Improved deep learning target detection Mosaic sample enhancement method

Abstract

The invention discloses an improved deep learning target detection Mosaic sample enhancement method. The method comprises the following steps: establishing a sample index file set IS for an original target detection sample set S; performing Mosaic enhancement operation on the original target detection sample set S to generate an enhanced sample set Smosaic, and performing synchronous association on the sample index file set IS to generate an index file set Imosaic of Mosaic; the enhanced sample set Smosaic is improved based on the aspect ratio constraint rule and the area constraint rule, and modified sample picture data information in the enhanced sample set Smosaic is edited; and integrating the improved sample marking information and the sample image data, and constructing a final optimized Mosaic sample set SFmosaic. The method has the advantages that for a target detection sample set subjected to Mosaic enhancement processing, on the basis that Mosaic basic enhancement sample features are reserved, introduction of wrong marks after Mosaic enhancement can be eliminated, mark information integrity and correctness of each object after enhancement are effectively saved, and a more reliable Mosaic enhancement sample set is provided for subsequent model training.

Description

Technical Field

[0001] The present invention relates to the technical field of deep learning target detection of remote sensing data, and in particular to an improved deep learning target detection Mosaic sample enhancement method. Background Art

[0002] With the continuous development of machine vision technology, object detection based on deep learning has been widely used in many fields such as security monitoring, autonomous driving, remote sensing monitoring and medical image analysis. Sample enhancement technology can provide a large amount of data input for it, which can further improve the detection accuracy and generalization ability of the model under the limitation of a limited sample set.

[0003] The core of sample enhancement technology is a series of transformations on the original sample set data, which gradually develops from the radiation and geometric transformation of a single sample to a multi-sample set. Mosaic data enhancement is an emerging enhancement technology based on multi-sample combination. It was first proposed in the YOLOv4 paper. By randomly combining 3, 4 or 9 sample images to generate new training samples, it not only expands the number of new sample sets, but also ensures that each new training sample contains different information from multiple images, thereby greatly increasing the diversity of data and helping to improve the generalization ability of the model. It has now become an essential algorithm for the training enhancement process in the single-stage target detection algorithm.

[0004] Model training with Mosaic data enhancement has great advantages: first, after Mosaic data enhancement, the batch size during training is theoretically increased, and more global sample features can be learned, so the generalization ability and accuracy of the model will be greatly improved; second, the feature expression of small targets in the sample is enhanced, and the model's detection ability for small targets is improved. However, the traditional Mosaic data enhancement method also has some shortcomings. For example, during the splicing process, due to the random scaling and cropping of the image, the coordinates of the target box may change significantly, thereby increasing the difficulty of target detection, which is obvious in remote sensing image target samples. In addition, the traditional Mosaic data enhancement method may not be flexible enough when dealing with boundary conditions, which may easily lead to edge effects at the image splicing, and even destroy the original complete target marker box, further leading to the addition of erroneous samples, causing the problem of sample set contamination.

[0005] Therefore, in order to further improve the effect of Mosaic data enhancement, an improved deep learning target detection Mosaic sample enhancement method is proposed. This method is optimized and improved on the basis of traditional Mosaic data enhancement, aiming to solve the above problems and improve the performance and accuracy of the target detection model, especially in the target detection application scenarios with non-unique target scales and complex backgrounds in remote sensing images. Summary of the invention

[0006] The purpose of the present invention is to provide an improved deep learning target detection Mosaic sample enhancement method to solve the above-mentioned problems existing in the prior art.

[0007] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0008] An improved deep learning target detection Mosaic sample enhancement method includes the following steps:

[0009] S1, Mosaic enhancement:

[0010] Create a sample index file set I for the original target detection sample set S S ; Perform Mosaic enhancement operation on the original target detection sample set S to generate enhanced sample set S mosaic , and the sample index file set I S Synchronize and associate to generate Mosaic index file set I mosaic ;

[0011] S2, Mosaic enhancement and optimization:

[0012] Improved enhanced sample set S based on aspect ratio constraint rule and area constraint rule mosaic , and edit the enhanced sample set S mosaic The modified sample image data information;

[0013] S3. Final optimization of Mosaic sample set acquisition:

[0014] Integrate the improved sample labeling information and sample image data to construct the final optimized Mosaic sample set SF mosaic .

