WO2016173073A1 - 一种基于双摄像头的三维建模方法及装置 - Google Patents
一种基于双摄像头的三维建模方法及装置 Download PDFInfo
- Publication number
- WO2016173073A1 WO2016173073A1 PCT/CN2015/080316 CN2015080316W WO2016173073A1 WO 2016173073 A1 WO2016173073 A1 WO 2016173073A1 CN 2015080316 W CN2015080316 W CN 2015080316W WO 2016173073 A1 WO2016173073 A1 WO 2016173073A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- dimensional
- distance
- target object
- dual camera
- hairstyle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three-dimensional [3D] modelling for computer graphics
Definitions
- the present invention relates to the field of mobile communications, and in particular to a three-dimensional modeling method and apparatus based on dual cameras.
- the mobile phone industry is developing rapidly, and the mobile phone dual camera will continue to enter the public's field of vision. Combined with the characteristics and development trend of the dual camera, it can easily construct three-dimensional images.
- related software and technology for 3D hair design and 3D clothing design are becoming more and more mature, such as Marvelous Designer clothing design software and Hair Pro 7.0light hair design software, which are used by many professional and non-professionals.
- the present invention provides a three-dimensional modeling method and apparatus based on dual cameras to solve the above technical problems.
- the present invention provides a dual camera based three-dimensional model construction method, wherein the method comprises: capturing a two-dimensional picture for a target object by using a dual camera; and having an X-axis and a Y based on the two-dimensional picture setting Two-dimensional coordinates of the axis; measuring the object distance using a dual camera; The object distance is a horizontal distance from the target object to the plane of the camera; and based on the object distance and the two-dimensional coordinates, a three-dimensional coordinate system having an X-axis Y-axis Z-axis with an intermediate point of the dual camera as an origin; The dual camera performs at least three-dimensional image acquisition on the front, left side, back, and right side of the target object to construct a three-dimensional model.
- setting a three-dimensional coordinate system based on the object distance and the two-dimensional coordinates comprises: selecting a plurality of target pixel points on the target object in the two-dimensional image based on the two-dimensional coordinates, and determining a target pixel
- the two-dimensional coordinates of the point (X0, Y0); according to the object distance L, the two-dimensional coordinates (X0, Y0), and the formula L ⁇ 2 X0 ⁇ 2+Y0 ⁇ 2+Z0 ⁇ 2, the target pixel is calculated.
- Three-dimensional coordinates (X0, Y0, Z0); based on the three-dimensional coordinates of the plurality of target pixel points, a three-dimensional coordinate system having an X-axis Y-axis and an Z-axis with an intermediate point of the dual camera as an origin.
- performing at least three-dimensional image acquisition on the front, left side, back, and right side of the target object includes: calculating a vertical distance Lz of the body center line of the target object and the dual camera plane Min(Z0)+maximum thickness of body part/2; wherein min(Z0) is the smallest value of Z0 in the three-dimensional coordinates of the plurality of target pixel points; using the Lz and the built-in gyroscope of the terminal to target
- the human body center line of the object is an axis, and the user is guided to use the dual camera around the target object to perform image capturing on at least the front, left side, back, and right side faces of the target object.
- the method further comprises: determining a appearance feature and a dress style of the target object based on the three-dimensional model, and combining the hairstyle and the dressing database to match the fit The hairstyle and clothing of the target object; the matched hairstyle and clothing are combined with the three-dimensional model and presented to the user.
- the method further includes: providing a user design interface; wherein the user design interface is an interface for a user to perform a hairstyle and a clothing design operation for the three-dimensional model; The hair and clothing of the model design are combined with the three-dimensional model and presented to the user.
- the present invention provides a dual camera-based three-dimensional model construction apparatus, wherein the apparatus includes: a measurement module for capturing a two-dimensional picture for a target object by using a dual camera; setting based on the two-dimensional picture Having two-dimensional coordinates of the X-axis and the Y-axis; measuring the object distance by using a dual camera; wherein the object distance is a horizontal distance of the target object to the plane of the camera; a three-dimensional coordinate building module for determining the object distance based on the object distance Dimension coordinates, a three-dimensional coordinate system having an X-axis Y-axis Z-axis with an intermediate point of the dual camera as an origin, and a model building module for utilizing the dual camera, at least the front and left sides of the target object, Three-dimensional image acquisition is performed on the back and right sides to construct a three-dimensional model.
- the target object performs image capturing on at least the front, left side, rear, and right side faces of the target object by the dual camera.
- the device further includes: a first dress design module, configured to determine an appearance feature and a dress style of the target object based on the three-dimensional model, and combine a hairstyle and a dressing database to match a hairstyle suitable for the target object and a garment; the matched hairstyle and the garment are combined with the three-dimensional model and displayed to the user; or the second dress design module is configured to provide a user design interface; wherein the user design interface is the user The three-dimensional model performs an interface between the hairstyle and the garment design operation; the hairstyle and the garment designed by the user for the three-dimensional model are combined with the three-dimensional model and displayed to the user.
- a first dress design module configured to determine an appearance feature and a dress style of the target object based on the three-dimensional model, and combine a hairstyle and a dressing database to match a hairstyle suitable for the target object and a garment; the matched hairstyle and the garment are combined with the three-dimensional model and displayed to the user; or the second dress design module is configured to provide a user design
- the present invention provides a three-dimensional dressing method for a terminal having a dual camera, wherein the method includes: at least facing the front, left side, and rear of the target object according to the prompt information of the terminal interface Shooting on the right side to construct a three-dimensional model; dressing the hairstyle and clothing on the three-dimensional model.
- performing the hairstyle and the costume on the three-dimensional model comprises: combining a hairstyle and a dressing database, selecting a hairstyle and a garment suitable for the target object; and combining the selected hairstyle and the garment with the three-dimensional model , displayed on the terminal interface.
- performing the hairstyle and the costume on the three-dimensional model comprises: providing a user design interface; wherein the user design interface is an interface for the user to perform a hairstyle and a clothing design operation for the three-dimensional model; The three-dimensional model of the hairstyle and clothing, combined with the three-dimensional model, Displayed on the terminal interface.
- FIG. 1 is a flow chart of a three-dimensional modeling method based on dual cameras according to a first embodiment of the present invention
- FIG. 2 is a schematic plan view of a photographing plane according to a second embodiment of the present invention.
- FIG. 3 is a schematic perspective view of a photograph according to a second embodiment of the present invention.
- FIG. 4 is a schematic diagram of three-dimensional coordinates according to a second embodiment of the present invention.
- Figure 5 is a schematic view of a center line of a human body according to a second embodiment of the present invention.
- FIG. 6 is a flowchart of a three-dimensional dressing method according to Embodiment 3 of the present invention.
- FIG. 7 is a flow chart of a hairstyle dressing of a three-dimensional model according to Embodiment 4 of the present invention.
- FIG. 8 is a structural block diagram of a dual camera based three-dimensional model constructing apparatus according to a fifth embodiment of the present invention.
