WO2017088714A1

WO2017088714A1 - Mobile terminal and three-dimensional image generation method therefor

Info

Publication number: WO2017088714A1
Application number: PCT/CN2016/106637
Authority: WO
Inventors: 张圣杰; 金蓉
Original assignee: 努比亚技术有限公司
Priority date: 2015-11-25
Filing date: 2016-11-21
Publication date: 2017-06-01
Also published as: CN105427369A

Abstract

A mobile terminal and a three-dimensional image generation method therefor. The mobile terminal comprises: a reading module (510), configured to: read panoramic image data corresponding to a panoramic picture of a shot three-dimensional object; an extraction module (520), configured to: extract characteristic data needed for generation of a three-dimensional image from the panoramic image data; and a generation module (530), configured to: initiate a three-dimensional image engine according to the extracted characteristic data so as to generate a three-dimensional image corresponding to the shot three-dimensional object.

Description

Mobile terminal and method for generating three-dimensional image thereof

Technical field

The present application relates to, but is not limited to, the field of communication technologies, and in particular to a mobile terminal and a method for generating a three-dimensional image thereof.

Background technique

Related technologies, the generation of three-dimensional characters on a computer requires the use of professional three-dimensional character models and development tools, while the professional quality requirements for developers are relatively high. In addition, the three-dimensional character image cannot be quickly generated on the computer, and this is especially true on the mobile terminal. Therefore, the related art cannot generate a vivid three-dimensional image in the daily use scenario of the mobile terminal, and thus cannot satisfy the user in the relevant application scenario. The growing demand for personalized interactions.

Summary of the invention

The following is an overview of the topics detailed in this document. This Summary is not intended to limit the scope of the claims.

This paper provides a mobile terminal and a method for generating a three-dimensional image thereof, which can generate a vivid three-dimensional image in a daily use scenario of the mobile terminal.

A mobile terminal provided by an embodiment of the present invention includes:

a reading module configured to: read panoramic image data corresponding to the panoramic photo of the captured three-dimensional object;

An extraction module, configured to: extract feature data required to generate a three-dimensional image from the panoramic image data;

And generating a module, configured to: according to the extracted feature data, activate a three-dimensional image engine to generate a three-dimensional image corresponding to the captured three-dimensional object.

Optionally, the three-dimensional object is a three-dimensional character object; the extraction module includes:

a pre-processing unit, configured to: extract the three-dimensional character object from the panoramic image data Overall image data, and calibrating the three-dimensional character objects of different orientations in the overall image data;

The first data extracting unit is configured to: extract face image data from the image data corresponding to the three-dimensional character object in different orientations, and extract relevant feature data from the face image data, where the related feature data includes Texture feature data of the face image;

The ratio calculating unit is configured to: distinguish the head, the upper body, the lower body, and the limbs in the image data corresponding to the different orientations of the three-dimensional human object, to correspondingly measure the head, the upper body, the lower body of the three-dimensional object and The length ratio of the limbs;

The second data extracting unit is configured to extract other feature data from the image data corresponding to the three-dimensional character object in different orientations, and the other feature data includes hairstyle feature data, wearing feature data, and color feature data.

Optionally, the pre-processing unit is configured to: use an image edge detection algorithm to distinguish a three-dimensional character from a background environment, and extract image data corresponding to the detected determined pixel edge to obtain overall image data of the three-dimensional object object. .

Optionally, the first data extracting unit is further configured to: after determining the area where the face image is located in the image data corresponding to the three-dimensional character object in different orientations, the face image is zoomed, rotated, and stretched One or more of the processes result in a preset standard size face image.

Optionally, the generating module includes:

a model building unit, configured to: perform three-dimensional reconstruction according to the extracted partial feature data related to the constructing character model in the feature data, to generate a character model corresponding to the captured three-dimensional character object;

The model rendering unit is configured to: perform a character model rendering according to the extracted other part of the feature data related to the character model rendering to generate a three-dimensional character image corresponding to the captured three-dimensional character object.

Optionally, the model building unit is configured to: calculate the length, width, height, and limb ratio data of the overall character image in the three-dimensional space by using the obtained length ratios of the head, the upper body, the lower body, and the limbs of the person to generate and The character model corresponding to the captured three-dimensional character object.

Optionally, the model rendering unit is further configured to: adopt a panoramic stitching fusion technology to not The splicing process is performed on the image information of the same orientation to generate a three-dimensional character image corresponding to the captured three-dimensional character object.

Optionally, the mobile terminal further includes:

The application association module is configured to: associate the generated three-dimensional character image with an application scenario in the mobile terminal;

The three-dimensional character image display module is configured to: when the associated application scene is in an active state, display a three-dimensional character image corresponding to the associated application scene on a display screen of the mobile terminal.

Optionally, the mobile terminal further includes:

a shooting module, configured to: activate a panoramic shooting mode in a camera application of the mobile terminal to capture and store a panoramic photo of the three-dimensional object, wherein the current movement is detected in real time during the panoramic shooting of the mobile terminal Whether the shooting angle of the terminal is within the set shooting angle range. If not, the corresponding correction prompt is issued.

Optionally, the shooting module is configured to: detect, by using one or more of a gravity sensor, an attitude sensor, a gyroscope, and a compass, whether the shooting angle of the current mobile terminal is in a set shooting angle range in real time. within.

The embodiment of the present invention further provides a method for generating a three-dimensional image, which is applied to a mobile terminal, and the method for generating the three-dimensional image includes:

Reading panoramic image data corresponding to the panoramic photo of the captured three-dimensional object;

Extracting feature data required to generate a three-dimensional image from the panoramic image data;

Based on the extracted feature data, a three-dimensional image engine is launched to generate a three-dimensional image corresponding to the captured three-dimensional object.

Optionally, the three-dimensional object is a three-dimensional character object; and extracting, from the panoramic image data, feature data required to generate a three-dimensional image includes:

Extracting overall image data of the three-dimensional human object from the panoramic image data, and calibrating the three-dimensional human object in different orientations in the overall image data;

Extracting face image data from the image data corresponding to the three-dimensional character object in different orientations, and extracting relevant feature data from the face image data, the related feature data including at least texture feature data of the face image;

Distinguishing between the head, the upper body, the lower body, and the limbs in the image data corresponding to the different orientations of the three-dimensional character object, to correspondingly calculate the length ratios of the head, the upper body, the lower body, and the limbs of the three-dimensional object;

Other feature data is extracted from the image data corresponding to the three-dimensional character object in different orientations, the other feature data including hairstyle feature data, wearing feature data, and color feature data.

Optionally, the extracting the overall image data of the three-dimensional character object from the panoramic image data includes:

The image edge detection algorithm is used to distinguish the three-dimensional character from the background environment, and the image data corresponding to the detected determined pixel edge is extracted, and the overall image data of the three-dimensional character object is obtained.

Optionally, after determining the area where the face image is located in the image data corresponding to the different orientations of the three-dimensional character object, the method further includes:

The face image is processed by one or more of zooming, rotating, and stretching to obtain a preset standard size face image.

