UAV Detection Device and Method Based on a Periodically Arranged Multispectral Imaging Chip

Abstract

Drone detection device and method based on a periodically arranged multi-spectral imaging chip. It relates to the field of drone detection devices based on periodically arranged multi-spectral imaging chips, and specifically to the technical field of drone detection based on periodically arranged multi-spectral imaging chips. It solves the problem that visible light and infrared detection are easily affected by the shape information and temperature information of drones during long-distance detection, resulting in too high a false alarm rate. The device includes: an optical lens, a multi-spectral imaging chip based on periodic arrangement, a circuit board, a power supply interface, a data transmission unit, an image display screen, and a data processing unit; The method includes the following steps: using the drone detection device to collect multi-spectral image data to obtain multi-spectral data blocks; according to the optimized model and the optimized yolo model, obtain the center position and center coordinates of the target object, and output the final target position.

Description

Technical Field

[0001] The present invention belongs to the technical field of point target detection, and particularly relates to the field of unmanned aerial vehicle (UAV) detection based on a multi-spectral imaging chip with a periodic arrangement. Background Art

[0002] With the development and popularization of the low-altitude economy, the flight threshold of UAVs is getting lower and lower. Due to the lack of understanding of some flight authorities of the Civil Aviation Administration, some UAVs may fly into some important places by mistake; therefore, identifying illegally flying UAVs is extremely important for military and public security management. Traditional UAV detection mainly relies on technologies such as visible light optoelectronic detection, infrared imaging detection, and radar wave detection. However, when detecting at a long distance, the number of pixels occupied by the UAV target is relatively small, and information such as shape and texture will be lost. Therefore, it is very difficult for traditional detection technologies to achieve accurate detection of long-distance UAV targets.

[0003] The steps of traditional radar detection of UAVs are as follows: the radar emits electromagnetic waves outward, and UAV targets within the transmission path range will radiate part of the radar signal. The sensor analyzes the received radar cross-section (RCS) echo to determine the position, shape, and speed of the UAV. With the development of information technology, the UAV identification technology based on acoustic characteristics has also developed rapidly. The rotor diameter of small UAVs is relatively small, and the rotation speed is relatively low. The main noise source is the payload noise. The motor speed can reach 20,000 revolutions, mainly high-frequency noise. These noises are superimposed together to generate harmonic noise signals. Yakubovskiy et al. proposed a method for extracting features outside the spectral peak, which can be used to classify aircraft.

[0004] Optoelectronic detection technology is also a major technology for UAV detection. Currently, the most widely used are visible light detection technology and infrared detection technology. Visible light detection technology mainly uses the morphological information of UAVs for detection, while infrared detection technology mainly relies on the thermal radiation information of UAVs. Sheu et al. developed a two-axis rotary tracking platform for anti-UAV, which mainly uses a visible light camera and an infrared thermal imager to detect UAV targets.

[0005] The above several detection technologies all have their limitations. Currently, most UAVs have functions such as adaptive flight and fixed-point cruising, and these UAVs do not generate radio frequency signals during operation; when the detection distance is far, the surface of the UAV is small, and its RCS is weak, so radar detection is difficult; in terms of acoustic detection, although the current signal processing and deep learning technologies have developed rapidly, UAV identification based on sound signals still has disadvantages such as short identification distance and poor anti-interference ability; in terms of optoelectronic detection, visible light and infrared detection are easily affected by the shape information and temperature information of UAVs at long distances, resulting in a high false alarm rate. Summary of the Invention

[0006] In order to solve the problem that visible light and infrared detection are easily affected by the shape information and temperature information of unmanned aerial vehicles (UAVs) during long-distance detection, resulting in an excessively high false alarm rate, the present invention provides a UAV detection device and method based on a multi-spectral imaging chip with a periodic arrangement, which uses the combination of multi-spectral information and image information for target detection to reduce the probability of misidentifying targets.