- the present invention provides a three-dimensional modeling method and device based on dual cameras, which are described below with reference to the drawings and The invention will be further described in detail by way of examples. It is understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
- FIG. 1 is a flow chart of a three-dimensional modeling method based on dual cameras. As shown in FIG. 1, the method includes (step S102 - step S106):
- Step S102 using a dual camera to capture a two-dimensional picture for the target object; setting two-dimensional coordinates having an X-axis and a Y-axis based on the two-dimensional picture; measuring the object distance by using the dual camera; wherein the object distance is the target object to the camera plane Horizontal distance;
- Step S104 based on the object distance and the two-dimensional coordinates, a three-dimensional coordinate system having an X-axis Y-axis Z-axis with an intermediate point of the dual camera as an origin;
- step S106 the three-dimensional image is collected on at least the front surface, the left side surface, the rear surface, and the right side surface of the target object by using the dual camera to construct a three-dimensional model.
- x1 is a projection point of the target object on the first sensor, a distance from a center point of the first sensor
- x2 is a target object on the second sensor a projection point, a distance from a center point of the second sensor
- the first sensor corresponds to one of the dual cameras
- the second sensor corresponds to another camera of the dual camera
- f is the distance from the equivalent center of the dual camera to the sensor
- d is the distance between the center points of the two sensors.
- the intermediate point of the dual camera is the origin, and the three-dimensional coordinate system with the X-axis Y-axis and the Z-axis.
- the human body center line is an axis, and the user is guided to use the above-mentioned dual camera around the target object to perform image capturing on at least the front, left side, back, and right side faces of the target object.
- the method of the embodiment further includes: determining a appearance feature and a dressing style of the target object based on the three-dimensional model, and combining a hair style and a dressing database to match a hairstyle and a clothing suitable for the target object; The above hairstyles and garments are combined with the above three-dimensional model and presented to the user.
- the user design interface is an interface for the user to perform a hairstyle and a clothing design operation for the three-dimensional model; and the hairstyle and the clothing designed by the user for the three-dimensional model are integrated with the three-dimensional model and displayed to the user.
- the main processes of the technical solution of the embodiment are divided into: A, obtaining a three-dimensional model of the target human body, B, performing hair style and clothing recommendation or design on the three-dimensional model.
- the technical solutions mainly include:
- the three-dimensional coordinates of the pixel points of various parts of the human body are acquired, and the three-dimensional model of the target human body is constructed by three-dimensional coordinates
- a two-dimensional picture can be obtained by using a common single camera, and the two-dimensional coordinate (X, Y) characteristic of the pixel can be obtained relatively easily according to the pixel size information.
- the dual camera can also get the coordinates of the (X, Y) point.
- the object distance L is obtained, that is, the target object to the camera plane.
- the horizontal distance. Dual camera ranging can be used. The specific method is as follows:
- X1 the projection point of the target object on the first sensor, the distance from the center point of the first sensor,
- X2 the projection point of the target object on the second sensor, the distance from the center point of the second sensor,
- d the distance between the center points of the two sensors.
- the object distance L can be calculated.
- FIG. 3 is a schematic diagram of a three-dimensional coordinate diagram shown in FIG. 3, as shown in FIG. 3 and FIG. 4, a three-dimensional coordinate system is established with the center of the dual camera as an origin, and the object distance L is obtained by using a dual camera ranging, and L is utilized.
- the Lz will correct the side body width value according to the 3D model of the target human side double camera.
- the center line of the human body (the center line diagram of the human body as shown in FIG. 5) is taken as the center, and the mode similar to the panoramic photograph is combined to guide the user at least on the front side of the target object in the mobile phone interface.
- the three-dimensional image acquisition of the dual camera is performed, and the three-dimensional coordinates of each pixel of the four faces of the human body with the center of the camera as the origin are obtained. Finally, the three-dimensional coordinates of the four face pixels are correspondingly converted.
- the three-dimensional image on the left side is rotated to the left by 90 degrees and shifted to the left by a certain distance.
- the three-dimensional image on the right side is oriented. Rotate right 90 degrees and offset to the right by a certain distance; the back three-dimensional image is rotated 180 degrees and offset backward by a certain distance, and finally four
- the three-dimensional images of the faces are spliced into a complete three-dimensional model of the target human body.
- the human body is in a straight state and is perpendicular to the ground plane.
- the dual camera ranging and existing face recognition technology are mainly used to make the target human body symmetrical in front of the center of the dual camera, that is, the human body center line is coplanar with the vertical center line of the dual camera.
- the whole body is presented in the camera scene, that is, the head is in the upper edge of the photo frame, and the foot is in the lower edge of the photo frame.
- the system After acquiring the 3D model and skin color information of the human body, the system can enter two modes: hairstyle and dressing expert recommendation mode, hairstyle and dressing personal design mode.
- the system extracts the human body shape and skin color from the three-dimensional model of the human body, combines the user's personal style, and various human body hair style clothing and related data information provided by professional hair stylists and fashion designers to obtain various hair styles suitable for the target human body. And dress up.
- the user can individually design the hairstyle and dress of the target human body three-dimensional model.
- the system has various common hairstyles and dress models.
- the system data is saved, including the storage of the target human body three-dimensional model, hair style and dressing data, which is convenient for direct call later.
- FIG. 6 is a flowchart of a three-dimensional dressing method. As shown in FIG. 6, the method includes (step S602 - step S604):
- Step S602 according to the prompt information of the terminal interface, at least the front, left side, back, and right side of the target object are photographed to construct a three-dimensional model;
- Step S604 the hairstyle and the costume are dressed for the three-dimensional model.
- this step There are at least two implementations of this step:
- Combining the hairstyle and dressing database selecting a hairstyle and a garment suitable for the above-mentioned target object; combining the selected hairstyle and the garment with the above-mentioned three-dimensional model and displaying on the terminal interface; or
- the user design interface is an interface for the user to perform a hairstyle and a clothing design operation for the three-dimensional model; and the hairstyle and the clothing designed by the user for the three-dimensional model are integrated with the three-dimensional model and displayed on the terminal interface.
- the hairstyle and dressing APP can be set in the terminal interface, and the hairstyle and the dressing interface are accessed by clicking the APP, thereby facilitating the user to perform the above two implementation modes.
- FIG. 7 is a flow chart of a three-dimensional model, as shown in FIG. 7, the process includes:
- step S701 the hairstyle and dressing recommendation and design application are entered.
- step S702 it is determined whether the target human body has a corresponding three-dimensional model. If not, step S704 is performed, and if yes, step S703 is performed.
- Step S703 introducing a three-dimensional model of the target human body from the system. Then step S707 is performed.
- Step S704 entering a camera framing interface.
- step S705 the mobile phone interface guides the user, and the target human body is directly in front of the center of the dual camera.
- Step S706 guiding the user to perform three-dimensional image acquisition on the front, back, left, and right sides of the target human body, and splicing the three-dimensional model of the human body.
