Intelligent sighting telescope

Abstract

The utility model is suitable for the technical field of sighting telescope, and provides an intelligent sighting telescope which comprises a machine body for supporting and installing all unit components. The objective lens unit focuses light information in front of the sighting telescope to the image acquisition unit; the image acquisition unit converts the optical information into corresponding first image information and transmits the first image information to the AI image processing unit; the AI image processing unit performs target detection on the video to obtain a target detection result of each frame of first image information in the video; based on a target detection result of the first image information, performing target marking on a target of the corresponding first image information by adopting a square frame to obtain corresponding second image information; the display unit displays an image based on the second image information, and a target in the image is marked by a box, so that a shooter can quickly observe the target; a shooter observes an image of the display unit through the eyepiece unit, and the eyepiece unit optically amplifies and displays the image displayed by the display unit.

Description

Technical Field

[0001] This utility model relates to the field of aiming scope technology, and in particular to an intelligent aiming scope. Background Technology

[0002] A scope is an optical aiming device that can be mounted on firearms and other weapons to assist the shooter in aiming and firing. The shooter can use the optical properties of the scope to observe the target in front of the firearm and to aim at the target using the aiming point in the scope.

[0003] In existing scopes, under the influence of complex surrounding environments, such as dense trees and overgrown vegetation, when a shooter uses the scope to observe a target (such as pheasants or wild boars that are permitted to be hunted), the complex surrounding environment interferes with the shooter's observation of the target, making it difficult for the shooter to quickly find and clearly observe the target, and also slowing down the judgment of key points of the target (such as the heart of an animal).

[0004] In conclusion, the existing structure obviously has inconveniences and defects in practical use, so it is necessary to improve it. Utility Model Content

[0005] In view of the above-mentioned shortcomings, the purpose of this utility model is to provide an intelligent aiming scope that can help the shooter quickly observe the target.

[0006] To achieve the above objectives, this utility model provides an intelligent aiming scope, including a main body, and the aiming scope further includes:

[0007] The objective lens unit is located at the front end of the main body, focuses the light information in front of the sight, and focuses the light information onto the image acquisition unit;

[0008] An image acquisition unit is disposed on the main body of the device and electrically connected to the AI ​​image processing unit. It converts the light information into corresponding first image information and transmits the first image information to the AI ​​image processing unit.

[0009] An AI image processing unit is disposed on the main body of the device and electrically connected to the display unit; it receives a video formed by multiple frames of the first image information, performs target detection on the video, and obtains the target detection result of each frame of the first image information in the video; based on the target detection result of the first image information, it uses a box to mark the target of the corresponding first image information to obtain the corresponding second image information, and sends the corresponding second image information to the display unit.

[0010] A display unit is disposed on the main body of the device, which displays an image based on the second image information;

[0011] The eyepiece unit, located at the rear end of the main body, optically magnifies the image displayed by the display unit.

[0012] According to the aforementioned smart aiming scope, the AI ​​image processing unit includes a CPU and an NPU that are electrically connected to each other; the CPU is electrically connected to the display unit.

[0013] The NPU includes a first image detection module, which receives a video formed by multiple frames of the first image information, performs target detection on the video, obtains the target detection result of each frame of the first image information in the video, and sends it to the CPU.

[0014] Based on the target detection result of the first image information, the CPU uses a box to mark the target of the corresponding first image information to obtain the corresponding second image information, and sends the corresponding second image information to the display unit.

[0015] According to the aforementioned smart aiming scope, the first image detection module performs target detection on the video based on the YOLOv5 algorithm.

[0016] According to the smart sight, the NPU further includes a second image detection module, which is electrically connected to the CPU;

[0017] The second image detection module receives a video formed by multiple frames of the first image information, performs target key point detection on the video, obtains the target key point detection result of the corresponding first image information, and sends the target key point detection result of the corresponding first image information to the CPU.