[0015] Preferably, sample index file set I S The area of ​​each labeled object sample in the original target detection sample set S is stored in ref and aspect ratio R ref and the image width W ref and high H ref , their calculation units are all pixels;

[0016] Area ref =W ref ×H ref

[0017] R ref =min(W ref ,H ref ) / max(W ref ,H ref )

[0018] Among them, R ref ∈(0,1];min(W ref ,H ref ) and max(W ref ,H ref ) mark the minimum and maximum sides of the rectangle for the target object, respectively.

[0019] Preferably, the enhanced sample set S mosaic Including 1*3 mosaic, 2*2 mosaic and 3*3 mosaic, which respectively mean that 3 samples, 4 samples and 9 samples are mosaicked and merged into 1 sample. At the same time, the background parts of the unfilled image samples are filled with default values.

[0020] Preferably, the enhanced sample index file set I mosaic The width, height and area information of the image are recorded in the new mosaic sample set S mosaic The information of the image in is recorded as W m , H m and Area m .

[0021] Preferably, in step S2, the enhanced sample set S is improved based on the aspect ratio constraint rule and the area constraint rule. mosaic include,

[0022] S21, Combined I mosaic And the newly generated enhanced sample set S mosaic , use the aspect ratio constraint rule to traverse one by one, and delete the sample labels NR after Mosaic enhancement that do not meet the labeling requirements rect , and record its spatial position information NR p ;

[0023] S22, Combined I mosaic And the newly generated enhanced sample set S mosaic , use the area constraint rule to traverse one by one, delete the sample marks NA after Mosaic enhancement that do not meet the marking requirements rect , and record its spatial position information NA p .

[0024] Preferably, the aspect ratio constraint rule is:

[0025]

[0026] Among them, R m For S mosaic The aspect ratio of the target mark in the image. If it is 1, the information is retained. If it is 0, it is automatically deleted. mr = 0 when the position information NRp (x LTR ,y LTR ,x RBR ,y RBR ), x LTR ,y LTR ,x RBR ,y RBR are respectively the upper left corner coordinates and the lower right corner coordinates of the rectangular mark information of the target object in the new mosaic sample image deleted by the aspect ratio constraint rule; ratio The effective pass rate for marking the aspect ratio of mosaic sample target objects.

[0027] Preferably, the area constraint rule is:

[0028]

[0029] Where r = min(W m / W ref ,H m / H ref ), L ma If it is 1, it means S mosaic The target mark information in is retained, and it is automatically deleted when it is 0. At the same time, L ma = 0 when the position information is NA p (x LTA ,y LTA ,x RBA ,y RBA ), x LTA ,y LTA ,x RBA ,y RBA are the upper left corner coordinates and lower right corner coordinates of the rectangular mark information of the target object in the new mosaic sample image deleted by the area rule; σ area It is the effective passing rate of marking area of ​​mosaic sample target object.

[0030] Preferably, the enhanced sample set S is edited mosaic The modified sample image data information is as follows:

[0031] NA p and NR p The image pixel part is filled with 0 value to remove the interference of pseudo-labeled image information in the Mosaic enhancement sample set.

[0032] Preferably, the enhanced sample set S mosaic The image pixel value follows the following expression,

[0033]

[0034] Among them, P mis the pixel value of the sample image after Mosaic; P image The original sample set pixel value; p is the specific position of the pixel after mosaic enhancement, which is expressed as (x, y) is the point coordinate; V P is the pixel value data at position p.

[0035] Preferably, in step S3, the integrated and improved label information output format is txt or json format, the mosaic enhanced sample image data is in jpg format, and is redistributed in a ratio of 8:2 according to train and val to form a complete and available Mosaic target detection enhanced sample set SF mosaic .

[0036] The beneficial effects of the present invention are: 1. The method of the present invention effectively solves the problem of introducing erroneous object labels into the target detection sample set through Mosaic enhancement and expansion. By establishing an index of the original sample set and the enhanced sample set, the relevant attribute information of the marked objects in the mosaic sample set can be quickly queried and merged, and the labeled samples are filtered according to the area and aspect ratio constraint rules, and the image samples are synchronously repaired. It can achieve and ensure the information integrity and reliability of all marked targets in the target detection sample after Mosaic enhancement, reduce the possibility of contaminating the original sample, and is a technical innovation in sample enhancement and enhanced expansion in the field of deep learning target detection technology. 2. The method of the present invention provides a certain reference model for the solution strategy of sample contamination caused by other sample enhancement technologies for target detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a flowchart of an improved deep learning target detection Mosaic sample enhancement method in an embodiment of the present invention;

[0038] Figure 2 1 is a schematic diagram of the result after conventional Mosaic enhancement in an embodiment of the present invention, A is the original sample set, B, C, and D are 1*3 mosaic, 2*2 mosaic, and 3*3 mosaic results respectively; wherein ① is the problem of introducing wrong labels, and ② is the problem of inconsistency between the mosaic result background filling and the remote sensing image background;

[0039] Figure 3 is a schematic diagram of introducing wrong label annotation and improved processing in a mosaic sample in an embodiment of the present invention;

[0040] Figure 4 Schematic diagram of mosaic image sample improvement and invalid background consistency in an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation methods described herein are only used to explain the present invention and are not used to limit the present invention.