[0007] The UAV detection device based on the multi-spectral imaging chip with a periodic arrangement includes: an optical lens, a multi-spectral imaging chip with a periodic arrangement, a circuit board, a power supply interface, a data transmission unit, an image display screen, and a data processing unit;

[0008] The circuit board is respectively connected to the optical lens, the power supply interface, and the data transmission unit; the multi-spectral imaging chip with a periodic arrangement is connected to the circuit board through pins, and the optical lens and the multi-spectral imaging chip with a periodic arrangement are connected through an optical path; the data processing unit is respectively connected to the data transmission unit and the image display screen;

[0009] The optical lens is used for spectral image acquisition, the multi-spectral imaging chip with a periodic arrangement is used for outputting multi-spectral image data, the circuit board is used for camera startup and multi-spectral image data storage, the power supply interface is used for transmitting power, the data transmission unit is used for transmitting the multi-spectral image data output by the multi-spectral imaging chip with a periodic arrangement to the data processing unit, the image display screen is used for displaying the final imaging of the target position, and the data processing unit completes data preprocessing and determines the final target position according to the multi-spectral image data output by the multi-spectral imaging chip with a periodic arrangement;

[0010] Set the minimum periodic unit of the multi-spectral imaging chip with a periodic arrangement to 3*3;

[0011] The data processing unit includes a preprocessing model, an optimized model, and an optimized yolo model;

[0012] The preprocessing model converts the multi-spectral image data into multi-spectral data blocks, the optimized model obtains the position of the target object according to the multi-spectral data blocks, and the optimized yolo model converts the multi-spectral data blocks into the center coordinates of the target object.

[0013] Furthermore, the preprocessing model specifically is: sequentially performing background and shadow processing, mosaic processing, ultra-boundary data truncation, and data type conversion on the multi-spectral image data.

[0014] Furthermore, the optimized model specifically is: changing the input of the inversion spectral data to nine-channel data input to obtain the optimized , where is the squared value of the cosine of the angle between two spectral vectors, representing the similarity between each pixel point and the target, , represents the sequence of pixel points, represents the reflection spectrum of the target, represents the transpose matrix of is the third-dimensional data of the hyperspectral data block, representing the spectrum of each pixel point on the spectral image, represents the transpose matrix of represents the autocorrelation coefficient matrix between the spectra corresponding to each pixel point obtained by processing the spectral image the inverse matrix of

[0015] Furthermore, the optimized YOLO model is specifically as follows: changing the input of the three-channel model to the input of the nine-channel model; replacing the C2 layer in the backbone network with the Effivient-v2 network; increasing the original three anchor boxes in the anchor box part to nine anchor boxes; adding a small target detection layer in the neck part to obtain the optimized YOLO model.

[0016] Furthermore, it is characterized in that the minimum period unit of the multi-spectral imaging chip based on periodic arrangement includes four light-transmitting films, and the transmittances of the four light-transmitting films are set as follows: film a (21): the main wavelength range of transmission is 550nm - 700nm, and 10% is transmitted in the remaining bands; film b (22): the main wavelength range of transmission is 350nm - 950nm, and 0% is transmitted in the remaining bands; film c (23): the main wavelength range of transmission is 500nm - 950nm, and 10% is transmitted in the remaining bands; film d (24): the main wavelength range of transmission is 350nm - 500nm and 600nm - 850nm, and 10% is transmitted in the remaining bands.

[0017] The method for detecting drones of the multi-spectral imaging chip based on periodic arrangement is implemented by the above-mentioned device for detecting drones of the multi-spectral imaging chip based on periodic arrangement, and is characterized in that the method includes the following steps:

[0018] S1. Using the drone detection device to collect multi-spectral image data and perform preprocessing to obtain a multi-spectral data block;

[0019] S2. According to the optimized model, calculate the similarity between each pixel point and the target, and obtain the position of the target object;

[0020] S3. According to the optimized YOLO model, obtain the center coordinates of the target object;

[0021] S4. Calculate the Euclidean distance between the position of the target object and the center coordinates of the target object, and output the final target position.

[0022] Further, the preprocessing is specifically as follows: Input the multi-spectral image data into the preprocessing model.

[0023] Further, make a judgment according to the similarity between each pixel point and the target. Pixel points with a similarity to the target greater than 0.85 are subjected to threshold segmentation processing to obtain a segmented image; then the segmented image is successively subjected to binarization, connected component judgment, and medium-wave filtering value processing to obtain the position of the target object.

[0024] Further, the specific method for obtaining the center coordinates of the target object is as follows: Input the multi-spectral data block into the optimized yolo model to obtain the xywh coordinates of the target object, where x represents the abscissa of the target object, y represents the ordinate, w represents the width, and h represents the height; perform coordinate conversion on the xywh coordinates of the target object to obtain the center coordinates of the target object.

