Target identification method and device in shielding environment

Abstract

The invention discloses a target identification method and device in a shielding environment, and belongs to the technical field of target identification. The method comprises the following steps: based on the imaging system, carrying out detection imaging on a target area in a shielded environment by adopting a single-point irradiation and single-point detection mode to obtain a target area image; performing background cancellation on the target area image to obtain a target image; comparing the target image with a standard image in a standard library one by one, and determining the type of the shielded target according to a comparison result; the standard library comprises a plurality of types of vehicle standard images; according to the imaging system, laser pulses are utilized to irradiate a target area, and the narrow laser pulses can penetrate through shelters such as forest vegetation and the like to obtain related information of a sheltered target, so that the information of the sheltered target can be fully expressed in an obtained target area image, and data support is provided for image processing and comparison; and the accuracy of target identification is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of target recognition, and in particular to a target recognition method and device in a shielded environment. Background Art

[0002] Ground vehicles will use natural shelters such as forest vegetation or simple artificial shelters such as camouflage nets to hide. However, traditional radar and photoelectric detection systems have great limitations in imaging detection and identification of vehicles hidden under forests, and cannot accurately identify targets.

[0003] Therefore, there is an urgent need to provide a target recognition method in an obscured environment to improve the accuracy of target recognition. Summary of the invention

[0004] The present invention provides a method and device for target recognition in a shielded environment, which can solve the problem of inaccurate target recognition in related technologies. The technical solution is as follows:

[0005] On the one hand, an imaging system for identifying the type of a target in a shielded environment is provided, comprising: a main control computer, a pulsed laser emission source, a beam splitter, a scanning driver, a mechanical scanning system, an optical lens, a single photon detector, and a single photon counter;

[0006] The main control computer sends a motion instruction to the scanning driver, and the scanning driver inputs a driving voltage to the mechanical scanning system so that the mechanical scanning system is aligned with a specified position of the target area;

[0007] The main control computer controls the pulse laser emission source to emit laser pulses, and the laser pulses are split by a beam splitter to obtain a laser pulse, and the laser pulse is irradiated to a specified position of the target area by a mechanical scanning system, and the scattered laser at the specified position is obtained by the mechanical scanning system, and is captured by an optical lens after passing through the beam splitter, and then detected by a single-photon detector and a single-photon counter, and the detection signal is sent to the main control computer;

[0008] The main control computer acquires and utilizes detection signals at a plurality of designated positions to perform image reconstruction to obtain an image of the target area; the plurality of designated positions cover the entire target area.

[0009] On the other hand, a method for target recognition in a shielded environment is provided, which is applied to a main control computer, and the main control computer is located in any of the above-mentioned imaging systems; the method comprises:

[0010] Based on the imaging system, a single-point illumination and single-point detection method is used to detect and image the target area in the shielded environment to obtain an image of the target area;

[0011] Perform background cancellation on the target area image to obtain the target image;

[0012] The target image is compared with standard images in a standard library one by one to determine the type of the obscured target according to the comparison result; the standard library includes multiple types of vehicle standard images.

[0013] On the other hand, a target recognition device in a shielded environment is provided, which is applied to a main control computer, and the main control computer is located in any of the above-mentioned imaging systems; the device comprises:

[0014] An image acquisition unit is used to detect and image the target area in the shielded environment by using a single-point illumination and single-point detection method based on the imaging system to obtain an image of the target area;

[0015] An image processing unit, used for performing background cancellation on the target area image to obtain a target image;

[0016] The comparison and identification unit is used to compare the target image with the standard images in the standard library one by one, so as to determine the type of the obscured target according to the comparison result; the standard library includes multiple types of vehicle standard images.

[0017] On the other hand, a computer device is provided, which includes a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory to implement the steps of the target recognition method in a shielded environment described above.

[0018] On the other hand, a computer-readable storage medium is provided, wherein a computer program is stored in the storage medium, and when the computer program is executed by a processor, the steps of the target recognition method in a shielded environment are implemented.

[0019] On the other hand, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the steps of the target recognition method in a shielded environment described above.