Optionally, the generating, according to the extracted feature data, the three-dimensional image engine to generate a three-dimensional image corresponding to the captured three-dimensional object comprises:

And performing three-dimensional reconstruction according to the extracted partial feature data related to the constructing character model in the feature data to generate a character model corresponding to the captured three-dimensional character object;

Character model rendering is performed according to the extracted other feature data related to the character model rendering in the feature data to generate a three-dimensional character image corresponding to the captured three-dimensional character object.

Optionally, after the three-dimensional image engine is started to generate the three-dimensional image corresponding to the captured three-dimensional object according to the extracted feature data, the method further includes:

Associating the generated three-dimensional character image with an application scenario in the mobile terminal;

When the associated application scenario is in an active state, a three-dimensional character image corresponding to the associated application scenario is displayed on a display screen of the mobile terminal.

Optionally, performing three-dimensional reconstruction according to the extracted partial feature data related to the built-in character model in the extracted feature data to generate a character model corresponding to the captured three-dimensional character object includes:

Calculating the length, width, height and limb ratio data of the overall character in the three-dimensional space by using the obtained length ratios of the head, upper body, lower body and limbs of the person to generate a character model corresponding to the captured three-dimensional object .

Optionally, after the three-dimensional reconstruction is performed on the part of the feature data related to the built-in character model in the extracted feature data, to generate a character model corresponding to the captured three-dimensional character object, the method further includes:

The image information of different orientations is spliced by a panoramic stitching fusion technique to generate a three-dimensional character image corresponding to the captured three-dimensional character object.

Optionally, the reading the panoramic image data corresponding to the panoramic photo of the captured three-dimensional object includes:

Activating a panoramic photographing mode in the camera application of the mobile terminal to capture and store a panoramic photo of the three-dimensional object, wherein during the panoramic photographing process, the mobile terminal detects whether the current shooting angle of the mobile terminal is in real time Within the set shooting angle range, if no, the corresponding correction prompt is issued.

Optionally, the real-time detecting whether the shooting angle of the current mobile terminal is within a set shooting angle range includes:

By using one or more of a gravity sensor, an attitude sensor, a gyroscope, and a compass, it is detected in real time whether the shooting angle of the current mobile terminal is within a set shooting angle range.

The embodiment of the invention further provides a computer readable storage medium storing computer executable instructions, which are implemented when executed by a processor.

In the embodiment of the present invention, the mobile terminal generates a three-dimensional shape based on the panoramic photo of the three-dimensional object. Like the extraction of the required feature data, and then based on the extracted feature data, the three-dimensional image engine is activated to generate a corresponding three-dimensional image. The embodiment of the invention can conveniently and quickly generate a three-dimensional image of the captured object, and facilitate the user to associate with the related application, thereby satisfying the personalized use requirement of the user and improving the user experience.

Other aspects will be apparent upon reading and understanding the drawings and detailed description.

BRIEF abstract

1 is a schematic structural diagram of hardware of an optional mobile terminal in implementing an embodiment of the present invention;

Figure 2 is a block diagram showing the electrical structure of the camera of Figure 1;

3 is a schematic diagram of functional modules of a first embodiment of a mobile terminal according to the present invention;

4 is a schematic diagram of a refinement function module of the extraction module of FIG. 3;

5 is a schematic diagram of a refinement function module of the generation module in FIG. 3;

6 is a schematic diagram of functional modules of a second embodiment of a mobile terminal according to the present invention;

7 is a schematic diagram of functional modules of a third embodiment of a mobile terminal according to the present invention;

8 is a schematic diagram of an embodiment of a panoramic photo taken by a mobile terminal according to the present invention;

9 is a schematic flow chart of a first embodiment of a method for generating a three-dimensional image according to the present invention;

FIG. 10 is a schematic diagram of the refinement process of step S20;

11 is a schematic flowchart of the refinement of step S30;

12 is a schematic flow chart of a second embodiment of a method for generating a three-dimensional image according to the present invention;

FIG. 13 is a schematic flow chart of a third embodiment of a method for generating a three-dimensional image according to the present invention.

Embodiments of the invention

It is to be understood that the embodiments described herein are merely illustrative of the application and are not intended to be limiting.

A mobile terminal embodying an embodiment of the present invention will now be described with reference to the accompanying drawings. In the following description, the use of a suffix such as "module", "part" or "unit" for representing an element is only advantageous for the present invention. The description of the embodiments does not have a specific meaning per se. Therefore, "module" and "component" can be used in combination.

The mobile terminal can be implemented in a variety of forms. For example, the terminals described herein may include, for example, mobile phones, smart phones, notebook computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablets), PMPs (Portable Multimedia Players), navigation devices, and the like. Mobile terminals and fixed terminals such as digital TVs, desktop computers, and the like. In the following, it is assumed that the terminal is a mobile terminal. However, those skilled in the art will appreciate that configurations in accordance with embodiments of the present invention can be applied to fixed type terminals in addition to components that are specifically for mobile purposes.

FIG. 1 is a schematic structural diagram of hardware of an optional mobile terminal in implementing an embodiment of the present invention.

The mobile terminal 100 may include a wireless communication unit 110, an A/V (Audio/Video) input unit 120, a user input unit 130, a sensing unit 140, an output unit 150, a memory 160, a controller 170, and the like. Figure 1 illustrates a mobile terminal having various components, but it should be understood that not all illustrated components are required to be implemented. More or fewer components can be implemented instead. The elements of the mobile terminal will be described in detail below.

Wireless communication unit 110 typically includes one or more components that permit radio communication between mobile terminal 100 and a wireless communication device or network.

The A/V input unit 120 is arranged to receive an audio or video signal. The A/V input unit 120 may include a camera 121 that processes image data of still pictures or video obtained by an image capturing device in a video capturing mode or an image capturing mode. The processed image frame can be displayed on the display unit 151. The image frames processed by the camera 121 may be stored in the memory 160 (or other storage medium) or transmitted via the wireless communication unit 110, and two or more cameras 121 may be provided according to the configuration of the mobile terminal.

The user input unit 130 may generate key input data according to a command input by the user to control the operation of the mobile terminal. The user input unit 130 allows the user to input various types of information, and may include a keyboard, a pot, a touch panel (eg, a touch sensitive component that detects changes in resistance, pressure values, capacitance, etc. due to contact), Roller, rocker, etc. In particular, a touch screen may be formed when the touch panel is superimposed on the display unit 151 in the form of a layer.

The sensing unit 140 detects the current state of the mobile terminal 100 (eg, the opening of the mobile terminal 100) Or the off state), the location of the mobile terminal 100, the presence or absence of the user's contact with the mobile terminal 100 (ie, touch input), the orientation of the mobile terminal 100, the direction of movement and the tilt angle of the mobile terminal 100, and the like, and are generated for A command or signal that controls the operation of the mobile terminal 100. For example, the sensing unit 140 includes an accelerometer 141 that is configured to detect real-time acceleration of the mobile terminal 100 to derive a direction of motion of the mobile terminal 100, and a gyroscope 142 that is configured to detect that the mobile terminal 100 is relative to its location The angle of inclination of the plane.

Output unit 150 is configured to provide an output signal (eg, an audio signal, a video signal, a vibration signal, etc.) in a visual, audio, and/or tactile manner. The output unit 150 may include a display unit 151, an audio output module 152, and the like.