[0025] Further, when the Euclidean distance between the position of the target object and the center coordinates of the target object is less than 10, the position of the target object is the final target position.

[0026] The beneficial effects of the method of the present invention are as follows:

[0027] Compared with the traditional UAV detection method, the present invention makes full use of the periodic structure of the multi-spectral imaging chip based on periodic arrangement, combines spectral data with image data, enables each pixel to independently output spectral information and image information, and uses the optimized model and the optimized yolo model to achieve accurate identification of small and medium-sized UAVs, making up for the defects that the number of pixels occupied by the UAV target is relatively small during detection in traditional technologies, resulting in the loss of shape and texture, or the situation of unidentifiable or misidentifiable objects such as birds. By combining spectral information and image information, the recognition rate is improved while the false alarm rate is reduced, and the waste of police force resources is reduced. Description of the Drawings

[0028] Figure 1 It is the structure diagram of the detection device in Embodiment 1 of the present invention;

[0029] Figure 2 It is the schematic diagram of the periodic structure of the multi-spectral imaging chip based on periodic arrangement in Embodiment 1 of the present invention, where 21 represents thin film a, 22 represents thin film b, 23 represents thin film c, and 24 represents thin film d;

[0030] Figure 3Schematic diagram of the band transmittance curves of the thin film units in the periodic structure of the multi-spectral imaging chip based on periodic arrangement in Embodiment 1 of the present invention, where the abscissa represents the band and the ordinate represents the transmittance;

[0031] Figure 4 Flowchart of the method in Embodiment 2 of the present invention. Detailed implementation manners

[0032] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0033] Embodiment 1

[0034] This embodiment provides a UAV detection device for a multi-spectral imaging chip based on periodic arrangement, as Figure 1 shown. The device includes: an optical lens 1, a multi-spectral imaging chip 2 based on periodic arrangement, a circuit board 3, a power supply interface 4, a data transmission unit 5, an image display screen 6, and a data processing unit 7.

[0035] The circuit board 3 is respectively connected to the optical lens 1, the power supply interface 4, and the data transmission unit 5; the multi-spectral imaging chip 2 based on periodic arrangement is connected to the circuit board 3 through pins, the optical lens 1 is adapted to the multi-spectral imaging chip 2 based on periodic arrangement and is connected through an optical path; the data processing unit 7 is respectively connected to the data transmission unit 5 and the image display screen 6.

[0036] The optical lens 1 is used for spectral image acquisition, the multi-spectral imaging chip 2 based on periodic arrangement is used for outputting multi-spectral image data, the circuit board 3 is used for camera startup and multi-spectral image data storage, the power supply interface 4 is used for power transmission, the data transmission unit 5 is used for transmitting the multi-spectral image data output by the multi-spectral imaging chip 2 based on periodic arrangement to the data processing unit 7, the image display screen 6 is used for displaying the final target position imaging, and the data processing unit 7 completes data preprocessing and final target position determination according to the multi-spectral image data output by the multi-spectral imaging chip 2 based on periodic arrangement.

[0037] Currently, the materials of UAVs are mainly carbon fiber, glass fiber, plastic, etc. The optical properties of such materials are relatively stable. Therefore, their reflectance spectra are relatively constant and do not change with distance; at the same time, the background spectrum also has special properties. A multi-spectral imaging chip based on periodic arrangement can be designed according to the difference between the background and target spectra.

[0038] The multi-spectral imaging chip 2 based on periodic arrangement is composed of a photoelectric conversion base and a light-transmitting thin film with a periodic structure. For the specific manufacturing process, please refer to the Chinese invention patent "Imaging Spectral Chip with Both Spectral and Imaging Functions and Its Preparation Method" (CN202010189838.5).