[0042] Embodiment 1

[0043] like Figure 1 As shown, in order to overcome the sample contamination problem caused by the Mosaic-based sample enhancement algorithm, an improved deep learning target detection Mosaic sample enhancement method is provided in this embodiment. The deep learning target detection training sample Mosaic enhancement algorithm first establishes a sample index for the original training sample set, and stores the geographic attribute information (including area and aspect ratio, etc.) of each marked object; secondly, when performing Mosaic enhancement, the enhanced sample set is subjected to geographic spatial statistics to obtain the relevant attribute information of the marked object in the Mosaic sample set; again, the results of the first two times are combined to make a judgment, and the sample is filtered and cleaned with a certain attribute threshold, and the image sample part of the unqualified marked object is masked, and finally a Mosaic enhanced sample set with a complete marked object after combined enhancement is obtained. The method of the present invention analyzes the incomplete target sample labeling information caused by splicing and segmentation in the conventional Mosaic algorithm, and successively formulates sample attribute index, aspect ratio and area constraint rules, improves the problem of introducing erroneous samples after Mosaic enhancement, and improves the stability and availability of the conventional Mosaic enhancement algorithm, especially for the small target detection sample enhancement in the remote sensing large scene, and has better effect.

[0044] The method of the present invention specifically includes the following parts:

[0045] 1. Mosaic Enhancement

[0046] Create a sample index file set I for the original target detection sample set S S ; Perform Mosaic enhancement operation on the original target detection sample set S to generate enhanced sample set S mosaic , and the sample index file set I S Synchronize and associate to generate Mosaic index file set I mosaic .

[0047] In this embodiment, the sample index file set I S The area of ​​each labeled object sample in the original target detection sample set S is stored in ref and aspect ratio R ref and the image width W ref and high H ref , their calculation units are all pixels; and the aspect ratio R refInstead of simply using the w÷h (w, h are the width and height of the marking rectangle of each target object), it is the ratio of the smallest side / largest side of the marking rectangle, so R ref ∈(0,1].

[0048] Area ref =W ref ×H ref

[0049] R ref =min(W ref ,H ref ) / max(W ref ,H ref )

[0050] Among them, min(W ref ,H ref ) and max(W ref ,H ref ) mark the minimum and maximum sides of the rectangle for the target object, respectively.

[0051] In this embodiment, the enhanced sample set S mosaic Including 1*3 mosaic, 2*2 mosaic and 3*3 mosaic, which respectively mean that 3 samples, 4 samples and 9 samples are mosaicked and merged into 1 sample. At the same time, the background parts of the unfilled image samples are filled with default values.

[0052] In this embodiment, the enhanced sample index file set I mosaic The image width, height and area are recorded in the new mosaic sample set S mosaic The information of the image in is recorded as W m , H m and Area m . Index File Set I mosaic , in addition to being able to index S mosaic In addition to the original attribute information of each marked object, S is added synchronously based on geographic statistics. mosaic Attribute information of each tag object in .

[0053] 2. Mosaic Enhancement and Optimization

[0054] Improvement of enhanced sample set S based on constraint rules mosaic , and edit the enhanced sample set S mosaic The modified sample image data information in . The constraint rules include aspect ratio constraint and area constraint.

[0055] (1) The aspect ratio constraint is: Combined with I mosaic And the newly generated enhanced sample set S mosaic, use the aspect ratio constraint rule to traverse one by one, and delete the sample labels NR after Mosaic enhancement that do not meet the labeling requirements rect , and record its spatial position information NR p The relevant formula is,

[0056]

[0057] Among them, R m For S mosaic The aspect ratio of the target mark in the image. If it is 1, the information is retained. If it is 0, it is automatically deleted. mr = 0 when the position information NR p (x LTR ,y LTR ,x RBR ,y RBR ), x LTR ,y LTR ,x RBR ,y RBR are respectively the upper left corner coordinates and the lower right corner coordinates of the rectangular mark information of the target object in the new mosaic sample image deleted by the aspect ratio constraint rule; ratio The effective pass rate for marking the aspect ratio of mosaic sample target objects is usually set to 0.22.