The display unit 151 can display information processed in the mobile terminal 100. For example, when the mobile terminal 100 is in a phone call mode, the display unit 151 can display a user interface (UI) or a graphical user interface (GUI) related to a call or other communication (eg, text messaging, multimedia file download, etc.). When the mobile terminal 100 is in a video call mode or an image capturing mode, the display unit 151 may display a captured image and/or a received image, a UI or GUI showing a video or image and related functions, and the like.

Meanwhile, when the display unit 151 and the touch panel are superposed on each other in the form of a layer to form a touch screen, the display unit 151 can function as an input device and an output device. The display unit 151 may include at least one of a liquid crystal display (LCD), a thin film transistor LCD (TFT-LCD), an organic light emitting diode (OLED) display, a flexible display, a three-dimensional (3D) display, and the like. Some of these displays may be configured to be transparent to allow a user to view from the outside, which may be referred to as a transparent display, and a typical transparent display may be, for example, a TOLED (Transparent Organic Light Emitting Diode) display or the like. According to a particular desired embodiment, the mobile terminal 100 may include two or more display units (or other display devices), for example, the mobile terminal may include an external display unit (not shown) and an internal display unit (not shown) . The touch screen can be used to detect touch input pressure values as well as touch input positions and touch input areas.

The audio output module 152 may convert audio data received by the wireless communication unit 110 or stored in the memory 160 when the mobile terminal is in a call signal receiving mode, a call mode, a recording mode, a voice recognition mode, a broadcast receiving mode, and the like. The audio signal is output as sound. Moreover, the audio output module 152 can provide audio output (eg, call signal reception sound, message reception sound, etc.) associated with a particular function performed by the mobile terminal 100. The audio output module 152 can To include pickups, buzzers, and so on.

The memory 160 may store a software program or the like for processing and control operations performed by the controller 170, or may temporarily store data (for example, a phone book, a message, a still image, a video, etc.) that has been output or is to be output. Moreover, the memory 160 may store data regarding vibration and audio signals of various manners that are output when a touch is applied to the touch screen.

The memory 160 may include at least one type of storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (eg, SD or DX memory, etc.), a random access memory (RAM), a static random access memory ( SRAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), magnetic memory, magnetic disk, optical disk, and the like. Moreover, the mobile terminal 100 can cooperate with a network storage device that performs a storage function of the memory 160 through a network connection.

Controller 170 typically controls the overall operation of the mobile terminal. For example, controller 170 performs the control and processing associated with voice calls, data communications, video calls, and the like. The controller 170 may perform a pattern recognition process to recognize a handwriting input or a picture drawing input performed on the touch screen as a character or an image.

The embodiments described herein can be implemented in a computer readable medium using, for example, computer software, hardware, or any combination thereof. For hardware implementations, the embodiments described herein may be through the use of application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays ( An FPGA, a processor, a controller, a microcontroller, a microprocessor, at least one of the electronic units designed to perform the functions described herein, in some cases, such an embodiment may be at the controller 170 Implemented in the middle. For software implementations, implementations such as procedures or functions may be implemented with separate software modules that permit the execution of at least one function or operation. The software code can be implemented by a software application (or program) written in any suitable programming language, which can be stored in memory 160 and executed by controller 170.

In addition, the mobile terminal of the embodiment of the present invention may further include: a reading module 510, an extracting module 520, and a generating module 530, where

The reading module 510 is configured to: read panoramic image data corresponding to the captured panoramic photo of the three-dimensional object; and the extracting module 520 is configured to: extract three generated from the panoramic image data The feature data required by the dimension image; the generating module 530 is configured to: according to the extracted feature data, activate the three-dimensional image engine to generate a three-dimensional image corresponding to the captured three-dimensional object.

In addition, referring to FIG. 2, FIG. 2 is a block diagram of the electrical structure of the camera of FIG. 1.

The photographic lens 1211 is composed of a plurality of optical lenses for forming a subject image, and is a single focus lens or a zoom lens. The photographic lens 1211 is movable in the optical axis direction under the control of the lens driver 1221, and the lens driver 1221 controls the focus position of the photographic lens 1211 in accordance with a control signal from the lens driving control circuit 1222, and can also be controlled in the case of the zoom lens. Focus distance. The lens drive control circuit 1222 performs drive control of the lens driver 1221 in accordance with a control command from the microcomputer 1217.

An imaging element 1212 is disposed on the optical axis of the photographic lens 1211 near the position of the subject image formed by the photographic lens 1211. The imaging element 1212 is provided to image the subject image and acquire captured image data. Photodiodes constituting each pixel are arranged two-dimensionally and in a matrix on the imaging element 1212. The photodiode generates a photoelectric conversion current corresponding to the amount of received light, and the photoelectric conversion current is charged by a capacitor connected to the photodiode. The front surface of each pixel is provided with a Bayer array of RGB color filters.

The imaging element 1212 is connected to the imaging circuit 1213. The imaging circuit 1213 performs charge accumulation control and image signal readout control in the imaging element 1212, and performs waveform shaping after reducing the reset noise of the read image signal (analog image signal). Further, gain improvement or the like is performed to obtain an appropriate signal level. The imaging circuit 1213 is connected to an A/D converter 1214 that performs analog-to-digital conversion on the analog image signal and outputs a digital image signal (hereinafter referred to as image data) to the bus 1227.

The bus 1227 is a transmission path for transmitting a variety of data read or generated inside the camera. The A/D converter 1214 is connected to the bus 1227, and an image processor 1215, a JPEG processor 1216, a microcomputer 1217, a SDRAM (Synchronous Dynamic Random Access Memory) 1218, and a memory interface are also connected. (hereinafter referred to as memory I/F) 1219, LCD (Liquid Crystal Display) driver 1220.

The image processor 1215 performs OB subtraction processing, white balance adjustment, color matrix calculation, gamma conversion, color difference signal processing, noise removal processing, simultaneous processing, edge processing, and the like on the image data based on the output of the imaging element 1212. deal with. JPEG processor 1216 is remembering image data When recorded on the recording medium 1225, the image data read from the SDRAM 1218 is compressed in accordance with the JPEG compression method. Further, the JPEG processor 1216 performs decompression of JPEG image data for image reproduction display. At the time of decompression, the file recorded on the recording medium 1225 is read, and after the compression processing is performed in the JPEG processor 1216, the decompressed image data is temporarily stored in the SDRAM 1218 and displayed on the LCD 1226. Further, in the present embodiment, the JPEG method is adopted as the image compression/decompression method. However, the compression/decompression method is not limited thereto, and other compression/decompression methods such as MPEG, TIFF, and H.264 may be used.

The microcomputer 1217 functions as a control unit of the entire camera, and collectively controls various processing sequences of the camera. The microcomputer 1217 is connected to the operation unit 1223 and the flash memory 1224.

The operating unit 1223 includes, but is not limited to, a physical button or a virtual button, and the entity or virtual button may be a power button, a camera button, an edit button, a dynamic image button, a reproduction button, a menu button, a cross button, an OK button, a delete button, an enlarge button A variety of input buttons and a variety of input keys and other operational controls to detect the operational status of these operational controls.