[0018] Based on the target detection results of the first image information, the CPU uses a box to mark the corresponding target in the first image information, and based on the target key point detection results of the first image information, the CPU uses a circle to mark the corresponding target key points in the first image information, so as to obtain the third image information.

[0019] The CPU sends the corresponding third image information to the display unit;

[0020] The display unit displays the image based on the third image information.

[0021] According to the smart aiming scope, the second image detection module performs target key point detection on the video based on the HRNet algorithm to obtain the target key point detection result of the corresponding first image information.

[0022] According to the smart sight, the NPU further includes an image processing module, which is electrically connected to the image acquisition unit and the first image detection module;

[0023] The image processing module receives multiple frames of the first image information transmitted by the image acquisition unit, performs 3D noise reduction and color enhancement processing on each frame of the first image information, and forms the video from the multiple frames of the first image information that have undergone 3D noise reduction and color enhancement processing, and sends it to the first image detection module.

[0024] According to the aforementioned smart sight, the display unit displays the aiming point;

[0025] The CPU determines whether the aiming point displayed by the display unit is within the frame of the image displayed by the display unit. If so, it controls the display unit to magnify the target in the image.

[0026] According to the aforementioned smart sight, the objective lens unit includes:

[0027] Objective lens, which comprises multiple first optical lenses;

[0028] The objective lens focusing device adjusts the distance between the first optical lenses to focus the light information onto the AI ​​image processing unit;

[0029] The eyepiece unit includes:

[0030] An eyepiece, comprising multiple second optical lenses, is disposed on the display side of the display unit;

[0031] An eyepiece focusing device adjusts the distance between the eyepiece and the display unit.

[0032] According to the aforementioned smart sight, the display unit includes a display screen, a protective pad, and a baffle; the baffle is disposed on the display side of the display screen, and the baffle has a circular hollow area corresponding to the display screen; the protective pad is disposed on the side of the display screen opposite to the baffle.

[0033] According to the aforementioned smart sight, the sight also includes a fill light and a battery;

[0034] The fill light is located on the outside of the fuselage and faces the front of the sight;

[0035] The battery is located in the middle of the main body of the device, between the AI ​​image processing unit and the display unit;

[0036] The image acquisition unit includes a CMOS image sensor, which converts the light information into corresponding first image information and transmits the first image information to the AI ​​image processing unit.

[0037] The intelligent aiming scope of this invention includes a main body, an objective lens unit, an image acquisition unit, an AI image processing unit, a display unit, and an eyepiece unit. The main body can support and mount each component unit. An objective lens unit is located at the front end of the fuselage, focusing the light information in front of the sight and directing it to an image acquisition unit. The image acquisition unit, also located on the fuselage, is electrically connected to an AI image processing unit, converting the light information into corresponding first image information and transmitting it to the AI ​​image processing unit. The AI ​​image processing unit, located on the fuselage, receives a video composed of multiple frames of the first image information. The AI ​​image processing unit can pre-train a model by inputting images of the shooter's target. It performs target detection on the video, obtaining the target detection result for each frame of the first image information. Based on the target detection result of the first image information, it uses bounding boxes to mark the corresponding targets in the first image information to obtain corresponding second image information, which is then sent to the display unit. The display unit displays an image based on the second image information, with the target marked by a bounding box, allowing the shooter to quickly observe the target. An eyepiece unit is located at the rear end of the fuselage, allowing the shooter to observe the image displayed on the display unit. The eyepiece unit optically magnifies the image displayed on the display unit. Therefore, the intelligent aiming scope of this invention can help the shooter quickly observe the target. Attached Figure Description

[0038] Figure 1 This is a cross-sectional view of an embodiment of the intelligent aiming scope provided by this utility model;

[0039] Figure 2 This is a three-dimensional structural diagram of an embodiment of the intelligent aiming scope provided by this utility model;

[0040] Figure 3 This is a three-dimensional structural schematic diagram of a display unit provided in an embodiment of the present invention;

[0041] Figure 4 This is an exploded view of the display unit provided in an embodiment of the present invention;

[0042] Figure 5 This is a three-dimensional structural diagram of a display screen provided in an embodiment of the present invention. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of this utility model clearer, the present utility model will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present utility model and are not intended to limit the present utility model.