[0058] (2) Area constraint: Combined with I mosaic And the newly generated enhanced sample set S mosaic , use the area constraint rule to traverse one by one, delete the sample marks NA after Mosaic enhancement that do not meet the marking requirements rect , and record its spatial position information NA p The relevant formula is,

[0059]

[0060] Where r = min(W m / W ref ,H m / H ref ), L ma If it is 1, it means S mosaic The target mark information in is retained, and it is automatically deleted when it is 0. At the same time, L ma = 0 when the position information is NA p (x LTA ,y LTA ,x RBA ,y RBA ), x LTA ,y LTA ,x RBA ,y RBAare respectively the upper left corner coordinates and the lower right corner coordinates of the target object rectangular mark information in the new mosaic sample image deleted by the area rule; σ area The effective passing rate of marking area for mosaic sample target objects is usually set to 0.75.

[0061] In this embodiment, the enhanced sample set S is edited. mosaic The modified sample image data information is as follows:

[0062] NA p and NR p The pixel part of the image is filled with 0 values ​​to remove the interference of the pseudo-labeled image information in the Mosaic enhanced sample set. The pixel value of the sample image after Mosaic enhancement follows the following expression:

[0063]

[0064] Among them, P m is the pixel value of the sample image after Mosaic, P image The original sample set pixel value, p is the specific position of the pixel after mosaic enhancement, which is expressed as (x, y) is the point coordinate, V P is the pixel value data at position p.

[0065] 3. Final optimization of Mosaic sample set acquisition

[0066] Integrate the improved sample labeling information and sample image data to construct the final optimized Mosaic sample set SF mosaic .

[0067] In this embodiment, the integrated and improved label information output format is usually in txt or json format, the mosaic enhanced sample image data is usually in jpg format, and is redistributed in a ratio of 8:2 according to train and val to form a complete and available Mosaic target detection enhanced sample set SF mosaic .

[0068] Embodiment 2

[0069] In this embodiment, remote sensing wind turbine target detection is taken as an example to specifically illustrate the execution process of the method of the present invention.

[0070] 1. Mosaic Enhancement

[0071] The original sample set S selects true color images in jpg format with a size of 1024*1024px as image samples. The target marking information of wind turbines is in txt format, where each line of the text records the rectangular marking information of a wind turbine target, represented by the center point (cx, cy) and width and height (w, h). The data is expressed as (cx, cy, w, h). For each sample image and label, an index file set I is established. S , the specific file format is text txt, the first line records the W of the image sample ref =1024,H ref =1024, each subsequent line records a wind turbine target and calculates its area Area ref and aspect ratio R ref .

[0072] For the original sample set S, 1*3, 2*2 and 3*3 mosaic enhancements are performed respectively to obtain the enhanced sample set S mosaic ,like Figure 2 As shown in the figure, it can be seen that different Mosaic enhancement methods may introduce different degrees of error samples, and the index file I after mosaic enhancement is updated synchronously mosaic , update the area, aspect ratio and other information of all targets in the mosaic sample set.

[0073] in, Figure 2 A is the original sample set, B is the sample enhanced by 1*3 mosaic, C is the sample enhanced by 2*2 mosaic, and D is the sample enhanced by 3*3 mosaic. It can be seen that the conventional Mosaic algorithm will introduce erroneous samples as indicated by the arrows, which will cause pollution: ① The original sample set is divided by the mosaic operation, resulting in incomplete target annotation information; ② After the mosaic process, the 114 pixel value used to fill the invalid value conflicts with the 0 invalid value of the remote sensing image background.

[0074] Utilize I mosaic You can quickly query the corresponding original sample in each mosaic sample, such as Figure 3 As shown in the figure, taking 2*2 mosaic enhancement as an example, it can be seen that the original sample 1 is at the lower left corner of the mosaic enhancement sample, and the original sample 2 is at the upper left corner of the mosaic enhancement sample. By counting the relative positions of the wind turbine target and the image sample, after traversal, it is found that there are 2 wrong samples in the original sample 1 after mosaicking; there is 1 wrong sample in the original sample 2 after mosaicking.