The detection result is output to the microcomputer 1217. Further, a touch panel is provided on the front surface of the LCD 1226 as a display, and the touch position of the user is detected, and the touch position is output to the microcomputer 1217. The microcomputer 1217 executes a plurality of processing sequences corresponding to the user's operation in accordance with the detection result from the operation position of the operation unit 1223.

The flash memory 1224 stores programs for executing various processing sequences of the microcomputer 1217. The microcomputer 1217 performs overall control of the camera in accordance with the program. Further, the flash memory 1224 stores various adjustment values of the camera, and the microcomputer 1217 reads out the adjustment value, and performs control of the camera in accordance with the adjustment value.

The SDRAM 1218 is an electrically rewritable volatile memory for temporarily storing image data or the like. The SDRAM 1218 temporarily stores image data output from the A/D converter 1214 and image data processed in the image processor 1215, the JPEG processor 1216, and the like.

The memory interface 1219 is connected to the recording medium 1225, and performs control for writing image data and a file header attached to the image data to the recording medium 1225 and reading out from the recording medium 1225. The recording medium 1225 is, for example, a recording medium such as a memory card that can be detachably attached to the camera body. However, the recording medium 1225 is not limited thereto, and may be a hard disk or the like built in the camera body.

The LCD driver 1210 is connected to the LCD 1226, and the number of images to be processed by the image processor 1215 According to the storage in the SDRAM 1218, when the display is required, the image data stored by the SDRAM 1218 is read and displayed on the LCD 1226, or the image data compressed by the JPEG processor 1216 is stored in the SDRAM 1218. When it is required to be displayed, the JPEG processor 1216 reads the compression of the SDRAM 1218. The image data that has passed is decompressed, and the decompressed image data is displayed on the LCD 1226. The LCD 1226 is configured to display an image on the back of the camera body. The LCD 1226 is an LCD, but is not limited thereto, and various display panels such as an organic EL may be used.

Based on the hardware structure of the mobile terminal and the electrical structure of the camera, an embodiment of a method for generating a mobile terminal and a three-dimensional image thereof according to the present invention is proposed.

Referring to FIG. 3, FIG. 3 is a schematic diagram of functional modules of a first embodiment of a mobile terminal according to the present invention. In this embodiment, the mobile terminal includes:

The reading module 510 is configured to: read panoramic image data corresponding to the panoramic photo of the captured three-dimensional object;

In this embodiment, in order to complete the creation of the three-dimensional image, it is necessary to obtain a panoramic photo of the subject, that is, a 360-degree image corresponding to the subject. The photographic subject in this embodiment is three-dimensional, and the form of the three-dimensional object is not limited, for example, a panoramic photo of a physical person may be taken, or a panoramic photo of a solid animal or a physical item may also be taken for generating a corresponding image on the mobile terminal. The three-dimensional image. In order to realize the subsequent image stitching processing of the three-dimensional image, there are enough overlapping information between the images taken at different angles in the acquired panoramic photo.

In addition, the panoramic photo of the three-dimensional object is saved on the mobile terminal or other device after the shooting is completed, and is read by the reading module 510 when the three-dimensional image generation process is required, wherein the method of reading is not limited, according to actual needs. Make settings.

The extracting module 520 is configured to: extract feature data required to generate a three-dimensional image from the panoramic image data;

In this embodiment, the feature data required to generate a three-dimensional image, such as facial texture, height, wearing, skin color, limb ratio, and the like, are extracted from the read panoramic image data by the extraction module 520, and then according to the extracted features. The data can be used to generate a corresponding three-dimensional image.

In addition, in this embodiment, the method for extracting feature data in an image is not limited, and may be set according to actual needs. For example, using edge detection to extract 3D objects from the environment background Come, or use the face detection algorithm to detect the face position and extract the facial texture features of the three-dimensional character object.

The generating module 530 is configured to: according to the extracted feature data, activate a three-dimensional image engine to generate a three-dimensional image corresponding to the captured three-dimensional object.

In this embodiment, in order to quickly generate a three-dimensional image that can be displayed on the mobile terminal corresponding to the captured three-dimensional object, the generating module 530 performs synthesis on all the extracted feature data by using a preset three-dimensional image engine, thereby generating corresponding The three-dimensional image.

The three-dimensional image engine is a three-dimensional graphics engine developed in this embodiment for facilitating generation of a three-dimensional image in the embodiment of the present invention. Currently, large-scale development tools such as OpenGL or DirectX are generally used to write 3D graphics applications on a microcomputer. However, since 3D graphics involve many algorithms and expertise, it is still difficult to quickly develop 3D applications. Therefore, the development of 3D applications requires a three-dimensional graphics development environment that encapsulates hardware operations and graphics algorithms, as well as an easy-to-use and feature-rich environment. This three-dimensional graphics development environment can be called a three-dimensional graphics engine. For example, OGRE (Object-Oriented Graphics Rendering Engine), OSG (Open Scene Graph), and the like.

In this embodiment, the mobile terminal performs extraction of feature data required to generate a three-dimensional image based on the panoramic photo of the three-dimensional object, and then starts the three-dimensional image engine to generate a corresponding three-dimensional image according to the extracted feature data. The embodiment of the invention can conveniently and quickly generate a three-dimensional image of the captured object, and facilitate the user to associate with the related application, thereby satisfying the personalized use requirement of the user and improving the user experience.

Referring to FIG. 4, FIG. 4 is a schematic diagram of a refinement function module of the extraction module of FIG. Based on the above embodiment, the three-dimensional object is described as a three-dimensional object in the embodiment. In this embodiment, the extraction module 520 includes:

The pre-processing unit 5201 is configured to: extract overall image data of the three-dimensional human object from the panoramic image data, and perform calibration on the three-dimensional human object in different orientations in the overall image data;

Optionally, the pre-processing unit 5201 is configured to: use an image edge detection algorithm to distinguish three-dimensional The character and the background environment extract the image data corresponding to the detected pixel edge closed, and obtain the overall image data of the three-dimensional character object.

In this embodiment, since the panoramic image data obtained by the shooting generally includes the image data of the three-dimensional human object and the image data of the environment in which the human object is located, the pre-processing unit 5201 takes the overall image data of the three-dimensional human object from the image data thereof. The environment image is extracted and processed separately. In addition, since the overall image data of the three-dimensional human object includes image data of different orientations of the three-dimensional human object, the pre-processing unit 5201 also performs one-to-one calibration on the three-dimensional human objects in different orientations of the overall image data of the three-dimensional human object. Used to make a distinction.

In this embodiment, the manner of extracting the whole image data of the three-dimensional character object is not limited. Since the three-dimensional character object in the panoramic image data is an integral closed area, for example, an image edge detection algorithm may be used to distinguish the three-dimensional character from the background environment, and thus, The image data corresponding to the detected determined pixel edge is extracted to obtain the overall image data of the three-dimensional human object.

In addition, in the present embodiment, the manner of calibrating the three-dimensional human objects in different directions in the overall image data of the three-dimensional human object is not limited, and is set according to actual needs. For example, a three-dimensional human object may be calibrated using a human body orientation detection algorithm, such as calibrating a human body orientation every 45° with reference to the front of the human object, and the orientation of the human object for 360° orientation may be calibrated to eight orientations. The feature data in the image of the person object corresponding to the different orientations is mostly different, so the character object feature data extraction in different orientation directions can be performed.