- step S707 a three-dimensional model of the target human body is obtained.
- Step S708 whether the expert recommendation mode is selected, if yes, step S709 is performed, and if no, step S710 is performed.
- step S709 the hairstyle and the dress suitable for the target human body are automatically displayed. Then step S711 is performed.
- step S710 the personal design mode is entered.
- step S711 the data is saved.
- FIG. 8 is a structural block diagram of a three-dimensional model building device based on dual cameras. As shown in FIG. 8, the device includes:
- the measuring module 10 is configured to capture a two-dimensional picture for the target object by using the dual camera; set two-dimensional coordinates having an X-axis and a Y-axis based on the two-dimensional picture; and measure the object distance by using the dual camera; wherein the object distance is the target object The horizontal distance of the camera plane;
- the three-dimensional coordinate building module 20 is configured to set a three-dimensional coordinate system having an X-axis Y-axis Z-axis with an intermediate point of the dual camera as an origin based on the object distance and the two-dimensional coordinates;
- the model building module 30 is configured to perform three-dimensional image acquisition on at least the front, left side, back, and right sides of the target object by using the dual camera to construct a three-dimensional model.
- the above measurement module 10 comprises:
- a first measuring unit configured to acquire a first position distance x1 and a second position distance x2; wherein x1 is a projection point of the target object on the first sensor, and a distance from a center point of the first sensor; the above x2 is a projection point of the target object on the second sensor, a distance from a center point of the second sensor; the first sensor corresponds to one camera of the dual camera, and the second sensor corresponds to another camera of the dual camera;
- the three-dimensional coordinate building module 20 includes:
- a first building unit configured to select a plurality of target pixel points on the target object in the two-dimensional image based on the two-dimensional coordinates, and determine a two-dimensional coordinate (X0, Y0) of the target pixel point;
- the third building unit is configured to set a three-dimensional coordinate system having an X-axis Y-axis Z-axis with an intermediate point of the dual camera as an origin based on the three-dimensional coordinates of the plurality of target pixel points.
- the above model building module 30 includes:
- the three-dimensional imaging unit is configured to use the above-mentioned Lz and a gyroscope built in the terminal to guide the user to use the dual camera around the target object with the center line of the target object as an axis, at least to the front, left side, and back of the target object. Image capture on the right side.
- the present embodiment provides two preferred embodiments, that is, the foregoing apparatus further includes:
- a first dress design module configured to determine an appearance feature and a dress style of the target object based on the three-dimensional model, and combine a hair style and a dressing database to match a hairstyle and a clothing suitable for the target object; and the matching the hairstyle and the clothing and the above
- the three-dimensional model is integrated and presented to the user; or,