[0075] 2. Mosaic Enhancement and Optimization

[0076] After statistical analysis, the target NR in the original sample 1 rect_1The aspect ratio of is 0.951, and the size after mosaicking is 0.143. According to the aspect ratio constraint rule, due to the σ less than 0.22 ratio , so delete it directly and record its four corner positions NR p_rect1 (x LTA ,y LTA ,x RBA ,y RBA )=(0,603,6,637); target NR in original sample 1 rect_2 The aspect ratio of the mosaic is 0.4, which is temporarily retained. Similarly, the target NR in the original 2 rect_1 After inlaying, it is 0.458, so it is also temporarily retained.

[0077] The area constraint rule is used to process the target labels of the mosaic label samples that fail to meet the requirements. Figure 3 As shown, the target NA in the original sample 1 rect_1 has been deleted, so for NA rect_2 The area is 4725px 2 , the area after mosaic is 490px 2 According to the area constraint rule, we can know that r = min (387 / 1024, 548 / 1024) = 0.378, NA m_rect_2 = r × NA rect_2 ×0.75=1339, so L ma_rect2 =0, then NA rect_2 Also introduced as an error, and removed, with its NA recorded in the mosaic p_rect2 (x LTA ,y LTA ,x RBA ,y RBA )=(0,847,13,883), similarly for the target NA in the original sample 2 2_rect_1 , after calculation, we get L ma2_rect1 = 0, which is also introduced as an erroneous sample and needs to be deleted, and its NA in the mosaic is recorded. p2_rect1 (x LTA ,y LTA ,x RBA ,y RBA )=(0,97,11,118). After the above processing, the effect comparison between the conventional Mosaic and the improved Mosaic is shown in Table 1.

[0078] Table 1 Target statistics before and after Mosaic enhancement improvement algorithm

[0079] Serial number algorithm Enhancement Target Marking Statistics Valid target markers Effective proportion 1 Regular Mosaic 2*2 22 19 86.4％ 2 Mosaic of the present invention 2*2 19 19 100％

[0080] According to the coordinates of the target box that does not meet the aspect ratio and area constraint rules obtained by the above process, the image sample pixels within its coordinate range are filled with 0 values ​​(such as Figure 4 At the same time, the values ​​of 114 in the three RGB bands are replaced with 0, so that the invalid pixel values ​​in the sample set image are consistent with the invalid background values ​​of the remote sensing image, as shown in Figure 4 As shown by the arrow in (2), the interference and unstable factors in the sample are further reduced.

[0081] 3. Final optimization of Mosaic sample set acquisition

[0082] After the above steps, based on the conventional Mosaic sample enhancement technology, the aspect ratio and area constraint rules are used to reduce the number of erroneous samples introduced by Mosaic, and the image samples of Mosaic are modified synchronously. Through 0-value masking and filling, the enhanced samples after Mosaic are finally obtained. On the basis of the original sample size of 10044, 2511 2*2 mosaic samples and 1116 3*3 mosaic samples are added to form SF mosaic The sample set, a total of 13671, is divided into 10937 training sample sets and 2734 validation sample sets with an 8:2 ratio.

[0083] By adopting the above technical solution disclosed in the present invention, the following beneficial effects are obtained:

[0084] The present invention provides an improved deep learning target detection Mosaic sample enhancement method, which effectively solves the problem of introducing erroneous object labels in the target detection sample set through Mosaic enhancement and expansion. By establishing an index of the original sample set and the enhanced sample set, the relevant attribute information of the labeled objects in the mosaic sample set can be quickly queried and merged, and the labeled samples can be filtered and labeled according to the area and aspect ratio constraint rules, and the image samples can be synchronously repaired. The information integrity and reliability of all labeled targets in the target detection sample after Mosaic enhancement can be achieved and guaranteed, and the possibility of contaminating the original sample can be reduced. It is a technical innovation in sample enhancement and enhanced expansion in the field of deep learning target detection technology. The present invention method provides a certain reference model for the solution strategy of sample contamination caused by other sample enhancement technologies for target detection.

[0085] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be considered as the scope of protection of the present invention.

Claims

1. An improved deep learning target detection Mosaic sample enhancement method, characterized by: The following steps are included: S1, Mosaic enhancement: Create a sample index file set I for the original target detection sample set S S ; Perform Mosaic enhancement operation on the original target detection sample set S to generate enhanced sample set S mosaic , and the sample index file set I S Synchronize and associate to generate Mosaic index file set I mosaic ; S2, Mosaic enhancement and optimization: Improved enhanced sample set S based on aspect ratio constraint rule and area constraint rule mosaic , and edit the enhanced sample set S mosaic The modified sample image data information; S3. Final optimization of Mosaic sample set acquisition: Integrate the improved sample labeling information and sample image data to construct the final optimized Mosaic sample set SF mosaic .

