A method for cooperative perception of optoelectronic pod environment

Abstract

The present invention discloses a method for cooperatively sensing an optoelectronic pod environment, which belongs to the field of environmental sensing technology and includes the following steps: S1, using an optoelectronic pod to collect initial environmental imaging; S2, using a subband of the initial environmental imaging to generate a transitional environmental imaging to obtain an image perception coefficient; S3, using the image perception coefficient to calculate the environmental perception degree and determine the environmental sensing result of the optoelectronic pod. The environmental sensing result of the present invention can accurately locate the key area or target in the initial environmental imaging, and the environmental sensing result obtained through multi-scale analysis, feature extraction and quantitative evaluation has a high accuracy.

Description

Technical Field

[0001] The present invention belongs to the technical field of environmental perception, and in particular relates to a method for cooperatively perceiving an environment of an optoelectronic pod. Background Art

[0002] With the continuous development of UAV technology, its application in military reconnaissance, civil monitoring and emergency rescue is becoming more and more extensive. As an important reconnaissance payload of UAV, optoelectronic pods have developed rapidly in recent years. The environmental perception capability of optoelectronic pods has become a key factor for UAVs to lock targets. However, complex and changing environmental conditions have put forward higher requirements on the perception capability of optoelectronic pods of UAVs. Traditional image-based target perception methods have limitations and their target recognition accuracy is low. Therefore, an environmental collaborative perception method based on image processing is needed to improve the environmental perception capability and adaptability of UAVs. Summary of the invention

[0003] In order to solve the above problems, the present invention proposes a method for cooperative perception of optoelectronic pod environment.

[0004] The technical solution of the present invention is: a method for cooperatively sensing an optoelectronic pod environment comprises the following steps:

[0005] S1. Collect initial environmental imaging using the optoelectronic pod;

[0006] S2, using the sub-band of the initial environment imaging to generate transition environment imaging, and obtain image perception coefficients;

[0007] S3. Calculate the environmental perception using the image perception coefficient and determine the environmental perception result of the optoelectronic pod.

[0008] Furthermore, S2 includes the following sub-steps:

[0009] S21, decomposing the initial environment imaging to obtain a first sub-band and a second sub-band;

[0010] S22, using the first sub-band and the second sub-band to process the initial environment imaging to obtain a transition environment imaging;

[0011] S23, converting the transition environment imaging into an index image to obtain an image perception coefficient.

[0012] The beneficial effect of the above further scheme is that in the present invention, an image is decomposed into a set of frequency-limited components, which are called sub-bands. Each sub-band is obtained by bandpass filtering the input image. The initial environment imaging is decomposed to split it into different frequency components to improve the image quality. The processed transition environment imaging is converted into an index image to facilitate the calculation of image perception coefficients.

[0013] Furthermore, in S22, the expression of the transition environment imaging X is:

[0014] ; In the formula, windows represents the smoothing window, z1 represents the first subband, z2 represents the second subband, and x represents the initial environment imaging.

[0015] S22 is equivalent to the image smoothing process.

[0016] Further, S23 includes the following sub-steps:

[0017] S231, converting the transition environment imaging into an index image;

[0018] S232, extracting the image matrix and the palette matrix of the index image;

[0019] S233, arranging the singular values ​​of the image matrix in descending order to obtain an image singular value sequence;

[0020] S234, generating image perception coefficients using the image singular value sequence and the palette matrix.

[0021] The beneficial effect of the above further scheme is that in the present invention, the index image is a special image representation method, which directly uses the pixel value as the subscript of the RGB palette (or color map). The index image contains two main parts: the image matrix and the palette matrix. The image matrix is ​​usually a two-dimensional matrix, in which the value of each element represents the index in the palette matrix. The palette matrix is ​​a matrix containing three columns and several rows, and the three elements of each row specify the intensity of the three RGB colors respectively.

[0022] By performing singular value decomposition on the image matrix, a series of singular values ​​are obtained and arranged in descending order. The singular values ​​reflect the important information components in the image matrix. Combining the image singular value sequence and the palette matrix, an image perception coefficient that can efficiently represent the image features can be generated.

[0023] Furthermore, in S234, the calculation formula of the image perception coefficient τ is:

[0024] ; Where MID represents the median of the singular value sequence of the image, m represents the number of rows of the palette matrix, n represents the number of columns of the palette matrix, and r represents the rank of the palette matrix.

