CN111161400A

CN111161400A - Glasses matching design equipment

Info

Publication number: CN111161400A
Application number: CN201911276019.8A
Authority: CN
Inventors: 左忠斌; 左达宇
Original assignee: Tianmu Aishi Beijing Technology Co Ltd
Current assignee: Tianmu Aishi Beijing Technology Co Ltd
Priority date: 2019-12-12
Filing date: 2019-12-12
Publication date: 2020-05-15
Anticipated expiration: 2039-12-12
Also published as: CN113115024A; CN113115024B; CN111161400B; WO2021115298A1

Abstract

The invention provides glasses equipment, which comprises a 3D acquisition device, a 3D synthesis device, a glasses adaptation device and a display device, wherein the 3D acquisition device is connected with the glasses adaptation device; the 3D acquisition device is used for acquiring a plurality of images of the head of the human body; a 3D synthesizing device for synthesizing a head 3D model using the plurality of images; the glasses adapting device is used for adapting the 3D model of the head and the 3D model of the glasses; the display device is used for displaying the adaptation effect of the head 3D model and the glasses 3D model; the 3D acquisition device comprises an image acquisition device and a background plate, wherein the background plate and the image acquisition device are relatively arranged in the rotation process, so that the background plate becomes a background pattern of an image acquired by the image acquisition device during acquisition. The method is firstly put forward to improve the 3D synthesis speed and the synthesis precision simultaneously by increasing the mode that the background plate rotates along with the camera in the glasses matching design equipment, thereby improving the effect of glasses matching and reducing the waiting time.

Description

Glasses matching design equipment

Technical Field

The invention relates to the technical field of glasses design, in particular to the field of automatic matching design of glasses realized through a 3D (three-dimensional) appearance measurement technology.

Background

Currently, when selecting glasses, a user usually goes to a glasses shop to select wearing on the spot. But this is time consuming and laborious. In order to solve the problem, some people propose to take a picture of the face of the user, and then remotely provide the user with pictures of a plurality of glasses, and the trial wearing of the glasses can be completed by matching the picture of the face with the picture of the glasses. However, since both pictures are planar pictures, the difference between the matching effect and the real effect is large, and it is difficult to find a truly satisfactory glasses for the user. And the matching is based on the existing picture library, and the personalized customized service is difficult to provide for the user.

There are also some glasses design software to match glasses through the user's head model. But the time for obtaining the head model of the user is longer firstly, so that the user waits for a long time and experiences poor. Some algorithms can reduce time, but lead to inaccurate head models, inaccurate models are used for glasses matching, users can misjudge the models, the presenting effect is different from the reality, and the user experience is poor. Some use even a limited pre-defined head model as the user head model. In the prior art, in order to simultaneously improve the synthesis speed and the synthesis precision, the synthesis is generally realized by a method of optimizing an algorithm. And the art has always considered that the approach to solve the above problems lies in the selection and updating of algorithms, and no method for simultaneously improving the synthesis speed and the synthesis precision from other angles has been proposed so far. However, the optimization of the algorithm has reached a bottleneck at present, and before no more optimal theory appears, the improvement of the synthesis speed and the synthesis precision cannot be considered.

In addition, most software can only be matched with a user by using the glasses in the glasses library, and cannot be customized individually. Even though some software can realize the design of the glasses, the designed glasses can only be used as the display of the effect and can not be used as the processing data due to the inaccuracy of the head model.

Meanwhile, at present, no glasses design equipment and no glasses acquisition equipment capable of accurately acquiring head data exist. Typically only as a demonstration and not to generate accurate process data.

Therefore, ① can simultaneously improve the 3D synthesis speed and the synthesis precision, improve the reality degree during glasses matching, reduce the waiting time, ② is low in cost, and the complexity of excessive equipment is not increased, ③ can provide accurate glasses processing data for customers, and personalized customization is realized.

Disclosure of Invention

In view of the above, the present invention has been made to provide an eyeglass matching designing apparatus that overcomes or at least partially solves the above-mentioned problems.

One aspect of the invention provides an eyeglass fitting method, comprising

Step 1: acquiring a plurality of images of the head of a user, wherein the images at least comprise facial images;

step 2: synthesizing a plurality of images into a head 3D model;

and 3, step 3: matching the head 3D model with the glasses model specifically comprises:

3-1, determining a plurality of point coordinates of the head 3D model;

3-2, determining a plurality of point coordinates of the 3D model of the glasses;

3-3, matching the coordinates of a plurality of points of the head 3D model with the coordinates of a plurality of points of the glasses 3D model through at least one conversion mode of rotation, translation and scaling;

3-4 display the matching effect to the user.

Another aspect of the present invention provides an eyeglass device, comprising a 3D acquisition apparatus, a 3D synthesis apparatus, an eyeglass adaptation apparatus, and a display apparatus;

the 3D acquisition device is used for acquiring a plurality of images of the head of the human body;

a 3D synthesizing device for synthesizing a head 3D model using the plurality of images;

the glasses adapting device is used for adapting the 3D model of the head and the 3D model of the glasses;

the display device is used for displaying the adaptation effect of the head 3D model and the glasses 3D model;

the 3D acquisition device comprises an image acquisition device and a background plate, wherein the background plate and the image acquisition device are relatively arranged in the rotation process, so that the background plate becomes a background pattern of an image acquired by the image acquisition device during acquisition.