[0044] In the description of this application, it should be understood that if terms such as "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential" appear, these terms indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application.

[0045] See Figures 1-5 In one embodiment of this utility model, a smart sight 100 is provided, including a body 10 and the sight 100 further including:

[0046] The objective lens unit 20 is located at the front end of the main body 10, focuses the light information in front of the sight 100, and focuses the light information onto the image acquisition unit 30;

[0047] The image acquisition unit 30 is disposed on the main body 10 and electrically connected to the AI ​​image processing unit 40. It converts light information into corresponding first image information and transmits the first image information to the AI ​​image processing unit 40.

[0048] AI image processing unit 40 is disposed on the main body 10 and electrically connected to display unit 50; it receives video formed by multiple frames of first image information, performs target detection on the video, and obtains the target detection result of each frame of first image information in the video; based on the target detection result of the first image information, it uses a box to mark the target of the corresponding first image information to obtain the corresponding second image information, and sends the corresponding second image information to display unit 50.

[0049] Display unit 50 is disposed on the main body 10 of the device, and displays an image based on the second image information;

[0050] The eyepiece unit 60 is located at the rear end of the main body 10 and optically magnifies the image displayed by the display unit 50.

[0051] In this embodiment, the sight 100 can assist the shooter in quickly observing the target in front of the sight 100. Specifically, the main body 10 of the sight 100 supports and mounts various unit components. The objective lens unit 20 focuses the light information emitted from the front of the sight 100 onto the image acquisition unit 30, which can quickly convert the light information into corresponding first image information. The AI ​​image processing unit 40 can be pre-trained in a pre-trained model on images containing shooting targets (which may be multiple). Multiple frames (at least two frames) of first image information form a video. The AI ​​image processing unit 40 performs target detection on the video, obtaining the target detection result for each frame of first image information in the video. The target detection result includes the position information of the target in the first image information. Based on the target detection result, the target in the corresponding first image information is marked with a box to obtain the corresponding second image information. When the display unit 50 displays an image based on the second image information, the target in the image is marked with a box. The shooter observes the image displayed by the display unit 50 through the eyepiece unit 60. The eyepiece unit 60 magnifies the image, allowing the shooter to quickly observe the target in the image. The color of the box can be preset to red, or it can be automatically generated to be a color with a high contrast to the background.

[0052] As an optional embodiment, the AI ​​image processing unit 40 includes a CPU (Central Processing Unit) and an NPU (Neural Network Processing Unit) electrically connected to each other; the CPU is electrically connected to the display unit 50;

[0053] The NPU includes a first image detection module, which receives a video formed by multiple frames of first image information, performs target detection on the video, obtains the target detection result of each frame of first image information in the video, and sends it to the CPU.

[0054] Based on the target detection results of the first image information, the CPU uses bounding boxes to mark the targets in the corresponding first image information to obtain the corresponding second image information, and then sends the corresponding second image information to the display unit 50.

[0055] In this embodiment, the first image detection module of the NPU continuously infers the first image information of each frame of the video and returns the inference result. Optionally, the first image detection module performs target detection on the video based on the YOLOv5 algorithm. The YOLOv5 algorithm can detect targets in the video in real time. It is a single-stage target recognition algorithm. Its principle is to solve the entire target recognition process as a regression problem. By segmenting the image into a grid and predicting the bounding box and category for each grid simultaneously, target recognition is achieved. The YOLOv5 algorithm has a fast detection speed, and after training and adjustment, it can achieve a high accuracy and a low false negative rate. It is also simple and easy to use. The target detection result of each frame of the first image information obtained by the first image detection module can be sent to the CPU. The CPU is the core of computation and control, and is the final execution unit for information processing and program execution. The CPU uses bounding boxes to mark the targets in the first image information to obtain the second image information, so that the targets in the image displayed by the display unit 50 are marked with bounding boxes.

