Absolute posture control method and device for three-dimensional objects based on fingerprint images

Through the three-dimensional object absolute attitude control method based on fingerprint images, the mapping problem between two-dimensional signals and three-dimensional attitude control in the existing technology is solved, and intuitive and convenient three-dimensional attitude control is realized, which reduces equipment costs and expands the human-computer interaction method. .

CN114356102BActive Publication Date: 2024-12-03TSINGHUA UNIVERSITY
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202210114014.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-01-30
Publication Date
2024-12-03
Estimated Expiration
2042-01-30

AI Technical Summary

Technical Problem

The existing two-dimensional control signals used in three-dimensional attitude control systems require complex mapping, which is difficult to meet human intuitive feelings, and traditional equipment is expensive and difficult to popularize.

Method used

The absolute attitude control method of three-dimensional object based on fingerprint images is adopted. By collecting finger fingerprint images in real time, the three-dimensional attitude is estimated, and mapping it into three-dimensional input signals, the absolute attitude of the target object in three-dimensional space is controlled.

Benefits of technology

It provides a more intuitive and convenient three-dimensional attitude control method, reduces equipment costs, expands human-computer interaction methods, and improves control accuracy and speed.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114356102B_ABST
    Figure CN114356102B_ABST
Patent Text Reader

Abstract

The present invention proposes a method and device for controlling the absolute posture of a three-dimensional object based on a fingerprint image, wherein the method includes: collecting the fingerprint image of the current finger in real time; inferring the three-dimensional posture of the current finger based on the sequence image; mapping the three-dimensional posture of the current finger into a three-dimensional input signal, and controlling the absolute posture of the target object in three-dimensional space based on the three-dimensional input signal; using the absolute posture obtained after control as the target posture, and calculating the transformation path of the controlled object to the target posture. The three-dimensional absolute posture control method of the present invention can effectively expand the existing human-computer interaction mode and provide convenience for the posture control of objects in three-dimensional space.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of human-computer interaction, and in particular to the problem of three-dimensional posture control. Background Art

[0002] With the continuous development of human-computer interaction technology, the interaction between humans and machines has been constantly changing and developing. In the fields of games, virtual reality (VR), security monitoring, spacecraft control, vehicle control, robot control, three-dimensional design, etc., most objects such as cameras, 3D models, airplanes, and cars exist in three-dimensional space, so it is a very important requirement to be able to accurately and efficiently control the three-dimensional posture of the target object. Among the existing technologies, there are still few object posture control systems that directly output three-dimensional control signals. The commonly used control input device is a traditional mouse, and then the posture of the target object is controlled by controlling the moving direction, speed and displacement distance of the mouse on a two-dimensional plane. Since the controlled object often exists in three-dimensional space, it is necessary to perform complex mapping between the 2D signal output by the traditional mouse and the three-dimensional posture. Intuitively speaking, directly using the control signal in three-dimensional space is more in line with human intuition, so it can greatly improve the accuracy and speed of the control system.

[0003] The existing three-dimensional target object posture control scheme still has the following limitations and shortcomings:

[0004] The 3D attitude control system based on 2D control signals requires a separate design of the mapping relationship between 2D signals and 3D attitude control. Therefore, the control method does not conform to human intuition and requires users to spend a certain amount of time and degree of learning before use. In addition, users need to constantly monitor the attitude changes of the target object during use to perceive the current control feedback.

[0005] In addition to traditional mice, 3D mice inspired by spacecraft control have also emerged to cope with more complex three-dimensional posture control scenarios. However, most of these devices require complex and sophisticated mechanical structure designs, which makes them expensive and difficult to integrate with existing human-computer interaction devices, which is not conducive to their popularization in a large consumer market. Summary of the invention

[0006] The present invention aims to solve one of the technical problems in the related art at least to a certain extent.

[0007] To this end, the first object of the present invention is to propose a three-dimensional object absolute posture control method based on fingerprint images, which is used to facilitate the posture control of objects in three-dimensional space.

[0008] The second object of the present invention is to provide a three-dimensional object absolute posture control device based on fingerprint images.

