Simulation scene complexity assessment method

Abstract

The invention relates to a simulation scene complexity assessment method, belongs to the technical field of simulation, and solves the problem of inaccurate scene complexity assessment in the prior art. The method comprises the following steps: acquiring a to-be-evaluated sequence image of a simulation scene and a corresponding reference sequence image; for each frame of image in the sequence images to be evaluated, calculating a target similarity and a target shielding degree corresponding to the frame of image based on the frame of image and a reference image corresponding to the frame of image; obtaining the basic complexity of the frame of image based on the target similarity and the target shielding degree; calculating an inter-frame information change degree of the frame image based on the frame image and a previous frame image of the frame image; obtaining the complexity of each frame of image based on the basic complexity and the inter-frame information change degree of each frame of image in the sequence image to be evaluated; and carrying out weighted summation on the complexity of each frame of image to obtain the complexity of the sequence image to be evaluated. And accurate scene complexity evaluation is realized.

Description

Technical Field

[0001] The present invention relates to the field of simulation technology, and in particular to a method for evaluating the complexity of a simulation scenario. Background Art

[0002] With the development of computer technology, various target recognition algorithms are widely used in various fields, such as vision-based target recognition technology. The performance evaluation of target recognition algorithms needs to consider the complexity of the scene. The scene complexity can characterize the impact of various interference factors in the scene on the difficulty of target recognition.

[0003] The complexity of the simulation scene is obtained from the complexity of the sequence of images that make up the simulation scene. Image complexity refers to the amount of information contained in the image and the complexity of the image structure. The degree of influence on the recognition target can usually be measured from the color, texture, edge and other aspects of the image. The existing simulation scene complexity evaluation is usually evaluated by comparing the statistical features such as color and texture of the target and the background. The use of statistical features alone cannot accurately evaluate the complexity of the image. It does not take into account the different effects of images at different times on the scene, so the scene complexity evaluation is inaccurate. Summary of the invention

[0004] In view of the above analysis, an embodiment of the present invention aims to provide a simulation scene complexity evaluation method to solve the problem of inaccurate scene complexity evaluation in the prior art.

[0005] On the one hand, an embodiment of the present invention provides a method for evaluating the complexity of a simulation scenario, comprising the following steps:

[0006] Obtaining a sequence image to be evaluated and a corresponding reference sequence image of a simulation scene;

[0007] For each frame image in the sequence of images to be evaluated, the target similarity and target shielding degree corresponding to the frame image are calculated based on the frame image and the reference image corresponding to the frame image; the basic complexity of the frame image is obtained based on the target similarity and the target shielding degree;

[0008] Calculating the inter-frame information variation degree of the frame image based on the frame image and the frame image before the frame image;

[0009] The complexity of each frame of the image is obtained based on the basic complexity of each frame of the image in the sequence of images to be evaluated and the information variation between frames;

[0010] The complexity of each frame of the image is weighted summed to obtain the complexity of the sequence of images to be evaluated.

[0011] Based on the further improvement of the above method, the inter-frame information variation degree of the frame image is calculated based on the frame image and the frame image before the frame image, including:

[0012] Determine the target area of ​​the target in the frame image and the frame image before the frame image respectively;

[0013] Based on the formula Calculate the target size change of the frame image;

[0014] Based on the formula Calculate the target position change degree of the frame image;

[0015] The inter-frame information variation of the frame image is obtained based on the target size variation and target position variation.

[0016] Among them, (w i-1 ,h i-1 ) represents the width and height of the target area in the i-1th frame image, (w i ,h i ) represents the width and height of the target area in the i-th frame image, k1 and k2 represent the normalization factors, △p i (x) represents the displacement of the target in the x direction from the i-1th frame to the i-th frame, △p i (y) represents the displacement of the target in the y direction from the i-1th frame to the i-th frame, △p i-1 (x) represents the displacement of the target in the x direction from the i-2th frame to the i-1th frame, △p i-1 (y) represents the displacement of the target in the y direction from the i-2th frame to the i-1th frame.

[0017] Based on a further improvement of the above method, the target similarity corresponding to the frame image is calculated based on the frame image and a reference image corresponding to the frame image, including:

[0018] If the target distance corresponding to the frame image exceeds a first threshold, a global background similarity corresponding to the frame image is calculated based on the frame image and a reference image corresponding to the frame image as a target similarity corresponding to the frame image;

[0019] Otherwise, the local background similarity corresponding to the frame image is calculated as the target similarity corresponding to the frame image.