[0020] The technical solution provided by the present invention can at least bring the following beneficial effects:

[0021] The imaging system uses laser pulses to illuminate the target area. The narrower laser pulses can penetrate obstructions such as trees and vegetation to obtain relevant information about the obscured target, so that the obtained target area image can fully express the information of the obscured target, providing data support for image processing and comparison, and improving the accuracy of target recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, 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 some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 is a schematic diagram of the principle of an imaging system for identifying target types in a shielded environment provided by an embodiment of the present invention;

[0024] Figure 2 It is a schematic diagram of a method for determining a target plane in a top-down detection according to an embodiment of the present invention;

[0025] Figure 3 This is a flow chart of a method for identifying a target in a shielded environment provided by an embodiment of the present invention;

[0026] Figure 4 An intensity image obtained by using an imaging system for a target area according to an embodiment of the present invention;

[0027] Figure 5 A range image obtained by using an imaging system for a target area according to an embodiment of the present invention;

[0028] Figure 6 This is a structural diagram of a target recognition device in a shielded environment provided by an embodiment of the present invention;

[0029] Figure 7 It is a hardware architecture diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0031] As mentioned above, traditional radar and optoelectronic detection systems have great limitations for imaging detection and identification of hidden vehicles under forests: ① It is difficult to obtain target information under shielding conditions, such as targets hidden in the woods; ② The three-dimensional features and distance information of the target cannot be obtained, and the target information is not fully grasped, which affects the accuracy of target detection and identification; ③ The use conditions are greatly affected by the natural environment and are easily disturbed.

[0032] In addition, the shortcomings of the SAR imaging method are mainly manifested in the following aspects: ① The attenuation of high-frequency microwave radars above the X-band is very large when penetrating vegetation, making it difficult to detect targets under vegetation; ② Although ultra-wideband SAR has a certain ability to penetrate vegetation, it is greatly interfered by clutter such as echoes from obstructions, resulting in a high false alarm rate and great difficulty in data processing; ③ The imaging resolution is low, the target information obtained is limited, and it is difficult to detect and identify targets.

[0033] Based on this, the inventive concept of the present invention is to use pulsed laser to detect and image the target area. The narrower laser beam can penetrate obstructions such as trees and vegetation to obtain relevant information of the obstructed target, thereby improving the accuracy of target recognition.

[0034] The specific implementation of the above concept is described below.

[0035] Please refer to Figure 1 , an embodiment of the present invention provides an imaging system for identifying the type of a target in a shielded environment, comprising: a main control computer, a pulsed laser emission source, a beam splitter, a scanning driver, a mechanical scanning system, an optical lens, a single photon detector and a single photon counter;

[0036] The main control computer sends a motion instruction to the scanning driver, and the scanning driver inputs a driving voltage to the mechanical scanning system so that the mechanical scanning system is aligned with a specified position of the target area;

[0037] The main control computer controls the pulse laser emission source to emit laser pulses, and the laser pulses are split by a beam splitter to obtain a laser pulse, and the laser pulse is irradiated to a specified position of the target area by a mechanical scanning system, and the scattered laser at the specified position is obtained by the mechanical scanning system, and is captured by an optical lens after passing through the beam splitter, and then detected by a single-photon detector and a single-photon counter, and the detection signal is sent to the main control computer;

[0038] The main control computer acquires and utilizes detection signals at a plurality of designated positions to perform image reconstruction to obtain an image of the target area; the plurality of designated positions cover the entire target area.

[0039] In the embodiment of the present invention, the shielding environment is vegetation shielding such as trees, grass, shrubs, etc., and the target may be a vehicle. The imaging system is used to image the vehicle shielded by the vegetation and identify the vehicle type.

[0040] In the embodiment of the present invention, the beam splitter splits the laser pulse into two beams, and the energy of the beam irradiated to the specified position is 1 / 2 of the laser pulse. The mechanical scanning system obtains the scattered laser at the specified position and is further divided into two beams by the beam splitter. That is to say, the energy of the scattered laser captured by the optical lens is 1 / 4 of the energy of the laser pulse emitted by the pulsed laser emission source. Although the energy is reduced, the backscattering of the target can be directly obtained by using the beam splitter, and the signal detected by the single-photon detector can directly characterize the target information at the specified position, thereby improving the processing speed of data calculation.