[0009] To achieve the above-mentioned purpose, the first aspect of the embodiment of the present invention proposes a method for absolute posture control of a three-dimensional object based on a fingerprint image, including: real-time acquisition of the fingerprint image of the current finger; inferring the three-dimensional posture of the current finger based on the sequence image; mapping the three-dimensional posture of the current finger into a three-dimensional input signal, and controlling the absolute posture of the target object in the three-dimensional space according to the three-dimensional input signal; using the absolute posture obtained after control as the target posture, and calculating the transformation path for transforming the controlled object to the target posture.

[0010] The fingerprint image-based three-dimensional object absolute posture control method proposed in the embodiment of the present invention, given a fingerprint image of a certain finger collected on a certain interactive device, can first predict the three-dimensional posture of the finger, and use it to control the target object in the real world or the virtual world, thereby serving as a new type of human-computer interaction system. In the present invention, the three-dimensional posture of the current finger is first predicted based on the 2D fingerprint image collected by the sensor, and then the three-dimensional posture of the finger is used as an input control signal to perform posture control on the target object in the real world or the virtual world. In the present invention, the input of the three-dimensional absolute posture control system is a 2D fingerprint image, and the output is the three-dimensional posture of the current finger, which is used to control the three-dimensional absolute posture of the target object. The three-dimensional absolute posture control system of the present invention can effectively expand the existing human-computer interaction mode and provide convenience for the posture control of objects in three-dimensional space.

[0011] In addition, the three-dimensional object absolute posture control method based on fingerprint image according to the above embodiment of the present invention may also have the following additional technical features:

[0012] Furthermore, in one embodiment of the present invention, real-time acquisition of the fingerprint image of the current finger also includes:

[0013] The fingerprint sequence images are preprocessed to remove background noise and enhance fingerprint ridges.

[0014] Furthermore, in one embodiment of the present invention, mapping the three-dimensional posture of the current finger into a three-dimensional input signal, and controlling the absolute posture of the target object in the three-dimensional space according to the three-dimensional input signal includes:

[0015] The mapping relationship between the finger posture and the posture of the controlled object is flexibly selected as needed, including mapping the roll angle of the finger to the yaw angle of the object, and mapping the pitch angle of the finger to the roll angle of the object, using mapping functions with the same accuracy;

[0016] Map the two angles of the finger to the same angle of the object at the same time, using mapping functions with different precisions.

[0017] Furthermore, in one embodiment of the present invention, before controlling the absolute posture of the target object in the three-dimensional space according to the three-dimensional input signal, the method further includes:

[0018] Fingerprint recognition and verification are performed on the fingerprint image, including frame-by-frame verification and first-frame verification; wherein, frame-by-frame verification includes that each frame of the fingerprint image needs to undergo fingerprint recognition and verification before subsequent object posture control is allowed; first-frame verification includes fingerprint recognition of the first frame of the fingerprint image, and after the verification is passed, the finger is kept on the control device to continue subsequent object posture control.

[0019] Furthermore, in one embodiment of the present invention, it also includes:

[0020] Different angle mapping functions are set for different fingerprint images, and the corresponding angle mapping function is called based on the fingerprint recognition result.

[0021] To achieve the above-mentioned purpose, the second embodiment of the present invention proposes a three-dimensional object absolute posture control based on fingerprint image, which includes: an acquisition module, which is used to acquire the fingerprint image of the current finger in real time; a prediction module, which is used to infer the three-dimensional posture of the current finger based on the sequence image; a mapping module, which is used to map the three-dimensional posture of the current finger into a three-dimensional input signal, and control the absolute posture of the target object in the three-dimensional space according to the three-dimensional input signal; a solution module, which is used to use the absolute posture obtained after control as the target posture, and calculate the transformation path of transforming the controlled object to the target posture.

[0022] Furthermore, in one embodiment of the present invention, the acquisition module is also used to:

[0023] The fingerprint sequence images are preprocessed to remove background noise and enhance fingerprint ridges.

[0024] Furthermore, in one embodiment of the present invention, the mapping module is further used to:

[0025] Before controlling the absolute posture of the target object in the three-dimensional space according to the three-dimensional input signal,

[0026] The fingerprint image is subjected to fingerprint recognition verification, including frame-by-frame verification and first-frame verification; wherein, the frame-by-frame verification includes that each frame of the fingerprint image needs to undergo fingerprint recognition and verification before subsequent object posture control is allowed; the first-frame verification includes performing fingerprint recognition on the first-frame image of the fingerprint image, and after the verification is passed, the finger is kept on the control device to continue the subsequent object posture control.