The third aspect of the present invention further provides a glasses device, comprising a 3D acquisition device, a 3D synthesis device, a glasses adaptation device, and a display device;

wherein 3D collection system includes image acquisition device, and when image acquisition device gathered the target object, two adjacent collection positions satisfied following condition:

wherein L is the linear distance between the optical centers of the two position image acquisition devices; f is the focal length of the image acquisition device; d is the rectangular length of a photosensitive element (CCD) of the image acquisition device; t is the distance from the photosensitive element of the image acquisition device to the surface of the target along the optical axis; delta is an adjustment coefficient;

and δ < 0.603; preferably δ <0.410, or δ < 0.356.

Alternatively, the projection is performed in a direction perpendicular to the surface of the background plate to be photographed, and the length W in the horizontal direction of the projection shape₁Length W in the vertical direction of the projected shape₂Is determined by the following conditions:

wherein d is₁For the length of the imaging element in the horizontal direction, d₂Is the length of the imaging element in the vertical direction, T is the vertical distance from the sensing element of the image acquisition device to the background plate in the direction of the optical axis, f is the focal length of the image acquisition device, A₁、A₂Is an empirical coefficient;

wherein A is₁>1.04，A₂>1.04, preferably, A₁>1.25，A₂>1.25

Optionally, a marker point is further included.

Optionally, the marker points are located on the seat.

Optionally, the 3D synthesis device and the glasses adaptation device are separately disposed or implemented on the same platform.

Optionally, the glasses adapting device is further used for glasses data modification.

Optionally, the adapting the 3D model of the head and the 3D model of the glasses includes performing a rough alignment of the 3D model of the head and the 3D model of the glasses, and then performing a secondary alignment of the 3D model of the head and the 3D model of the glasses.

Optionally, the 3D data of the glasses is sent to a processing device.

Invention and technical effects

1. The method has the advantages that the 3D synthesis speed and the synthesis precision are simultaneously improved by increasing the mode that the background plate rotates along with the camera in the glasses matching design equipment, so that the glasses matching effect is improved, the waiting time is reduced, and the glasses data can be used for processing.

2. Through optimizing the size of the background plate, when reducing rotatory burden, guarantee to improve 3D synthetic speed and synthetic precision simultaneously to improve the effect that glasses match, reduce latency, make glasses data can be used for processing.

3. Through optimizing camera position, can improve 3D synthetic speed and synthetic precision simultaneously to improve the effect that glasses match, reduce latency, make glasses data can be used for processing. When the position is optimized, the angle and the head size do not need to be measured, and the device is suitable for various crowds. More convenient and strong adaptability.

4. For the above reasons, accurate head data can be provided to the user, so that the data is used for custom-making of the glasses.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:

fig. 1 is a schematic structural diagram of glasses matching design equipment provided in an embodiment of the present invention.

The correspondence of reference numerals to the respective components is as follows:

the device comprises a background plate 1, an image acquisition device 2, a rotary beam 3, a rotary device 4, a support 5, a seat 6, a base 7, a transverse column 51 and a vertical column 52.

Detailed Description

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

The glasses matching design equipment comprises a background plate 1, an image acquisition device 2, a rotary beam 3, a rotary device 4, a support 5, a seat 6 and a base 7.

The support comprises a cross column 51 and a vertical column 52, the vertical column 52 is connected with the base 7, the cross column 51 is connected with the rotating beam 3 through the rotating device 4, and therefore the rotating beam 3 can rotate 360 degrees under the driving of the rotating device 4. The background plate 1 and the image acquisition device 2 are positioned at two ends of the rotating beam 3 and are arranged oppositely, and the rotating beam 3 rotates synchronously and always keeps opposite arrangement.

The base is provided with a seat 6, and the seat 6 is positioned between the background plate 1 and the image acquisition device 2. When the person sits down, the head is located just near the axis of rotation and between the image capture device 2 and the background plate 1, and preferably the person's head is located on the optical axis of the image capture device 2. The height of the head of each person is different because each person is different in height. The position of the human head in the field of view of the image acquisition device 2 can be adjusted by adjusting the height of the seat 6.

The adjustable seat 6 can be connected to the base by a manual adjustment device, for example, the seat 6 is connected to the base by a screw rod, and the height of the seat is adjusted by rotating the screw rod. Preferably, the lifting driving device is in data connection with the controller, and the height of the lifting device is controlled through the controller, so that the height of the seat is adjusted. The controller may be directly connected in the eyewear matching design device, for example, may be prevented from being near the seat armrests to facilitate user adjustment. The controller may also be a mobile terminal such as a cell phone. Therefore, the mobile terminal is connected with the glasses matching design equipment, and the height of the seat can be controlled by controlling the lifting driving device in the mobile terminal. The mobile terminal can be operated by an operator or a user, is more convenient and is not limited by position. Of course, the controller may also be assumed by the upper computer, or by the server and the cluster server. Of course, the cloud platform may also be responsible for the network. The upper computers, the servers, the cluster servers and the cloud platforms can be shared with the upper computers, the servers, the cluster servers and the cloud platforms which are used for 3D synthesis processing, and double functions of control and 3D synthesis are achieved.