The first data extracting unit 5202 is configured to: determine an area where the face image is located from the image data corresponding to the three-dimensional character object in different orientations, and extract relevant feature data from the data of the face image, the correlation The feature data includes at least texture feature data of the face image;

Optionally, the first data extracting unit 5202 is further configured to: after determining the area where the face image is located in the image data corresponding to the three-dimensional character object in different orientations, the face image is zoomed, rotated, and stretched. One or more of the processes result in a preset standard size face image.

Since the facial image data feature is an important distinguishing feature, the first data extracting unit 5202 in the present embodiment performs face detection on different image data for different orientations, and determines the location of the face image in the image data of the existing face. The area, and then the location of the key points of the face, such as the center of the eye, the corner of the mouth, the bridge of the nose, etc., due to the different shooting distances and angles selected during the shooting, the size of the head of the corresponding image Angle orientation is also different, so The face region feature data can be extracted by processing the face by zooming and/or rotating and/or stretching to obtain a normal standard face avatar of a preset standard size.

In this embodiment, the manner of extracting the feature data of the face region is not limited. For example, the LBP algorithm (Local Binary Patterns) or the HOG algorithm (Histogram of Oriented Gradient) or Gabor filter may be adopted. The algorithm and the like perform feature extraction of the image. For example, texture feature data, brightness feature data, and the like of the face image are extracted.

The ratio calculating unit 5203 is configured to: distinguish the head, the upper body, the lower body, and the limbs in the image data corresponding to the different orientations of the three-dimensional human object, to correspondingly measure the head, the upper body, and the lower body of the three-dimensional object And the length ratio of the limbs;

In order to make the generated three-dimensional character image more realistic, in addition to extracting the facial feature data of the three-dimensional character, the ratio calculating unit 5203 further determines the head, the upper body, and the lower body in the image data corresponding to the different orientations. And the area where the limbs are located is obtained by correspondingly calculating the length ratios of the head, the upper body, the lower body and the limbs of the three-dimensional object. For example, from the image of the person according to the relative position of the different parts of the human body and the correlation function to distinguish the head, upper body, lower body and limbs of the person, and then according to the pixel coordinates of each part area, such as the maximum coordinate distance, calculate and Determine the length ratio of the head, upper body, lower body and limbs.

If the subject is a human object, since the distinguishing feature of the human body other than the head is not particularly obvious, the length ratio of the head, the upper body, the lower body, and the limbs of the three-dimensional object may not be calculated, and may be performed according to actual needs. Settings.

The second data extracting unit 5204 is configured to: extract other feature data from the image data corresponding to the three-dimensional character object in different orientations, where the other feature data includes at least the hair style feature data, the wearing feature data, and the color feature data. One.

In addition, in order to make the generated three-dimensional character image more realistic, the second data extraction unit 5204 continues to acquire the hairstyle feature data, the wearing feature data, the color feature data, and the like of the captured three-dimensional character object. For example, the combination of edge detection and feature extraction is used to obtain the 360° appearance characteristic data of the three-dimensional character hairstyle; according to the upper body and the lower body region, the feature detection of the three-dimensional character is performed, such as extracting the appearance style of the clothing and the characteristic data such as the main printing. Then, color characteristic data such as hair color, skin color, pupil color, and wearing color of the three-dimensional character can be further extracted. Among them, the extraction method of the feature data is not limited, for example, LBP algorithm (Local Binary Patterns), or HOG algorithm (Histogram of Oriented Gradient), Gabor filter algorithm, etc. perform feature extraction of images.

In this embodiment, in order to make the finally generated three-dimensional character image more realistic, more feature data is extracted from the overall image data of the three-dimensional human object, including distinctive facial feature data and body limb ratio data, Hair styling data, wearing feature data, color characterization data, etc., thereby providing the user with a more playable three-dimensional character image.

Referring to FIG. 5, FIG. 5 is a schematic diagram of a refinement function module of the generation module in FIG. Based on the foregoing embodiment, in this embodiment, the generating module 530 includes:

The model building unit 5301 is configured to: perform three-dimensional reconstruction according to the extracted partial feature data related to the built-in character model in the feature data, to generate a character model corresponding to the captured three-dimensional character object;

Optionally, the model building unit 5301 is configured to: calculate the length, width, height, and limb ratio data of the overall character image in the three-dimensional space by using the obtained length ratios of the head, the upper body, the lower body, and the limbs of the person to generate and The character model corresponding to the three-dimensional character object is captured.

In this embodiment, since the captured panoramic image is a two-dimensional image, in order to obtain a corresponding three-dimensional image, all the two-dimensional feature data extracted before is three-dimensionally reconstructed by the model construction unit 5301, and correspondingly obtained by the ascending dimension processing method. 3D feature data.

In addition, using the obtained length ratios of the head, upper body, lower body, and limbs of the person, the length, width, height, and limb ratio data of the overall figure in the three-dimensional space are calculated for generating and photographing the three-dimensional character object. Corresponding to the preliminary three-dimensional character model.

The model rendering unit 5302 is configured to perform character model rendering according to the extracted other partial feature data related to the character model rendering in the feature data to generate a three-dimensional character image corresponding to the captured three-dimensional character object.

Optionally, the model rendering unit 5302 is further configured to perform splicing processing on the image information of different orientations by using a panoramic stitching fusion technique to generate a three-dimensional character image corresponding to the photographed three-dimensional character object.

In this embodiment, the model rendering unit 5302 performs character model rendering on the preliminary three-dimensional character model obtained by the model building unit 5301, and uses feature data extracted from the corresponding person image data in the panoramic image, such as facial features. Data, hair styling data, wearing feature data, color feature data, etc. are rendered one by one; in addition, panoramic splicing fusion technology may be used to splicing image information of different orientations to finally generate and image the three-dimensional object objects Corresponding 3D characters.

In this embodiment, the rendering using the extracted feature data enables the generated three-dimensional character image to be closer to life than the captured three-dimensional character, thereby bringing a more interesting use experience to the user.

Referring to FIG. 6, FIG. 6 is a schematic diagram of functional modules of a second embodiment of a mobile terminal according to the present invention. In this embodiment, the mobile terminal further includes:

The application association module 540 is configured to: associate the generated three-dimensional character image with an application scenario in the mobile terminal;

The three-dimensional character image display module 550 is configured to display a three-dimensional character image corresponding to the associated application scene on the display screen of the mobile terminal when the associated application scene is in an active state.

In this embodiment, in order to further meet the personalized interaction requirement of the user when using the application, the application association module 540 associates the generated three-dimensional character image with the application scenario in the mobile terminal, for example, the two-dimensional character image of Wang Er and the king. The contact phone number of the second is associated; the three-dimensional character image of Li San is associated with the voice assistant. And displaying, by the three-dimensional character image display module 550, a three-dimensional character image corresponding to the associated application scene on the display screen of the mobile terminal, for example, when receiving the call of Wang Er, displaying the three-dimensional image of Wang Er on the display screen of the mobile terminal Character image; or when the voice assistant is turned on, the three-dimensional character image of Li San is displayed.