[0039] The target object has good reflectance in the 400nm - 950nm band, and the spectrum of the background has a higher response in the blue band. Therefore, the transmittance of the thin film of the multi-spectral imaging chip 2 based on periodic arrangement is designed as follows: the transmittance in the blue band is lower to reduce the transmittance of the background, while increasing the transmittance of the spectral bands with high target reflectance, which is beneficial to increasing more target spectral information and image information. As Figure 2 shown, based on the Si-based thin film substrate, the minimum periodic unit of the multi-spectral imaging chip 2 based on periodic arrangement is etched into a 3*3 periodic structure, and each periodic unit has a spectral modulation thin film with different transmittances. The wavelength range that the multi-spectral imaging chip 2 based on periodic arrangement can transmit is: 350nm - 950nm, and the spectral transmittance of each periodic unit is related to the spectra of the point target and the background, that is, each pixel can independently output spectral information and image information. The periodic structure of the multi-spectral imaging chip 2 based on periodic arrangement can not only improve the resolution of the image, but also amplify the target spectral characteristics according to the difference between the spectrum of the point target and the background spectrum.

[0040] The minimum periodic unit includes four light-transmitting thin films. The transmittances of the four light-transmitting thin films are set as follows: thin film a21: the main wavelength range of transmission is 550nm - 700nm, and 10% is transmitted in the remaining bands; thin film b22: the main wavelength range of transmission is 350nm - 950nm, and 0% is transmitted in the remaining bands; thin film c23: the main wavelength range of transmission is 500nm - 950nm, and 10% is transmitted in the remaining bands; thin film d24: the main wavelength range of transmission is 350nm - 500nm and 600nm - 850nm, and 10% is transmitted in the remaining bands. The band transmittance curves of each thin film unit are as Figure 3 shown.

[0041] Through the design of the light-transmitting thin film spectroscopic material, the incident light is split, and the target spectrum captured is transmitted with a higher transmittance, while the background spectrum is transmitted with a lower transmittance. Then, when imaging, the brightness of the background is reduced and the brightness of the target is increased. The difference in brightness between the background and the target can provide favorable conditions for subsequent algorithm recognition.

[0042] According to the size of the multi-spectral imaging chip 2 based on periodic arrangement and the size of the pixel, the field of view angle and focal length of the optical lens 1 are set to detect the unmanned aerial vehicle within the field of view. The field of view angle and focal length of the optical lens 1 are 150 degrees and 1.7mm respectively.

[0043] The data processing unit 7 includes a preprocessing model, an optimized model, and an optimized YOLO model;

[0044] The preprocessing model converts the multispectral image data into multispectral data blocks, and the optimized model obtains the position of the target object based on the multispectral data blocks, and the optimized YOLO model converts the multispectral data blocks into the center coordinates of the target object.

[0045] Specifically, the preprocessing model sequentially processes the multispectral image data through background and shadow processing, mosaic processing, super-boundary data truncation, and data type conversion.

[0046] The background and shadow processing includes background subtraction and shadow correction; the background subtraction means subtracting the signal data output by the multispectral imaging chip 2 arranged in a cycle under a dark background to achieve the effect of data correction; the shadow correction means correcting the situation where the multispectral image data is bright in the center and dark at the edges.

[0047] The mosaic processing means performing interpolation processing on the multispectral image data to obtain multispectral data with spectral and image information.

[0048] Specifically, the super-boundary data truncation and data type conversion are as follows: truncating the part of the multispectral data block whose value is greater than 1023 or less than 0, and at the same time converting the decimal data into octal data to obtain the multispectral data block.

[0049] The optimized model is specifically: changing the input of the inversion spectral data to the input of nine-channel data to obtain the optimized , where is the square value of the cosine of the angle between two spectral vectors, representing the similarity between each pixel point and the target, , represents the sequence of pixel points, represents the reflection spectrum of the target, represents the transpose matrix of is the third-dimensional data of the multispectral data block, representing the spectrum of each pixel point on the spectral image, represents the transpose matrix of represents the autocorrelation coefficient matrix between the spectra corresponding to each pixel point obtained by processing the spectral image the inverse matrix of represents the modulus of the reflection spectrum vector of the target; represents the modulus of the spectral vector of each pixel point of the spectral image, Represents an inner product calculation function.