[0056] As an optional embodiment, the NPU also includes a second image detection module electrically connected to the CPU;

[0057] The second image detection module receives a video formed by multiple frames of first image information, performs target key point detection on the video, obtains the target key point detection results of the corresponding first image information, and sends the target key point detection results of the corresponding first image information to the CPU.

[0058] Based on the target detection results of the first image information, the CPU uses bounding boxes to mark the corresponding targets in the first image information, and based on the target key point detection results of the first image information, the CPU uses circular boxes to mark the corresponding target key points in the first image information to obtain the third image information.

[0059] The CPU sends the corresponding third image information to the display unit 50;

[0060] The display unit 50 displays an image based on third image information.

[0061] In this embodiment, to facilitate the shooter's quick observation of key locations of the target (e.g., an animal's heart), a second image detection module is set in the NPU. Optionally, the second image detection module performs target keypoint detection on the video based on the HRNet (High-Resolution Network) algorithm to obtain the target keypoint detection results of the corresponding first image information. The HRNet algorithm can detect target keypoints in the video in real time. It is a network structure for keypoint detection. Its principle is to learn features of different resolutions by constructing parallel multi-resolution sub-networks, thereby better capturing multi-scale information, having stronger robustness and generalization ability, and being able to adapt to detection tasks of different scales and poses. The CPU can mark the target and target keypoints in the first image information to obtain third image information. When the display unit 50 displays the image based on the third image information, the target and target keypoints in the image are marked with square boxes and circles, respectively. The color of the circle can be preset to green.

[0062] As an optional embodiment, the NPU also includes an image processing module electrically connected to the image acquisition unit 30 and the first image detection module;

[0063] The image processing module receives multiple frames of first image information transmitted by the image acquisition unit 30, performs 3D noise reduction and color enhancement processing on each frame of first image information, and forms a video from the multiple frames of first image information that have undergone 3D noise reduction and color enhancement processing and sends it to the first image detection module.

[0064] In this embodiment, even when the first image information is acquired in a low-light environment, after the first image information is processed by the image processing module through 3D noise reduction and color enhancement, the image displayed by the display unit 50 can achieve the effect of full-color night vision, and it can also facilitate the first image detection module to achieve target detection.

[0065] As an optional embodiment, display unit 50 displays the aiming point;

[0066] The CPU determines whether the aiming point displayed by the display unit 50 is within the frame of the image displayed by the display unit 50. If so, it controls the display unit 50 to magnify the target in the image.

[0067] In this embodiment, the scope 100 assists the shooter in aiming and firing by using an aiming point. The aiming point can be displayed in the form of a crosshair. When the aiming point in the display unit 50 is within the box, the target is further magnified so that the shooter can observe the target more clearly.

[0068] See Figures 1-2As an optional embodiment, the objective lens unit 20 includes:

[0069] Objective lens 21, which includes multiple first optical lenses 211;

[0070] The objective lens focusing device 22 adjusts the distance between the first optical lenses 211 to focus the light information onto the AI ​​image processing unit 40;

[0071] The eyepiece unit 60 includes:

[0072] An eyepiece 61, comprising multiple second optical lenses 611, is disposed on the display side of the display unit 50;

[0073] The eyepiece focusing device 62 adjusts the distance between the eyepiece 61 and the display unit 50.

[0074] In this embodiment, the objective lens 21 focuses the light information in front of the sight 100 onto the image acquisition unit 30. The objective lens 21 is composed of multiple (e.g., 5) high-precision lenses. The objective lens focusing device 22 is a mechanical focusing device. By manually rotating and adjusting the objective lens focusing device 22, the shooter can change the relative positions between the lenses, thereby clearly focusing the light information onto the image acquisition unit 30. The shooter observes the image displayed on the display screen 51 through the eyepiece 61, which magnifies the image. The distance between the eyepiece 61 and the display unit 50 is adjusted by rotating the eyepiece focusing device 62, so that the eyepiece 61 can be adapted to shooters with different degrees of myopia.

