Smart glasses with cut prevention function

Abstract

The invention provides smart glasses with cut prevention function, which include glasses, a camera unit, an identification module, a prediction module, a deciding module and a warning unit. The camera unit is installed on the glasses. The camera unit captures a continuous image in a direction of a user. The identification module identifies a cutlery feature and a hand feature from the continuous image. The prediction module generates a cutlery prediction trajectory based on the displacement of the cutlery features. The prediction module generates a hand prediction trajectory based on the displacement of hand features. The deciding module generates a warning signal when it decides that the cutlery prediction trajectory overlaps or intersects with the hand prediction trajectory. The warning unit generates a warning message based on the warning signal.

Description

Technical field

[0001] The invention is a technical field of eyeglasses, specifically referring to a cut-resistant smart eyeglass that prevents cuts by a user using a knife. Prior technology

[0002] The common way of cutting vegetables, which is to suppress the vegetables, meat or fruits to be processed with one hand, the other hand to hold the kitchen knife to perform the cutting action. Among them, when the user is proficient will constantly suppress vegetables, meat or fruits with the inertial movement, and move while cutting.

[0003] However, the above-mentioned cutting movements often result in cutting the hands due to carelessness or the influence of habitual movements. In addition, for the elderly, due to presbyopia, visual deterioration and other factors, the elderly have more blurred vision, which also increases the probability of the above-mentioned inadvertent cut of the hand.

[0004] In summary, the inventor of the present invention contemplated and designed a cut-proof smart glasses with a view to improving the lack of learning technology, thereby enhancing its implementation and utilization in industry. Invention content

[0005] It is for the purpose of the present invention to provide a cut-resistant smart glasses to improve the aforementioned problem.

[0006] Based on the foregoing purposes, the invention provides a cut-resistant smart glasses comprising an eyeglass, a camera unit, a recognition module, a prediction module, a judgment module and a warning unit. The glasses are corresponding to the user's eye having a two-lens frame portion, and the two opposite sides of the frame are connected backwards respectively with a one-lens leg that can be bent and retracted. The video camera unit is provided at the glasses. The camera unit retrieves a continuous image in the direction of the user's line of sight. The recognition module is electrically connected to the camera unit to receive that continuous image. The recognition module recognizes a tool feature and a hand feature from the continuous image. The prediction module is electrically connected to that recognition module. The prediction module generates a tool prediction trajectory based on the displacement of the tool feature. The prediction module generates a hand prediction trajectory based on the displacement of that hand feature. The module was judged to be electrically connected to that prediction module. The judgment module generates an alert signal when it determines that the tool's predicted trajectory has overlap or interleaving with the hand's predicted trajectory. The alert unit is electrically connected to that judgment module. The warning unit generates an alert message based on the warning signal.

[0007] Preferably, the warning unit is a positive low-frequency patch and a negative low-frequency patch. The warning message is a low-frequency signal applied to the user.

[0008] Preferably, the cut-resistant smart glasses include a wireless transmission unit. The recognition module, the prediction module, and the judgment module are disposed in a portable electronic device. The wireless transmission unit is electrically connected to the portable electronic device and transmits the continuous image to the recognition module.

[0009] Preferably, the cut-prevention smart glasses include a storage unit located in the portable electronic device. The storage unit stores a plurality of reference tool features. The recognition module identifies the tool features from the continuous image based on these reference tool features.

[0010] Preferably, the cut-resistant smart glasses include a storage unit located in the portable electronic device. The storage unit stores a plurality of reference hand features. The recognition module identifies the hand features from the continuous images based on the reference hand features.

[0011] Preferably, the camera unit is disposed between the two lens frames.

[0012] The technical features of the present invention will be described in detail below with reference to specific embodiments and accompanying drawings, so that those skilled in the art can easily understand the purpose, technical features and advantages of the present invention. Simple Explanation of the Diagram

[0013] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0014] Figure 1 is a block diagram of the anti-cut smart glasses of the present invention.

[0015] Figure 2 is a schematic diagram of the structure of the anti-cut smart glasses of the present invention.

[0016] Figure 3 is a schematic diagram illustrating the application of the anti-cut smart glasses of the present invention. Implementation

[0017] The advantages, features, and technical methods of the present invention will be more readily understood by referring to the exemplary embodiments and accompanying drawings. The present invention may be implemented in different forms and should not be construed as limited to the embodiments set forth herein. Rather, the embodiments provided will make this disclosure more thorough, complete, and fully convey the scope of the invention to those skilled in the art. The invention will be defined only by the appended claims.