[0027] Furthermore, in one embodiment of the present invention, a verification module is also included, which is used to:

[0028] Different angle mapping functions are set for different fingerprint images, and the corresponding angle mapping function is called based on the fingerprint recognition result.

[0029] Furthermore, in one embodiment of the present invention, a personalized control module is also included, which is used to:

[0030] By combining fingerprint recognition technology with fingerprint-based three-dimensional posture control, personalized control parameters can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0032] Figure 1 A schematic flow chart of a method for absolute posture control of a three-dimensional object based on a fingerprint image provided by an embodiment of the present invention.

[0033] Figure 2 A schematic diagram of a flow chart of a three-dimensional object absolute posture control device based on fingerprint images provided in an embodiment of the present invention.

[0034] Figure 3 This is a flow chart of a three-dimensional absolute posture control system based on fingerprint images provided in an embodiment of the present invention.

[0035] Figure 4 A schematic diagram of finger gesture definition provided by an embodiment of the present invention.

[0036] Figure 5 A schematic diagram of the coverage intervals of commonly used finger gestures provided by an embodiment of the present invention.

[0037] Figure 6 A schematic diagram of a linear control signal curve provided by an embodiment of the present invention.

[0038] Figure 7 A schematic diagram of a nonlinear control signal curve provided by an embodiment of the present invention.

[0039] Figure 8 A schematic diagram of a frame-by-frame verification posture control system provided by an embodiment of the present invention.

[0040] Fig. 9 A schematic diagram of a posture control system for first frame verification provided by an embodiment of the present invention.

[0041] Fig.10 A schematic diagram of an adaptive posture control system based on fingerprint verification provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0042] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0043] The following describes a method and device for absolute posture control of a three-dimensional object based on a fingerprint image according to an embodiment of the present invention with reference to the accompanying drawings.

[0044] Figure 1 A schematic flow chart of a method for absolute posture control of a three-dimensional object based on a fingerprint image provided by an embodiment of the present invention.

[0045] like Figure 1 As shown, the three-dimensional object absolute posture control method based on fingerprint image includes the following steps:

[0046] S1: collect the fingerprint image of the current finger in real time;

[0047] With the continuous development of fingerprint sensing technology, in addition to the traditional optical fingerprint collection method, fingerprint collection devices can also be integrated into various existing touch screen devices to obtain fingerprint images. The ridge information of the fingerprint contains rich finger information, including the finger posture information when collecting the fingerprint, so the three-dimensional posture of the finger can be inferred based on the fingerprint image. The finger posture is used as a three-dimensional input signal, so the three-dimensional posture of the target object can be conveniently and intuitively controlled. The target objects here include cameras, 3D models, robotic arms, vehicles, spacecraft and other objects that require multi-degree-of-freedom control. At the same time, the finger posture signal based on the fingerprint image can also be combined with a variety of human-computer interaction technologies (such as gesture operations based on the touch screen) to further expand the diversity of interaction methods, and the control system combined with fingerprint identity information also has higher security and personalized settings.

[0048] The present invention is divided into three stages as a whole, namely, collecting fingerprint images, obtaining finger postures, and controlling the postures of target objects. In the first stage, the fingerprint image in the fingerprint collection device is obtained. Since human-computer interaction generally requires high real-time performance, the collection of fingerprint images is carried out in real time; in the second stage, the three-dimensional posture of the current finger is predicted based on the collected fingerprint image as the signal input of the subsequent control system; in the third stage, the obtained three-dimensional posture of the finger is used as a control signal to control the absolute posture of the target object in three-dimensional space. The first stage is the basic step of the present invention. The collected fingerprint image contains the three-dimensional posture information of the current finger; the second stage estimates the three-dimensional posture of the finger based on the fingerprint image; the third stage uses the predicted three-dimensional posture of the finger as the posture control signal of the control system, thereby specifying the target posture of the controlled object in three-dimensional space, and through posture path planning, the controlled object reaches the target three-dimensional posture specified by the user's finger. The present invention includes the collection of fingerprint images, the estimation of the three-dimensional posture of the finger based on the fingerprint image, and the three-dimensional posture control of the target object based on the finger posture. The flowchart of the present invention is shown in the attached Figure 3 The present invention also proposes combining fingerprint recognition with gesture control to achieve security and personalization of control.