[0020] Based on the further improvement of the above method, the global background similarity corresponding to the frame image is calculated based on the frame image and the reference image corresponding to the frame image in the following manner:

[0021] Searching for an affected area in the frame image based on a target template in a reference image corresponding to the frame image;

[0022] Calculate the features of the target template and each affected area respectively; calculate the similarity between the target template and each affected area based on the calculated features;

[0023] The weighted sum of the similarities between the target template and each affected area is used to obtain the global background similarity of the frame image.

[0024] Based on a further improvement of the above method, searching for an affected area in the frame image based on a target template in a reference image corresponding to the frame image includes:

[0025] The frame image is scanned with the target template size as the sliding window size to extract the candidate affected area;

[0026] Calculate the mutual correlation coefficient between the candidate influence region and the target template;

[0027] If the mutual correlation coefficient is greater than the second threshold, the candidate influence region is the influence region.

[0028] Based on the further improvement of the above method, the similarity between the target template and each affected area is weighted and summed to obtain the global background similarity of the frame image, including:

[0029] Calculate the distance between the target template and each influence area

[0030] According to the formula Calculate the weight of the jth influence area

[0031] According to the formula Calculate the global background similarity CDGB of the i-th frame image i ;

[0032] Among them, δ xj =|x T -x Bj |,δ yj =|y T -y Bj |,(x T ,y T ) represents the center coordinate of the target template, (x Bj ,y Bj ) represents the center coordinates of the affected area, represents the width and height of the target template corresponding to the i-th frame image, θ represents the rate of change coefficient, CoS j represents the similarity between the target template and the jth impact area, N ia Indicates the number of affected areas.

[0033] Based on the further improvement of the above method, the local background similarity corresponding to the frame image is calculated in the following way:

[0034] Extract the target and its local background from the frame image, and calculate multiple feature maps of the target and its local background;

[0035] The saliency map of each feature map is calculated based on the image visual saliency algorithm, and the comprehensive saliency map of the target and its local background is obtained based on the saliency map of each feature map;

[0036] Extract the comprehensive saliency map of the target area from the comprehensive saliency map of the target and its local background according to Get the local background similarity corresponding to the frame image, where It represents the mean saliency of the comprehensive saliency map of the target area, and IDLB represents the similarity of the local background corresponding to the frame image.

[0037] Based on the further improvement of the above method, the target shielding degree corresponding to the frame image is calculated based on the frame image and the reference image corresponding to the frame image in the following manner:

[0038] Respectively calculating the grayscale features, gradient features and texture features of the target area of ​​the frame image and the target template in the reference image corresponding to the frame image;

[0039] Calculate the feature difference map of the grayscale feature, gradient feature and texture feature of the target area and the target template to obtain a comprehensive difference map;

[0040] The weight of each pixel in the target area is calculated based on the Gaussian kernel model to obtain a Gaussian weight map of the target area;

[0041] Based on the comprehensive difference map and Gaussian weight map, the target occlusion degree corresponding to the i-th frame image is calculated using the following formula:

[0042]

[0043] Among them, G(k) represents the value of the k-th pixel in the Gaussian weight map, dis(k) represents the value of the k-th pixel in the integrated difference map, and NL represents the number of pixels in the integrated difference map.

[0044] Based on the further improvement of the above method, the constructed Gaussian kernel model is expressed as:

[0045] G(x,y)=g(x,σ r )·g(y,σ c )

[0046]

[0047] Among them, (r0,c0) is the center position of the Gaussian kernel model, r p and c p Respectively represent the number of pixel rows and columns in the target area, σ r and σ cThey represent the scale factors of the Gaussian kernel function in the vertical and horizontal directions respectively, and G(x,y) represents the weight of the (x,y) position.

[0048] Based on the further improvement of the above method, the complexity of each frame image is obtained by using the following formula based on the basic complexity of each frame image and the information variation between frames:

[0049]

[0050] Among them, TRC i and CDI i They represent the basic complexity of the i-th frame image and the degree of information change between frames, and ξ represents the weight.