[0075] See Figures 3-5 As an optional embodiment, the display unit 50 includes a display screen 51, a protective pad 52, and a baffle 53; the baffle 53 is disposed on the display side of the display screen 51, and the baffle 53 is provided with a circular hollow area 531 corresponding to the display screen 51; the protective pad 52 is disposed on the side of the display screen 51 opposite to the baffle 53.

[0076] In this embodiment, the display screen 51 may optionally be a 2.1-inch display screen from BOE. A baffle 53 is provided on the display side of the display screen 51, and a cutout area 531 is provided on the baffle 53 to expose the effective display area of ​​the display side of the display screen 51. The cutout area 531 is circular, which allows for a larger display area compared to a square area. A protective pad 52 is provided on the other side of the display screen 51 to protect it.

[0077] See Figures 1-2 As an optional embodiment, the sight 100 also includes a supplementary light 70 and a battery 80;

[0078] The supplementary light 70 is located on the outside of the main body 10 and faces the front of the scope 100;

[0079] The battery 80 is located in the middle of the main body 10, between the AI ​​image processing unit 40 and the display unit 50;

[0080] The image acquisition unit 30 includes a CMOS image sensor, which converts light information into corresponding first image information and transmits the first image information to the AI ​​image processing unit 40.

[0081] In this embodiment, the fill light 70 emits near-infrared light to illuminate the front of the scope 100. In the absence of light, the objective lens unit 20 will be unable to acquire effective light information, resulting in excessive noise in the image acquisition unit 30, thus preventing the generation of effective video for transmission to the AI ​​image processing unit 40. By turning on the fill light 70, the target in front of the scope 100 can be illuminated to facilitate the acquisition of effective light information. The battery 80 can optionally be an 18650 battery. The battery 80 is located between the AI ​​image processing unit 40 and the display unit 50, close to the center of the scope 100, which improves the stability of the scope 100 during installation.

[0082] In summary, the intelligent sight of this invention includes a main body, an objective lens unit, an image acquisition unit, an AI image processing unit, a display unit, and an eyepiece unit. The main body can support and mount all the unit components. An objective lens unit is located at the front end of the fuselage, focusing the light information in front of the sight and directing it to an image acquisition unit. The image acquisition unit, also located on the fuselage, is electrically connected to an AI image processing unit, converting the light information into corresponding first image information and transmitting it to the AI ​​image processing unit. The AI ​​image processing unit, located on the fuselage, receives a video composed of multiple frames of the first image information. The AI ​​image processing unit can pre-train a model by inputting images of the shooter's target. It performs target detection on the video, obtaining the target detection result for each frame of the first image information. Based on the target detection result of the first image information, it uses bounding boxes to mark the corresponding targets in the first image information to obtain corresponding second image information, which is then sent to the display unit. The display unit displays an image based on the second image information, with the target marked by a bounding box, allowing the shooter to quickly observe the target. An eyepiece unit is located at the rear end of the fuselage, allowing the shooter to observe the image displayed on the display unit. The eyepiece unit magnifies the image displayed on the display unit. Therefore, the intelligent aiming scope of this invention can help the shooter quickly observe the target.

[0083] Of course, there may be other embodiments of this utility model. Without departing from the spirit and essence of this utility model, those skilled in the art can make various corresponding changes and modifications based on this utility model, but these corresponding changes and modifications should all fall within the protection scope of the appended claims of this utility model.