[0049] The present invention needs to collect fingerprint images. Compared with the capacitive images in traditional touch screen devices, fingerprint images contain more information about the shape and posture of the finger, so they can be used to accurately estimate the posture of the finger in three-dimensional space. There are many sensing technologies for acquiring fingerprint images, such as optical fingerprint collectors, optical under-screen fingerprint collectors, and ultrasonic under-screen fingerprint collectors. The present invention can be applied to various fingerprint sensing technologies. Since the estimated three-dimensional posture of the finger is required to control the three-dimensional posture of the target object in real time and accurately, it is necessary to collect the fingerprint image data in real time, that is, to collect fingerprint sequence image data.

[0050] S2: infer the 3D posture of the current finger according to the sequence image; map the 3D posture of the current finger into a 3D input signal, and control the absolute posture of the target object in the 3D space according to the 3D input signal;

[0051] Furthermore, in one embodiment of the present invention, real-time acquisition of the fingerprint image of the current finger also includes:

[0052] The fingerprint sequence images are preprocessed to remove background noise and enhance fingerprint ridges.

[0053] According to the fingerprint ridge direction, fingerprint area shape and other information in the fingerprint image, the three-dimensional posture of the current finger can be inferred. The following only describes a typical finger posture estimation algorithm to assist in understanding this stage of the present invention. Specifically, the present invention estimates the three-dimensional posture of the current finger based on the collected fingerprint image as a subsequent control signal.

[0054] Since the fingerprint image modality and quality obtained by different sensors vary greatly, it is necessary to preprocess the acquired image first to remove background noise and enhance the fingerprint ridges. The three-dimensional posture of the current finger is estimated based on the preprocessed fingerprint image. In the present invention, the posture estimation algorithm based on deep learning is taken as an example. The input of the algorithm is the fingerprint image after image preprocessing, and the output is the predicted three-dimensional posture of the finger. The definition of the three-dimensional posture of the finger is shown in the attached Figure 4 , represented by three angles, namely the roll angle α, the pitch angle β and the yaw angle γ.

[0055] S3: mapping the current three-dimensional posture of the finger into a three-dimensional input signal, and controlling the absolute posture of the target object in the three-dimensional space according to the three-dimensional input signal;

[0056] Furthermore, in one embodiment of the present invention, mapping the three-dimensional posture of the current finger into a three-dimensional input signal, and controlling the absolute posture of the target object in the three-dimensional space according to the three-dimensional input signal includes:

[0057] The mapping relationship between the finger posture and the posture of the controlled object is flexibly selected as needed, including mapping the roll angle of the finger to the yaw angle of the object, and mapping the pitch angle of the finger to the roll angle of the object, using mapping functions with the same accuracy;

[0058] Map the two angles of the finger to the same angle of the object at the same time, using mapping functions with different precisions.

[0059] The absolute posture control of the target object in the present invention is divided into two steps, namely, mapping of finger posture and object posture control and posture transformation solution.

[0060] First, the three-dimensional posture of the finger P = (p α , p β , p γ), this posture can be mapped into a three-dimensional control signal to control the three-dimensional posture of the target object (such as a camera, 3D model, etc.). Taking into account the different finger operation habits of different users when controlling the posture of an object, it is necessary to first specify the finger three-dimensional posture zero point P0. There are many ways to define the zero point, which can be set to a fixed value (such as a roll angle of 0°, a pitch angle of -45°, and a yaw angle of 0°); or a specific frame of fingerprint image can be selected (such as the first frame image obtained at the beginning of the interaction), and then the three-dimensional posture of the finger estimated based on the image is used as the zero point P0. The present invention takes this zero point definition method as an example to calculate the relative value of the finger posture estimated based on each frame image in the previous stage relative to the posture zero point P0.