[0041] Considering that a laser pulse can only irradiate one position point, but cannot irradiate a large area, the imaging and signal detection of the embodiment of the present invention are realized by single-point irradiation and single-point detection. Multiple position points can be set at intervals for the target area, and each position point is used as a designated position for a single irradiation. The main control computer controls the mechanical scanning system to irradiate the designated position. After each position point is irradiated and signal detection is completed, the program setting is used to irradiate and detect the signal of the next position point. In this way, signal detection can be completed for multiple designated positions covering the entire target area. The main control computer can realize image reconstruction of the target area based on the detection signals of multiple designated positions and the position information corresponding to the detection signals sent by the mechanical scanning system.

[0042] In addition, the system adopts single-point irradiation and single-point detection to design the point-by-point scanning optical path, which helps to concentrate energy and improve the signal-to-noise ratio of the imaging system when the laser power is not high. At the same time, it is easy to use background cancellation to filter out ambient stray light.

[0043] In one embodiment of the present invention, the single photon detector is provided with a corresponding distance gate based on the detection state of the imaging system for the shielded target, so that the single photon detector can only detect the laser pulse signal within the corresponding distance, thereby improving the accuracy of image reconstruction.

[0044] In one implementation, if the imaging system's detection state for the obscured target is a top-down detection, a distance gate is set based on the height of the obscured target; for example, if the average height of the vehicle is 2.5 meters, then the height of 2.5 meters from the target plane can be used as the distance gate, thereby filtering out vegetation crown information.

[0045] Considering that the target area may be in a non-planar area, such as a slope area such as a hillside, please refer to Figure 2, three points that can form a triangle can be selected in the target area. For each selected point, the following are performed: obtaining the echo of the selected point, and using the most recent peak signal in the echo of the selected point as the ground echo corresponding to the selected point, through the time corresponding to the peak and the observation angle between the selected point and the observation position; using the observation angles of the three selected points at the observation position to determine the reference plane. When setting the range gate, use the reference plane as the target plane, and take the set height (for example, 2.5m) from the target plane as the range gate. In this way, the accuracy of filtering vegetation crown information can be improved, and the accuracy of target recognition results can be further improved.

[0046] If the detection state of the imaging system for the shielded target is horizontal detection, the distance gate is set based on the horizontal distance between the shielded target and the imaging system. The distance gate can be set according to the situation where the vegetation is in front of and behind the target, so that after the distance gate is set, the target can be covered and the vegetation in front and behind the target can be filtered out.

[0047] In one embodiment of the present invention, when the echo signal reflected by the target area enters the photon detector, the range gate is opened, and when there is no echo signal at other times, the range gate is closed. This can effectively reduce the interference of atmospheric backscattering and background noise, obtain information such as the intensity and distance of the target, realize laser ranging and three-dimensional imaging, obtain a three-dimensional image of a certain area, and distinguish target objects at different distances, which has obvious advantages for detecting targets hidden by trees and vegetation.

[0048] In the embodiment of the present invention, the imaging system can realize fully automatic laser pulse irradiation and signal detection for the target area, and complete the image reconstruction of the current area. The imaging system is based on a single-photon detector, which has the advantages of high detection sensitivity, large dynamic range, easy integration, etc., and has stronger anti-interference ability and higher resolution, and can detect in poor detection environments such as weak light and noise.

[0049] Please refer to Figure 3 The embodiment of the present invention further provides a method for target recognition in a shielded environment, which is applied to a main control computer, and the main control computer is located in any imaging system described in the above embodiments; the method comprises the following steps 300-304:

[0050] Step 300: Based on the imaging system, a single-point illumination and single-point detection method is used to perform detection imaging on a target area in a shielded environment to obtain an image of the target area.

[0051] In the embodiment of the present invention, the method of using the imaging system to obtain the target area image can refer to the above embodiment, which will not be repeated here. In the target area image obtained by the imaging system, most of the interference caused by vegetation shielding can be eliminated, the effective information amount of target recognition is increased, and the accuracy of target recognition is improved.