Claims

1. A smart scope comprising a body, characterized in that, The scope also includes: The objective lens unit is located at the front end of the main body, focuses the light information in front of the sight, and focuses the light information onto the image acquisition unit; An image acquisition unit is disposed on the main body of the device and electrically connected to the AI ​​image processing unit. It converts the light information into corresponding first image information and transmits the first image information to the AI ​​image processing unit. An AI image processing unit is disposed on the main body of the device and electrically connected to the display unit; it receives a video formed by multiple frames of the first image information, performs target detection on the video, and obtains the target detection result of each frame of the first image information in the video; based on the target detection result of the first image information, it uses a box to mark the target of the corresponding first image information to obtain the corresponding second image information, and sends the corresponding second image information to the display unit. A display unit is disposed on the main body of the device, which displays an image based on the second image information; The eyepiece unit, located at the rear end of the main body, optically magnifies the image displayed by the display unit.

2. The intelligent riflescope of claim 1, wherein, The AI ​​image processing unit includes a CPU and an NPU that are electrically connected to each other; the CPU is electrically connected to the display unit. The NPU includes a first image detection module, which receives a video formed by multiple frames of the first image information, performs target detection on the video, obtains the target detection result of each frame of the first image information in the video, and sends it to the CPU. Based on the target detection result of the first image information, the CPU uses a box to mark the target of the corresponding first image information to obtain the corresponding second image information, and sends the corresponding second image information to the display unit.

3. The intelligent aiming scope according to claim 2, characterized in that, The first image detection module performs target detection on the video based on the YOLOv5 algorithm.

4. The intelligent aiming scope according to claim 2, characterized in that, The NPU also includes a second image detection module, which is electrically connected to the CPU; The second image detection module receives a video formed by multiple frames of the first image information, performs target key point detection on the video, obtains the target key point detection result of the corresponding first image information, and sends the target key point detection result of the corresponding first image information to the CPU. Based on the target detection results of the first image information, the CPU uses a box to mark the corresponding target in the first image information, and based on the target key point detection results of the first image information, the CPU uses a circle to mark the corresponding target key points in the first image information, so as to obtain the third image information. The CPU sends the corresponding third image information to the display unit; The display unit displays the image based on the third image information.

5. The intelligent aiming scope according to claim 4, characterized in that, The second image detection module performs target key point detection on the video based on the HRNet algorithm to obtain the target key point detection results corresponding to the first image information.

6. The intelligent aiming scope according to claim 2, characterized in that, The NPU also includes an image processing module, which is electrically connected to the image acquisition unit and the first image detection module; The image processing module receives multiple frames of the first image information transmitted by the image acquisition unit, performs 3D noise reduction and color enhancement processing on each frame of the first image information, and forms the video from the multiple frames of the first image information that have undergone 3D noise reduction and color enhancement processing, and sends it to the first image detection module.

7. The intelligent aiming scope according to claim 2, characterized in that, The display unit displays the aiming point; The CPU determines whether the aiming point displayed by the display unit is within the frame of the image displayed by the display unit. If so, it controls the display unit to magnify the target in the image.

8. The intelligent aiming scope according to claim 1, characterized in that, The objective lens unit includes: Objective lens, which comprises multiple first optical lenses; The objective lens focusing device adjusts the distance between the first optical lenses to focus the light information onto the image acquisition unit; The eyepiece unit includes: An eyepiece, comprising multiple second optical lenses, is disposed on the display side of the display unit; An eyepiece focusing device adjusts the distance between the eyepiece and the display unit.

9. The intelligent aiming scope according to claim 1, characterized in that, The display unit includes a display screen, a protective pad, and a baffle; the baffle is disposed on the display side of the display screen, and the baffle has a circular hollow area corresponding to the display screen; the protective pad is disposed on the side of the display screen opposite to the baffle.

10. The intelligent aiming scope according to claim 1, characterized in that, The scope also includes a fill light and a battery; The fill light is located on the outside of the fuselage and faces the front of the sight; The battery is located in the middle of the main body of the device, between the AI ​​image processing unit and the display unit; The image acquisition unit includes a CMOS image sensor, which converts the light information into corresponding first image information and transmits the first image information to the AI ​​image processing unit.

Images