

FIG6A is a side view of the rotating image capturing system 10 at a first height H21 according to an embodiment of the present invention. Referring to FIG6A , the protrusion 132 is located at the bottom through hole 133, and the body 130 has a first height H21.

FIG6B is a side view of the rotating image capturing system 10 at a second height H22 according to an embodiment of the present invention. Referring to FIG6B , the protrusion 132 is located in the middle through hole 133, and the body 130 has a second height H22.

FIG6C is a side view of the rotating image capturing system 10 at a third height H23 according to an embodiment of the present invention. Referring to FIG6C , the protrusion 132 is located at the uppermost through hole 133, and the body 130 has a third height H23.

Table (1) shows the corresponding relationship of the three-stage adjustment: Table (1) Symbol Stage Height from bottom (cm) Recommended subject types H21 First Height 18 Documentary materials or small objects such as printed materials, advertising papers H22 Second height twenty four Medium-sized objects such as mice and cell phones H23 The third height 30 Large objects such as water bottles and table lamps Assuming that the object to be photographed and the image capturing system 10 are located on the same desktop, the higher the height of the main body 130 is, the more likely it is that the entirety of a larger object can be captured. If the details of a small object are to be clearly presented, the height of the main body 130 can be lowered.

It should be noted that the height and number of perforations shown in FIG. 3A to FIG. 6C are only for illustrative purposes and can be changed by the user according to actual needs. According to different needs, the body 130 can be rotated to any inclination or elevation angle. In addition, the fixing member is not limited to the short arm 131 and the protrusion 132.

Fig. 7A is a schematic diagram of the field of view of horizontal shooting according to an embodiment of the present invention. Referring to Fig. 3A and Fig. 7A, when the body 130 is in an upright state, the field of view FOV1 of the image capture device 110 has a horizontal extension distance that is longer than a vertical extension distance.

Fig. 7B is a schematic diagram of an image IMH taken horizontally according to an embodiment of the present invention. Referring to Fig. 7B, in the context of a group photo, the image IMH taken horizontally may capture six people, but only half of their bodies may be in the frame.

Fig. 7C is a schematic diagram of the field of view of vertical shooting according to an embodiment of the present invention. Referring to Fig. 5 and Fig. 7C, when the main body 130 is lying flat, the field of view FOV2 of the image capture device 110 has a vertical extension distance that is longer than a horizontal extension distance.

FIG7D is a schematic diagram of an image shot vertically according to an embodiment of the present invention. Referring to FIG7D , in the context of a group photo, the image IMV shot vertically may only capture two of the six people, but the full bodies of the two people can be captured.

Hereinafter, the method described in the embodiment of the present invention will be described with reference to the devices and components in the image capturing system 10. Each process of the method can be adjusted according to the implementation situation, and is not limited thereto.

FIG8 is a flow chart of a multi-dimensional image processing method according to an embodiment of the present invention. Referring to FIG8 , the processor 123 obtains a first image and a second image through two or more image capture devices 110 (step S810). Specifically, the first image and the second image are respectively obtained by the two image capture devices 110 shooting in different directions. Taking horizontal shooting as an example, the first image is obtained by an image capture device 110 with a 180-degree field of view shooting toward the north, and the second image is obtained by another image capture device 110 with a 180-degree field of view shooting toward the south.

Taking vertical shooting as an example, FIG9A is a schematic diagram illustrating an application scenario according to an embodiment of the present invention. Referring to FIG9A , it is assumed that the image capturing system 10 is located between the persons P1 and P2. FIG9B is a schematic diagram illustrating the captured images IM1~IM4 in the application scenario of FIG9A according to an embodiment of the present invention. Referring to FIG9B , it is assumed that the image capturing system 10 includes four lenses (for example, belonging to four image capturing devices 110, respectively). Images IM1~IM4 are images captured by the four lenses, respectively. For example, lens 1 corresponds to objects on the table (for example, looking down at the display area), lens 2 corresponds to person P2, lens 3 corresponds to the ceiling (for example, looking up at the display area), and lens 4 corresponds to person P1. The processor 123 stitches the images IM1-IM4 together. The stitched image formed by the images IM1-IM4 includes person images corresponding to the persons P1 and P2.

In one embodiment, the processor 123 further performs image processing such as distortion correction, brightness adjustment, and white balance correction on the images IM1-IM4.