[0051] Compared with the prior art, the present invention obtains the sequence images to be evaluated and the corresponding reference images of the simulation scene, calculates the target similarity and the target occlusion degree according to each frame image in the sequence images to be evaluated and the corresponding reference image, and obtains the target recognition complexity of each frame image, and at the same time considers the information change degree of each frame image compared with its previous frame image, thereby comprehensively combining the basic complexity of each frame image and the information change degree between frames to obtain the complexity of each frame image, so as to accurately evaluate the complexity of each frame image, and in addition, based on the target distance in each frame image, the complexity of each frame image is weightedly summed to obtain the sequence image to be evaluated, that is, the scene complexity, thereby further improving the accuracy of scene complexity evaluation.

[0052] In the present invention, the above-mentioned technical solutions can also be combined with each other to achieve more preferred combination solutions. Other features and advantages of the present invention will be described in the subsequent description, and some advantages can become obvious from the description, or can be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained through the contents particularly pointed out in the description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The accompanying drawings are only used for the purpose of illustrating specific embodiments and are not to be considered as limiting the present invention. In the entire drawings, the same reference symbols represent the same components;

[0054] Figure 1 The present invention is a flowchart of a method for evaluating the complexity of a simulation scenario. DETAILED DESCRIPTION

[0055] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.

[0056] A specific embodiment of the present invention discloses a method for evaluating the complexity of a simulation scene, such as Figure 1 As shown, the following steps are included:

[0057] S1, obtaining a sequence image to be evaluated and a corresponding reference sequence image of a simulation scene;

[0058] S2. For each frame image in the sequence of images to be evaluated, the target similarity and target shielding degree corresponding to the frame image are calculated based on the frame image and the reference image corresponding to the frame image; and the basic complexity of the frame image is obtained based on the target similarity and the target shielding degree;

[0059] S3, calculating the inter-frame information variation degree of the frame image based on the frame image and the frame image before the frame image;

[0060] S4, obtaining the complexity of each frame of the image in the sequence of images to be evaluated based on the basic complexity of each frame of the image and the degree of information variation between frames;

[0061] S5. Perform weighted summation on the complexity of each frame of the image to obtain the complexity of the sequence of images to be evaluated.

[0062] It should be noted that the reference sequence images corresponding to the sequence images to be evaluated in the simulation scene refer to the sequence images captured by the image capturing device when there is no interference, and the sequence images to be evaluated are the sequence images with interference added, and the interference may be, for example, weather interference such as clouds and fog, and artificial interference such as smoke. The images in the sequence images to be evaluated and the reference sequence images correspond one to one; each frame of the sequence images to be evaluated has a corresponding reference image.

[0063] Compared with the prior art, the simulation scene complexity evaluation method provided in this embodiment obtains the sequence images to be evaluated and the corresponding reference images of the simulation scene, calculates the target similarity and the target occlusion degree according to each frame image in the sequence images to be evaluated and the corresponding reference image to obtain the target recognition complexity of each frame image, and at the same time considers the information change degree of each frame image compared with its previous frame image, thereby comprehensively considering the basic complexity of each frame image and the information change degree between frames to obtain the complexity of each frame image, thereby accurately evaluating the complexity of each frame image, and in addition, based on the target distance in each frame image, the complexity of each frame image is weightedly summed to obtain the sequence image to be evaluated, that is, the scene complexity, thereby further improving the accuracy of scene complexity evaluation.

[0064] Target similarity refers to the similarity between the target and the background. The more similar the target and the background are, the more difficult it is to identify the target.

[0065] Specifically, for each frame image in the sequence of images to be evaluated, the target similarity corresponding to the frame image is calculated based on the frame image and a reference image corresponding to the frame image, including:

[0066] If the target distance corresponding to the frame image exceeds a first threshold, a global background similarity corresponding to the frame image is calculated based on the frame image and a reference image corresponding to the frame image as a target similarity corresponding to the frame image;

[0067] Otherwise, the local background similarity corresponding to the frame image is calculated based on the frame image and the reference image corresponding to the frame image as the target similarity corresponding to the frame image.