[0061] P′=(p′ α , p′ β , p′ γ ),

[0062] And map it as the input signal of the gesture control system. Figure 5 ), in order to completely and fully control the 3D absolute posture of the target object, it is also necessary to map the 3D posture of the finger as the control signal to the control range. Set Q = (q α ,q β ,q γ ) is the target posture of the controlled object, and the following mapping is an example:

[0063] q α =g1(p′ α )

[0064] q β =g2(p′ β )

[0065] q γ =g3(p′ γ )

[0066] Among them, g1(·), g2(·), g3(·), etc. are control signal functions that map the three-dimensional posture of the finger to the three-dimensional posture of the target object. There are many ways to define the mapping function. In the present invention, a simple linear mapping function q(x)=sx is taken as an example (see Appendix Figure 6 As shown), the three-dimensional absolute attitude control system is explained.

[0067] When |s| = 1, g(·) is an identity mapping, and the estimated 3D posture of the finger is directly used as the target posture of the controlled object. In this mapping method, since the posture range that the finger can reach is limited (such as the attached Figure 5 As a result, the controllable three-dimensional posture range will be limited;

[0068] When |s| < 1, g(·) is a compression mapping, which reduces the estimated finger 3D posture value and uses it as the target posture of the controlled object. In this mapping method, a large range of finger posture changes will cause a small range of changes in the posture of the controlled object, so the posture of the object can be controlled more precisely.

[0069] When |s|>1, g(·) is an amplification mapping, which amplifies the estimated finger 3D posture value as the target posture of the controlled object. In this mapping method, a small range of finger posture changes will cause a large range of changes in the posture of the controlled object. Therefore, the posture of the object can be roughly controlled over a large range and quickly, and the target object can be transformed to the desired 3D posture more quickly.

[0070] Another type of mapping is nonlinear mapping. Figure 7 As shown in the figure, for example, the finger posture can be quantized into a number of discrete object postures. At this time, the object can be quickly and accurately adjusted to a common posture without considering the slight differences in the finger posture.

[0071] Considering that the comfort ranges of different angles (roll, pitch and yaw) of the same finger are different and the ranges of fingerprint information are also different, different angles can use their own mapping functions. For example, since the pitch angle of the finger can change in a small range (about 90 degrees), using an enlarged mapping of s=4 on the pitch angle can increase the range of posture changes of the controlled object to 360 degrees. Although the effective range of the yaw angle can be 360 ​​degrees, the comfortable range is about 90 degrees, and an enlarged mapping of s=4 can also be used. The range of the roll angle is about 180 degrees, so an enlarged mapping of s=2 is used.

[0072] There are many mapping relationships between finger postures and the postures of the controlled object. The names do not need to be consistent, but the mapping relationship can be flexibly selected as needed. For example, the roll angle of the finger can be mapped to the yaw angle of the object, and the pitch angle of the finger can be mapped to the roll angle of the object. You can even map the two angles of the finger to the same angle of the object at the same time, but use mapping functions of different precisions, so that different precision posture control can be achieved through one finger.

[0073] S4: Taking the absolute posture obtained after control as the target posture, calculating the transformation path for transforming the controlled object to the target posture.

[0074] After the target posture of the controlled object is given, the object needs to be transformed to the target posture specified by the finger. In this step, the posture transformation method varies greatly depending on the controlled object. For example, when controlling a three-dimensional object in the virtual world, the object can be directly transformed to the target posture without considering the limitations of physical laws. However, when controlling objects in the real world such as robotic arms and surveillance cameras, since the posture cannot be changed instantaneously, path planning is required based on the target posture to calculate the optimal path required for the object to transform to the target posture. This problem is a relatively mature problem in the field of robot control, and there are many mature algorithms that can be used. The following only describes a simple transformation path for illustration: First, calculate the relative posture transformation of the target posture to be achieved relative to the current object posture, and express this posture transformation with axis angles: axis and angle It means that the controlled object can be rotated from the current posture to the target posture by an angle of θ around the axis ω. According to this posture transformation formula, the object posture transformation process can be smoothly transformed to the target posture within a certain time interval by time interpolation.