In one embodiment, the image capture system 10 may be initialized and verify whether the operating performance of each device and its components/modules is normal.

Please refer to Figure 8, the processor 123 generates a first body parameter of the first object in the first image, and generates a second body parameter of the second object in the second image (step S820). Specifically, the body parameter may correspond to one or more parts of an object (e.g., a person, an animal, a product, or a work of art). For example, Figure 10 is a schematic diagram illustrating body parameters according to an embodiment of the present invention. Please refer to Figure 10, where a person is taken as an example of an object. Body parameters include the size of the head ph1 and body pd1 of a person in the image. For example, length, width, and height, or the proportion of a part in the window size w1. The window size w1 may be a predefined size. For example, one-fourth of the first image. It should be noted that body parameters are not limited to the head and the body, and different types of objects may have parts corresponding to different body parameters.

In one embodiment, the processor 123 may determine the actual size of the object according to the ratio between the image size and the actual size of the object, and use it as the size in the body shape parameters. In another embodiment, the processor 123 may use the image size of the object as the size in the body shape parameters. In yet another embodiment, the processor 123 may normalize the image size, and use the normalized value as the actual size of the object.

Please refer to Figure 8, the processor 123 determines the reference body shape parameter based on the first body shape parameter and the second body shape parameter (step S830). In one embodiment, the reference body shape parameter is a default body shape parameter. The default body shape parameter is pre-defined or can be adjusted according to the instruction input by the user. For example, the default body shape parameter is one twentieth of the first image or 50×100 pixels. However, the default body shape parameter may change depending on the object type corresponding to the first and/or second body shape parameter. In another embodiment, the reference body shape parameter is a statistical value of the first body shape parameter and the second body shape parameter. The statistical value is, for example, an average value or a weighted average.

The processor 123 adjusts the body size of the first object and/or the second object in the corresponding image according to the reference body parameters (step S840). That is, the processor 123 adjusts the body size of the object image corresponding to the first object in the first image according to the reference body parameters, and/or the processor 123 adjusts the body size of the object image corresponding to the second object in the second image according to the reference body parameters. Similarly, if there are more image capture devices 110, the processor 123 can also adjust the body sizes of the object images corresponding to other objects in the images captured by other image capture devices 110 according to the reference body parameters.

It is worth noting that in various application scenarios, the position of the object may also change. The object may sometimes be farther from the image capture device 110, but sometimes it may be closer to the image capture device 110. Therefore, the size of the object image in the overall image may change with the change of the object's position, thereby affecting the viewing experience. The embodiment of the present invention can adjust the object image to a suitable body size.

FIG. 11 is a flow chart of body shape adjustment according to an embodiment of the present invention. Referring to FIG. 11 , the processor 123 may adjust the body shape size of the first object and/or the second object in the corresponding image to be the same as the reference body shape parameter (step S1110). The processor 123 may compare the body shape size of the first object and/or the second object with the reference body shape parameter respectively. If the body shape size of the object is smaller than the reference body shape parameter, the processor 123 may enlarge the body shape size of the object image of the object to achieve the image zoom-in effect. If the body shape size of the object is larger than the reference body shape parameter, the processor 123 may reduce the body shape size of the object image of the object to achieve the image zoom-out effect. If the body size of the object is equal to the reference body parameter, the processor 123 may maintain the body size of the object image of the object.

In one embodiment, the processor 123 may determine the ratio/proportion between the body size and the reference body parameters and determine the adjustment parameters accordingly, for example, enlarging by 1.5 times or reducing by 1.2 times.

FIG12A is a flowchart of reference body shape adjustment according to an embodiment of the present invention. Referring to FIG12A , the processor 123 may set the reference body shape parameters as the default body shape parameters (step S1210). The processor 123 may determine the ratio/proportion between the body shape size and the default body shape parameters, and determine the adjustment parameters accordingly.

For example, FIG. 12B is a schematic diagram of reference body shape adjustment according to an embodiment of the present invention. Referring to FIG. 12 , the first image IM11 includes an object image of a person P1, and the second image IM21 includes an object image of a person P2. The ratio of the body shape size of the object image of the person P1 to the preset body shape parameters is 5/4, so the adjustment parameters of the first image IM11 are reduced by 4/5 times, and the body shape size of the person image in the adjusted first image IM12 is the same as the reference body shape parameters. The ratio of the body shape size of the object image of the person P2 to the preset body shape parameters is 1/2, so the adjustment parameters of the second image IM21 are magnified by 2 times, and the body shape size of the person image in the adjusted second image IM22 is the same as the reference body shape parameters. That is, the body shapes of the two person images in the adjusted first image IM12 and the second image IM22 are the same.