[0068] During implementation, the target similarity is calculated in different ways according to the distance from the target. When the target is far away, the similarity between the global background and the target affects the recognition accuracy from the similarity perspective, so the global background similarity is used as the target similarity; when the target is close, the similarity between the local background and the target affects the recognition accuracy from the similarity perspective, so the local background similarity should be considered as the target similarity, and the corresponding similarity evaluation focus is determined according to the distance from the target, so that it is more suitable for the complexity evaluation of the scene and improves the accuracy of the evaluation. During implementation, the first threshold is determined according to the actual application scenario.

[0069] Specifically, the global background similarity corresponding to the frame image is calculated based on the frame image and the reference image corresponding to the frame image in the following manner:

[0070] S211, searching for an affected area in the frame image based on a target template in a reference image corresponding to the frame image;

[0071] S212, extracting features of the target template and each affected area respectively; calculating the similarity between the target template and each affected area based on the extracted features;

[0072] S213: Perform weighted summation on the similarities between the target template and each affected area to obtain the global background similarity of the frame image.

[0073] During implementation, for the i-th frame image in the sequence of images to be evaluated, that is, the i-th image to be evaluated, it is necessary to first extract the minimum circumscribed rectangular area of ​​the target from the corresponding reference image to obtain the target template.

[0074] Then, searching the affected area in the frame image based on the target template in the reference image corresponding to the frame image specifically includes:

[0075] S2111, performing sliding scanning on the frame image with the target template size as the sliding window size to extract candidate impact regions;

[0076] S2112. Calculate the mutual correlation coefficient between the candidate influence region and the target template; if the mutual correlation coefficient is greater than a second threshold, the candidate influence region is the influence region.

[0077] In implementation, not all background areas will affect the recognition of the target, and some areas that are significantly different from the target should be excluded to improve computational efficiency. Therefore, the size of the target template is used as the sliding window size, and the sliding step is 1 pixel. A sliding scan is performed in the image to be evaluated to obtain the candidate impact area.

[0078] Specifically, the correlation coefficient between the candidate influence region and the target template is calculated using the following formula:

[0079]

[0080] Where (x,y)∈T i Represents the element (x, y) of the target template corresponding to the i-th frame image, T i (x,y) represents the pixel value of the element (x,y) of the target template, represents the average pixel value of the target template, B ij represents the jth candidate influence region of the i-th frame image, (u, v) represents the center coordinates of the jth candidate influence region, Represents the union pixel value of the jth candidate influence area.

[0081] If the correlation coefficient between the candidate influence region and the target template is greater than a second threshold, the candidate influence region is the influence region. The second threshold can be set according to calculation accuracy and efficiency requirements.

[0082] After the influence area is obtained, the features of the target template and each influence area are calculated respectively, and the similarity between the target template and each influence area is calculated based on the features.

[0083] During implementation, the features may include HOG (Histogram of Oriented Gradient) features and LBP (Local Binary Pattern) features. The similarity is calculated based on each feature, and then the similarity between the target template and the affected area is obtained by adding and averaging.

[0084] During implementation, the following formula is used to calculate the similarity between the target template and the affected area:

[0085]

[0086] Among them, S represents the number of features, L s represents the length of the sth feature, Represents the lth element value of the sth feature of the target template, represents the lth element value of the sth feature of the affected area, and ε represents the parameter. ε is a very small positive number to prevent the denominator from being zero.

[0087] Specifically, the similarity between the target template and each affected area is weighted and summed to obtain the global background similarity of the frame image, including:

[0088] Calculate the distance between the target template and each influence area

[0089] According to the formula Calculate the weight of the jth influence area

[0090] According to the formula Calculate the global background similarity CDGB of the i-th frame image i ;

[0091] Among them, δ xj =|x T -x Bj |,δ yj =|y T -y Bj |,(x T ,y T ) represents the center coordinate of the target template, (x Bj ,y Bj ) represents the center coordinates of the affected area, represents the width and height of the target template corresponding to the i-th frame image, θ represents the rate of change coefficient, CoS j represents the similarity between the target template and the jth impact area, N ia Indicates the number of affected areas.

[0092] The influence of the influence area is related to the distance from the target. The farther the distance, the smaller the influence. In order to reflect this difference, the distance between the target template and each influence area is calculated, and the weight of each influence area is determined based on the distance, so as to accurately obtain the global background similarity.

[0093] When implemented, the weight calculation function satisfies Where d is the distance between the impact area and the center of the target template.