[0052] It should be noted that since the imaging system uses a single-photon detector to detect the target reflection signal, two images can be obtained after image reconstruction, one is the intensity image and the other is the distance image. Figure 4 and Figure 5 , which are intensity image and distance image acquired by imaging system for target area respectively.

[0053] Step 302: performing background cancellation on the target area image to obtain a target image.

[0054] In an embodiment of the present invention, the target area image includes a background image and a target image after the target area is irradiated by ambient light. By performing background cancellation on the target area image, a target image reflected from the near-laser irradiated target to the single-photon detector can be obtained.

[0055] Step 304 , comparing the target image with standard images in a standard library one by one, so as to determine the type of the obscured target according to the comparison result; the standard library includes multiple types of vehicle standard images.

[0056] In the embodiment of the present invention, in order to know the type of the obscured target vehicle, a standard library may be constructed first, which includes multiple types of vehicle standard images, and the type of the obscured target may be quickly known by comparing them one by one.

[0057] In one implementation, the comparison method of the target image and the standard image may include: calculating the HU moment function of the corresponding image for the target image and the standard image respectively; using the HU moment function of the corresponding image, calculating the distance between the feature vectors corresponding to the target image and the standard image;

[0058] Then, determining the type of the obscured target according to the comparison result includes: determining the type of vehicle in the standard image corresponding to the minimum distance as the type of the obscured target.

[0059] When calculating the HU moment function of the corresponding image, the following may be specifically included:

[0060] Step 2040: binarizing the image to obtain a binary image;

[0061] Step 2042: extracting edge contours of the binary image using a gradient operator;

[0062] Step 2044: Calculate the HU moment function based on the edge contour.

[0063] The edge contour is the boundary that separates the graphics and is one of the key information for identifying camouflage. It is mainly formed by the mutation of grayscale values ​​in the image. The operator can be used to binarize the background and target images to obtain the binary image f(x, y). Then, the feature quantity of the binary image is counted and the image moment function is used to measure the background image and the target image under the forest for comparison.

[0064] In the embodiment of the present invention, the edge of the image is where the pixel grayscale changes most dramatically, so a gradient operator can be used to extract the edge contour. The gradient operator can be a Sobel operator, a Prewitt operator, a zerocross operator, a Roberts operator, a log operator, or a Canny operator.

[0065] Since the moment function can describe the global characteristics of the image shape and can provide different types of geometric feature information in the image, such as size, position, direction, shape, etc., in the embodiment of the present invention, the use of the moment function for comparison can further improve the accuracy of target recognition.

[0066] Considering that the zero-order moment, first-order moment, second-order moment, etc. in the image are low-order moments, the third-order moment and above are often called high-order moments, and the low-order moment mainly describes the overall characteristics of the image area, such as area, centroid, main axis, direction, etc., and the high-order moment mainly describes the details of the image area, such as distortion, etc. Therefore, when the order of the moment function increases, its complexity will make its physical meaning smaller, but in engineering practice, the significance of the moment invariant is more significant, and the specific definition is as follows:

[0067] The two-dimensional p+q-order moment of an image f(x,y) of size M×N is defined as:

[0068]

[0069] Where p=0,1,2···,q=0,1,2···. The corresponding p+q-order central moment is defined as:

[0070]

[0071] In the formula, p=0,1,2···,q=0,1,2···. Among them,

[0072]

[0073] The normalized p+q-order central moment is defined as:

[0074]

[0075] In the formula, p+q=2,3···.