FIG12C is a flowchart of statistical body shape adjustment according to an embodiment of the present invention. Referring to FIG12C , the processor 123 may set the reference body shape parameter to the statistical value of the first body shape parameter and the second body shape parameter (step S1220). The processor 123 may determine the ratio/proportion of the body size to the statistical value of the body shape parameter and determine the adjustment parameter accordingly.

For example, FIG. 12D is a schematic diagram of statistical body shape adjustment according to an embodiment of the present invention. Referring to FIG. 12D , the body size of the reference person PR in the reference image IMR is the average value of the body sizes of the object images of the persons P1 and P2. The ratio of the body size of the object image of the person P1 to the average value of the body shape parameters is 4/3, so the adjustment parameter of the first image IM11 is reduced by 3/4 times, and the body size of the person image in the adjusted first image IM13 is the same as the average value of the body shape parameters. The ratio of the body size of the object image of the person P2 to the average value of the body shape parameters is 2/3, so the adjustment parameter of the second image IM21 is magnified by 3/2 times, and the body size of the person image in the adjusted second image IM23 is the same as the reference body shape parameters. That is, the body sizes of the two person images in the adjusted first image IM13 and the second image IM23 are the same.

Thus, even if the distances between multiple objects and the image capture device 110 are different, the embodiment of the present invention can adjust the object images of these objects to be consistent, thereby improving the visual and interactive experience.

FIG. 13 is a flowchart of image integration according to an embodiment of the present invention. Referring to FIG. 13 , the processor 123 may combine the first image and the second image into an integrated image (step S1310). The first image and the second image are located in different image regions in the integrated image. In other words, the processor 123 divides the integrated image into a plurality of image regions.

For example, FIG. 14A is a schematic diagram of image areas A1, A2, and A3 according to the first embodiment of the present invention. Referring to FIG. 14A , the integrated image CM1 includes image areas A1, A2, and A3. The image areas A1, A2, and A3 have the same height, but the widths of the image areas A1, A2, and A3 are respectively lengths W1, W2, and W3. The ratio of the lengths W1, W2, and W3 is, for example, 1:1:1.5.

In one embodiment, the processor 123 may allocate multiple images to different image regions.

For example, FIG. 14B is a schematic diagram of the image configuration according to the first embodiment of the present invention. Referring to FIG. 14B , the first and second objects are taken as human beings, and area A1 is, for example, image IM4 of person P1 in FIG. 9B . The image of the person in image IM4 can be half-body or full-body, and person P1 can also display products in the upward-viewing area. Area A2 is, for example, image IM2 of person P2 in FIG. 9B . The image of the person in image IM2 can be half-body or full-body, and person P2 can also display products in the downward-viewing area. Area A3 is, for example, image IM1 of the downward-viewing display area or image IM3 of the upward-viewing display area in FIG. 9B . That is, a larger image area is provided for product display.

FIG14C is a schematic diagram of another image configuration according to the first embodiment of the present invention. Referring to FIG14C, the first and second objects are people, for example, area A1 is image IM2 of person P2 in FIG9B. Area A2 is image IM4 of person P1 in FIG9B. Area A3 is image IM1 of the top-view display area or image IM3 of the top-view display area in FIG9B.

FIG15A is a schematic diagram of image regions A1, A2, A3 according to the second embodiment of the present invention. Referring to FIG15A, the difference from FIG14A is that the ratio of the widths of image regions A1, A3, A2 in the integrated image CM2 (i.e., the ratio of the lengths W1, W3, and W2) is, for example, 1:1.5:1.

FIG15B is a schematic diagram of the image configuration according to the second embodiment of the present invention. Referring to FIG15B , the first and second objects are people, for example, area A1 is the image IM4 of person P1 in FIG9B . Area A2 is the image IM2 of person P2 in FIG9B . Area A3 is the image IM1 of the overhead display area or the image IM3 of the overhead display area in FIG9B . In this way, the attention to the product is increased.

