Unmanned aerial vehicle defect detection system

Abstract

The utility model provides an unmanned aerial vehicle defect detection system. The unmanned aerial vehicle defect detection system comprises a visible light sensor, an infrared sensor, a speed sensor, a fusion unit and an image recognition unit, the visible light sensor, the infrared sensor and the speed sensor are all connected with the fusion unit; the fusion unit is connected with the image recognition unit. Through the arrangement of the speed sensor and the digital logic circuit influenced by the speed value, the visible light image and the infrared image can be accurately fused, a clear grey-scale map with more information is output for image recognition, and unmanned aerial vehicle defect detection is achieved with low cost.

Description

Technical Field

[0001] The utility model belongs to the technical field of defect detection, and in particular relates to a drone defect detection system. Background Art

[0002] Drones are small in size, simple in structure, and flexible in control. They can take off and land vertically, hover freely, and adapt to various natural environments. They have the advantages of autonomous flight and autonomous landing. They can operate in some complex and dangerous environments that are not suitable for human entry. Therefore, they are widely used in many fields. Image fusion refers to the processing and integration of multiple images obtained by different sensors or the same sensor at different times to obtain a more accurate and comprehensive image description of the same scene. Image fusion makes full use of the complementary information contained in multiple fused images to effectively extract the information features of multiple images.

[0003] In the prior art, image fusion is generally performed in existing drones through computer software, so corresponding software equipment must be provided, resulting in high costs. Utility Model Content

[0004] In view of this, the utility model provides a UAV defect detection system, aiming to solve the problem that image fusion in UAVs in the prior art is generally performed by computer software, which is costly.

[0005] A first aspect of an embodiment of the utility model provides a drone defect detection system, comprising:

[0006] Visible light sensor, infrared sensor, speed sensor, fusion unit, image recognition unit;

[0007] The visible light sensor, the infrared sensor and the speed sensor are all connected to the fusion unit; and the fusion unit is connected to the image recognition unit.

[0008] In a possible implementation, the fusion unit includes: an infrared calculation circuit and an image fusion circuit;

[0009] The speed sensor and the infrared sensor are both connected to the infrared calculation circuit; the infrared calculation circuit, the visible light sensor and the infrared sensor are all connected to the image fusion circuit.

[0010] In a possible implementation, the infrared calculation circuit includes a first calculation circuit and a correction circuit; the correction circuit is connected to the speed sensor; the correction circuit and the infrared sensor are both connected to the first calculation circuit; and the first calculation circuit is connected to the image fusion circuit.

[0011] In a possible implementation, the correction circuit includes: a first comparator, a gray point selection circuit, and a first divider;

[0012] One of the input terminals of the first comparator is connected to the speed sensor, and the input value of the other input terminal is a given speed value; the output terminal of the first comparator is connected to the gray point selection circuit;

[0013] The gray point selection circuit is connected to the first divider; the first divider is connected to the first calculation circuit.

[0014] In a possible implementation, the gray point selection circuit includes: a second comparator, a first selector, a first mask, a first AND gate, a first adder, a second adder, and a second selector;

[0015] An output terminal of the first comparator is connected to the first masker;

[0016] One of the input terminals of the second comparator is connected to the infrared sensor, and the input value of the other input terminal is a given gray value; the output terminal of the second comparator is connected to the first selector; the first selector is connected to the first masker; the first masker is connected to one input terminal of the first AND gate; the other input terminal of the first AND gate is a high level;

[0017] The first AND gate is connected to the second selector; the output end of the first selector is connected to the first adder; the output end of the second selector is connected to the second adder; the first adder and the second adder are both connected to the first divider.

[0018] In a possible implementation, the first calculation circuit includes: a second masker, a second AND gate, a third selector, and a first multiplier;

[0019] The second masker is connected to the first masker; the second masker is connected to one input terminal of the second AND gate; the other input terminal of the second AND gate is at a high level;

[0020] The output end of the second AND gate is connected to the third selector; the third selector is connected to an input end of the first multiplier; and the other input end of the first multiplier is connected to the first divider.

[0021] In a possible implementation, the image fusion circuit includes: a zeroing circuit, a third adder, a second multiplier, a third multiplier, a fourth multiplier, and a fourth adder;

[0022] The visible light sensor is connected to the zeroing circuit, the second multiplier, and the third multiplier; the zeroing circuit is connected to an input end of the third adder; the other input end of the third adder is connected to the infrared calculation circuit; the output end of the third adder is connected to the fourth multiplier; the second multiplier, the third multiplier, and the fourth multiplier are all connected to the fourth adder.

[0023] In a possible implementation, the system further includes a display unit; the display unit is connected to the image recognition unit.

[0024] In a possible implementation, the system further includes a power supply; the visible light sensor, the infrared sensor, the speed sensor, the fusion unit, and the image recognition unit are all connected to the power supply.