- the second dressing design module is configured to provide a user design interface; wherein the user design interface is an interface for the user to perform the hairstyle and the clothing design operation for the three-dimensional model; the hairstyle and the clothing designed by the user for the three-dimensional model, and the three-dimensional model described above Converged and presented to the user.
- the present invention provides a three-dimensional hairstyle and dress recommendation and design of the dual camera, which enables the user to carry out his own hairstyle and dress design and obtain professional recommendation, and is more entertaining and practical, in line with the increasing demand of people. . Improve user experience and increase mobile phone selling points.
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Processing Or Creating Images (AREA)
- Image Processing (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
提供了一种基于双摄像头的三维建模方法及装置。本发明提供双摄像头的三维发型与装扮推荐与设计,有效地解决了现有技术中三维发型和服装设计的灵活性和通用性不够的问题,可以使用户进行自身发型和装扮设计以及获得专业人士的推荐,且娱乐性和实用性较大,符合人们日益增长需求。提升用户体验,增加手机卖点。
Description
本申请要求于2015年04月28日提交中国专利局,申请号为CN 201510209458.2、发明名称为“一种基于双摄像头的三维建模方法及装置”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
本发明涉及移动通讯领域,特别是涉及一种基于双摄像头的三维建模方法及装置。
目前手机行业发展迅速,手机双摄像头也将不断进入大众视野,结合双摄像头特点和发展趋势,其能较为容易的构建三维图像。同时,三维发型设计和三维服装设计的相关软件和技术也越来越成熟,如:Marvelous Designer服装设计软件和Hair Pro 7.0light发型设计软件等被众多专业和非专业人士使用。
针对三维发型设计和三维服装设计,对具体个人三维模型的建立上比较复杂,需对各个方面的参数进行设置,精度上也比较低,且大都只能依赖电脑进行相关设计,灵活性和通用性不够。
针对相关技术中三维发型和服装设计的灵活性和通用性不够的问题,目前尚未提出有效的解决方案。
发明内容
针对相关技术中三维发型和服装设计的灵活性和通用性不够的问题,本发明提供了一种基于双摄像头的三维建模方法及装置,用以解决上述技术问题。
根据本发明的一个方面,本发明提供了一种基于双摄像头的三维模型构建方法,其中,该方法包括:利用双摄像头针对目标对象拍摄二维图片;基于该二维图片设置具备X轴和Y轴的二维坐标;利用双摄像头测量物距;其中,
所述物距是目标对象到摄像头平面的水平距离;基于所述物距以及所述二维坐标,设置以双摄像头的中间点为原点、具备X轴Y轴Z轴的三维坐标系;利用所述双摄像头,至少对所述目标对象的正面、左侧面、后面、右侧面进行三维图像采集,构建三维模型。
优选地,利用双摄像头测量物距,包括:获取第一位置距离x1和第二位置距离x2;其中,所述x1是目标对象在第一传感器上的投影点,与所述第一传感器的中心点的距离;所述x2是目标对象在第二传感器上的投影点,与所述第二传感器的中心点的距离;所述第一传感器对应于双摄像头中的一个摄像头,所述第二传感器对应于双摄像头中的另一个摄像头;基于公式:x1/f=x/L和x2/f=(x+d)/L,计算得到物距L;其中,f为双摄像头的等效中心到传感器的距离,d为第一传感器和第二传感器的中心点的距离。
优选地,基于所述物距以及所述二维坐标,设置三维坐标系,包括:基于所述二维坐标,在所述二维图片中选取目标对象上的多个目标像素点,确定目标像素点的二维坐标(X0,Y0);根据所述物距L,二维坐标(X0,Y0),以及公式L^2=X0^2+Y0^2+Z0^2,计算得到目标像素点的三维坐标(X0,Y0,Z0);基于所述多个目标像素点的三维坐标,设置以双摄像头的中间点为原点、具备X轴Y轴Z轴的三维坐标系。
优选地,利用所述双摄像头,至少对所述目标对象的正面、左侧面、后面、右侧面进行三维图像采集,包括:计算目标对象的人体中心线与双摄像头平面的垂直距离Lz=min(Z0)+人体部位最大厚度/2;其中,所述min(Z0)为所述多个目标像素点的三维坐标中数值最小的Z0;利用所述Lz以及终端内置的陀螺仪,以目标对象的人体中心线为轴,引导用户围绕所述目标对象利用所述双摄像头,至少对所述目标对象的正面、左侧面、后面、右侧面进行图像拍摄。
优选地,构建所述三维模型之后,所述方法还包括:基于所述三维模型确定所述目标对象的外表特征和着装风格,结合发型与装扮数据库,匹配出适合
所述目标对象的发型和服装;将匹配出的所述发型和服装与所述三维模型相融合,展示给用户。
优选地,构建所述三维模型之后,所述方法还包括:提供用户设计界面;其中,所述用户设计界面是用户为所述三维模型进行发型与服装设计操作的界面;将用户为所述三维模型设计的发型与服装,与所述三维模型相融合,展示给用户。
根据本发明的一个方面,本发明提供了一种基于双摄像头的三维模型构建装置,其中,该装置包括:测量模块,用于利用双摄像头针对目标对象拍摄二维图片;基于该二维图片设置具备X轴和Y轴的二维坐标;利用双摄像头测量物距;其中,所述物距是目标对象到摄像头平面的水平距离;三维坐标搭建模块,用于基于所述物距以及所述二维坐标,设置以双摄像头的中间点为原点、具备X轴Y轴Z轴的三维坐标系;模型构建模块,用于利用所述双摄像头,至少对所述目标对象的正面、左侧面、后面、右侧面进行三维图像采集,构建三维模型。
优选地,所述测量模块包括:第一测量单元,用于获取第一位置距离x1和第二位置距离x2;其中,所述x1是目标对象在第一平面传感器传感器上的投影点,与所述第一传感器的中心点的距离;所述x2是目标对象在第二传感器上的投影点,与所述第二传感器的中心点的距离;所述第一传感器对应于双摄像头中的一个摄像头,所述第二传感器对应于双摄像头中的另一个摄像头;第二测量单元,用于基于公式:x1/f=x/L和x2/f=(x+d)/L,计算得到物距L;其中,f为双摄像头的等效中心到传感器的距离,d为第一传感器和第二传感器的中心点的距离。
优选地,所述三维坐标搭建模块包括:第一搭建单元,用于基于所述二维坐标,在所述二维图片中选取目标对象上的多个目标像素点,确定目标像素点的二维坐标(X0,Y0);第二搭建单元,用于根据所述物距L,二维坐标(X0,
Y0),以及公式L^2=X0^2+Y0^2+Z0^2,计算得到目标像素点的三维坐标(X0,Y0,Z0);第三搭建单元,用于基于所述多个目标像素点的三维坐标,设置以双摄像头的中间点为原点、具备X轴Y轴Z轴的三维坐标系。
优选地,所述模型构建模块包括:距离计算单元,用于计算目标对象的人体中心线与双摄像头平面的垂直距离Lz=min(Z0)+人体部位最大厚度/2;其中,所述min(Z0)为所述多个目标像素点的三维坐标中数值最小的Z0;三维拍摄单元,用于利用所述Lz以及终端内置的陀螺仪,以目标对象的人体中心线为轴,引导用户围绕所述目标对象利用所述双摄像头,至少对所述目标对象的正面、左侧面、后面、右侧面进行图像拍摄。