FIG15C is a schematic diagram of another image configuration according to the second embodiment of the present invention. Referring to FIG15C, the first and second objects are people, for example, and area A1 is, for example, image IM2 of person P2 in FIG9B. Area A2 is, for example, image IM1 of the top-view display area or image IM3 of the top-view display area in FIG9B. Area A3 is, for example, image IM4 of person P1 in FIG9B.

It should be noted that the sizes, quantities and positions of the image areas in FIGS. 14A to 14C and 15A to 15C, as well as the image allocation positions, are merely examples and can be modified by the user according to actual needs.

In summary, the multi-faceted image processing method and image shooting system of the present invention can provide horizontal and vertical shooting, and can adjust the size of the object image in multiple images to a suitable size. In addition, it can provide screen segmentation to configure multiple images to different image areas.

Embodiments of the present invention can provide the following features:

The user's entire body can be included in the frame, allowing for better body language or display of taller, larger products (e.g., floor lamps or bookcases).

The presenter can show every aspect of the product from a straight-on perspective. In addition, viewers can accurately discuss the details of each component (for example, circuit board discussion, notes during a video tutorial, or textbook explanation) without misunderstandings or difficulties in explanation due to perspective.

The embodiment of the present invention can provide multiple usage modes. Through lens screen segmentation and UI planning, screen connection can be used to increase the interaction between two people, and two people can simultaneously present multiple products or simultaneously present four aspects of a product. In addition, the embodiment of the present invention provides users with a richer video conferencing experience and achieves better interactive effects in explanation and presentation.

Although the present invention has been disclosed as above by the embodiments, they are not intended to limit the present invention. Any person with ordinary knowledge in the relevant technical field can make some changes and modifications without departing from the spirit and scope of the present invention. Therefore, the protection scope of the present invention shall be defined by the scope of the attached patent application.

10: Image capture system 110: Image capture device 120: Image processing device 121: Communication transceiver 122: Memory 123: Processor 130: Main body 131: Short arm 132: Bump 133: Perforation 135: Bracket H11, H21: First height H12, H22: Second height H13, H23: Third height FOV1, FOV2: Field of view IMH, IMV, IM1~IM4: Image S810~S840, S1110, S1210, S1220, S1310: Steps P1, P2: Person ph1: Head pd1: Body w1: Window size IM11, IM12, IM13: First image IM21, IM22, IM23: Second image PR: Reference person IMR: Reference image W1, W2, W3: Length CM1, CM2: Integrated image A1, A2, A3: Image area

FIG. 1 is a component block diagram of an image capturing system according to an embodiment of the present invention. FIG. 2 is a component block diagram of an image processing device according to an embodiment of the present invention. FIG. 3A is a stereoscopic diagram of an image capturing system at a first height according to an embodiment of the present invention. FIG. 3B is a partial enlarged diagram of an image capturing system according to an embodiment of the present invention. FIG. 3C is a stereoscopic diagram of an image capturing system at a second height according to an embodiment of the present invention. FIG. 4A is a side view of an image capturing system at a first height according to an embodiment of the present invention. FIG. 4B is a side view of an image capturing system at a second height according to an embodiment of the present invention. FIG. 4C is a side view of an image capturing system at a third height according to an embodiment of the present invention. FIG. 5 is a stereoscopic view of a rotating image capturing system according to an embodiment of the present invention. FIG. 6A is a side view of a rotating image capturing system at a first height according to an embodiment of the present invention. FIG. 6B is a side view of a rotating image capturing system at a second height according to an embodiment of the present invention. FIG. 6C is a side view of a rotating image capturing system at a third height according to an embodiment of the present invention. FIG. 7A is a schematic diagram of a horizontally captured field of view according to an embodiment of the present invention. FIG. 7B is a schematic diagram of an image captured horizontally according to an embodiment of the present invention. FIG. 7C is a schematic diagram of a vertically shot field of view according to an embodiment of the present invention. FIG. 7D is a schematic diagram of an image shot vertically according to an embodiment of the present invention. FIG. 8 is a flow chart of a multi-faceted image processing method according to an embodiment of the present invention. FIG. 9A is a schematic diagram of an application scenario according to an embodiment of the present invention. FIG. 9B is a schematic diagram of an image captured in the application scenario of FIG. 9A according to an embodiment of the present invention. FIG. 10 is a schematic diagram of body shape parameters according to an embodiment of the present invention. FIG. 11 is a flow chart of body shape adjustment according to an embodiment of the present invention. FIG. 12A is a flow chart of reference body shape adjustment according to an embodiment of the present invention. FIG. 12B is a schematic diagram of reference body shape adjustment according to an embodiment of the present invention. FIG. 12C is a flowchart of statistical body shape adjustment according to an embodiment of the present invention. FIG. 12D is a schematic diagram of statistical body shape adjustment according to an embodiment of the present invention. FIG. 13 is a flowchart of image integration according to an embodiment of the present invention. FIG. 14A is a schematic diagram of an image area according to the first embodiment of the present invention. FIG. 14B is a schematic diagram of an image configuration according to the first embodiment of the present invention. FIG. 14C is a schematic diagram of another image configuration according to the first embodiment of the present invention. FIG. 15A is a schematic diagram of an image area according to the second embodiment of the present invention. FIG. 15B is a schematic diagram of an image configuration according to the second embodiment of the present invention. FIG. 15C is a schematic diagram of another image configuration according to the second embodiment of the present invention.