[0075] The following examples illustrate the application of the three-dimensional absolute posture control system of the present invention to several common target object controls. The following objects can exist in the virtual world or the real world. For a three-dimensional object model, the roll angle of the finger can be simply mapped to the roll angle of the object, the pitch angle can be mapped to the pitch angle of the object, and the yaw angle can be mapped to the yaw angle of the object; for camera control, the roll angle of the finger can be mapped to the roll rotation of the camera, the pitch angle can be mapped to the up and down pitch of the camera, and the yaw angle can be mapped to the left and right rotation of the camera; for PTZ camera control, the pitch angle of the finger can be mapped to the up and down pitch of the camera, and the yaw angle can be mapped to the left and right rotation of the camera; for quadcopter control, the roll angle of the finger can be mapped to the left and right roll and displacement of the aircraft, and the pitch angle can be mapped to the front and back roll and displacement of the aircraft; for fixed-wing aircraft control, the mapping method is more direct, and the roll angle of the finger can be mapped to the roll control of the aircraft, and the pitch angle can be mapped to the pitch control.

[0076] Furthermore, in one embodiment of the present invention, before controlling the absolute posture of the target object in the three-dimensional space according to the three-dimensional input signal, the method further includes:

[0077] Fingerprint recognition and verification are performed on the fingerprint image, including frame-by-frame verification and first-frame verification; wherein, frame-by-frame verification includes that each frame of the fingerprint image needs to undergo fingerprint recognition and verification before subsequent object posture control is allowed; first-frame verification includes fingerprint recognition of the first frame of the fingerprint image, and after the verification is passed, the finger is kept on the control device to continue subsequent object posture control.

[0078] In addition, by combining the existing fingerprint recognition technology with fingerprint-based gesture control, the security and privacy control of the control system can be further expanded. For example, in a highly confidential control system, only legal registered users are allowed to control. The following describes two methods of introducing fingerprint recognition. Figure 8 This is a schematic diagram of the frame-by-frame verification method. In this case, each frame of the image needs to be verified by the fingerprint recognition system before subsequent object posture control is allowed. Fig. 9 This is a schematic diagram of the first-frame verification method. At this time, only the first-frame image when the finger is pressed needs to be fingerprinted. After the verification is passed, as long as the finger does not leave the control device, subsequent object posture control can continue. Once the finger leaves, re-identification is required.

[0079] Furthermore, in one embodiment of the present invention, it also includes:

[0080] Different angle mapping functions are set for different fingerprint images, and the corresponding angle mapping function is called based on the fingerprint recognition result.

[0081] In addition, by combining fingerprint recognition technology with fingerprint-based gesture control, personalized control parameters can be achieved. For example, for multiple registered fingerprints (fingerprints of different users or different fingerprints of one user), set their own angle mapping functions. The corresponding angle mapping function is called based on the fingerprint recognition result, while the default angle mapping function (such as the attached Fig.10 shown).

[0082] The fingerprint image-based three-dimensional object absolute posture control method proposed in the embodiment of the present invention, given a fingerprint image of a certain finger collected on a certain interactive device, can first predict the three-dimensional posture of the finger, and use it to control the target object in the real world or the virtual world, thereby serving as a new type of human-computer interaction system. In the present invention, the three-dimensional posture of the current finger is first predicted based on the 2D fingerprint image collected by the sensor, and then the three-dimensional posture of the finger is used as an input control signal to perform posture control on the target object in the real world or the virtual world. In the present invention, the input of the three-dimensional absolute posture control system is a 2D fingerprint image, and the output is the three-dimensional posture of the current finger, which is used to control the three-dimensional absolute posture of the target object. The three-dimensional absolute posture control system of the present invention can effectively expand the existing human-computer interaction mode and provide convenience for the posture control of objects in three-dimensional space.

[0083] In order to implement the above embodiment, the present invention also proposes a three-dimensional object absolute posture control device based on fingerprint image.

[0084] Figure 2A schematic structural diagram of a three-dimensional object absolute posture control device based on fingerprint images provided in an embodiment of the present invention.

[0085] like Figure 2 As shown, the fingerprint image-based three-dimensional object absolute posture control device includes: an acquisition module 10, a prediction module 20, a mapping module 30, and a solution module 40, wherein the acquisition module is used to acquire the fingerprint image of the current finger in real time; the prediction module is used to infer the three-dimensional posture of the current finger based on the sequence image; the mapping module is used to map the three-dimensional posture of the current finger into a three-dimensional input signal, and control the absolute posture of the target object in the three-dimensional space according to the three-dimensional input signal; the solution module is used to use the absolute posture obtained after control as the target posture, and calculate the transformation path of transforming the controlled object to the target posture.