[0025] Furthermore, S3 includes the following sub-steps:

[0026] S31. Calculate the environmental perception of the optoelectronic pod according to the image perception coefficient;

[0027] S32. Generate environmental perception results according to the environmental perception of the optoelectronic pod.

[0028] The beneficial effect of the above further scheme is that in the present invention, the environmental perception result can highlight the key pixel points in the initial environmental imaging and quickly identify important features or targets in the environment.

[0029] Furthermore, in S31, the calculation formula of the environmental perception H is:

[0030] ; In the formula, τ represents the image perception coefficient, K max Represents the maximum pixel value of the initial environment imaging, K min Represents the minimum pixel value of the initial environment imaging, K ave represents the average pixel value of the initial environment imaging, MAX(·) represents the maximum value operation, and MIN(·) represents the minimum value operation.

[0031] The beneficial effect of the above further solution is that in the present invention, the image perception coefficient is used as an adjustment factor to optimize the calculation result of the environmental perception to adapt to different application scenarios and requirements.

[0032] Further, in S32, if the initial environment imaging satisfies The pixel point is taken as the environmental perception result of the optoelectronic pod; where k represents the pixel value of the pixel point in the initial environmental imaging, and k* represents the average pixel value of the D neighborhood of the pixel point in the initial environmental imaging.

[0033] The beneficial effects of the present invention are as follows: the present invention can realize multi-scale analysis by decomposing the initial environmental imaging into different sub-bands, capture the characteristic information of different frequency and spatial domains, and in the process of generating sub-band decomposition and transitional environmental imaging, can selectively retain the important information of the image; the environmental perception result can accurately locate the key area or target in the initial environmental imaging, and through multi-scale analysis, feature extraction and quantitative evaluation, the obtained environmental perception result has high accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 Flow chart of the cooperative perception method of optoelectronic pod environment. DETAILED DESCRIPTION

[0035] The embodiments of the present invention will be further described below in conjunction with the accompanying drawings.

[0036] like Figure 1 As shown, the present invention provides a method for cooperatively sensing an optoelectronic pod environment, comprising the following steps:

[0037] S1. Collect initial environmental imaging using the optoelectronic pod;

[0038] S2, using the sub-band of the initial environment imaging to generate transition environment imaging, and obtain image perception coefficients;

[0039] S3. Calculate the environmental perception using the image perception coefficient and determine the environmental perception result of the optoelectronic pod.

[0040] In this embodiment of the present invention, S2 includes the following sub-steps:

[0041] S21, decomposing the initial environment imaging to obtain a first sub-band and a second sub-band;

[0042] S22, using the first sub-band and the second sub-band to process the initial environment imaging to obtain a transition environment imaging;

[0043] S23, converting the transition environment imaging into an index image to obtain an image perception coefficient.

[0044] In the present invention, an image is decomposed into a set of band-limited components, which are called sub-bands. Each sub-band is obtained by bandpass filtering the input image. The initial environment imaging is decomposed to split it into different frequency components to improve the image quality. The processed transition environment imaging is converted into an index image to facilitate the calculation of image perception coefficients.

[0045] In the embodiment of the present invention, in S22, the expression of the transition environment imaging X is:

[0046] ; In the formula, windows represents the smoothing window, z1 represents the first subband, z2 represents the second subband, and x represents the initial environment imaging.

[0047] S22 is equivalent to the image smoothing process.

[0048] In this embodiment of the present invention, S23 includes the following sub-steps:

[0049] S231, converting the transition environment imaging into an index image;

[0050] S232, extracting the image matrix and the palette matrix of the index image;

[0051] S233, arranging the singular values ​​of the image matrix in descending order to obtain an image singular value sequence;

[0052] S234, generating image perception coefficients using the image singular value sequence and the palette matrix.

[0053] In the present invention, indexed image is a special image representation method, which directly uses pixel values ​​as subscripts of RGB palette (or color map). Indexed image contains two main parts: image matrix and palette matrix. Image matrix is ​​usually a two-dimensional matrix, in which the value of each element represents the index in the palette matrix. The palette matrix is ​​a matrix containing three columns and several rows, and the three elements of each row specify the intensity of the three RGB colors respectively.