[0094] θ is a positive number related to the rate of change. For the rate of change coefficient θ, when the distance between the affected area and the center of the target template reaches the maximum d max When , the influence degree is the minimum θ0≥3, then the rate of change coefficient is:

[0095]

[0096] The maximum spacing can be calculated based on the image size.

[0097] During implementation, the global background similarity is normalized to the range of [0,1) to facilitate fusion with other indicators.

[0098] When it is close to the target, the local background similarity is used as the target similarity.

[0099] Specifically, the local background similarity corresponding to the frame image is calculated in the following manner:

[0100] S221, extracting the target and its local background from the frame image, and calculating multiple feature maps of the target and its local background;

[0101] S222, calculating a saliency map of each feature map based on an image visual saliency algorithm, and obtaining a comprehensive saliency map of the target and its local background based on the saliency map of each feature map;

[0102] S223, extracting a comprehensive salient map of the target area from the comprehensive salient map of the target and its local background, according to Get the local background similarity corresponding to the frame image, where It represents the mean saliency of the comprehensive saliency map of the target area, and IDLB represents the similarity of the local background corresponding to the frame image.

[0103] The local background similarity reflects the influence of the local background on target recognition and detection by measuring the prominence of the target area in the local background. The higher the prominence of the target area, the greater the detectability of the target and the smaller the value of the local influence.

[0104] During implementation, for the i-th frame image in the sequence of images to be evaluated, the minimum circumscribed rectangle surrounding the target in the frame image is taken as the target area, and the target and its local area are the areas in the frame image that coincide with the center of the target area and have an area twice the size of the target area.

[0105] During implementation, multiple feature maps of the target and its local area are calculated, such as intensity feature map, gradient feature map, LBP feature map and phase consistency feature map. Intensity feature is the grayscale feature of the image. During implementation, the gradient feature of the image is calculated by the Sobel operator to obtain the gradient feature map.

[0106] During implementation, the image visual saliency algorithm is, for example, the Graph-Based Visual Saliency (GBVS) algorithm. For each feature map, a saliency map of each feature map is calculated based on the image visual saliency algorithm, and the saliency maps of all feature maps are linearly averaged to obtain a comprehensive saliency map of the target and its local background.

[0107] Then, the image corresponding to the target area is extracted from the comprehensive saliency map to obtain the comprehensive saliency map of the target area. The saliency level of the target area is represented by the mean saliency of the comprehensive saliency map of the target area. The higher the saliency of the target in its local area, the greater the difference between the target and the surrounding area, and the easier it is to detect the target. Therefore, the local background similarity is: in represents the mean saliency of the comprehensive saliency map of the target area of ​​the i-th frame image, and IDLB represents the local background similarity corresponding to the i-th frame image.

[0108] Target obscuration refers to the degree to which the target area is obscured by clouds, fog, and artificial interference. When the target is obscured, its contrast drops significantly, making it difficult to identify the target. The greater the obscuration, the more difficult it is to identify the target.

[0109] For the i-th frame image, the target occlusion degree corresponding to the frame image is calculated based on the frame image and the reference image corresponding to the frame image in the following manner:

[0110] S231, respectively calculating the grayscale features, gradient features, and texture features of the target area of ​​the frame image and the target template in the reference image corresponding to the frame image;

[0111] S232, calculating a feature difference map of grayscale features, gradient features, and texture features of the target area and the target template to obtain a comprehensive difference map;

[0112] S233, calculating the weight of each pixel in the target area based on the Gaussian kernel model to obtain a Gaussian weight map of the target area;

[0113] S234, based on the comprehensive difference map and the Gaussian weight map, the target shielding degree corresponding to the i-th frame image is calculated using the following formula:

[0114]

[0115] Among them, G(k) represents the value of the k-th pixel in the Gaussian weight map, dis(k) represents the value of the k-th pixel in the integrated difference map, and NL represents the number of pixels in the integrated difference map.

[0116] During implementation, the grayscale features of the target area and the target template, that is, the grayscale images of the target area and the target template. The gradient feature can be calculated using the Sobel operator to obtain a gradient feature map, and the texture feature can be obtained using an LBP feature map.

[0117] During implementation, the feature difference map of the grayscale features of the target area and the target template is calculated as an example for explanation.