[0086] Furthermore, in one embodiment of the present invention, the acquisition module is also used to:

[0087] The fingerprint sequence images are preprocessed to remove background noise and enhance fingerprint ridges.

[0088] Furthermore, in one embodiment of the present invention, the mapping module is further used to:

[0089] Before controlling the absolute posture of the target object in the three-dimensional space according to the three-dimensional input signal,

[0090] The fingerprint image is subjected to fingerprint recognition verification, including frame-by-frame verification and first-frame verification; wherein, the frame-by-frame verification includes that each frame of the fingerprint image needs to undergo fingerprint recognition and verification before subsequent object posture control is allowed; the first-frame verification includes performing fingerprint recognition on the first-frame image of the fingerprint image, and after the verification is passed, the finger is kept on the control device to continue the subsequent object posture control.

[0091] Furthermore, in one embodiment of the present invention, a verification module is also included, which is used to:

[0092] Different angle mapping functions are set for different fingerprint images, and the corresponding angle mapping function is called based on the fingerprint recognition result.

[0093] Furthermore, in one embodiment of the present invention, a personalized control module is also included, which is used to:

[0094] By combining fingerprint recognition technology with fingerprint-based three-dimensional posture control, personalized control parameters can be achieved.

[0095] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0096] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0097] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A three-dimensional object absolute posture control method based on fingerprint image, characterized in that: The following steps are involved: The fingerprint image of the current finger is collected in real time by an optical fingerprint collector and / or an ultrasonic fingerprint collector to obtain fingerprint sequence image data, and the fingerprint image is preprocessed to remove background noise and enhance the fingerprint ridges; According to the processed fingerprint sequence image data, the three-dimensional posture of the current finger is inferred P = (p α , p β , p γ ); Mapping the three-dimensional posture of the current finger into a three-dimensional input signal, and controlling the absolute posture of a target object in three-dimensional space according to the three-dimensional input signal, wherein the target object includes a robotic arm, a vehicle, a robot, and a spacecraft; The absolute posture obtained after control is used as the target posture, and the transformation path of the controlled object to the target posture is calculated; The three-dimensional posture of the finger estimated based on the image is used as the zero point P0 of the three-dimensional posture of the finger, and the relative value of the finger posture estimated based on each frame of the image relative to the zero point P0 of the three-dimensional posture of the finger is calculated, P′=(p α ′,p β ′,p γ ′), maps it to the input signal of the posture control system, and maps the finger three-dimensional posture as the control signal on the control range, setting Q = (q α ,q β ,q γ ) is the target posture of the controlled object, which has the following mapping: q α =g1 (p′ α ) q β =g2 (p′ β ) q γ =g3 (p′ γ ) Among them, g1 (·), g2 (·), and g3 (·) are control signal functions that map the three-dimensional posture of the finger to the three-dimensional posture of the target object. The mapping function is defined as the linear mapping function number q(x) = sx. When |s| = 1, g(·) is an identity mapping, and the estimated three-dimensional posture of the finger is directly used as the target posture of the controlled object. When |s| < 1, g(·) is a compression mapping, and the estimated three-dimensional posture value of the finger is reduced and used as the target posture of the controlled object. When |s| > 1, g(·) is an enlargement mapping, and the estimated three-dimensional posture value of the finger is enlarged and used as the target posture of the controlled object.

2. The method according to claim 1, characterized in that Mapping the three-dimensional posture of the current finger into a three-dimensional input signal, and controlling the absolute posture of the target object in the three-dimensional space according to the three-dimensional input signal, comprises: The mapping relationship between the finger posture and the posture of the controlled object is flexibly selected as needed, including mapping the roll angle of the finger to the yaw angle of the object, and mapping the pitch angle of the finger to the roll angle of the object, using mapping functions with the same accuracy; Map the two angles of the finger to the same angle of the object at the same time, using mapping functions with different precisions.