In this embodiment, by associating the three-dimensional character image with the application scenario of the built-in application of the mobile terminal, when the corresponding application scenario of the application is activated, the three-dimensional character image related to the application scenario is displayed on the mobile terminal, thereby satisfying the user. Use the application's personalized interaction requirements, such as the ability to give voice to a 3D character, or facial expressions, to provide users with more User-friendly and playable experience.

Referring to FIG. 7, FIG. 7 is a schematic diagram of functional modules of a third embodiment of a mobile terminal according to the present invention. In this embodiment, the mobile terminal further includes:

The shooting module 560 is configured to: start a panoramic shooting mode in the camera application of the mobile terminal to capture and store a panoramic photo of the three-dimensional object, wherein the current detection is performed in real time during the panoramic shooting of the mobile terminal Whether the shooting angle of the mobile terminal is within the set shooting angle range, and if not, a corresponding correction prompt is issued.

Optionally, the shooting module 560 is configured to detect, in real time, whether the shooting angle of the current mobile terminal is within a set shooting angle range by using one or more of a gravity sensor, an attitude sensor, a gyroscope, and a compass. Inside.

In this embodiment, the panoramic shooting module in the camera application is activated by the shooting module 560, and the photographing object (a person or an animal or an item that needs to generate a three-dimensional image) is focused, and then circular motion is started around the photographing object along the same radius distance. Clockwise or counterclockwise can be used until the camera acquires image data of 360° orientation of the subject, as shown in Figure 8.

In this embodiment, considering the related requirements for taking a panoramic photo, for example, there is sufficient overlapping information between images of different angles and orientations acquired at the time of shooting for subsequent splicing processing of the three-dimensional model, and therefore, can be used during shooting. Gravity sensors, attitude sensors, gyroscopes, compasses, etc. monitor the shooting process to determine if the current mobile terminal is in the proper horizontal position. For example, it is determined whether the shooting angle when the mobile terminal moves is within the set shooting angle range, and the user is given a certain voice prompt according to the detection situation. For example, whether the camera moves at a tolerable shooting angle position, whether the angle of rotation of the camera is too large or too small, etc., so that there is sufficient overlapping information between images acquired at different angles and orientations. After the shooting is completed, the shooting module 560 saves the image data of the captured panoramic photo to the mobile terminal to facilitate subsequent generation processing of the three-dimensional image.

Referring to FIG. 9, FIG. 9 is a schematic flowchart diagram of a first embodiment of a method for generating a three-dimensional image according to the present invention. In this implementation, the method is applied to a mobile terminal, and the method for generating the three-dimensional image includes:

Step S10, reading panoramic image data corresponding to the captured panoramic photo of the three-dimensional object;

In addition, the panoramic photo of the three-dimensional object is saved on the mobile terminal or other device after the shooting is completed, and is read when the three-dimensional image generation process is required. The method of reading is not limited, and is set according to actual needs.

Step S20, extracting feature data required to generate a three-dimensional image from the panoramic image data;

In addition, in this embodiment, the method for extracting feature data in an image is not limited, and may be set according to actual needs. For example, the edge detection method is used to extract the three-dimensional object from the environmental background, or the face detection algorithm is used to detect the position of the face and extract the facial texture features of the three-dimensional object.

Step S30, according to the extracted feature data, launch a three-dimensional image engine to generate a three-dimensional image corresponding to the captured three-dimensional object.

In this embodiment, the mobile terminal performs extraction of feature data required to generate a three-dimensional image based on the panoramic photo of the three-dimensional object, and then starts the three-dimensional image engine to generate a corresponding three-dimensional image according to the extracted feature data. The embodiment of the invention can conveniently and quickly generate a three-dimensional image of the captured object, and is convenient for the user to associate with the related application, so as to meet the personalized use requirement of the user, and improve the use. User experience.

Referring to FIG. 10, FIG. 10 is a schematic diagram of the refinement process of step S20. Based on the above embodiment, in the embodiment, the three-dimensional object is taken as a three-dimensional object, and the step S20 includes:

Step S201, extracting overall image data of the three-dimensional human object from the panoramic image data, and calibrating the three-dimensional human object in different orientations in the overall image data;

Optionally, in step S201, extracting the whole image data of the three-dimensional character object from the panoramic image data comprises: using an image edge detection algorithm to distinguish a three-dimensional character from a background environment, and closing the detected determined pixel edge The corresponding image data is extracted to obtain the overall image data of the three-dimensional human object.

In this embodiment, since the panoramic image data obtained by the shooting generally includes the image data of the three-dimensional human object and the image data of the environment in which the human object is located, the overall image data of the three-dimensional human object is taken from the environment image thereof. Extracted and processed separately. In addition, since the overall image data of the three-dimensional human object includes image data of different orientations of the three-dimensional human object, the three-dimensional human objects of different orientations in the overall image data of the three-dimensional human object are uniformly calibrated for distinguishing.

Step S202, extracting from the image data corresponding to the three-dimensional character object in different orientations Face image data, and extracting related feature data from the face image data, the related feature data including at least texture feature data of the face image;

Optionally, in step S202, after determining, according to the image data corresponding to the different orientations, the image of the face image, the method further includes: converting the face image by one of zooming, rotating, and stretching One or more kinds of processing to obtain a preset standard size face image.

Since the facial image data feature is an important distinguishing feature, in this embodiment, the face detection is performed on all the image data in different directions, and the location area of the face image in the image data of the face is determined, and then Positioning the key points of the face on the basis, such as the center of the eye, the corner of the mouth, the bridge of the nose, etc., due to the different shooting distances and angles selected during the shooting, the head size and angle orientation of the characters in the corresponding images are also different. Therefore, the facial region feature data can be extracted by processing the face by scaling and/or rotating and/or stretching to obtain a preset standard size normal face avatar.

Step S203, distinguishing between the head, the upper body, the lower body, and the limbs in the image data corresponding to the different orientations of the three-dimensional human object, to correspondingly calculate the length ratio of the head, the upper body, the lower body, and the limbs of the three-dimensional object. ;

In order to make the generated three-dimensional character image more realistic, in addition to extracting the facial feature data of the three-dimensional character, the embodiment further determines the head, the upper body, the lower body and the limbs in the image data corresponding to the different orientations. Correspondingly, the length ratios of the head, upper body, lower body and limbs of different three-dimensional object objects are obtained. For example, from the image of the person according to the relative position of the different parts of the human body and the correlation function to distinguish the head, upper body, lower body and limbs of the person, and then according to the pixel coordinates of each part area, such as the maximum coordinate distance, calculate and Determine the length ratio of the head, upper body, lower body and limbs.

Step S204, extracting other feature data from the image data corresponding to the three-dimensional character object in different orientations, the other feature data including at least one of hairstyle feature data, wearing feature data, and color feature data.

In addition, in order to make the generated three-dimensional character image more realistic, in this embodiment, the hairstyle feature data, the wearing feature data, the color feature data, and the like of the captured three-dimensional character object are further acquired. For example, the combination of edge detection and feature extraction is used to obtain the 360° appearance characteristic data of the three-dimensional character hairstyle; according to the upper body and the lower body region, the feature detection of the three-dimensional character is performed, such as extracting the appearance style of the clothing and the characteristic data such as the main printing. Then, color characteristic data such as hair color, skin color, pupil color, and wearing color of the three-dimensional character can be further extracted. Among them, the extraction method of the feature data is not limited, for example, the LBP algorithm (Local Binary Patterns), or the HOG algorithm (Histogram of Oriented Gradient), the Gabor filter algorithm, etc. extract.