[0054] By performing singular value decomposition on the image matrix, a series of singular values ​​are obtained and arranged in descending order. The singular values ​​reflect the important information components in the image matrix. Combining the image singular value sequence and the palette matrix, an image perception coefficient that can efficiently represent the image features can be generated.

[0055] In the embodiment of the present invention, in S234, the calculation formula of the image perception coefficient τ is:

[0056] ; Where MID represents the median of the singular value sequence of the image, m represents the number of rows of the palette matrix, n represents the number of columns of the palette matrix, and r represents the rank of the palette matrix.

[0057] In this embodiment of the present invention, S3 includes the following sub-steps:

[0058] S31. Calculate the environmental perception of the optoelectronic pod according to the image perception coefficient;

[0059] S32. Generate environmental perception results according to the environmental perception of the optoelectronic pod.

[0060] In the present invention, the environmental perception result can highlight the key pixels in the initial environmental imaging and quickly identify important features or targets in the environment.

[0061] In the embodiment of the present invention, in S31, the calculation formula of the environmental perception H is:

[0062] ; In the formula, τ represents the image perception coefficient, K max Represents the maximum pixel value of the initial environment imaging, K min Represents the minimum pixel value of the initial environment imaging, K ave represents the average pixel value of the initial environment imaging, MAX(·) represents the maximum value operation, and MIN(·) represents the minimum value operation.

[0063] In the present invention, the image perception coefficient is used as an adjustment factor to optimize the calculation result of the environmental perception to adapt to different application scenarios and requirements.

[0064] In the embodiment of the present invention, in S32, if the initial environment imaging satisfies The pixel point is taken as the environmental perception result of the optoelectronic pod; where k represents the pixel value of the pixel point in the initial environmental imaging, and k* represents the average pixel value of the D neighborhood of the pixel point in the initial environmental imaging.

[0065] Those skilled in the art will appreciate that the embodiments described herein are intended to help readers understand the principles of the present invention, and should be understood that the protection scope of the present invention is not limited to such specific statements and embodiments. Those skilled in the art can make various other specific variations and combinations that do not deviate from the essence of the present invention based on the technical revelations disclosed by the present invention, and these variations and combinations are still within the protection scope of the present invention.

Claims

1. A method for cooperatively sensing an optoelectronic pod environment, characterized in that: The following steps are involved: S1. Collect initial environmental imaging using the optoelectronic pod; S2, using the sub-band of the initial environment imaging to generate transition environment imaging, and obtain image perception coefficients; S3, using the image perception coefficient to calculate the environmental perception, and determine the environmental perception result of the optoelectronic pod; The S2 comprises the following sub-steps: S21, decomposing the initial environment imaging to obtain a first sub-band and a second sub-band; S22, using the first sub-band and the second sub-band to process the initial environment imaging to obtain a transition environment imaging; S23, converting the transition environment imaging into an index image to obtain an image perception coefficient; In S22, the expression of the transition environment imaging X is: ; In the formula, windows represents the smoothing window, z1 represents the first subband, z2 represents the second subband, and x represents the initial environment imaging; The S23 comprises the following sub-steps: S231, converting the transition environment imaging into an index image; S232, extracting the image matrix and the palette matrix of the index image; S233, arranging the singular values ​​of the image matrix in descending order to obtain an image singular value sequence; S234, generating image perception coefficients using the image singular value sequence and the palette matrix; In S234, the calculation formula of the image perception coefficient τ is: ; Where MID represents the median of the singular value sequence of the image, m represents the number of rows of the palette matrix, n represents the number of columns of the palette matrix, and r represents the rank of the palette matrix; The S3 comprises the following sub-steps: S31. Calculate the environmental perception of the optoelectronic pod according to the image perception coefficient; S32, generating an environmental perception result according to the environmental perception of the optoelectronic pod; In S31, the calculation formula of the environmental perception H is: ; In the formula, τ represents the image perception coefficient, K max Represents the maximum pixel value of the initial environment imaging, K min Represents the minimum pixel value of the initial environment imaging, K ave represents the average pixel value of the initial environment imaging, MAX(·) represents the maximum value operation, and MIN(·) represents the minimum value operation; In S32, if the initial environment imaging satisfies The pixel point is taken as the environmental perception result of the optoelectronic pod; where k represents the pixel value of the pixel point in the initial environmental imaging, k* represents the average pixel value of the D neighborhood of the pixel point in the initial environmental imaging, and H represents the environmental perception degree.

Images