[0118] For each pixel in the grayscale feature map, the value corresponding to the pixel position in the feature difference map is calculated using the following formula:

[0119]

[0120] Among them, dis(x,y) represents the value at position (x,y) in the feature difference map, T(x,y) represents the value at position (x,y) in the grayscale feature map of the target template, P(x,y) represents the value at position (x,y) in the grayscale feature map of the target area, and ε represents a parameter.

[0121] In the same way, we get the feature difference map of gradient feature and the feature difference map of texture feature. The feature difference maps of the three features are weighted fused to get the comprehensive difference map.

[0122] Usually, the shape of the target is not a standard rectangular frame. Therefore, there are a large number of background pixels in the target area intercepted by the rectangular frame, especially outside the target area. To this end, a Gaussian kernel model is established to assign smaller weights to pixels farther from the center.

[0123] Specifically, the constructed Gaussian kernel model is expressed as:

[0124] G(x,y)=g(x,σ r )·g(y,σ c )

[0125]

[0126] Among them, (r0,c0) is the center position of the Gaussian kernel model, r p and c p Respectively represent the number of pixel rows and columns in the target area. r and σ c Represent the scale factors of the Gaussian kernel function in the vertical and horizontal directions respectively. G(x,y) represents the weight of the (x,y) position, thus obtaining a Gaussian weight map.

[0127] Based on the comprehensive difference map and Gaussian weight map, the target occlusion degree corresponding to the i-th frame image is calculated using the following formula:

[0128]

[0129] Among them, G(k) represents the value of the k-th pixel in the Gaussian weight map, dis(k) represents the value of the k-th pixel in the integrated difference map, and NL represents the number of pixels in the integrated difference map.

[0130] The above calculation formula normalizes the Gaussian weights. Since the value range of dis is [0,1], the value range of LDTI is [0,1]. When the image is not occluded, LDTI = 0. As the degree of occlusion increases, the value of LDTI also increases.

[0131] The basic complexity of the i-th frame image is obtained by weighted summing of the target similarity and target occlusion of the i-th frame image. In implementation, the weights may be the same, all 0.5.

[0132] The change of target information between frames is an important factor affecting the target tracking and recognition performance. Traditional indicators are too simple, usually taking the first frame as the comparison object to calculate the information change. The present invention proposes the target size change and target position change to measure the inter-frame information change of each frame image, that is, for the i-th frame image, the target size change and target position change compared with the previous frame image are calculated to measure the inter-frame information change of the i-th frame image.

[0133] Specifically, for each frame image in the sequence of images to be evaluated, the inter-frame information variation degree of the frame image is calculated based on the frame image and the previous frame image of the frame image, including:

[0134] Determine the target area in the frame image and the frame image before the frame image respectively;

[0135] Based on the formula Calculate the target size change of the frame image;

[0136] Among them, (w i-1 ,h i-1 ) represents the width and height of the target area in the i-1th frame image, (w i ,h i ) represents the width and height of the target area in the i-th frame image, and k1 represents the normalization factor.

[0137] In implementation, the normalization factor k1 is determined by the maximum change in the target size in the image sequence. The target size change in adjacent frames generally does not exceed the target size. Therefore, in implementation, k1 is set to 2. The target size change of the first frame of the sequence image to be evaluated is 0.

[0138] When the width and height of the target do not change, CDOS i = 0; when the target size change is the same as the size of the previous frame target, CDOS i = 1. For some CDOS i If it is greater than 1, it is set to 1, so the final target size change is: CDOS i =min{1,CDOS i}.

[0139] The target position change is a description of the target motion information between frames, including the target motion amplitude and direction change. Therefore, when constructing the target position change index, the target size should be taken into account.

[0140] Based on the above ideas, based on the formula The target position change degree of the frame image is calculated.