In this embodiment, the execution order of the above steps S202, S203, and S204 is not limited. In order to make the final generated three-dimensional character image more realistic, more feature data is extracted from the overall image data of the three-dimensional character object, including distinctive facial feature data and body limb ratio data, hair style characteristic data, wearing Feature data, color feature data, etc., to provide users with more playable 3D characters.

Referring to FIG. 11, FIG. 11 is a schematic flowchart of the refinement of step S30. Based on the above embodiment, in the embodiment, the foregoing step S30 includes:

Step S301, performing three-dimensional reconstruction according to the extracted partial feature data related to the constructing character model in the feature data, to generate a character model corresponding to the captured three-dimensional character object;

Optionally, step S301 includes: calculating, by using the obtained length ratios of the head, the upper body, the lower body, and the limbs of the person, the length, width, height, and limb ratio data of the overall character in the three-dimensional space to generate and photograph the said A character model corresponding to a three-dimensional character object.

In this embodiment, since the captured panoramic image is a two-dimensional image, in order to obtain a corresponding three-dimensional image, three-dimensional reconstruction is performed on all the two-dimensional feature data extracted before, and the processing is performed in an ascending dimension. The corresponding three-dimensional feature data is obtained.

Step S302: Perform character model rendering according to the extracted other feature data related to the character model rendering in the feature data to generate a three-dimensional character image corresponding to the captured three-dimensional character object.

Optionally, the step S302 may further include: performing splicing processing on the image information of different orientations by using a panoramic stitching fusion technology to generate a three-dimensional character image corresponding to the photographed three-dimensional character object.

In this embodiment, the character model is rendered on the obtained preliminary three-dimensional character model, and the feature data extracted from the corresponding person image data in the panoramic image, such as facial feature data, hair styling data, wearing feature data, and color features, is used. Data and the like are rendered one by one; in addition, the panoramic stitching fusion technology may be used to splicing the image information of different orientations, thereby finally generating a three-dimensional character image corresponding to the photographed three-dimensional character object.

Referring to FIG. 12, FIG. 12 is a schematic flowchart diagram of a second embodiment of a method for generating a three-dimensional image according to the present invention. Based on the above embodiment, in this implementation, after the step S30, the method further includes:

Step S40: associate the generated three-dimensional character image with an application scenario in the mobile terminal;

In step S50, when the associated application scenario is in an active state, a three-dimensional character image corresponding to the associated application scenario is displayed on the display screen of the mobile terminal.

In this embodiment, in order to further satisfy the personalized interaction requirement of the user when using the application, the generated three-dimensional character image is associated with the application scenario in the mobile terminal, for example, the two-dimensional character image of Wang Er is related to the contact phone number of Wang Er. Link; the three-dimensional character image of Li San is related to the voice assistant Union. And displaying a three-dimensional character image corresponding to the associated application scene on the display screen of the mobile terminal, for example, when receiving the call of Wang Er, displaying the three-dimensional character image of Wang Er on the display screen of the mobile terminal; or opening the voice assistant At the time, Li San’s three-dimensional figure is displayed.

In this embodiment, by associating the three-dimensional character image with the application scenario of the built-in application of the mobile terminal, when the corresponding application scenario of the application is activated, the three-dimensional character image related to the application scenario is displayed on the mobile terminal, thereby satisfying the user. Use the application's personalized interaction requirements, such as the ability to give voice functions to three-dimensional characters, or facial expressions, to provide users with a more user-friendly and playable experience.

Referring to FIG. 13, FIG. 13 is a schematic flowchart diagram of a third embodiment of a method for generating a three-dimensional image according to the present invention. Based on the foregoing embodiment, in this implementation, before step S10, the method further includes:

Step S01, starting a panoramic shooting mode in the camera application of the mobile terminal to capture and store a panoramic photo of the three-dimensional object, wherein in the panoramic shooting process of the mobile terminal, detecting the current shooting of the mobile terminal in real time Whether the angle is within the set shooting angle range. If not, the corresponding correction prompt is issued.

Optionally, in step S01, by using one or more of a gravity sensor, an attitude sensor, a gyroscope, and a compass, it is detected in real time whether the shooting angle of the current mobile terminal is within a set shooting angle range.

In this embodiment, the panoramic shooting module in the camera application is activated, and the photographing object (a character or an animal or an item that needs to generate a three-dimensional image) is focused, and then circular motion is started around the photographing object along the same radius distance, clockwise or inverse The hour hand can be used until the camera acquires the image data of the 360° orientation of the photographing object, and the process is as shown in FIG. 8 .

In this embodiment, considering the related requirements for taking a panoramic photo, for example, there is sufficient overlapping information between images of different angles and orientations acquired at the time of shooting for subsequent splicing processing of the three-dimensional model, and therefore, can be used during shooting. Gravity sensors, attitude sensors, gyroscopes, compasses, etc. monitor the shooting process to determine if the current mobile terminal is in the proper horizontal position. For example, it is determined that the shooting angle when the mobile terminal moves is within the set shooting angle range, and the user is given a certain voice prompt according to the detection situation. For example: whether the camera is moving in a tolerable shot Whether the angle of the camera is rotated, whether the angle of rotation of the camera is too large or too small, etc., so that there is sufficient overlapping information between the acquired images of different angles and orientations. After the shooting is completed, the image data of the captured panoramic photo is saved in the mobile terminal to facilitate subsequent generation processing of the three-dimensional image.

The embodiment of the invention further provides a computer readable storage medium storing computer executable instructions, which are implemented by the processor to implement the method for generating the three-dimensional image.

The above is only an alternative embodiment of the present invention, and thus does not limit the scope of the patent application, and the equivalent structure or equivalent process transformation made by the specification and the drawings of the present application, or directly or indirectly applied to other related technologies. The fields are all included in the scope of patent protection of this application.

Industrial applicability

The embodiment of the invention can conveniently and quickly generate a three-dimensional image of the captured object, and facilitate the user to associate with the related application, thereby satisfying the personalized use requirement of the user and improving the user experience.