[0018] It should be understood that although the terms "first," "second," etc., may be used in this invention to describe various elements, components, regions, sections, layers, and / or portions, these elements, components, regions, sections, layers, and / or portions should not be limited by these terms. These terms are only used to distinguish one element, component, region, section, layer, and / or portion from another element, component, region, section, layer, and / or portion.

[0019] Unless otherwise defined, all terms used in this invention (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It will be further understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology and this invention, and will not be interpreted as having an idealized or overly formal meaning unless expressly defined herein.

[0020] Please refer to Figures 1 and 2 together. Figure 1 is a block diagram of the anti-cut smart glasses of the present invention. Figure 2 is a block diagram of a first embodiment of the anti-cut smart glasses of the present invention. Figure 3 is an application diagram of the anti-cut smart glasses of the present invention. As shown in the figures, the anti-cut smart glasses G of the present invention mainly includes a pair of glasses 1, a camera unit 2, a recognition module 3, a prediction module 4, a judgment module 5, and an alert unit 6.

[0021] The eyeglasses 1 can be composed of components such as ordinary eyeglasses or reading glasses, which are well-known or commonly used by those skilled in the art, and have two frame portions 11 corresponding to the user's eyes. The frame portions 11 may contain ordinary lenses, reading lenses, or no lenses. Additionally, each side of the frame portion 11 is connected to a foldable temple portion 12. Incidentally, the frame portions 11 and temple portions 12 may have storage spaces at desired locations to accommodate components such as power supply units or wireless transmission units.

[0022] The camera unit 2 can be a general-purpose camera, a multi-functional camera, or a depth camera; preferably, the camera unit 2 is a depth camera. The camera unit 2 is disposed on the glasses 1; preferably, the camera unit 2 is disposed between the two frame portions 11. The camera unit 2 captures continuous images 21 of the scene in the user's line of sight.

[0023] The recognition module 3 is electrically connected to the camera unit 2 to receive the continuous images 21. The recognition module 3 identifies a knife feature 31 and a hand feature 32 from the continuous images 21. Furthermore, the recognition module 3 can be a computer processor that executes instructions to read data from the storage unit and performs convolutional neural network operations using a deep learning network. This allows for training with appropriate training data and achieves easy convergence. However, the invention is not limited to this; other types of algorithms or other deep learning algorithms can also be applied to the recognition method of this invention for different types of image recognition.

[0024] The prediction module 4 is electrically connected to the recognition module 3. The prediction module 4 generates a predicted tool trajectory 41 based on the displacement of the tool feature 31. The prediction module 4 also generates a predicted hand trajectory 42 based on the displacement of the hand feature 32. Furthermore, the prediction module 4 can be a computer processor that can execute instructions to read data from a storage unit. It utilizes artificial intelligence to analyze and predict the corresponding predicted tool trajectory 41 and hand trajectory 42 based on the user's tool-holding trajectory and hand movements. The prediction module 4 can record and collect the user's tool-holding movements and hand movements for data analysis and integration in robot intelligent learning, thereby generating the predicted tool trajectory 41 and hand trajectory 42.

[0025] The judgment module 5 is electrically connected to the prediction module 4. The judgment module 5 can be a computer processor that executes instructions to read data from the storage unit for judgment, decision-making, or other purposes. Specifically, the judgment module 5 generates a warning signal 51 when it determines that the predicted tool trajectory 41 overlaps or intersects with the predicted hand trajectory 42. It is worth noting that the identification module 3, prediction module 4, and judgment module 5 can be integrated into a single component, such as a processing module or a control module.

[0026] The warning unit 6 is electrically connected to the judgment module 5. The warning unit 6 generates a warning message 61 based on the warning signal 51. For example, the warning unit 6 can output sound, light, or a combination thereof. It can generate a warning message 61 through sound, light, or a combination thereof. Thus, when the judgment module 5 determines that the user may cut their hand based on the predicted trajectory of the knife 41 and the predicted trajectory of the hand 42, it can output a warning message 61 in advance to remind the user.

[0027] Preferably, the warning unit 6 comprises a positive low-frequency patch and a negative low-frequency patch. The positive and negative low-frequency patches can be respectively attached to the user's two hands, or the same hand holding the device, to form a conductive path with the user. In other words, the warning message 61 is a low-frequency signal (or low-frequency current) acting on the user. In practical applications, warning messages 61 using sound, light, or a combination thereof have limited preventative effect. For example, even if the user hears or sees the warning message 61, they may continue cutting due to inertia, resulting in hand injuries. Therefore, this invention utilizes positive and negative low-frequency patches to output a low-frequency signal (or low-frequency current), which can semi-forcefully or forcibly stop the user's current action or retract the originally planned action, thereby ensuring that the user will not cut their hand due to continued cutting due to inertia.