优选地,所述装置还包括:第一装扮设计模块,用于基于所述三维模型确定所述目标对象的外表特征和着装风格,结合发型与装扮数据库,匹配出适合所述目标对象的发型和服装;将匹配出的所述发型和服装与所述三维模型相融合,展示给用户;或者,第二装扮设计模块,用于提供用户设计界面;其中,所述用户设计界面是用户为所述三维模型进行发型与服装设计操作的界面;将用户为所述三维模型设计的发型与服装,与所述三维模型相融合,展示给用户。
根据本发明的一个方面,本发明提供了一种三维装扮方法,应用于具有双摄像头的终端,其中,该方法包括:根据终端界面的提示信息,至少对目标对象的正面、左侧面、后面、右侧面进行拍摄,以构建三维模型;对所述三维模型进行发型和服装的装扮。
优选地,对所述三维模型进行发型和服装的装扮,包括:结合发型与装扮数据库,挑选适合所述目标对象的发型和服装;将挑选出的所述发型和服装与所述三维模型相融合,展示在终端界面上。
优选地,对所述三维模型进行发型和服装的装扮,包括:提供用户设计界面;其中,所述用户设计界面是用户为所述三维模型进行发型与服装设计操作的界面;将用户为所述三维模型设计的发型与服装,与所述三维模型相融合,
展示在终端界面上。
本发明有益效果如下:
1)利用双摄像头相关技术,得到精度较高的人物三维模型,以及人体肤色等,如偏白、偏黑等。
2)利用现有三维发型和装扮设计技术和算法,配合双摄像头得到的三维模型和人体肤色等信息,推荐相关发型与装扮,以及支持自身对发型和装扮进行设计。
3)随时随地对自身三维发型与装扮进行设计或获取推荐。
上述说明仅是本发明技术方案的概述,为了能够更清楚了解本发明的技术手段,而可依照说明书的内容予以实施,并且为了让本发明的上述和其它目的、特征和优点能够更明显易懂,以下特举本发明的具体实施方式。
图1是根据本发明实施例一的基于双摄像头的三维建模方法流程图;
图2是根据本发明实施例二的拍摄平面示意图;
图3是根据本发明实施例二的拍摄立体示意图;
图4是根据本发明实施例二的三维坐标示意图;
图5是根据本发明实施例二的人体中心线示意图;
图6是根据本发明实施例三的三维装扮方法的流程图;
图7是根据本发明实施例四的三维模型的发型装扮流程图;
图8是根据本发明实施例五的基于双摄像头的三维模型构建装置的结构框图。
为了解决现有技术中三维发型和服装设计的灵活性和通用性不够的问题,本发明提供了一种基于双摄像头的三维建模方法及装置,以下结合附图以及实
施例,对本发明进行进一步详细说明。应当理解,此处所描述的具体实施例仅仅用以解释本发明,并不限定本发明。
本发明第一实施例
本实施例提供了一种基于双摄像头的三维建模方法,该方法可以在终端设备侧实现。图1所示的是基于双摄像头的三维建模方法流程图,如图1所示,该方法包括(步骤S102-步骤S106):
步骤S102,利用双摄像头针对目标对象拍摄二维图片;基于该二维图片设置具备X轴和Y轴的二维坐标;利用双摄像头测量物距;其中,上述物距是目标对象到摄像头平面的水平距离;
步骤S104,基于上述物距以及上述二维坐标,设置以双摄像头的中间点为原点、具备X轴Y轴Z轴的三维坐标系;
步骤S106,利用上述双摄像头,至少对上述目标对象的正面、左侧面、后面、右侧面进行三维图像采集,构建三维模型。
通过本实施例,解决了相关技术中三维发型和服装设计的灵活性和通用性不够的问题。下面对本实施例的详细实现过程进行介绍。
利用双摄像头测量物距,可以通过以下优选实施方式实现:
获取第一位置距离x1和第二位置距离x2;其中,上述x1是目标对象在第一传感器上的投影点,与上述第一传感器的中心点的距离;上述x2是目标对象在第二传感器上的投影点,与上述第二传感器的中心点的距离;上述第一传感器对应于双摄像头中的一个摄像头,上述第二传感器对应于双摄像头中的另一个摄像头;基于公式:x1/f=x/L和x2/f=(x+d)/L,计算得到物距L;其中,f为双摄像头的等效中心到传感器的距离,d为两个传感器中心点的距离。
基于物距上述二维坐标,设置三维坐标系,可以通过以下优选实施方式实现:基于上述二维坐标,在上述二维图片中选取目标对象上的多个目标像素点,确定目标像素点的二维坐标(X0,Y0);根据上述物距L,二维坐标(X0,
Y0),以及公式L^2=X0^2+Y0^2+Z0^2,计算得到目标像素点的三维坐标(X0,Y0,Z0);基于上述多个目标像素点的三维坐标,设置以双摄像头的中间点为原点、具备X轴Y轴Z轴的三维坐标系。
利用上述双摄像头,至少对上述目标对象的正面、左侧面、后面、右侧面进行三维图像采集,可以通过以下优选实施方式实现:计算目标对象的人体中心线与双摄像头平面的垂直距离Lz=min(Z0)+人体部位最大厚度/2;其中,上述min(Z0)为上述多个目标像素点的三维坐标中数值最小的Z0;利用上述Lz以及终端内置的陀螺仪,以目标对象的人体中心线为轴,引导用户围绕上述目标对象利用上述双摄像头,至少对上述目标对象的正面、左侧面、后面、右侧面进行图像拍摄。
构建三维模型之后,优选地,本实施例的方法还包括:基于上述三维模型确定上述目标对象的外表特征和着装风格,结合发型与装扮数据库,匹配出适合上述目标对象的发型和服装;将匹配出的上述发型和服装与上述三维模型相融合,展示给用户。
或者,提供用户设计界面;其中,上述用户设计界面是用户为上述三维模型进行发型与服装设计操作的界面;将用户为上述三维模型设计的发型与服装,与上述三维模型相融合,展示给用户。
本发明第二实施例
本实施例技术方案的主要过程分为:A、获取目标人体的三维模型,B、对三维模型进行发型和服装推荐或设计。
A、获取人体三维模型,技术方案主要包含:
获取人体各部位像素点三维坐标,通过三维坐标构建目标人体三维模型。
(1)利用普通单摄像头能得到二维的图片,并能较为容易的根据像素点大小信息得到像素点二维坐标(X,Y)特性。同理双摄像头也能得到(X,Y)点的坐标,为了得到三维坐标关键就是得到物距L,即目标对象到摄像头平面
的水平距离。可使用双摄像头测距。其具体方法如下:
图2所示的是拍摄平面示意图,如图2所示,被测点A在双摄像头分别成像。光轴平行时:x1/f=x/L,x2/f=(x+d)/L。其中,
x1:目标对象在第一传感器上的投影点,与第一传感器的中心点的距离,
x2:目标对象在第二传感器上的投影点,与第二传感器的中心点的距离,
f:像距,镜头等效中心到传感器的距离,
d:两个传感器中心点的距离。
基于上述两个公式,可以计算得到物距L。
(2)获取人体四个面的三维模型,具体方案如下:
基于二维坐标,在二维图片中选取目标对象上的多个目标像素点,确定目标像素点的二维坐标(X0,Y0)。图3所示的是拍摄立体示意图,图4所示的三维坐标示意图,如图3和4所示,以双摄像头中心为原点建立三维坐标系,利用双摄像头测距得到物距L,利用L,X0,Y0便可得到目标像素点的三维坐标(X0,Y0,Z0),其中L^2=X0^2+Y0^2+Z0^2。确定目标对象的人体中心线与摄像头平面的垂直距离Lz=min(Z0)+人体部位最大厚度/2,其中,min(Z0)为多个目标像素点的三维坐标中数值最小的Z0,也可以解释为目标对象的身上,距离双摄像头最近的目标像素点。
Lz会根据目标人体侧面双摄像头三维模型中侧身宽度值做相应的修正。利用上述Lz,同时借助手机内陀螺仪,以人体中心线(如图5所示的人体中心线示意图)为圆心,结合以类似全景拍照的模式,在手机界面引导用户至少对目标对象的正面,左侧面,后面,右侧面进行双摄像头三维图像采集,得到以摄像头中心为原点的人体四个面各个像素点的三维坐标。最后对四个面像素的三维坐标做相应的位置转换,在三维上呈现以人体中心线为轴,左侧面三维图像向左旋转90度并向左偏移一定距离;右侧面三维图像向右旋转90度并向右偏移一定距离;后面三维图像向旋转180度并向后偏移一定距离,最后将四
个面的三维图像拼接成目标人体完整的三维模型。
B、对三维模型进行发型和服装推荐或设计。
进入三维发型与装扮应用后,进行如下选项:
1.获取目标人体三维模型。
(1)在手机界面引导用户将手机摄像头与地面垂直,主要利用手机内置陀螺仪实现。人体处于站直状态与地平面垂直,利用双摄像头测距和现有人脸识别技术,主要利用人脸对称,使目标人体处于双摄像头中心正前方,即人体中心线与双摄像头垂直中心线共面,如下下图所示,且整个身体都呈现在摄像头场景内,即头部在相框上边缘内,脚在相框下边缘内。
(2)以类似全景模式方式结合陀螺仪和人体中心线到双摄像头距离,引导用户对目标人体前后左右四个面进行三维图像获取后,系统对四个面的三维图像进行拼接,形成目标人体完整三维模型。