[0050] Since the conventional YOLO model has a large number of layers and parameters, and the inference time is long, and the flight speed of the drone is relatively fast, it is necessary to update the recognition rate of the drone. Therefore, the conventional YOLO model is optimized as follows:

[0051] (1) Change the input of the three-channel model of the conventional YOLO model to the input of a nine-channel model. The number of channels of the original model is the three RGB channels, and the number of channels of the optimized YOLO model is nine-channel data. Each channel of the nine-channel data is image information, and the nine vertical channels are spectral information. After changing to the nine-channel model input, both image information and spectral information can be used for the detection of target objects;

[0052] (2) Replace the C2 layer in the backbone network with the Effivient-v2 network with a simple structure and faster inference time. By introducing the Effivient-v2 network, while not reducing the accuracy of the training set, the training speed and the number of parameters are improved, and the network prediction speed for faster drones can be enhanced;

[0053] (3) Increase the original three anchor boxes in the anchor box part to nine anchor boxes; increase the detection range of the anchor boxes;

[0054] (4) Add a small target detection layer in the Neck part to increase the recognition of drones at a long distance.

[0055] After steps (1) to (4), an optimized YOLO model is obtained.

[0056] Example 2

[0057] This example further limits Example 1. The detection method is implemented by the above-mentioned drone detection device based on a periodically arranged multispectral imaging chip. As Figure 4 shown, the method includes the following steps:

[0058] S1. Use the drone detection device to collect multispectral image data and perform preprocessing to obtain multispectral data blocks.

[0059] The relevant operations of step S1 are introduced with specific examples:

[0060] Input the multispectral image data into the preprocessing model.

[0061] S2. According to the optimized model, calculate the similarity between each pixel point and the target, and obtain the position of the target object.

[0062] The relevant operations of step S2 are introduced with specific examples:

[0063] Judgment is made based on the similarity of each pixel point to the target. Pixel points with a similarity to the target greater than 0.85 are subjected to threshold segmentation processing to obtain the segmented image; then the segmented image is successively subjected to binarization, connected component judgment, and medium-wave filtering value processing to obtain the position of the target object.

[0064] S3. According to the optimized YOLO model, obtain the center coordinates of the target object.

[0065] The relevant operations of step S3 are introduced with a specific example:

[0066] Input the multispectral data block into the optimized YOLO model to obtain the xywh coordinates of the target object, where x represents the abscissa of the target object, y represents the ordinate, w represents the width, and h represents the height; perform coordinate conversion on the xywh coordinates of the target object to obtain the center coordinates of the target object.

[0067] S4. Calculate the Euclidean distance between the position of the target object and the center coordinates of the target object, and output the final target position.

[0068] The relevant operations of step S4 are introduced with a specific example:

[0069] When the Euclidean distance between the position of the target object and the center coordinates of the target object is less than 10, the position of the target object is the final target position.

[0070] When there is only a small amount of image information and texture information of the UAV due to factors such as the environment and weather, the improved YOLO model cannot identify it. At this time, we use the optimized model to perform spectral dimension recognition on the multispectral data block to obtain pixel-by-pixel spectral data, and process the pixel-by-pixel spectral data with the spectra in the database. Make full use of the spectral information to detect the UAV, so that when the UAV image information is less, the UAV can also be identified by using the spectral information and the image information.

[0071] The database is the UAV spectral data collected in advance under different weather conditions and distances.

Claims

1. An unmanned aerial vehicle detection device based on a multi-spectral imaging chip with periodic arrangement, characterized in that, Including: An optical lens (1), a multi-spectral imaging chip (2) arranged in a cycle, a circuit board (3), a power supply interface (4), a data transmission unit (5), an image display screen (6), and a data processing unit (7); The circuit board (3) is respectively connected to the optical lens (1), the power supply interface (4), and the data transmission unit (5); the multi-spectral imaging chip (2) arranged in a cycle is connected to the circuit board (3) through pins, and the optical lens (1) and the multi-spectral imaging chip (2) arranged in a cycle are connected through an optical path; the data processing unit (7) is respectively connected to the data transmission unit (5) and the image display screen (6); The optical lens (1) is used for spectral image acquisition, the multi-spectral imaging chip (2) arranged in a cycle is used for outputting multi-spectral image data, the circuit board (3) is used for camera startup, camera parameter control, and multi-spectral image data storage, the power supply interface (4) is used for transmitting power, the data transmission unit (5) is used for transmitting the multi-spectral image data output by the multi-spectral imaging chip (2) arranged in a cycle to the data processing unit (7), the image display screen (6) is used for displaying the final target position imaging, and the data processing unit (7) completes data preprocessing and final target position determination according to the multi-spectral image data output by the multi-spectral imaging chip (2) arranged in a cycle; Set the minimum cycle unit of the multi-spectral imaging chip (2) arranged in a cycle to 3*3; The data processing unit (7) includes a preprocessing model, an optimized model and an optimized YOLO model; The optimized model is specifically as follows: The input of the inversion spectral data is changed to the input of nine-channel data to obtain the optimized , where is the square value of the cosine of the angle between two spectral vectors, representing the similarity between each pixel point and the target, , represents the sequence of pixel points, represents the reflection spectrum of the target, represents 's transpose matrix, is the third-dimensional data of the multispectral data block, representing the spectrum of each pixel point on the spectral image, represents 's transpose matrix, represents the autocorrelation coefficient matrix between the spectra corresponding to each pixel point obtained by processing the spectral image 's inverse matrix; The optimized YOLO model is specifically: changing the input of the three-channel model to the input of the nine-channel model; replacing the C2 layer in the backbone network with the Effivient-v2 network; increasing the original three anchor boxes in the anchor box part to nine anchor boxes; Adding a small target detection layer in the neck part to obtain the optimized YOLO model; The preprocessing model converts the multispectral image data into multispectral data blocks, and the optimized model obtains the position of the target object based on the multispectral data blocks, and the optimized YOLO model converts the multispectral data blocks into the center coordinates of the target object.