3. The method according to claim 1, characterized in that Before controlling the absolute posture of the target object in the three-dimensional space according to the three-dimensional input signal, the method further includes: The fingerprint image is subjected to fingerprint recognition verification, including frame-by-frame verification and first-frame verification; wherein, the frame-by-frame verification includes that each frame of the fingerprint image needs to undergo fingerprint recognition and verification before subsequent object posture control is allowed; the first-frame verification includes performing fingerprint recognition on the first-frame image of the fingerprint image, and after the verification is passed, the finger is kept on the control device to continue subsequent object posture control.

4. The method according to claim 3, characterized in that Also includes: Respective angle mapping functions are set for different fingerprint images, and the corresponding angle mapping function is called based on the result of the fingerprint recognition.

5. A three-dimensional object absolute posture control device based on fingerprint image, characterized in that: include: The acquisition module acquires the fingerprint image of the current finger in real time through an optical fingerprint acquisition device, an electrical fingerprint acquisition device, and / or an ultrasonic fingerprint acquisition device to obtain fingerprint sequence image data, pre-processes the fingerprint image, removes background noise, and enhances the fingerprint ridges; The prediction module infers the three-dimensional posture of the current finger based on the processed fingerprint sequence image data; a mapping module, mapping the three-dimensional posture of the current finger into a three-dimensional input signal, and controlling the absolute posture of a target object in three-dimensional space according to the three-dimensional input signal, wherein the target object includes a robotic arm, a vehicle, a robot, and a spacecraft; The solving module takes the absolute posture obtained after control as the target posture and calculates the transformation path of the controlled object to the target posture; The three-dimensional posture of the finger estimated based on the image is used as the zero point P0 of the three-dimensional posture of the finger, and the relative value of the finger posture estimated based on each frame of the image relative to the zero point P0 of the three-dimensional posture of the finger is calculated, P′=(p α ′,p β ′,p γ ′), maps it to the input signal of the posture control system, and maps the finger three-dimensional posture as the control signal on the control range, setting Q = (q α ,q β ,q γ ) is the target posture of the controlled object, which has the following mapping: q α =g1 (p′ α ) q β =g2 (p′ β ) q γ =g3 (p′ γ ) Among them, g1 (·), g2 (·), and g3 (·) are control signal functions that map the three-dimensional posture of the finger to the three-dimensional posture of the target object. The mapping function is defined as the linear mapping function number q(x) = sx. When |s| = 1, g(·) is an identity mapping, and the estimated three-dimensional posture of the finger is directly used as the target posture of the controlled object. When |s| < 1, g(·) is a compression mapping, and the estimated three-dimensional posture value of the finger is reduced and used as the target posture of the controlled object. When |s| > 1, g(·) is an enlargement mapping, and the estimated three-dimensional posture value of the finger is enlarged and used as the target posture of the controlled object.

6. The device according to claim 5, characterized in that The mapping module is further used for: Before controlling the absolute posture of the target object in the three-dimensional space according to the three-dimensional input signal, The fingerprint image is subjected to fingerprint recognition verification, including frame-by-frame verification and first-frame verification; wherein, the frame-by-frame verification includes that each frame of the fingerprint image needs to undergo fingerprint recognition and verification before subsequent object posture control is allowed; the first-frame verification includes performing fingerprint recognition on the first-frame image of the fingerprint image, and after the verification is passed, the finger is kept on the control device to continue subsequent object posture control.

7. The device according to claim 6, characterized in that Also includes verification modules for: Respective angle mapping functions are set for different fingerprint images, and the corresponding angle mapping function is called based on the result of the fingerprint recognition.

8. The device according to claim 5, characterized in that Also includes a personalized control module for: By combining fingerprint recognition technology with fingerprint-based three-dimensional posture control, personalized control parameters can be achieved.

Citation Information

Patent Citations

  • Gestures for controlling, manipulating, and editing of media files using touch sensitive devices

    CN103631496A

  • A monocular texture-free three-dimensional object attitude tracking method based on a three-dimensional geometric model.

    CN109325444A

  • Game control method based on intelligent bracelet, intelligent bracelet and storage medium

    CN110102044A

  • Method and device for estimating three-dimensional posture of finger through plane fingerprint

    CN113569638A

  • Three-dimensional fingerprint reconstruction method and device

    CN113570699A