2.打开已存三维人体模型。
3.获取人体三维模型和肤色信息后,系统可以进入两种模式:发型与装扮专家推荐模式、发型与装扮个人设计模式。
a)发型与装扮专家推荐模式
系统将人体三维模型得出人体身体形态、肤色,结合用户个人风格,和专业发型设计师、服装设计师提供的各种人体形态发型服装和搭配相关数据信息,得出适合目标人体的各种发型和装扮。
b)发型与装扮个人设计模式
该模式用户可以对目标人体三维模型进行发型与装扮进行单独设计,为方便用户操作,系统中存有各种常用发型和装扮样板。
系统数据保存,包括目标人体三维模型、发型与装扮数据的存储,方便后期直接调用。
本发明第三实施例
本实施例提供了一种三维装扮方法,应用于具有双摄像头的终端,图6所示的是三维装扮方法的流程图,如图6所示,该方法包括(步骤S602-步骤S604):
步骤S602,根据终端界面的提示信息,至少对目标对象的正面、左侧面、后面、右侧面进行拍摄,以构建三维模型;
步骤S604,对上述三维模型进行发型和服装的装扮。其中,该步骤至少存在两种实现方式:
结合发型与装扮数据库,挑选适合上述目标对象的发型和服装;将挑选出的上述发型和服装与上述三维模型相融合,展示在终端界面上;或者,
提供用户设计界面;其中,上述用户设计界面是用户为上述三维模型进行发型与服装设计操作的界面;将用户为上述三维模型设计的发型与服装,与上述三维模型相融合,展示在终端界面上。
对于上述两种实现方式,可以在终端界面设置发型与装扮APP(Application,应用程序),通过点击APP进入发型与装扮界面,从而方便用户执行上述两种实现方式。
本发明第四实施例
图7所示的是三维模型的发型装扮流程图,如图7所示,该流程包括:
步骤S701,进入发型与装扮推荐与设计应用。
步骤S702,判断目标人体是否存在对应的三维模型,如果否,则执行步骤S704,如果是,则执行步骤S703。
步骤S703,从系统中导入目标人体三维模型。然后执行步骤S707。
步骤S704,进入摄像头取景界面。
步骤S705,手机界面引导用户,目标人体处于双摄像头中心正前方。
步骤S706,引导用户对目标人体前后左右四个面进行三维图像获取,拼接人体三维模型。
步骤S707,得到目标人体三维模型。
步骤S708,是否选择专家推荐模式,如果是,则执行步骤S709,如果否,则执行步骤S710。
步骤S709,自动显示适合目标人体的发型与装扮。然后执行步骤S711。
步骤S710,进入个人设计模式。
步骤S711,数据保存。
本发明第五实施例
本实施例提供了一种基于双摄像头的三维模型构建装置,应用于终端侧,图8所示的是基于双摄像头的三维模型构建装置的结构框图,如图8所示,该装置包括:
测量模块10,用于利用双摄像头针对目标对象拍摄二维图片;基于该二维图片设置具备X轴和Y轴的二维坐标;利用双摄像头测量物距;其中,上述物距是目标对象到摄像头平面的水平距离;
三维坐标搭建模块20,用于基于上述物距以及上述二维坐标,设置以双摄像头的中间点为原点、具备X轴Y轴Z轴的三维坐标系;
模型构建模块30,用于利用上述双摄像头,至少对上述目标对象的正面、左侧面、后面、右侧面进行三维图像采集,构建三维模型。
通过本实施例,解决了相关技术中三维发型和服装设计的灵活性和通用性不够的问题。
优选地,上述测量模块10包括:
第一测量单元,用于获取第一位置距离x1和第二位置距离x2;其中,上述x1是目标对象在第一传感器上的投影点,与上述第一传感器的中心点的距离;上述x2是目标对象在第二传感器上的投影点,与上述第二传感器的中心点的距离;上述第一传感器对应于双摄像头中的一个摄像头,上述第二传感器对应于双摄像头中的另一个摄像头;
第二测量单元,用于基于公式:x1/f=x/L和x2/f=(x+d)/L,计算得到物距L;其中,f为双摄像头的等效中心到传感器的距离,d为两个传感器中心点的距离。
优选地,上述三维坐标搭建模块20包括:
第一搭建单元,用于基于上述二维坐标,在上述二维图片中选取目标对象上的多个目标像素点,确定目标像素点的二维坐标(X0,Y0);
第二搭建单元,用于根据上述物距L,二维坐标(X0,Y0),以及公式L^2=X0^2+Y0^2+Z0^2,计算得到目标像素点的三维坐标(X0,Y0,Z0);
第三搭建单元,用于基于上述多个目标像素点的三维坐标,设置以双摄像头的中间点为原点、具备X轴Y轴Z轴的三维坐标系。
优选地,上述模型构建模块30包括:
距离计算单元,用于计算目标对象的人体中心线与双摄像头平面的垂直距离Lz=min(Z0)+人体部位最大厚度/2;其中,上述min(Z0)为上述多个目标像素点的三维坐标中数值最小的Z0;
三维拍摄单元,用于利用上述Lz以及终端内置的陀螺仪,以目标对象的人体中心线为轴,引导用户围绕上述目标对象利用上述双摄像头,至少对上述目标对象的正面、左侧面、后面、右侧面进行图像拍摄。
对于后期的三维模型的装扮,本实施例提供了两种优选实施方式,即上述装置还包括:
第一装扮设计模块,用于基于上述三维模型确定上述目标对象的外表特征和着装风格,结合发型与装扮数据库,匹配出适合上述目标对象的发型和服装;将匹配出的上述发型和服装与上述三维模型相融合,展示给用户;或者,
第二装扮设计模块,用于提供用户设计界面;其中,上述用户设计界面是用户为上述三维模型进行发型与服装设计操作的界面;将用户为上述三维模型设计的发型与服装,与上述三维模型相融合,展示给用户。
从以上的描述可知,本发明提供双摄像头的三维发型与装扮推荐与设计,可以使用户进行自身发型和装扮设计以及获得专业人士的推荐,且娱乐性和实用性较大,符合人们日益增长需求。提升用户体验,增加手机卖点。
以上所述,仅为本发明的具体实施方式,但本发明的保护范围并不局限于此,任何熟悉本技术领域的技术人员在本发明揭露的技术范围内,可轻易想到的变化或替换,都应涵盖在本发明的保护范围之内。因此,本发明的保护范围应以所述权利要求的保护范围为准。
Claims (14)
- 一种基于双摄像头的三维模型构建方法,其特征在于,所述方法包括:利用双摄像头针对目标对象拍摄二维图片;基于该二维图片设置具备X轴和Y轴的二维坐标;利用双摄像头测量物距;其中,所述物距是目标对象到摄像头平面的水平距离;基于所述物距以及所述二维坐标,设置以双摄像头的中间点为原点、具备X轴Y轴Z轴的三维坐标系;利用所述双摄像头,至少对所述目标对象的正面、左侧面、后面、右侧面进行三维图像采集,构建三维模型。
- 如权利要求1所述的方法,其特征在于,利用双摄像头测量物距,包括:获取第一位置距离x1和第二位置距离x2;其中,所述x1是目标对象在第一传感器上的投影点,与所述第一传感器的中心点的距离;所述x2是目标对象在第二传感器上的投影点,与所述第二传感器的中心点的距离;所述第一传感器对应于双摄像头中的一个摄像头,所述第二传感器对应于双摄像头中的另一个摄像头;基于公式:x1/f=x/L和x2/f=(x+d)/L,计算得到物距L;其中,f为双摄像头的等效中心到传感器的距离,d为第一传感器与第二传感器的中心点的距离。
- 如权利要求1所述的方法,其特征在于,基于所述物距以及所述二维坐标,设置三维坐标系,包括:基于所述二维坐标,在所述二维图片中选取目标对象上的多个目标像素点,确定目标像素点的二维坐标(X0,Y0);根据所述物距L,二维坐标(X0,Y0),以及公式L^2=X0^2+Y0^2+Z0^2, 计算得到目标像素点的三维坐标(X0,Y0,Z0);基于所述多个目标像素点的三维坐标,设置以双摄像头的中间点为原点、具备X轴Y轴Z轴的三维坐标系。
- 如权利要求3所述的方法,其特征在于,利用所述双摄像头,至少对所述目标对象的正面、左侧面、后面、右侧面进行三维图像采集,包括:计算目标对象的人体中心线与双摄像头平面的垂直距离Lz=min(Z0)+人体部位最大厚度/2;其中,所述min(Z0)为所述多个目标像素点的三维坐标中数值最小的Z0;利用所述Lz以及终端内置的陀螺仪,以目标对象的人体中心线为轴,引导用户围绕所述目标对象利用所述双摄像头,至少对所述目标对象的正面、左侧面、后面、右侧面进行图像拍摄。
- 如权利要求1所述的方法,其特征在于,构建所述三维模型之后,所述方法还包括:基于所述三维模型确定所述目标对象的外表特征和着装风格,结合发型与装扮数据库,匹配出适合所述目标对象的发型和服装;将匹配出的所述发型和服装与所述三维模型相融合,展示给用户。