S810~S840: Steps

Claims (12)

A multi-faceted image processing method includes: obtaining a first image and a second image, wherein the first image and the second image are respectively captured by two image capture devices in different directions; generating a first body parameter of a first object in the first image, and generating a second body parameter of a second object in the second image; determining a reference body parameter according to the first body parameter and the second body parameter; and adjusting the body size of at least one of the first object and the second object in the corresponding image according to the reference body parameter, including: adjusting the body size of at least one of the first object and the second object in the corresponding image to be the same as the reference body parameter. A multi-faceted image processing method as described in claim 1, wherein the reference body shape parameter is a default body shape parameter. The multi-faceted image processing method as described in claim 1, wherein the reference body shape parameter is a statistical value of the first body shape parameter and the second body shape parameter. A multi-faceted image processing method as described in claim 1, wherein the first body shape parameter includes the size of at least one part of the first object in the first image. The multi-faceted image processing method as described in claim 1, wherein after the step of adjusting the body size of at least one of the first object and the second object in the image according to the reference body parameter, further comprises: Combining the first image and the second image into an integrated image, wherein the first image and the second image are located in different image areas in the integrated image. A multi-faceted image shooting system includes: two image capture devices for shooting in different directions and obtaining a first image and a second image respectively; and an image processing device coupled to the two image capture devices and used to: generate a first body parameter of a first object in the first image and a second body parameter of a second object in the second image; determine a reference body parameter according to the first body parameter and the second body parameter; and adjust the body size of at least one of the first object and the second object in the corresponding image according to the reference body parameter, wherein the image processing device is further used to: adjust the body size of at least one of the first object and the second object in the corresponding image to be the same as the reference body parameter. A multi-faceted image capturing system as described in claim 6, wherein the reference body shape parameter is a default body shape parameter. A multi-faceted image capturing system as described in claim 6, wherein the reference body shape parameter is a statistical value of the first body shape parameter and the second body shape parameter. A multi-faceted image capturing system as described in claim 6, wherein the first body shape parameter includes the size of at least one part of the first object in the first image. A multi-faceted image capturing system as described in claim 6, wherein the image processing device is further used to: combine the first image and the second image into an integrated image, wherein the first image and the second image are located in different image areas in the integrated image. A multi-faceted image processing method includes: obtaining a first image and a second image, wherein the first image and the second image are respectively taken by two image capture devices in different directions; generating a first body parameter of a first object in the first image, and generating a second body parameter of a second object in the second image; determining a reference body parameter according to the first body parameter and the second body parameter, wherein the reference body parameter is a statistical value of the first body parameter and the second body parameter; and adjusting the body size of at least one of the first object and the second object in the corresponding image according to the reference body parameter. A multi-faceted image shooting system includes: two image capture devices for shooting in different directions and obtaining a first image and a second image respectively; and an image processing device coupled to the two image capture devices and used to: generate a first body shape parameter of a first object in the first image and generate a second body shape parameter of a second object in the second image; determine a reference body shape parameter based on the first body shape parameter and the second body shape parameter, wherein the reference body shape parameter is a statistical value of the first body shape parameter and the second body shape parameter; and adjust the body shape size of at least one of the first object and the second object in the corresponding image based on the reference body shape parameter.

Images