[0028] Furthermore, the anti-cut smart glasses G includes a wireless transmission unit 7. The recognition module 3, prediction module 4, and judgment module 5 are integrated into a portable electronic device 9. The wireless transmission unit 7 is electrically connected to the portable electronic device 9 and transmits the continuous image 21 to the recognition module 3. This effectively reduces the size of the glasses 1, thereby miniaturizing the user's comfort when wearing them.

[0029] Preferably, the anti-cut smart glasses G includes a storage unit 8, which is located in the portable electronic device 9. The storage unit 8 stores a plurality of reference knife features 81 and a plurality of reference hand features 82. The recognition module 3 identifies the knife feature 31 from the continuous image 21 based on the reference knife feature 81. The recognition module 3 identifies the hand feature 32 from the continuous image 21 based on the reference hand feature 82. In other words, the recognition module 3 can quickly identify the knife feature 31 and hand feature 32 using image comparison methods combined with machine learning and other artificial intelligence, thereby reducing the need for potentially large amounts of computing resources.

[0030] Incidentally, the connection between the various electronic components can be achieved by means of wiring inside the frame portion 11 and the temple portion 12, or by means of contact points or connecting lines at the connecting shaft of the frame portion 11 and the temple portion 12. These are technical means that are well known or commonly used by those skilled in the art, and will not be described in detail here.

[0031] In addition, the positive low-frequency patch and the negative low-frequency patch can be electrically connected to the glasses 1 or the portable electronic device 9 using interfaces such as solid wires and TYPE-C.

[0032] Furthermore, the anti-cut smart glasses of the present invention may include a power supply unit and related power circuitry. The power supply unit may be a rechargeable battery, such as a lithium battery, which is disposed in the glasses 1 and configured to supply the power required for the operation of the anti-cut smart glasses of the present invention. Incidentally, the anti-cut smart glasses of the present invention may include a charging and transmission interface, such as TYPE-C, which is well known to those skilled in the art and will not be described in detail here.

[0033] The above description is illustrative only and not restrictive. Any equivalent modifications or alterations made without departing from the spirit and scope of this invention should be included in the appended claims.

[0034] G: Cut-resistant smart glasses 1: Glasses 11: Frame section 12: Temples of the mirror 2: Camera Unit 21: Continuous Images 3: Identification Module 31: Tool Characteristics 32: Hand features 4: Prediction Module 41: Tool Prediction Trajectory 42: Hand Prediction Trajectory 5: Detect the module 51: Warning Signal 6: Warning Unit 61: Warning Message 7: Wireless transmission unit 8: Storage Unit 81: Reference tool characteristics 82: Refer to hand features 9: Portable electronic devices

Claims

1. A smart glasses device for preventing cuts, comprising: a pair of glasses having two frame portions corresponding to the user's eyes, and each of the two frame portions having a foldable temple portion connected to opposite sides of each frame portion; a camera unit disposed on the glasses; the camera unit capturing a continuous image in the user's line of sight; a recognition module electrically connected to the camera unit to receive the continuous image; the recognition module identifying a knife feature and a hand feature from the continuous image; and a prediction module electrically connected to the recognition module; the prediction module generating a predicted knife trajectory based on the displacement of the knife feature; and the prediction module generating a predicted hand trajectory based on the displacement of the hand feature. A judgment module is electrically connected to the prediction module; the judgment module generates a warning signal when it determines that the predicted trajectory of the tool overlaps or intersects with the predicted trajectory of the hand; and a warning unit is electrically connected to the judgment module; the warning unit generates a warning message based on the warning signal.

2. The anti-cut smart glasses according to claim 1, wherein the warning unit is a positive low-frequency patch and a negative low-frequency patch; the warning message is a low-frequency signal acting on the user.

3. The anti-cut smart glasses according to claim 2, wherein the anti-cut smart glasses include a wireless transmission unit; the identification module, the prediction module and the judgment module are disposed in a portable electronic device; the wireless transmission unit is electrically connected to the portable electronic device and transmits the continuous image to the identification module.

4. The anti-cut smart glasses according to claim 3, wherein the anti-cut smart glasses includes a storage unit disposed in the portable electronic device; the storage unit stores a plurality of reference tool features; and the recognition module identifies the tool features from the continuous image based on the reference tool features.

5. The anti-cut smart glasses according to claim 3, wherein the anti-cut smart glasses includes a storage unit disposed in the portable electronic device; the storage unit stores a plurality of reference hand features; and the recognition module identifies the hand features from the continuous image based on the reference hand features.

6. The anti-cut smart glasses according to any one of claims 1 to 5, wherein the camera unit is disposed between the two frame portions.

Images