- 如权利要求1所述的方法,其特征在于,构建所述三维模型之后,所述方法还包括:提供用户设计界面;其中,所述用户设计界面是用户为所述三维模型进行发型与服装设计操作的界面;将用户为所述三维模型设计的发型与服装,与所述三维模型相融合,展示给用户。
- 一种基于双摄像头的三维模型构建装置,其特征在于,所述装置包括:测量模块,用于利用双摄像头针对目标对象拍摄二维图片;基于该二维图片设置具备X轴和Y轴的二维坐标;利用双摄像头测量物距;其中,所述物 距是目标对象到摄像头平面的水平距离;三维坐标搭建模块,用于基于所述物距以及所述二维坐标,设置以双摄像头的中间点为原点、具备X轴Y轴Z轴的三维坐标系;模型构建模块,用于利用所述双摄像头,至少对所述目标对象的正面、左侧面、后面、右侧面进行三维图像采集,构建三维模型。
- 如权利要求7所述的装置,其特征在于,所述测量模块包括:第一测量单元,用于获取第一位置距离x1和第二位置距离x2;其中,所述x1是目标对象在第一传感器上的投影点,与所述第一传感器的中心点的距离;所述x2是目标对象在第二传感器上的投影点,与所述第二传感器的中心点的距离;所述第一传感器对应于双摄像头中的一个摄像头,所述第二传感器对应于双摄像头中的另一个摄像头;第二测量单元,用于基于公式:x1/f=x/L和x2/f=(x+d)/L,计算得到物距L;其中,f为双摄像头的等效中心到传感器的距离,d为第一传感器和第二传感器的中心点的距离。
- 如权利要求7所述的装置,其特征在于,所述三维坐标搭建模块包括:第一搭建单元,用于基于所述二维坐标,在所述二维图片中选取目标对象上的多个目标像素点,确定目标像素点的二维坐标(X0,Y0);第二搭建单元,用于根据所述物距L,二维坐标(X0,Y0),以及公式L^2=X0^2+Y0^2+Z0^2,计算得到目标像素点的三维坐标(X0,Y0,Z0);第三搭建单元,用于基于所述多个目标像素点的三维坐标,设置以双摄像头的中间点为原点、具备X轴Y轴Z轴的三维坐标系。
- 如权利要求9所述的装置,其特征在于,所述模型构建模块包括:距离计算单元,用于计算目标对象的人体中心线与双摄像头平面的垂直距离Lz=min(Z0)+人体部位最大厚度/2;其中,所述min(Z0)为所述多个目标像素点的三维坐标中数值最小的Z0;三维拍摄单元,用于利用所述Lz以及终端内置的陀螺仪,以目标对象的人体中心线为轴,引导用户围绕所述目标对象利用所述双摄像头,至少对所述目标对象的正面、左侧面、后面、右侧面进行图像拍摄。
- 如权利要求7所述的装置,其特征在于,所述装置还包括:第一装扮设计模块,用于基于所述三维模型确定所述目标对象的外表特征和着装风格,结合发型与装扮数据库,匹配出适合所述目标对象的发型和服装;将匹配出的所述发型和服装与所述三维模型相融合,展示给用户;或者,第二装扮设计模块,用于提供用户设计界面;其中,所述用户设计界面是用户为所述三维模型进行发型与服装设计操作的界面;将用户为所述三维模型设计的发型与服装,与所述三维模型相融合,展示给用户。
- 一种三维装扮方法,应用于具有双摄像头的终端,其特征在于,所述方法包括:根据终端界面的提示信息,至少对目标对象的正面、左侧面、后面、右侧面进行拍摄,以构建三维模型;对所述三维模型进行发型和服装的装扮。
- 如权利要求12所述的方法,其特征在于,对所述三维模型进行发型和服装的装扮,包括:结合发型与装扮数据库,挑选适合所述目标对象的发型和服装;将挑选出的所述发型和服装与所述三维模型相融合,展示在终端界面上。
- 如权利要求12所述的方法,其特征在于,对所述三维模型进行发型和服装的装扮,包括:提供用户设计界面;其中,所述用户设计界面是用户为所述三维模型进行发型与服装设计操作的界面;将用户为所述三维模型设计的发型与服装,与所述三维模型相融合,展示在终端界面上。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510209458.2 | 2015-04-28 | ||
| CN201510209458.2A CN106157360A (zh) | 2015-04-28 | 2015-04-28 | 一种基于双摄像头的三维建模方法及装置 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2016173073A1 true WO2016173073A1 (zh) | 2016-11-03 |
Family
ID=57198908
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2015/080316 Ceased WO2016173073A1 (zh) | 2015-04-28 | 2015-05-29 | 一种基于双摄像头的三维建模方法及装置 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN106157360A (zh) |
| WO (1) | WO2016173073A1 (zh) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106597424A (zh) * | 2016-12-22 | 2017-04-26 | 惠州Tcl移动通信有限公司 | 一种基于双摄像头的测距方法、系统及移动终端 |
| CN109064386A (zh) * | 2018-07-23 | 2018-12-21 | 西安建筑科技大学 | 一种三维立体衣服模型的建立方法 |
| CN110070025A (zh) * | 2019-04-17 | 2019-07-30 | 上海交通大学 | 基于单目图像的三维目标检测系统及方法 |
| CN110619807A (zh) * | 2018-06-20 | 2019-12-27 | 北京京东尚科信息技术有限公司 | 生成全局热力图的方法和装置 |
| CN115499641A (zh) * | 2022-09-20 | 2022-12-20 | 北京三月雨文化传播有限责任公司 | 一种快速构建数字展览文件的方法及智能终端 |
| CN118351229A (zh) * | 2022-11-25 | 2024-07-16 | 龙岩川净电器有限责任公司 | 一种基于瞳距仿生双摄的3d建模技术 |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106598428A (zh) * | 2016-11-29 | 2017-04-26 | 宇龙计算机通信科技(深圳)有限公司 | 播放全景视频的方法、系统及终端设备 |
| CN106651822A (zh) * | 2016-12-20 | 2017-05-10 | 宇龙计算机通信科技(深圳)有限公司 | 图片复原方法及装置 |
| CN108510537B (zh) * | 2017-02-28 | 2020-06-12 | 深圳市掌网科技股份有限公司 | 3d建模方法和装置 |
| CN107194981A (zh) * | 2017-04-18 | 2017-09-22 | 武汉市爱米诺网络科技有限公司 | 发型虚拟展示系统及其方法 |
| CN107480172A (zh) * | 2017-06-30 | 2017-12-15 | 深圳天珑无线科技有限公司 | 物品匹配的方法、装置及终端 |
| CN107864372B (zh) * | 2017-09-22 | 2021-02-26 | 捷开通讯(深圳)有限公司 | 立体拍照方法、装置及终端 |
| CN108195306B (zh) * | 2017-12-25 | 2020-01-31 | 珠海市万瑙特健康科技有限公司 | 获取人体安全包络线的方法 |
| CN108664569A (zh) * | 2018-04-24 | 2018-10-16 | 杭州数为科技有限公司 | 一种发型推荐方法、系统、终端及介质 |
| CN111339588B (zh) * | 2020-02-20 | 2023-02-28 | 广州易达建信科技开发有限公司 | 一种二维图纸与三维模型检查方法、系统及存储介质 |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102620713A (zh) * | 2012-03-26 | 2012-08-01 | 梁寿昌 | 一种利用双摄像头测距和定位的方法 |