If only the presentation of the 3D avatar is performed, the absolute size of each part is not needed as long as the 3D avatar parts are in the right proportions. However, for matching and designing the glasses, if the absolute size of the 3D head model is not available, the actual matching and designing of the glasses cannot be completed, and meaningful data cannot be provided for the final processing of the glasses. In order to obtain the absolute size of the header 3D information, the user's head needs to be calibrated. However, if the user directly attaches the mark to the head according to the conventional method, the user experience is not good. And other positions are difficult to be pasted with the marked points. Therefore, the present invention skillfully sets a head rest on the seat 6, sets mark points on the head rest, and records the absolute distances between the mark points. When the image acquisition device 2 rotates to the back of the user, the mark points are acquired, and the size of the head 3D model is finally calculated according to the preset distance of the mark points. Meanwhile, the mark points are arranged at the position, so that the facial information acquisition of the user is not influenced. Therefore, it is one of the inventions of the present invention that the absolute distance of the head 3D information can be obtained while the user experience can be improved. Meanwhile, the mark point may be provided on the seat 6 as long as the position can be acquired by the image acquisition device 2. The marking point may be a standard gauge block, that is, a marker having a certain spatial size and a predetermined absolute size. Of course, in addition to setting the mark points on the head rest, the corresponding standard gauge blocks may be set at other positions as long as the standard gauge blocks are within the visual field of the camera and are still relative to the human head. For example, a hat, hair clip, etc. containing known marker points may be worn by the user.

The image acquisition device 2 is used for acquiring an image of a target object, and may be a CCD, a CMOS, a camera, a video camera, an industrial camera, a monitor, a camera, a mobile phone, a tablet, a notebook, a mobile terminal, a wearable device, a smart glasses, a smart watch, a smart bracelet, or all devices with an image acquisition function. The image acquisition device comprises a camera body with a photosensitive element and a lens. Preferably, the camera body can adopt an industrial camera, such as MER-2000-19U 3M/C. Industrial cameras have a smaller volume and simplify unwanted functions and have better performance than home cameras. The image acquisition means 2 may be connected to the processing unit so as to transfer the acquired image to the processing unit. The connection method includes a wired method and a wireless method, and the transmission is performed by a plurality of protocols such as a data line, a network cable, an optical fiber, 4G, and 5G, wifi, for example, and it is needless to say that the transmission may be performed by using a combination of these.

The device further comprises a processor, which may also be a processing unit, for synthesizing a 3D model of the object according to the plurality of images acquired by the image acquisition means and according to a 3D synthesis algorithm, to obtain 3D information of the object.

The processing unit obtains 3D information of the object from a plurality of images in the set of images (a specific algorithm is described in detail below). The processing unit may be directly disposed in the housing where the image capturing device is located, or may be connected to the image capturing device 2 through a data line or in a wireless manner. For example, an independent computer, a server, a cluster server, or the like may be used as a processing unit, and the image data acquired by the image acquisition device 2 may be transmitted thereto to perform 3D synthesis. Meanwhile, the data of the image acquisition device 2 can be transmitted to the cloud platform, and 3D synthesis is performed by using the powerful computing capability of the cloud platform.

The background plate 1 is entirely of a solid color, or mostly (body) of a solid color. In particular, the color plate can be a white plate or a black plate, and the specific color can be selected according to the color of the object body. The background plate 1 is generally a flat plate, and preferably also a curved plate, such as a concave plate, a convex plate, a spherical plate, and even in some application scenarios, the background plate 1 with a wavy surface; the plate can also be made into various shapes, for example, three sections of planes can be spliced to form a concave shape as a whole, or a plane and a curved surface can be spliced. In addition to the shape of the surface of the background plate 1 being variable, the shape of the edge thereof may be selected as desired. Typically rectilinear, to form a rectangular plate. But in some applications the edges may be curved.

Preferably, the background plate 1 is a curved plate, so that the projection size of the background plate 1 can be minimized in the case of obtaining the maximum background range. This makes the background plate 1 require a smaller space when rotating, which is advantageous for reducing the volume of the apparatus, and reducing the weight of the apparatus, avoiding the rotation inertia, and thus being more advantageous for controlling the rotation.

Regardless of the surface shape and edge shape of the background plate 1, the projection is performed in a direction perpendicular to the surface to be photographed, and the projection shape has a length W in the horizontal direction₁Length W in the vertical direction of the projected shape₂Is determined by the following conditions:

wherein d is₁For the length of the imaging element in the horizontal direction, d₂Is the length of the imaging element in the vertical direction, T is the vertical distance from the sensing element of the image acquisition device to the background plate in the direction of the optical axis, f is the focal length of the image acquisition device, A₁、A₂Are empirical coefficients.