2. The improved deep learning target detection Mosaic sample enhancement method according to claim 1, characterized in that: Sample Index File Set I S The area of ​​each labeled object sample in the original target detection sample set S is stored in ref and aspect ratio R ref and the image width W ref and high H ref , their calculation units are all pixels; Area ref =W ref ×H ref R ref =min(W ref ,H ref ) / max(W ref ,H ref ) Among them, R ref ∈(0,1];min(W ref ,H ref ) and max(W ref ,H ref ) mark the minimum and maximum sides of the rectangle for the target object, respectively.

3. The improved deep learning target detection Mosaic sample enhancement method according to claim 1, characterized in that: Enhanced sample set S mosaic Including 1*3 mosaic, 2*2 mosaic and 3*3 mosaic, which respectively mean that 3 samples, 4 samples and 9 samples are mosaicked and merged into 1 sample. At the same time, the background parts of the unfilled image samples are filled with default values.

4. The improved deep learning target detection Mosaic sample enhancement method according to claim 1, characterized in that: Enhanced sample index file set I mosaic The width, height and area information of the image are recorded in the new mosaic sample set S mosaic The information of the image in is recorded as W m , H m and Area m .

5. The improved deep learning target detection Mosaic sample enhancement method according to claim 1, characterized in that: In step S2, the enhanced sample set S is improved based on the aspect ratio constraint rule and the area constraint rule. mosaic include, S21, Combined I mosaic And the newly generated enhanced sample set S mosaic , use the aspect ratio constraint rule to traverse one by one, and delete the sample labels NR after Mosaic enhancement that do not meet the labeling requirements rect , and record its spatial position information NR p ; S22, Combined I mosaic And the newly generated enhanced sample set S mosaic , use the area constraint rule to traverse one by one, and delete the samples marked NA after Mosaic enhancement that do not meet the marking requirements rect , and record its spatial position information NA p .

6. The improved deep learning target detection Mosaic sample enhancement method according to claim 5, characterized in that: The aspect ratio constraint rule is: Among them, R m For S mosaic The aspect ratio of the target mark in the image. If it is 1, the information is retained. If it is 0, it is automatically deleted. mr = 0 when the position information NR p (x LTR ,y LTR ,x RBR ,y RBR ), x LTR ,y LTR ,x RBR ,y RBR are respectively the upper left corner coordinates and the lower right corner coordinates of the rectangular mark information of the target object in the new mosaic sample image deleted by the aspect ratio constraint rule; ratio The effective pass rate for marking the aspect ratio of mosaic sample target objects.

7. The improved deep learning target detection Mosaic sample enhancement method according to claim 6, characterized in that: The area constraint rule is: Where r = min(W m / W ref ,H m / H ref ), L ma If it is 1, it means S mosaic The target mark information in is retained, and it is automatically deleted when it is 0. At the same time, L ma = 0 when the position information is NA p (x LTA ,y LTA ,x RBA ,y RBA ), x LTA ,y LTA ,x RBA ,y RBA are the upper left corner coordinates and lower right corner coordinates of the rectangular mark information of the target object in the new mosaic sample image deleted by the area rule; σ area It is the effective passing rate of marking area of ​​mosaic sample target object.

8. The improved deep learning target detection Mosaic sample enhancement method according to claim 7, characterized in that: Edit Enhanced Sample Set S mosaic The modified sample image data information is as follows: NA p and NR p The image pixel part is filled with 0 value to remove the interference of pseudo-labeled image information in the Mosaic enhancement sample set.

9. The improved deep learning target detection Mosaic sample enhancement method according to claim 8, characterized in that: Enhanced sample set S mosaic The image pixel value follows the following expression, Among them, P m is the pixel value of the sample image after Mosaic; P image The original sample set pixel value; p is the specific position of the pixel after mosaic enhancement, which is expressed as (x, y) is the point coordinate; V P is the pixel value data at position p.

10. The improved deep learning target detection Mosaic sample enhancement method according to claim 1, characterized in that: In step S3, the integrated and improved label information output format is txt or json format, the mosaic enhanced sample image data is in jpg format, and is redistributed in a ratio of 8:2 according to train and val to form a complete and available Mosaic target detection enhanced sample set SF mosaic .

Images