[0141] in, △p i (x)=(x i -x i-1 ) represents the displacement of the target in the x direction from the i-1th frame to the i-th frame, △p i (y)=(y i -y i-1 ) represents the displacement of the target in the y direction from the i-1th frame to the i-th frame, △p i-1 (x)=(x i-1 -x i-2 ) represents the displacement of the target in the x direction from the i-2th frame to the i-1th frame, △p i-1 (y)=(y i-1 -y i-2 ) represents the displacement of the target in the y direction from the i-2th frame to the i-1th frame, x i Indicates the x-axis coordinate of the center position of the target area in the i-th frame image, y i Indicates the y-axis coordinate of the center position of the target area in the i-th frame image, x i-1 Indicates the x-axis coordinate of the center position of the target area in the i-1th frame image, y i-1 Indicates the y-axis coordinate of the center position of the target area in the i-1th frame image, x i-2 Indicates the x-axis coordinate of the center position of the target area in the i-2th frame image, y i-2 Indicates the y-axis coordinate of the center position of the target area in the i-2th frame image.

[0142] The normalization factor k2 is set to 2, which means that when the target displacement change is equal to the target size, the target size change reaches the maximum value of 1, and if it is greater than 1, it is also set to 1. Therefore, the final target size change is: CDOP i =min{1,CDOP i When the target is stationary or moving at a constant speed, the target position change degree CDOP i =0.

[0143] The target position change degree of the first frame of the sequence image to be evaluated and the second needle image is 0.

[0144] The inter-frame information variation of the i-th frame image is obtained by combining the target size variation and the target position variation. Inter-frame information change index CDI i The value range is [0,1]. When the target has not changed in size and displacement relative to the previous frame, CDIi The minimum value is 0. As the size change and displacement amplitude increase, CDI i It is also constantly getting bigger.

[0145] After obtaining the basic complexity of each frame and the degree of information variation between frames, the complexity of each frame is obtained using the following formula:

[0146]

[0147] Among them, TRC i and CDI i They represent the basic complexity of the i-th frame image and the degree of information change between frames, and ξ represents the weight.

[0148] Considering that the geometric mean is less affected by extreme values, the complexity of each frame image is determined based on the concept of geometric mean.

[0149] When implemented, the TRC indicator should be assigned more weight, i.e., ξ>0.5.

[0150] After obtaining the complexity of each frame of the image, the complexity of each frame of the image is weighted and summed to obtain the complexity of the sequence of images to be evaluated. Since a single frame of image with high complexity has a greater impact on the complexity of the sequence of images to be evaluated, the weight of the image with high complexity is increased. Specifically, the weight of each frame of the image is calculated in the following way:

[0151]

[0152] Among them, F i Represents the complexity of the i-th frame image in the sequence image to be evaluated, ω i Represents the weight of the i-th frame image.

[0153] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0154] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.

Claims

1. A simulation scene complexity evaluation method, characterized in that: The following steps are involved: Obtaining a sequence image to be evaluated and a corresponding reference sequence image of a simulation scene; For each frame image in the sequence of images to be evaluated, the target similarity and target shielding degree corresponding to the frame image are calculated based on the frame image and the reference image corresponding to the frame image; the basic complexity of the frame image is obtained based on the target similarity and the target shielding degree; Calculating the inter-frame information variation degree of the frame image based on the frame image and the frame image before the frame image; The complexity of each frame of the image is obtained based on the basic complexity of each frame of the image in the sequence of images to be evaluated and the information variation between frames; The complexity of each frame of the image is weighted summed to obtain the complexity of the sequence of images to be evaluated.

2. The simulation scenario complexity evaluation method according to claim 1, characterized in that: Calculating the inter-frame information variation degree of the frame image based on the frame image and a frame image before the frame image includes: Determine the target area of ​​the target in the frame image and the frame image before the frame image respectively; Based on the formula Calculate the target size change of the frame image; Based on the formula Calculate the target position change degree of the frame image; The inter-frame information variation of the frame image is obtained based on the target size variation and target position variation. Among them, (w i-1 ,h i-1 ) represents the width and height of the target area in the i-1th frame image, (w i ,h i ) represents the width and height of the target area in the i-th frame image, k1 and k2 represent the normalization factors, △p i (x) represents the displacement of the target in the x direction from the i-1th frame to the i-th frame, △p i (y) represents the displacement of the target in the y direction from the i-1th frame to the i-th frame, △p i-1 (x) represents the displacement of the target in the x direction from the i-2th frame to the i-1th frame, △p i-1 (y) represents the displacement of the target in the y direction from the i-2th frame to the i-1th frame.