After a large number of experiments, preferably, A₁>1.04，A₂>1.04; more preferably 2>A₁>1.1，2>A₂>1.1。

In some of the application scenarios, it is possible to,the edges of the background plate 1 are non-linear, resulting in non-linear projected image edges after projection. At this time, W is measured at different positions₁、W₂All are different, so that W is actually calculated₁、W₂It is not easy to determine. Therefore, it is possible to take 3 to 5 points on the opposite sides of the background plate 1 at the edges, respectively, measure the linear distances between the opposite points, and take the average of the measurements as W in the above-mentioned condition₁、W₂。

If the background plate 1 is too large, making the cantilever too long, the volume of the device will increase, at the same time placing an extra burden on the rotation, making the device more vulnerable. However, if the background plate 1 is too small, the background is not simple, and the calculation load is increased.

The following table shows experimental control results:

the experimental conditions are as follows:

acquiring an object: real human head

A camera: MER-2000-19U3M/C

Lens: OPT-C1616-10M

Empirical coefficient	Time of synthesis	Synthetic accuracy
			A₁＝1.2，A₂＝1.2	3.3 minutes	Height of
A₁＝1.4，A₂＝1.4	3.4 minutes	Height of
			A₁＝0.9，A₂＝0.9	4.5 minutes	Middle and high
Is free of	7.8 minutes	In

The rotating beam 3 is connected with the fixed beam through the rotating device 4, the rotating device 4 drives the rotating beam 3 to rotate, so that the background plate 1 and the image acquisition device 2 at two ends of the beam are driven to rotate, however, no matter how the background plate rotates, the image acquisition device 1 and the background plate 2 are arranged oppositely, and particularly, the optical axis of the image acquisition device 1 penetrates through the center of the background plate 2.

The light source is arranged around the lens of the image acquisition device 2,

the light source can be an LED light source or an intelligent light source, namely, the light source parameters are automatically adjusted according to the conditions of the target object and the ambient light. Usually, the light sources are distributed around the lens of the image capturing device 2, for example, the light sources are ring-shaped LED lamps around the lens. When the collected object is a human body, the intensity of the light source needs to be controlled, and human discomfort is avoided. In particular, a light softening means, for example a light softening envelope, may be arranged in the light path of the light source. Or the LED surface light source is directly adopted, so that the light is soft, and the light is more uniform. Preferably, an OLED light source can be adopted, the size is smaller, the light is softer, and the flexible OLED light source has the flexible characteristic and can be attached to a curved surface. In addition, the light source may also be arranged on the housing of the rotating beam 3 carrying the image capturing device 2.

3D acquisition camera (image acquisition device) position optimization

According to a number of experiments, the separation distance of the acquisitions preferably satisfies the following empirical formula:

when 3D acquisition is performed, the positions of two adjacent image acquisition devices 2, or two adjacent acquisition positions of the image acquisition devices 2 satisfy the following conditions:

wherein L is the linear distance between the optical centers of the two image acquisition devices; f is the focal length of the image acquisition device; d is the rectangular length of a photosensitive element (CCD) of the image acquisition device; t is the distance from the photosensitive element of the image acquisition device to the surface of the target along the optical axis; δ is the adjustment factor, δ < 0.603.

When the image pickup device 2 is at any one of the two positions, the distance from the photosensitive element to the surface of the object along the optical axis is taken as T. In addition to this method, in another case, L is A_n、A_n+1Linear distance between optical centers of two image capturing devices, and A_n、A_n+1Two image acquisition devices adjacent to each other_n-1、 A_n+2Two image acquisition devices and A_n、A_n+1The distances from the respective photosensitive elements of the two image acquisition devices to the surface of the target object along the optical axis are respectively T_n-1、T_n、T_n+1、T_n+2，T＝(T_n-1+T_n+T_n+1+T_n+2)/4. Of course, the average value may be calculated by using more positions than the adjacent 4 positions.

L should be a straight-line distance between the optical centers of the two image capturing devices, but since the position of the optical center of the image capturing device is not easily determined in some cases, the center of the photosensitive element of the image capturing device, the geometric center of the image capturing device 2, the axial center of the connection between the image capturing device 2 and the pan/tilt head (or platform, support), and the center of the proximal or distal surface of the lens may be used instead in some cases, and the error caused by the displacement is found to be within an acceptable range through experiments.

In general, parameters such as object size and angle of view are used as means for estimating the position of a camera in the prior art, and the positional relationship between two cameras is also expressed in terms of angle. Because the angle is not well measured in the actual use process, it is inconvenient in the actual use. Also, the size of the object may vary with the variation of the measurement object. For example, when the head of a child is collected after 3D information on the head of an adult is collected, the head size needs to be measured again and calculated again. The inconvenient measurement and the repeated measurement bring errors in measurement, thereby causing errors in camera position estimation. According to the scheme, the experience conditions required to be met by the position of the camera are given according to a large amount of experimental data, so that the problem that the measurement is difficult to accurately measure the angle is solved, and the size of an object does not need to be directly measured. In the empirical condition, d and f are both fixed parameters of the camera, and corresponding parameters can be given by a manufacturer when the camera and the lens are purchased without measurement. And T is only a straight line distance, and can be conveniently measured by using a traditional measuring method, such as a ruler and a laser range finder. Therefore, the empirical formula of the invention enables the preparation process to be convenient and fast, and simultaneously improves the arrangement accuracy of the camera position, so that the camera can be arranged in an optimized position, thereby simultaneously considering the 3D synthesis precision and speed, and the specific experimental data is shown in the following.