[0025] The drone defect detection system provided by the embodiment of the utility model includes a visible light sensor, an infrared sensor, a speed sensor, a fusion unit, and an image recognition unit; the visible light sensor, the infrared sensor, and the speed sensor are all connected to the fusion unit; and the fusion unit is connected to the image recognition unit. By setting a speed sensor and a digital logic circuit affected by the speed value, the visible light image and the infrared image can be accurately fused, and a clear grayscale image with more information can be output for image recognition, so as to realize drone defect detection at a relatively low cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0027] Figure 1 It is a structural schematic diagram of a UAV defect detection system provided by an embodiment of the utility model;

[0028] Figure 2 It is a structural schematic diagram of a correction circuit provided by an embodiment of the utility model;

[0029] Figure 3 It is a structural schematic diagram of a gray point selection circuit provided by an embodiment of the utility model;

[0030] Figure 4 is a schematic diagram of the structure of a first calculation circuit provided by an embodiment of the utility model;

[0031] Figure 5 It is a structural schematic diagram of an image fusion circuit provided by an embodiment of the utility model. DETAILED DESCRIPTION

[0032] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details.

[0033] Figure 1 This is a flowchart of the implementation of the drone defect detection system provided by the embodiment of the utility model. Figure 1 As shown, the UAV defect detection system includes: a visible light sensor 11, an infrared sensor 12, a speed sensor 13, a fusion unit 14, and an image recognition unit 15; the visible light sensor 11, the infrared sensor 12, and the speed sensor 13 are all connected to the fusion unit 14; and the fusion unit 14 is connected to the image recognition unit 15.

[0034] In the embodiment of the present utility model, the recognition algorithm adopted by the image recognition unit is a conventional algorithm in the prior art.

[0035] In some embodiments, the fusion unit 14 includes: an infrared computing circuit and an image fusion circuit; the speed sensor 13 and the infrared sensor 12 are both connected to the infrared computing circuit; the infrared computing circuit, the visible light sensor 11, and the infrared sensor 12 are all connected to the image fusion circuit.

[0036] In some embodiments, the infrared calculation circuit includes a first calculation circuit and a correction circuit; the correction circuit is connected to the speed sensor 13; the correction circuit and the infrared sensor 12 are both connected to the first calculation circuit; and the first calculation circuit is connected to the image fusion circuit.

[0037] Figure 2 : is a structural diagram of the correction circuit provided by the embodiment of the utility model. In some embodiments, the correction circuit includes: a first comparator 21, a gray point selection circuit 22, and a first divider 23; one of the input ends of the first comparator 21 is connected to the speed sensor 13, and the input value of the other input end is a given speed value; the output end of the first comparator 21 is connected to the gray point selection circuit; the gray point selection circuit 22 is connected to the first divider 23; the first divider 23 is connected to the first calculation circuit.

[0038] In the embodiment of the utility model, when the UAV flies at a high speed, it is easy to generate a heat track, that is, the point-like hot spots become linear along the speed direction. Therefore, the utility model designs a gray point selection circuit to correct the gray image at a high speed. The specific implementation circuit refers to the following embodiment.

[0039] Figure 3: It is a structural schematic diagram of the gray point selection circuit provided by the embodiment of the utility model. In some embodiments, the gray point selection circuit includes: a second comparator 31, a first selector 32, a first masker 33, a first AND gate 34, a first adder 35, a second adder 36, and a second selector 37; the output end of the first comparator 21 is connected to the first masker 33; one of the input ends of the second comparator 31 is connected to the infrared sensor 12, and the input value of the other input end is a given gray value; the output end of the second comparator 31 is connected to the first selector 32; the first selector 32 is connected to the first masker 33; the first masker 33 is connected to an input end of the first AND gate 34; the other input end of the first AND gate 34 is a high level; the first AND gate 34 is connected to the second selector 37; the output end of the first selector 32 is connected to the first adder 35; the output end of the second selector 37 is connected to the second adder 36; the first adder 35 and the second adder 36 are both connected to the first divider 23.

[0040] In an embodiment of the utility model, the image detected by the infrared sensor is an infrared grayscale image. It is input into the second comparator and compared with a given grayscale value. The pixel point greater than the given grayscale value is considered to be a hotspot, and the output is a high level, which instructs the first selector to select the pixel value as the first point. At the same time, when the speed is greater than the given speed value, the first comparator outputs a high level to the first masker. At this time, the first masker outputs a high level, and through the combination of the first masker and the AND gate, it instructs the second selector to select a point after the first point as the second point. The second point is on the extension line of the thermal trajectory of the first point, but not on the thermal trajectory. The first divider calculates the ratio of the second point to the first point, that is, the ratio of the ordinary pixel point to the hotspot.

[0041] Figure 4 : is a schematic diagram of the structure of the first calculation circuit provided by the embodiment of the utility model. In some embodiments, the first calculation circuit includes: a second masker 41, a second AND gate 42, a third selector 43, and a first multiplier 44; the second masker 41 is connected to the first masker 33; the second masker 41 is connected to an input end of the second AND gate 42; the other input end of the second AND gate 42 is a high level; the output end of the second AND gate 42 is connected to the third selector 43; the third selector 43 is connected to an input end of the first multiplier 44; the other input end of the first multiplier 44 is connected to the first divider 23.