3. The simulation scenario complexity evaluation method according to claim 1, characterized in that: Calculating the target similarity corresponding to the frame image based on the frame image and a reference image corresponding to the frame image includes: If the target distance corresponding to the frame image exceeds a first threshold, a global background similarity corresponding to the frame image is calculated based on the frame image and a reference image corresponding to the frame image as a target similarity corresponding to the frame image; Otherwise, the local background similarity corresponding to the frame image is calculated as the target similarity corresponding to the frame image.

4. The simulation scenario complexity evaluation method according to claim 3, characterized in that: The global background similarity corresponding to the frame image is calculated based on the frame image and the reference image corresponding to the frame image in the following manner: Searching for an affected area in the frame image based on a target template in a reference image corresponding to the frame image; Calculate the features of the target template and each affected area separately; Calculate the similarity between the target template and each impact region based on the calculated features; The weighted sum of the similarities between the target template and each affected area is used to obtain the global background similarity of the frame image.

5. The simulation scenario complexity evaluation method according to claim 4, characterized in that: Searching for an affected area in the frame image based on a target template in a reference image corresponding to the frame image includes: The frame image is scanned with the target template size as the sliding window size to extract the candidate affected area; Calculate the mutual correlation coefficient between the candidate influence region and the target template; If the mutual correlation coefficient is greater than the second threshold, the candidate influence region is the influence region.

6. The simulation scenario complexity evaluation method according to claim 4, characterized in that: The similarity between the target template and each affected area is weighted and summed to obtain the global background similarity of the frame image, including: Calculate the distance between the target template and each influence area According to the formula Calculate the weight of the jth influence area According to the formula Calculate the global background similarity CDGB of the i-th frame image i ; Among them, δ xj =|x T -x Bj |,δ yj =|y T -y Bj |,(x T ,y T ) represents the center coordinate of the target template, (x Bj ,y Bj ) represents the center coordinates of the affected area, represents the width and height of the target template corresponding to the i-th frame image, θ represents the rate of change coefficient, CoS j represents the similarity between the target template and the jth impact area, N ia Indicates the number of affected areas.

7. The simulation scenario complexity evaluation method according to claim 3, characterized in that: The local background similarity corresponding to the frame image is calculated in the following way: Extract the target and its local background from the frame image, and calculate multiple feature maps of the target and its local background; The saliency map of each feature map is calculated based on the image visual saliency algorithm, and the comprehensive saliency map of the target and its local background is obtained based on the saliency map of each feature map; Extract the comprehensive saliency map of the target area from the comprehensive saliency map of the target and its local background according to Get the local background similarity corresponding to the frame image, where It represents the mean saliency of the comprehensive saliency map of the target area, and IDLB represents the similarity of the local background corresponding to the frame image.

8. The simulation scenario complexity evaluation method according to claim 3, characterized in that: Based on the frame image and the reference image corresponding to the frame image, the target occlusion degree corresponding to the frame image is calculated in the following manner: Respectively calculating the grayscale features, gradient features and texture features of the target area of ​​the frame image and the target template in the reference image corresponding to the frame image; Calculate the feature difference map of the grayscale feature, gradient feature and texture feature of the target area and the target template to obtain a comprehensive difference map; The weight of each pixel in the target area is calculated based on the Gaussian kernel model to obtain a Gaussian weight map of the target area; Based on the comprehensive difference map and Gaussian weight map, the target occlusion degree corresponding to the i-th frame image is calculated using the following formula: Among them, G(k) represents the value of the k-th pixel in the Gaussian weight map, dis(k) represents the value of the k-th pixel in the integrated difference map, and NL represents the number of pixels in the integrated difference map.

9. The simulation scenario complexity evaluation method according to claim 8, characterized in that: The constructed Gaussian kernel model is expressed as: G(x,y)=g(x,σ r )·g(y,σ c ) Among them, (r0,c0) is the center position of the Gaussian kernel model, r p and c p Respectively represent the number of pixel rows and columns in the target area, σ r and σ c They represent the scale factors of the Gaussian kernel function in the vertical and horizontal directions respectively, and G(x,y) represents the weight of the (x,y) position.

10. The simulation scenario complexity evaluation method according to claim 1, characterized in that: Based on the basic complexity of each frame and the information variation between frames, the complexity of each frame is obtained using the following formula: Among them, TRC i and CDI i They represent the basic complexity of the i-th frame image and the degree of information change between frames, and ξ represents the weight.

Images