Experiments were conducted using the apparatus of the present invention, and the following experimental results were obtained.

The camera lens is replaced, and the experiment is carried out again, so that the following experiment results are obtained.

From the above experimental results and a lot of experimental experiences, it can be found that the value of δ should satisfy δ <0.603, and at this time, a part of the 3D model can be synthesized, although a part cannot be automatically synthesized, it is acceptable in the case of low requirements, and the part which cannot be synthesized can be compensated manually or by replacing the algorithm. Particularly, when the value of δ satisfies δ <0.410, the balance between the synthesis effect and the synthesis time can be optimally taken into consideration; delta <0.356 can be chosen for better synthesis, where the synthesis time is increased but the synthesis quality is better. Of course, to further enhance the synthesis effect, δ <0.311 may be selected. When the delta is 0.681, the synthesis is not possible. It should be noted that the above ranges are only preferred embodiments and should not be construed as limiting the scope of protection.

Moreover, as can be seen from the above experiment, for the determination of the photographing position of the camera, only the camera parameters (focal length f, CCD size) and the distance T between the camera CCD and the object surface need to be obtained according to the above formula, which makes it easy to design and debug the device. Since the camera parameters (focal length f, CCD size) are determined at the time of purchase of the camera and are indicated in the product description, they are readily available. Therefore, the camera position can be easily calculated according to the formula without carrying out complicated view angle measurement and object size measurement. Particularly, in some occasions, the lens of the camera needs to be replaced, and then the position of the camera can be obtained by directly replacing the conventional parameter f of the lens and calculating; similarly, when different objects are collected, the measurement of the size of the object is complicated due to the different sizes of the objects. By using the method of the invention, the position of the camera can be determined more conveniently without measuring the size of the object. And the camera position determined by the invention can give consideration to both the synthesis time and the synthesis effect. Therefore, the above-described empirical condition is one of the points of the present invention.

The above data are obtained by experiments for verifying the conditions of the formula, and do not limit the invention. Without these data, the objectivity of the formula is not affected. Those skilled in the art can adjust the equipment parameters and the step details as required to perform experiments, and obtain other data which also meet the formula conditions.

3D information acquisition method flow

The object is placed between the image capturing device 2 and the background plate 1. Preferably on the extension of the rotation axis of the rotation means 4, i.e. at the centre of the circle around which the image acquisition means 2 is rotated. Therefore, the distance between the image acquisition device 2 and the target object is basically unchanged in the rotation process, so that the situation that the image acquisition is not clear due to the drastic change of the object distance or the requirement on the depth of field of the camera is too high (the cost is increased) is avoided.

When the subject is a human head, a seat 6 may be placed between the image pickup device 2 and the background plate 1, and when the person is seated, the head is located right near the rotation axis and between the image pickup device 2 and the background plate 1. Since each person is of a different height, the height of the area to be collected (e.g. the head of a person) is different. The position of the human head in the field of view of the image acquisition device 2 can be adjusted by adjusting the height of the seat 6. When the object is collected, the seat 6 can be replaced by a storage table.

In addition to adjusting the height of the seat 6, the center of the target object can be ensured to be located at the center of the field of view of the image capturing device 2 by adjusting the height of the image capturing device 2 and the height of the background plate 1 in the vertical direction. For example, the background plate 1 may be moved up and down along a first mounting post and the horizontal bracket carrying the image capturing mechanism 2 may be moved up and down along a second mounting post. Typically, the movement of the background plate 1 and the image capturing device 2 is synchronized to ensure that the optical axis of the image capturing device passes through the center position of the background plate 1.

The size of the target object is greatly different in each acquisition. If the image acquisition device 2 acquires images at the same position, the ratio of the target object in the images can be changed greatly. For example, when the size of the object a is proper in the image, if the object B is changed to be a smaller object, the proportion of the object B in the image will be very small, which greatly affects the subsequent 3D synthesis speed and accuracy. Therefore, the image acquisition device 2 can be driven to move back and forth on the horizontal support, and the proportion of the target object in the picture acquired by the image acquisition device 2 is ensured to be proper. Meanwhile, the head size of the user can be adjusted by adjusting the focal length. But generally the size of the human head is relatively fixed and therefore can be achieved with a fixed focal length.

3D Synthesis Process

According to the above-described acquisition method, the image acquisition device 2 acquires a set of images of the object by moving relative to the object;

the processing unit obtains 3D information of the object according to a plurality of images in the group of images. The specific algorithm is as follows. Of course, the processing unit may be directly disposed in the housing where the image capturing device 2 is located, or may be connected to the image capturing device 2 through a data line or in a wireless manner. For example, an independent computer, a server, a cluster server, or the like may be used as a processing unit, and image data acquired by the image acquisition device may be transmitted thereto to perform 3D synthesis. Meanwhile, the data of the image acquisition device can be transmitted to the cloud platform, and 3D synthesis is performed by utilizing the strong computing power of the cloud platform.