[0042] In an embodiment of the utility model, the second masker is combined with the second AND gate to instruct the third selector to select pixel points on the thermal trajectory other than the first point as the third point, and then the first multiplier multiplies the grayscale of the third point by the output value of the divider, which is the correction value of the pixel value of the third point. The effect of this circuit is to restore the pixel values ​​of non-hot spots on the thermal trajectory to the pixel values ​​of normal pixels to complete the correction of the infrared image.

[0043] Figure 5 : is a structural schematic diagram of an image fusion circuit provided by an embodiment of the utility model. In some embodiments, the image fusion circuit includes: a zeroing circuit 51, a third adder 52, a second multiplier 53, a third multiplier 54, a fourth multiplier 55, and a fourth adder 56; the visible light sensor 11 is connected to the zeroing circuit 51, the second multiplier 53, and the third multiplier 54; the zeroing circuit 51 is connected to an input end of the third adder 52; the other input end of the third adder 52 is connected to the infrared calculation circuit; the output end of the third adder 52 is connected to the fourth multiplier 55; the second multiplier 53, the third multiplier 54, and the fourth multiplier 55 are all connected to the fourth adder 56.

[0044] In the embodiment of the utility model, after the RGB three-channel image is input, the zeroing circuit sets the value of any channel to 0, and then the third adder adds the pixel value of the corrected infrared image to it. At this time, the three channels contain both the information of the visible light image and the information of the infrared image, and the two images are fused. Then, according to the conventional RGB image conversion grayscale image method, the pixel values ​​in the channels are multiplied by the corresponding weights using multipliers, and then added to obtain a grayscale image. The image recognition unit recognizes the grayscale image and determines the defect.

[0045] In some embodiments, the system further includes a display unit; the display unit is connected to the image recognition unit 15 .

[0046] In some embodiments, the system further includes a power supply; the visible light sensor 11, the infrared sensor 12, the speed sensor 13, the fusion unit 14, and the image recognition unit 15 are all connected to the power supply.

[0047] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the utility model.

[0048] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A drone defect detection system, characterized in that: include: Visible light sensor, infrared sensor, speed sensor, fusion unit, image recognition unit; The visible light sensor, the infrared sensor, and the speed sensor are all connected to the fusion unit; and the fusion unit is connected to the image recognition unit.

2. The drone defect detection system according to claim 1, characterized in that: The fusion unit includes: an infrared calculation circuit and an image fusion circuit; The speed sensor and the infrared sensor are both connected to the infrared calculation circuit; the infrared calculation circuit, the visible light sensor and the infrared sensor are all connected to the image fusion circuit.

3. The drone defect detection system according to claim 2, characterized in that: The infrared calculation circuit includes a first calculation circuit and a correction circuit; the correction circuit is connected to the speed sensor; the correction circuit and the infrared sensor are both connected to the first calculation circuit; the first calculation circuit is connected to the image fusion circuit.

4. The drone defect detection system according to claim 3, characterized in that: The correction circuit includes: a first comparator, a gray point selection circuit, and a first divider; One of the input terminals of the first comparator is connected to the speed sensor, and the input value of the other input terminal is a given speed value; the output terminal of the first comparator is connected to the gray point selection circuit; The gray point selection circuit is connected to the first divider; the first divider is connected to the first calculation circuit.

5. The drone defect detection system according to claim 4, characterized in that: The gray point selection circuit includes: a second comparator, a first selector, a first mask, a first AND gate, a first adder, a second adder, and a second selector; The output terminal of the first comparator is connected to the first masker; One of the input ends of the second comparator is connected to the infrared sensor, and the input value of the other input end is a given gray value; the output end of the second comparator is connected to the first selector; the first selector is connected to the first mask; the first mask is connected to one input end of the first AND gate; the other input end of the first AND gate is a high level; The first AND gate is connected to the second selector; the output end of the first selector is connected to the first adder; the output end of the second selector is connected to the second adder; the first adder and the second adder are both connected to the first divider.

6. The drone defect detection system according to claim 5, characterized in that: The first calculation circuit includes: a second masker, a second AND gate, a third selector, and a first multiplier; The second masker is connected to the first masker; the second masker is connected to one input end of the second AND gate; the other input end of the second AND gate is at a high level; The output end of the second AND gate is connected to the third selector; the third selector is connected to an input end of the first multiplier; and the other input end of the first multiplier is connected to the first divider.

7. The drone defect detection system according to claim 2, characterized in that: The image fusion circuit comprises: a zeroing circuit, a third adder, a second multiplier, a third multiplier, a fourth multiplier, and a fourth adder; The visible light sensor is connected to the zeroing circuit, the second multiplier, and the third multiplier; the zeroing circuit is connected to an input end of the third adder; the other input end of the third adder is connected to the infrared calculation circuit; the output end of the third adder is connected to the fourth multiplier; the second multiplier, the third multiplier, and the fourth multiplier are all connected to the fourth adder.

8. The drone defect detection system according to claim 1, characterized in that: The system further comprises a display unit; the display unit is connected with the image recognition unit.

9. The drone defect detection system according to claim 1, characterized in that: The system also includes a power supply; the visible light sensor, the infrared sensor, the speed sensor, the fusion unit, and the image recognition unit are all connected to the power supply.

Images