2. The drone detection device of the multi-spectral imaging chip based on periodic arrangement according to claim 1, wherein, The preprocessing model is specifically: sequentially passing the multi-spectral image data through background and shadow processing, mosaic processing, ultra-boundary data truncation, and data type conversion.

3. The drone detection device of the multi-spectral imaging chip based on periodic arrangement according to claim 1, wherein The minimum cycle unit of the multi-spectral imaging chip (2) arranged in a cycle includes four light-transmitting films, and the transmittances of the four light-transmitting films are set as follows: film a (21): the main wavelength range of transmission is 550nm - 700nm, and 10% is transmitted in the remaining bands; film b (22): the main wavelength range of transmission is 350nm - 950nm, and 0% is transmitted in the remaining bands; film c (23): the main wavelength range of transmission is 500nm - 950nm, and 10% is transmitted in the remaining bands; film d (24): the main wavelength range of transmission is 350nm - 500nm and 600nm - 850nm, and 10% is transmitted in the remaining bands.

4. A method for detecting drones using a multi-spectral imaging chip with periodic arrangement, wherein the detection method is implemented using the drone detection device based on the multi-spectral imaging chip with periodic arrangement according to any one of claims 1 to 3, characterized in that, The method includes the following steps: S1. Using a drone detection device to collect multi-spectral image data and perform preprocessing to obtain multi-spectral data blocks; S2. According to the optimized model, calculate the similarity between each pixel point and the target, and obtain the position of the target object; S3. According to the optimized YOLO model, obtain the center coordinates of the target object; S4. Calculate the Euclidean distance between the position of the target object and the center coordinates of the target object, and output the final target position.

5. The method for detecting an unmanned aerial vehicle using the multi-spectral imaging chip based on periodic arrangement according to claim 4, wherein The specific preprocessing is as follows: input the multispectral image data into the preprocessing model.

6. The method for detecting an unmanned aerial vehicle by using the multi-spectral imaging chip based on periodic arrangement according to claim 4, characterized in that, Judgment is made according to the similarity of each pixel point to the target. Pixel points with a similarity to the target greater than 0.85 are subjected to threshold segmentation processing to obtain the segmented image; then the segmented image is successively subjected to binarization, connected component judgment, and medium-wave filtering value processing to obtain the position of the target object.

7. The method for detecting an unmanned aerial vehicle using the multi-spectral imaging chip based on periodic arrangement according to claim 4, wherein, The specific method for obtaining the center coordinates of the target object is as follows: input the multispectral data block into the optimized yolo model to obtain the xywh coordinates of the target object, where x represents the abscissa of the target object, y represents the ordinate, w represents the width, and h represents the height; perform coordinate conversion on the xywh coordinates of the target object to obtain the center coordinates of the target object.

8. The method for detecting an unmanned aerial vehicle using the multi-spectral imaging chip based on periodic arrangement according to claim 7, wherein When the Euclidean distance between the position of the target object and the center coordinates of the target object is less than 10, the position of the target object is the final target position.

Images