When the collected pictures are used for 3D synthesis, the existing algorithm can be adopted, and the optimized algorithm provided by the invention can also be adopted, and the method mainly comprises the following steps:

step 1: and performing image enhancement processing on all input photos. The contrast of the original picture is enhanced and simultaneously the noise suppressed using the following filters.

In the formula: g (x, y) is the gray value of the original image at (x, y), f (x, y) is the gray value of the original image at the position after being enhanced by the Wallis filter, and m_gIs the local gray average value, s, of the original image_gIs the local standard deviation of gray scale of the original image, m_fFor the transformed image local gray scale target value, s_fThe target value of the standard deviation of the local gray scale of the image after transformation. c belongs to (0, 1) as the expansion constant of the image variance, and b belongs to (0, 1) as the image brightness coefficient constant.

The filter can greatly enhance image texture modes of different scales in an image, so that the quantity and the precision of feature points can be improved when the point features of the image are extracted, and the reliability and the precision of a matching result are improved in photo feature matching.

The method mainly comprises the steps of ① constructing a Hessian matrix, generating all interest points for feature extraction, aiming at generating stable edge points (mutant points) of an image, ② constructing a scale space feature point position, comparing each pixel point processed by the Hessian matrix with 26 points in a two-dimensional image space and scale space neighborhood, preliminarily positioning key points, filtering weak key points compared with energy, screening out the finally positioned key points, selecting a stable key point, and taking the maximum charar direction as a wavelet characteristic vector matching region, taking the maximum charar direction of the wavelet characteristic vector matching region as a wavelet characteristic vector matching horizontal characteristic vector, taking the maximum charar direction of the wavelet characteristic vector matching region as a vertical characteristic vector matching vector, taking the maximum charar direction of the wavelet characteristic vector matching horizontal characteristic vector of two adjacent points as a vertical characteristic vector matching region, taking the maximum charar direction of the wavelet characteristic vector matching horizontal characteristic vector matching region as a vertical characteristic vector matching region, taking the maximum charar vector matching horizontal characteristic vector matching horizontal characteristic vector matching region as a vertical characteristic vector matching region, taking the wavelet characteristic vector matching region as a vertical characteristic vector matching region, taking the maximum charar matching vector matching horizontal characteristic vector matching region as a vertical characteristic vector matching region, taking the wavelet transform region as a vertical characteristic vector matching region, and a wavelet transform region, and a vertical characteristic vector matching region as a wavelet transform region, wherein the wavelet transform region, the wavelet.

And step 3: inputting matched feature point coordinates, resolving sparse human face three-dimensional point cloud and position and posture data of a photographing camera by using a light beam method adjustment, namely obtaining model coordinate values of the sparse human face model three-dimensional point cloud and the position; and performing multi-view photo dense matching by taking the sparse feature points as initial values to obtain dense point cloud data. The process mainly comprises four steps: stereo pair selection, depth map calculation, depth map optimization and depth map fusion. For each image in the input data set, we select a reference image to form a stereo pair for use in computing the depth map. Therefore, we can get rough depth maps of all images, which may contain noise and errors, and we use its neighborhood depth map to perform consistency check to optimize the depth map of each image. And finally, carrying out depth map fusion to obtain the three-dimensional point cloud of the whole scene.

And 4, step 4: and reconstructing a human face curved surface by using the dense point cloud. The method comprises the steps of defining an octree, setting a function space, creating a vector field, solving a Poisson equation and extracting an isosurface. And obtaining an integral relation between the sampling point and the indicating function according to the gradient relation, obtaining a vector field of the point cloud according to the integral relation, and calculating the approximation of the gradient field of the indicating function to form a Poisson equation. And (3) solving an approximate solution by using matrix iteration according to a Poisson equation, extracting an isosurface by adopting a moving cube algorithm, and reconstructing a model of the measured point cloud.

The method comprises the following steps of 5, carrying out full-automatic texture mapping on a face model, carrying out texture mapping after the surface model is built, wherein the main process comprises ① obtaining texture data to obtain a surface triangular surface grid of a target reconstructed through an image, ② analyzing the visibility of a triangular surface of the reconstructed model, calculating a visible image set and an optimal reference image of each triangular surface by using calibration information of the image, ③ clustering the triangular surfaces to generate texture patches, clustering the triangular surfaces into a plurality of reference image texture patches according to the visible image set, the optimal reference image and the neighborhood topological relation of the triangular surfaces, automatically sequencing ④ texture patches to generate texture images, sequencing the generated texture patches according to the size relation, generating the texture image with the minimum surrounding area, and obtaining texture mapping coordinates of each triangular surface.

It should be noted that the above algorithm is an optimization algorithm of the present invention, the algorithm is matched with the image acquisition condition, and the use of the algorithm takes account of the time and quality of the synthesis, which is one of the inventions of the present invention. Of course, it can be implemented using conventional 3D synthesis algorithms in the prior art, except that the synthesis effect and speed are somewhat affected.