Claims

A mobile terminal includes:

a reading module configured to: read panoramic image data corresponding to the panoramic photo of the captured three-dimensional object;

An extraction module, configured to: extract feature data required to generate a three-dimensional image from the panoramic image data;

And generating a module, configured to: according to the extracted feature data, activate a three-dimensional image engine to generate a three-dimensional image corresponding to the captured three-dimensional object.
The mobile terminal of claim 1, wherein the three-dimensional object is a three-dimensional character object; the extraction module comprises:

a pre-processing unit, configured to: extract overall image data of the three-dimensional human object from the panoramic image data, and calibrate the three-dimensional human object in different orientations in the overall image data;

The first data extracting unit is configured to: determine an area where the face image is located from the image data corresponding to the three-dimensional character object in different orientations, and extract relevant feature data from the data of the face image, the related feature The data includes texture feature data of the face image;

The ratio calculating unit is configured to: distinguish the head, the upper body, the lower body, and the limbs in the image data corresponding to the different orientations of the three-dimensional human object, to correspondingly measure the head, the upper body, the lower body of the three-dimensional object and The length ratio of the limbs;

The second data extracting unit is configured to extract other feature data from the image data corresponding to the three-dimensional character object in different orientations, the other feature data including at least one of hairstyle feature data, wearing feature data, and color feature data. Kind.
The mobile terminal of claim 2, wherein

The preprocessing unit is configured to: use an image edge detection algorithm to distinguish the three-dimensional character from the background environment, and extract image data corresponding to the detected determined pixel edge to obtain overall image data of the three-dimensional human object.
The mobile terminal of claim 2, wherein

The first data extracting unit is further configured to: after determining the area where the face image is located in the image data corresponding to the different orientation of the three-dimensional human object, the face image is subjected to one of zooming, rotating, and stretching Or a plurality of processes to obtain a preset standard size face image.
The mobile terminal of claim 2, wherein the generating module comprises:

a model building unit, configured to: perform three-dimensional reconstruction according to the extracted partial feature data related to the constructing character model in the feature data, to generate a character model corresponding to the captured three-dimensional character object;

The model rendering unit is configured to: perform a character model rendering according to the extracted other part of the feature data related to the character model rendering to generate a three-dimensional character image corresponding to the captured three-dimensional character object.
The mobile terminal of claim 5, wherein

The model building unit is configured to: calculate the length, width, height, and limb ratio data of the overall character in the three-dimensional space by using the obtained ratio of the length of the head, the upper body, the lower body, and the limbs to generate and photograph the image. A character model corresponding to a three-dimensional character object.
The mobile terminal of claim 5, wherein

The model rendering unit is further configured to perform splicing processing of image information of different orientations by using a panoramic stitching fusion technique to generate a three-dimensional character image corresponding to the photographed three-dimensional character object.
The mobile terminal of claim 5, the mobile terminal further comprising:

The application association module is configured to: associate the generated three-dimensional character image with an application scenario in the mobile terminal;

The three-dimensional character image display module is configured to: when the associated application scene is in an active state, display a three-dimensional character image corresponding to the associated application scene on a display screen of the mobile terminal.
The mobile terminal according to any one of claims 1 to 8, the mobile terminal further comprising:

a shooting module, configured to: activate a panoramic shooting mode in a camera application of the mobile terminal to capture and store a panoramic photo of the three-dimensional object, wherein the current movement is detected in real time during the panoramic shooting of the mobile terminal Is the shooting angle of the terminal at the set shooting angle? Within the scope, if no, the corresponding correction prompt is issued.
The mobile terminal of claim 9, wherein

The photographing module is configured to detect, in real time, whether the photographing angle of the current mobile terminal is within a set photographing angle range by using one or more of a gravity sensor, an attitude sensor, a gyroscope, and a compass.
A method for generating a three-dimensional image is applied to a mobile terminal, and the method for generating the three-dimensional image includes:

Reading panoramic image data corresponding to the panoramic photo of the captured three-dimensional object;

Extracting feature data required to generate a three-dimensional image from the panoramic image data;

Based on the extracted feature data, a three-dimensional image engine is launched to generate a three-dimensional image corresponding to the captured three-dimensional object.
The method for generating a three-dimensional image according to claim 11, wherein the three-dimensional object is a three-dimensional object object; and extracting feature data required for generating a three-dimensional image from the panoramic image data comprises:

Extracting overall image data of the three-dimensional human object from the panoramic image data, and calibrating the three-dimensional human object in different orientations in the overall image data;

Determining, from the image data corresponding to the three-dimensional character object in different orientations, an area of the face image, and extracting relevant feature data from the data of the face image, the related feature data including texture feature data of the face image ;

Distinguishing between the head, the upper body, the lower body, and the limbs in the image data corresponding to the different orientations of the three-dimensional character object, to correspondingly calculate the length ratios of the head, the upper body, the lower body, and the limbs of the three-dimensional object;

The other feature data is extracted from the image data corresponding to the three-dimensional character object in different orientations, the other feature data including at least one of hairstyle feature data, wearing feature data, and color feature data.
The method for generating a three-dimensional image according to claim 12, wherein the extracting the overall image data of the three-dimensional human object from the panoramic image data comprises:

The image edge detection algorithm is used to distinguish the three-dimensional character from the background environment, and the image data corresponding to the detected determined pixel edge is extracted, and the overall image data of the three-dimensional character object is obtained.
The method for generating a three-dimensional image according to claim 12, wherein the determining, after the image of the face image from the image data corresponding to the different orientations of the three-dimensional character object, further comprises:

The face image is processed by one or more of zooming, rotating, and stretching to obtain a preset standard size face image.
The method for generating a three-dimensional image according to claim 12, wherein the initiating the three-dimensional image engine to generate the three-dimensional image corresponding to the captured three-dimensional object according to the extracted feature data comprises:

And performing three-dimensional reconstruction according to the extracted partial feature data related to the constructing character model in the feature data to generate a character model corresponding to the captured three-dimensional character object;

Character model rendering is performed according to the extracted other feature data related to the character model rendering in the feature data to generate a three-dimensional character image corresponding to the captured three-dimensional character object.
The method for generating a three-dimensional image according to claim 15, wherein said three-dimensional reconstruction is performed based on part of feature data related to a constructed character model among said extracted feature data, to generate said three-dimensional character object with said image The corresponding character models include:

Calculating the length, width, height and limb ratio data of the overall character in the three-dimensional space by using the obtained length ratios of the head, upper body, lower body and limbs of the person to generate a character model corresponding to the captured three-dimensional object .
The method for generating a three-dimensional image according to claim 15, wherein said three-dimensional reconstruction is performed based on part of feature data related to a constructed character model among said extracted feature data, to generate said three-dimensional character object with said image After the corresponding character model, it also includes:

The image information of different orientations is spliced by a panoramic stitching fusion technique to generate a three-dimensional character image corresponding to the captured three-dimensional character object.
A method of generating a three-dimensional image according to claim 15, wherein said And taking the feature data, after starting the three-dimensional image engine to generate a three-dimensional image corresponding to the captured three-dimensional object, the method further includes:

Associating the generated three-dimensional character image with an application scenario in the mobile terminal;

When the associated application scenario is in an active state, a three-dimensional character image corresponding to the associated application scenario is displayed on a display screen of the mobile terminal.
The method for generating a three-dimensional image according to any one of claims 11 to 18, wherein the reading of the panoramic image data corresponding to the panoramic photo of the captured three-dimensional object further comprises:

Activating a panoramic photographing mode in the camera application of the mobile terminal to capture and store a panoramic photo of the three-dimensional object, wherein during the panoramic photographing process, the mobile terminal detects whether the current shooting angle of the mobile terminal is in real time Within the set shooting angle range, if no, the corresponding correction prompt is issued.
The method for generating a three-dimensional image according to claim 19, wherein the real-time detecting whether the shooting angle of the current mobile terminal is within a set shooting angle range comprises:

By using one or more of a gravity sensor, an attitude sensor, a gyroscope, and a compass, it is detected in real time whether the shooting angle of the current mobile terminal is within a set shooting angle range.