| CN102980556A (zh) * | 2012-11-29 | 2013-03-20 | 北京小米科技有限责任公司 | 一种测距方法及装置 |
| US20130258486A1 (en) * | 2012-03-27 | 2013-10-03 | Dumitru Mihai Ionescu | Head-mount display |
| CN103793832A (zh) * | 2014-03-11 | 2014-05-14 | 徐巍冉 | 一种应用于网络试衣并基于图像采集的三维建模方法 |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5035372B2 (ja) * | 2010-03-17 | 2012-09-26 | カシオ計算機株式会社 | 三次元モデリング装置、三次元モデリング方法、ならびに、プログラム |
| CN102402641A (zh) * | 2010-09-14 | 2012-04-04 | 盛乐信息技术(上海)有限公司 | 一种基于网络的三维虚拟试衣系统及方法 |
-
2015
- 2015-04-28 CN CN201510209458.2A patent/CN106157360A/zh active Pending
- 2015-05-29 WO PCT/CN2015/080316 patent/WO2016173073A1/zh not_active Ceased
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102620713A (zh) * | 2012-03-26 | 2012-08-01 | 梁寿昌 | 一种利用双摄像头测距和定位的方法 |
| US20130258486A1 (en) * | 2012-03-27 | 2013-10-03 | Dumitru Mihai Ionescu | Head-mount display |
| CN102980556A (zh) * | 2012-11-29 | 2013-03-20 | 北京小米科技有限责任公司 | 一种测距方法及装置 |
| CN103793832A (zh) * | 2014-03-11 | 2014-05-14 | 徐巍冉 | 一种应用于网络试衣并基于图像采集的三维建模方法 |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106597424A (zh) * | 2016-12-22 | 2017-04-26 | 惠州Tcl移动通信有限公司 | 一种基于双摄像头的测距方法、系统及移动终端 |
| CN110619807A (zh) * | 2018-06-20 | 2019-12-27 | 北京京东尚科信息技术有限公司 | 生成全局热力图的方法和装置 |
| CN109064386A (zh) * | 2018-07-23 | 2018-12-21 | 西安建筑科技大学 | 一种三维立体衣服模型的建立方法 |
| CN109064386B (zh) * | 2018-07-23 | 2022-10-11 | 西安建筑科技大学 | 一种三维立体衣服模型的建立方法 |
| CN110070025A (zh) * | 2019-04-17 | 2019-07-30 | 上海交通大学 | 基于单目图像的三维目标检测系统及方法 |
| CN110070025B (zh) * | 2019-04-17 | 2023-03-31 | 上海交通大学 | 基于单目图像的三维目标检测系统及方法 |
| CN115499641A (zh) * | 2022-09-20 | 2022-12-20 | 北京三月雨文化传播有限责任公司 | 一种快速构建数字展览文件的方法及智能终端 |
| CN115499641B (zh) * | 2022-09-20 | 2023-09-12 | 广东鸿威国际会展集团有限公司 | 一种快速构建数字展览文件的方法及智能终端 |
| CN118351229A (zh) * | 2022-11-25 | 2024-07-16 | 龙岩川净电器有限责任公司 | 一种基于瞳距仿生双摄的3d建模技术 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106157360A (zh) | 2016-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2016173073A1 (zh) | 一种基于双摄像头的三维建模方法及装置 | |
| CN107273846B (zh) | 一种人体体型参数确定方法及装置 | |
| US9928411B2 (en) | Image processing apparatus, image processing system, image processing method, and computer program product | |
| CN106373178B (zh) | 生成人工图像的装置和方法 | |
| CN110363867B (zh) | 虚拟装扮系统、方法、设备及介质 | |
| CA2573246C (en) | System and method for detecting breast cancer using 3d imaging | |
| WO2024007478A1 (zh) | 基于单手机的人体三维建模数据采集与重建方法及系统 | |
| JP5842541B2 (ja) | 三次元ポートレートの作成装置 | |
| CN106840112B (zh) | 一种利用自由空间视线凝视点测量的空间几何量测量方法 | |
| KR20210099507A (ko) | 신체 측정 디바이스 및 그 제어 방법 | |
| KR20180108709A (ko) | 사용자의 현실적인 신체 모델에 가상으로 옷을 입혀보는 방법 | |
| CN100353384C (zh) | 电子游戏中玩家快速置入方法 | |
| CN114375177A (zh) | 身体测量装置及其控制方法 | |
| CN107230224B (zh) | 三维虚拟服装模型制作方法及装置 | |
| JP2022133133A (ja) | 生成装置、生成方法、システム、およびプログラム | |
| CN104599317A (zh) | 一种实现3d扫描建模功能的移动终端及方法 | |
| US10152827B2 (en) | Three-dimensional modeling method and electronic apparatus thereof | |
| CN107680166A (zh) | 一种智能定制服装的方法和装置 | |
| CN110197420A (zh) | 一种智能试衣系统 | |
| CN113298956A (zh) | 图像处理方法、美甲方法、美妆方法和装置、终端设备 | |
| CN111445570B (zh) | 一种定制化服装设计生产设备及方法 | |
| JP2003085411A (ja) | 画像入出力装置 | |
| CN107864372A (zh) | 立体拍照方法、装置及终端 | |
| WO2016184285A1 (zh) | 物品图像处理方法、装置和系统 | |
| CN110910487A (zh) | 构建方法、构建装置、电子装置和计算机可读存储介质 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 15890452 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 16.04.2018) |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 15890452 Country of ref document: EP Kind code of ref document: A1 |