Glasses matching and making

Step 1: first, the picture information of the head of the user is collected. The user sits on the seat 6 of the acquisition device, the height of the seat 6 is adjusted according to the height of the user, and meanwhile, the height of the background plate 1 and the height of the camera can also be adjusted, so that the center of the head of the user and the optical axis of the image acquisition device 2 are on the same horizontal plane. The horizontal position of the image acquisition device 2 is adjusted, so that the head of the user is positioned in the middle of the image, the acquisition is complete, and most area is occupied. The rotation means drives the rotation beam 3 through 360 ° so that the image acquisition device 2 rotates through 360 ° around the user's head. In the rotating process, the image acquisition device 2 acquires images at least once every L distance, so that a plurality of pictures of the head of the human body at different angles are obtained. Of course, for glasses matching, the front and side information of the human head is important, and the absence of the back information of the head does not hinder the matching and design of the glasses. Thus, the head part information may also be acquired at the time of acquisition, i.e. the range of rotation may be less than 360 °.

Step 2: and synthesizing the plurality of images into a head 3D model. Synthesizing a plurality of photos into a 3D model by using 3D synthesis software, and adding texture information after obtaining the 3D mesh model, thereby forming the head 3D model. Of course, in order to be compatible better, other existing synthesis methods can also implement the establishment of the 3D model, so that the adopted method can use a common 3D picture matching algorithm.

And 3, step 3: existing model glasses are matched with human faces. The step can be realized on an upper computer, a server, a cluster server or a cloud platform, can be independently arranged, and can also be shared with the 3D synthesis step. The method specifically comprises the following steps:

3-1: and importing a head 3D model, and displaying the model in a face front mode.

3-2: a plurality of point coordinates of the head 3D model are determined. The plurality of points are typically selected as points associated with the eyeglass frame, the two temples. For example, the part of the head that is intended to contact the eyeglasses can be selected: the ear root, the sides of the nose, as the basis for gross alignment. Determining coordinates P of a selection point₁(x₁,y₁,z₁)、P₂(x₂,y₂,z₂)、P₃(x₃,y₃,z₃). Of course, it is also possible to select points such as pinna, nose, etc. which do not contact the glasses, so that only a more imprecise coarse alignment and a fine adjustment are performed.

3-3: importing a 3D model of the glasses, and determining the P on the model of the glasses₁(x₁,y₁,z₁)、P₂(x₂,y₂,z₂)、 P₃(x₃,y₃,z₃) Point Q corresponding to point₁(X_g1,Y_g1,Z_g1)、Q₂(X_g2,Y_g2,Z_g2)、Q₃(X_g3,Y_g3,Z_g3). Will P₁And Q₁、P₂And Q₂、P₃And Q₃The respective lenses are aligned so that the 3D model of the glasses is substantially in place on the 3D model of the head, so that the glasses are substantially integrated with the head model.

For example, the sizes of the front glasses and the head are matched to be normalized according to the accurate size of a real object, so that when the sizes are matched, large deviation can not occur, the head is placed in the direction that the nose is in the front, the left ear and the right ear are behind, and the front glasses and the head are arranged in a left-right mode.

Spatial coordinates (0,90,0) (100,89,0) (52,89,56) are selected above the left ear, right ear, nose, respectively. Suppose the spatial coordinates of the nose, left ear and right ear corresponding to the spectacle model are (0,0,0) (-50,0-45) (50, 0-45).

First, the nose is aligned

Translation of spatial dimensions of all points of the glasses

x_delta＝52-0＝52

y_delta＝89-0＝89

z_delta＝56-0＝56

Second, spatial point translation of the eyewear model

Nose corresponding point (0+52 ═ 52, 0+89 ═ 89,0+56 ═ 56)

Left ear corresponding point (-50+52 ═ 2,0+89 ═ 89-45+56 ═ 11)

Right ear corresponding point (50+52 ═ 102,0+89 ═ 89, -45+56 ═ 11)

Optional, manual trimming

And zooming in the Z-axis direction, namely zooming the left side of the Z-axis of the glasses, so that the coordinate of the Z-axis 11 is approximately in the position of 0, and the glasses legs are approximately matched and compacted with the human face.

3-4: and (4) accurate alignment. And displaying the matching effect to the user through the display. The user or the operator observes the matched 3D model of the glasses and the head model in the display, and drags and moves the glasses model or the head model, so that the glasses model and the head model are accurately aligned and meet the common wearing requirements. In addition to manual fine adjustment, automatic fine adjustment may also be implemented, with adjustment modes including translation, rotation, and zooming.

For example, the space has a point A (12,23,34)

1. Translate point A (5,6,7)

New coordinates of translated point A

X’＝x+5＝17

Y’＝23+6＝29

Z’＝34+7＝41

The spatial coordinates of the point A after translation are (17,29,41)

2. Scaling the coordinate of the point A by 2 times in the X direction, scaling the coordinate of the point A by 0.8 time in the y direction, and scaling the coordinate of the point A by 10 times in the z direction

X’＝12*2＝24

Y’＝23*0.8＝18.4

Y’＝34*10＝340

The space coordinate of the zoomed point A is (24,18.4,340)

3. Point a is rotated 30 degrees along the X-axis,

coordinate of point A rotated by 30 degrees

X’＝12

Y’＝23*cos30。-23*sin30。＝23*0.866-23*0.5＝8.418

Z’＝34*sin30。-34*cos30。＝34*0.5-34*0.866＝-12.444

Spatial coordinates of point A rotated 30 degrees along the X-axis (12,8.418, -12.444)

The same principle is applied along the Y-axis and the z-axis.