[0076] A set of 7 two-dimensional moment invariants can be derived from the second-order and third-order normalized central moments: this set of moments is invariant to translation, scaling, mirroring and rotation. Specifically, the 7 two-dimensional moment invariants are:

[0077] φ1=η 20 +η 02

[0078] φ2=(η 20 +η 02 ) 2 +4η1 2 1

[0079] φ3=(η 30 -3η 12 ) 2 +(3η 21 -η 03 ) 2

[0080] φ4=(η 30 +η 12 ) 2 +(η 21 +η 03 ) 2

[0081] φ5=(η 30 -3η 12 )(η 30 +η 12 )[(η 30 +η 12 ) 2 -3(η 21 +η 03 ) 2 ]+

[0082] (3η 21 -η 03 )(η 21 +η 03 )[3(η 30 +η 12 ) 2 -(η 21 +η 03 ) 2 ]

[0083] φ6=(η 20 -η 020 )[(η 30 +η 12 ) 2 -(η 21 +η 03 )2 ]+4η 11 (η 30 +η 12 )(η 21 +η 03 )

[0084] φ7=(3η 21 -η 03 )(η 30 +η 12 )[(η 30 +η 12 ) 2 -3(η 21 +η 03 ) 2 ]+

[0085] (3η 21 -η 03 )(η 21 +η 03 )[3(η 30 +η 12 ) 2 -(η 21 +η 03 ) 2 ]

[0086] According to the above formula, a corresponding set of 7 two-dimensional moment invariants can be calculated for the target image and the standard image respectively as the moment function of the corresponding image.

[0087] When using the moment function of two images to calculate the distance between the feature vectors corresponding to the target image and the standard image, it can be calculated by the following formula:

[0088]

[0089] Among them, w i The weight of each moment function, A i ,B i are the 7 moment invariants of the standard image and the target image.

[0090] Among them, the larger the distance of the feature vectors, the lower the similarity, and vice versa. Therefore, the vehicle type in the standard image corresponding to the minimum distance can be determined as the type of the obscured target.

[0091] In addition, considering that the imaging system can obtain two types of images, intensity image and distance image, for the target area, and the information granularity contained in these two images is different, the moment function of the first target image obtained by the intensity image and the second target image obtained by the distance image can be calculated respectively, and then the distance of the feature vector is calculated by using the two types of moment functions and the moment function of the standard image respectively, and then the distance mean of the moment function of the two types of images is calculated, and the vehicle type in the standard image corresponding to the minimum mean can be determined as the type of the obscured target.

[0092] The detection method based on the single-photon detector in the embodiment of the present invention can simultaneously obtain multiple images of the target, which is rich in information, greatly simplifies the automatic target recognition algorithm, has outstanding target differentiation ability, is easy to distinguish the target type, can provide more decision-making information for correctly identifying and tracking the target, and improves the probability and reliability of target recognition.

[0093] Please refer to Figure 6 The embodiment of the present invention provides a target recognition device in a shielded environment, which is applied to a main control computer, and the main control computer is located in any of the above-mentioned imaging systems; the device includes:

[0094] An image acquisition unit 600 is used to detect and image a target area in a shielded environment by using a single-point illumination and single-point detection method based on the imaging system to obtain an image of the target area;

[0095] An image processing unit 602 is used to perform background cancellation on the target area image to obtain a target image;

[0096] The comparison and identification unit 604 is used to compare the target image with the standard images in the standard library one by one, so as to determine the type of the obscured target according to the comparison result; the standard library includes multiple types of vehicle standard images.

[0097] In one embodiment of the present invention, the comparison method of the target image and the standard image specifically includes: calculating the HU moment function of the corresponding image for the target image and the standard image respectively; using the HU moment function of the corresponding image, calculating the distance between the feature vectors corresponding to the target image and the standard image;

[0098] When the comparison and identification unit determines the type of the obscured target according to the comparison result, it specifically includes: determining the vehicle type in the standard image corresponding to the minimum distance as the type of the obscured target.

[0099] In one embodiment of the present invention, when the comparison and identification unit executes the calculation of the HU moment function of the corresponding image, it specifically includes: binarizing the image to obtain a binary image; extracting the edge contour of the binary image using a gradient operator; and calculating the HU moment function based on the edge contour.

[0100] It should be noted that the target recognition device under an obstructed environment provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the target recognition device under an obstructed environment provided in the above embodiment and the target recognition method embodiment under an obstructed environment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0101] The embodiment of the present application also provides a computer device, please refer to Figure 7 The computer device includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, at least one program, a code set or an instruction set is loaded and executed by the processor to implement the target recognition method in a shielded environment provided by the above-mentioned method embodiments.

[0102] An embodiment of the present application also provides a computer-readable storage medium, on which is stored at least one instruction, at least one program, code set or instruction set, and the at least one instruction, at least one program, code set or instruction set is loaded and executed by a processor to implement the target recognition method in a shielded environment provided by the above-mentioned method embodiments.

[0103] An embodiment of the present application also provides a computer program product, which includes a computer program. A processor of a computer device reads the computer program from a computer-readable storage medium, and the processor executes the computer program, so that the computer device executes the target recognition method in a shielded environment described in any of the above embodiments.

[0104] For the convenience of description, the above system or device is described by dividing it into various modules or units according to its functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0105] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application or certain parts of the embodiments.

[0106] Finally, it should be noted that, in this article, relational terms such as first, second, third and fourth are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0107] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. An imaging system for identifying target types in a shielded environment, characterized in that: include: Main control computer, pulse laser emission source, beam splitter, scanning driver, mechanical scanning system, optical lens, single photon detector and single photon counter; The main control computer sends a motion instruction to the scanning driver, and the scanning driver inputs a driving voltage to the mechanical scanning system so that the mechanical scanning system is aligned with a specified position of the target area; The main control computer controls the pulse laser emission source to emit laser pulses, and the laser pulses are split by a beam splitter to obtain a laser pulse, and the laser pulse is irradiated to a specified position of the target area by a mechanical scanning system, and the scattered laser at the specified position is obtained by the mechanical scanning system, and is captured by an optical lens after passing through the beam splitter, and then detected by a single-photon detector and a single-photon counter, and the detection signal is sent to the main control computer; The main control computer acquires and utilizes detection signals at a plurality of designated positions to perform image reconstruction to obtain an image of the target area; the plurality of designated positions cover the entire target area.

2. The imaging system according to claim 1, characterized in that The single photon detector is provided with a corresponding distance gate based on the detection state of the shielding target by the imaging system.

3. The imaging system according to claim 2, characterized in that If the detection state of the imaging system for the shielded target is a downward detection, a range gate is set based on the height of the shielded target; If the detection state of the imaging system for the shielded target is head-on detection, the range gate is set based on the horizontal distance between the shielded target and the imaging system.

4. A method for target recognition in an obscured environment, characterized in that: Applied to a host computer, the host computer being located in the imaging system according to any one of claims 1 to 3; the method comprising: Based on the imaging system, a single-point illumination and single-point detection method is used to detect and image the target area in the shielded environment to obtain an image of the target area; Perform background cancellation on the target area image to obtain the target image; The target image is compared with standard images in a standard library one by one to determine the type of the obscured target according to the comparison result; the standard library includes multiple types of vehicle standard images.

5. The method according to claim 4, characterized in that The comparison method of the target image and the standard image includes: calculating the HU moment function of the corresponding image for the target image and the standard image respectively; using the HU moment function of the corresponding image, calculating the distance between the feature vectors corresponding to the target image and the standard image; Determining the type of the obscured target according to the comparison result includes: determining the type of vehicle in the standard image corresponding to the minimum distance as the type of the obscured target.

6. The method according to claim 5, characterized in that The calculating of the HU moment function of the corresponding image includes: Binarize the image to obtain a binary image; Use the gradient operator to extract the edge contour of the binary image; Calculate the HU moment function based on the edge contour.

7. A target recognition device in a shielded environment, characterized in that: Applied to a main control computer, the main control computer is located in the imaging system according to any one of claims 1 to 3; the device comprises: An image acquisition unit is used to detect and image the target area in the shielded environment by using a single-point illumination and single-point detection method based on the imaging system to obtain an image of the target area; An image processing unit, used for performing background cancellation on the target area image to obtain a target image; The comparison and identification unit is used to compare the target image with the standard images in the standard library one by one, so as to determine the type of the obscured target according to the comparison result; the standard library includes multiple types of vehicle standard images.

8. A computer device, characterized in that: The computer device includes a memory and a processor, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory to implement the steps of any of the methods described in claims 4-6.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in any one of claims 4 to 6 are implemented.

10. A computer program product, characterized in that The method comprises a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 4 to 6.

Images