3-5: the eyewear data is modified. Besides matching, the user can change the shape of the glasses on the basis of the preset glasses on the matched glasses and the 3D model of the head, so that personalized customization can be realized. And the final designed wearing effect is displayed to the user through the display. For example, a round temple may be modified to be square; the 5mm wide side of the glasses legs can be modified into 6mm wide; the glasses frame can be provided with bulges or depressions at certain positions, and other ways of changing the shape and the size of the glasses frame.

3-6: and 3D data output. And 3, outputting the 3D data obtained in the steps 3-4 and 3-5 to a 3D printer or a processing platform, and processing and manufacturing according to the selected 3D glasses model.

The rotation movement of the invention is that the front position collection plane and the back position collection plane are crossed but not parallel in the collection process, or the optical axis of the front position image collection device and the optical axis of the back position image collection device are crossed but not parallel. That is, the capture area of the image capture device moves around or partially around the target, both of which can be considered as relative rotation. Although the embodiment of the present invention exemplifies more orbital rotation, it should be understood that the limitation of the present invention can be used as long as the non-parallel motion between the acquisition region of the image acquisition device and the target object is rotation. The scope of the invention is not limited to the embodiment with track rotation.

The adjacent acquisition positions refer to two adjacent positions on a movement track where acquisition actions occur when the image acquisition device moves relative to a target object. This is generally easily understood for the image acquisition device movements. However, when the target object moves to cause relative movement between the two, the movement of the target object should be converted into the movement of the target object, which is still, and the image capturing device moves according to the relativity of the movement. And then measuring two adjacent positions of the image acquisition device in the converted movement track.

The target object, and the object all represent objects for which three-dimensional information is to be acquired. The object may be a solid object or a plurality of object components. For example, the head, hands, etc. The three-dimensional information of the target object comprises a three-dimensional image, a three-dimensional point cloud, a three-dimensional grid, a local three-dimensional feature, a three-dimensional size and all parameters with the three-dimensional feature of the target object. Three-dimensional in the present invention means having XYZ three-direction information, particularly depth information, and is essentially different from only two-dimensional plane information. It is also fundamentally different from some definitions, which are called three-dimensional, panoramic, holographic, three-dimensional, but actually comprise only two-dimensional information, in particular not depth information.

In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the claims, any of the claimed embodiments may be used in any combination.

The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It will be appreciated by those skilled in the art that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functionality of some or all of the components in an apparatus in accordance with embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.

Thus, it should be appreciated by those skilled in the art that while a number of exemplary embodiments of the invention have been illustrated and described in detail herein, many other variations or modifications consistent with the principles of the invention may be directly determined or derived from the disclosure of the present invention without departing from the spirit and scope of the invention. Accordingly, the scope of the invention should be understood and interpreted to cover all such other variations or modifications.

Claims

1. An eyeglass fitting method characterized by: comprises that

step 2: synthesizing a plurality of images into a head 3D model;

3-1, determining a plurality of point coordinates of the head 3D model;

3-4 display the matching effect to the user.

2. An eyewear apparatus characterized by: the system comprises a 3D acquisition device, a 3D synthesis device, a glasses adaptation device and a display device;

3. An eyewear apparatus characterized by: the system comprises a 3D acquisition device, a 3D synthesis device, a glasses adaptation device and a display device;

wherein L is the linear distance between the optical centers of the two position image acquisition devices; f is the focal length of the image acquisition device; d is the rectangular length of the photosensitive element of the image acquisition device; t is the distance from the photosensitive element of the image acquisition device to the surface of the target along the optical axis; delta is an adjustment coefficient;

and δ <0.603, preferably δ <0.410, or δ < 0.356. Or δ < 0.311; or δ < 0.284; or δ < 0.261; or δ < 0.241; or δ < 0.107.

4. The apparatus and method of claims 2-3, wherein: projected in a direction perpendicular to the surface of the background plate, and the projection shape has a length W in the horizontal direction₁Length W in the vertical direction of the projected shape₂Is determined by the following conditions:

wherein A is₁>1.04，A₂>1.04; preferably, A₁>1.25，A₂>1.25。

5. The apparatus and method of claims 2-3, wherein: marking points are also included.

6. The apparatus and method of claim 5, wherein: the mark points are positioned on the seat.

7. The apparatus and method of claims 2-3, wherein: the 3D synthesis device and the glasses adapting device are separately arranged or realized on the same platform.

8. The apparatus and method of claims 2-3, wherein: the glasses adaptation device is also used for glasses data modification.

9. The apparatus and method of claims 1-3, wherein: the adapting of the 3D model of the head and the 3D model of the glasses comprises first performing a coarse alignment of the 3D model of the head and the 3D model of the glasses and then performing a secondary alignment of the 3D model of the head and the 3D model of the glasses.

10. The apparatus and method of claims 1-3, wherein: and sending the 3D data of the glasses to the processing equipment.