CN115375558A - Method for removing image shadow of unmanned aerial vehicle - Google Patents
Method for removing image shadow of unmanned aerial vehicle Download PDFInfo
- Publication number
- CN115375558A CN115375558A CN202111622343.8A CN202111622343A CN115375558A CN 115375558 A CN115375558 A CN 115375558A CN 202111622343 A CN202111622343 A CN 202111622343A CN 115375558 A CN115375558 A CN 115375558A
- Authority
- CN
- China
- Prior art keywords
- image
- color
- unmanned aerial
- aerial vehicle
- enhancement
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000012937 correction Methods 0.000 claims abstract description 19
- 230000009466 transformation Effects 0.000 claims abstract description 10
- 230000002708 enhancing effect Effects 0.000 claims abstract description 8
- 230000001131 transforming effect Effects 0.000 claims abstract description 4
- 238000012545 processing Methods 0.000 abstract description 11
- 230000000694 effects Effects 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000000605 extraction Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 241000592183 Eidolon Species 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
- G06T5/94—Dynamic range modification of images or parts thereof based on local image properties, e.g. for local contrast enhancement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a method for removing an unmanned aerial vehicle image shadow. The method for removing the shadow of the unmanned aerial vehicle image comprises the following steps: acquiring an image, and acquiring an original image by adopting an unmanned aerial vehicle to acquire an overhead image; enhancing the image, namely enhancing the original image by utilizing an enhancement algorithm to form an enhanced image; color transformation, namely transforming the color space of the enhanced image to form a transformed image; color correction, which is to use the processing function to carry out color correction on the transformed image to form a corrected image; and (5) image inversion, namely performing color inverse transformation on the corrected image to form a final image. The method can enhance the effect of the image and remove the information loss caused by the shadow.
Description
Technical Field
The invention belongs to the technical field of image processing, and particularly relates to a method for removing an unmanned aerial vehicle image shadow.
Background
At present, unmanned aerial vehicles are more and more widely applied, and especially, the unmanned aerial vehicles are highly valued in the aspects of meteorology, agriculture, geological exploration, forest protection and the like. Carry out data acquisition at the high altitude through unmanned aerial vehicle, acquire relevant influence data, can provide more directly perceived and abundant reference data for the operation personnel, be favorable to the operation personnel to carry out subsequent work.
For the image data acquired by the unmanned aerial vehicle, shadows basically exist due to the influence of terrain factors, and image pixels in shadow areas in the original images are seriously compressed, so that information is deficient. This brings many disadvantages for the subsequent processing of the image and the extraction of effective image data, which further affects the smooth development of the subsequent work.
Therefore, designing a method for removing the shadow of the image of the unmanned aerial vehicle can enhance the effect of the image and remove the information loss caused by the shadow, which is a problem to be solved urgently at present.
Disclosure of Invention
Based on the above, the invention provides a method for removing the shadow of the unmanned aerial vehicle image, which overcomes the defects of the prior art, and the method carries out combined image processing by adopting an algorithm, and carries out brightness adjustment under the condition of changing a color space aiming at the uneven brightness generated by enhancement after the enhancement is carried out by using the algorithm, so as to finally form a high-quality image and provide a reliable data base for the development of subsequent work.
The invention provides a technical scheme that:
a method for removing the shadow of the image of an unmanned aerial vehicle comprises the following steps: acquiring an image, and acquiring an original image by adopting an unmanned aerial vehicle to acquire an overhead image; enhancing the image, namely enhancing the original image to form an enhanced image; color transformation, namely transforming the color space of the enhanced image to form a transformed image; color correction, which is to perform color correction on the transformed image to form a corrected image; and (5) image inversion, namely performing color inverse transformation on the corrected image to form a final image.
Further, in the image acquiring step, the acquired original image is an image with a resolution of 5472 × 3648, which includes 2000 ten thousand pixels.
Further, in the image enhancement step, an enhancement algorithm is adopted to perform brightness enhancement processing on the original image.
Further, in the image enhancement step, the enhancement algorithm adopts a Retinex algorithm.
Further, in the color transformation step, the enhanced image is transformed from an RGB color space to an HSV color space.
Further, in the color correction step, the transformed image is processed by using a function
Further, in the color correction step, the function is a two-dimensional gamma function.
Further, in the image inversion step, the color of the corrected image is converted from HSV color space to RGB color space.
The invention has the beneficial effects that:
the combined image processing is carried out by adopting the algorithm, and after the image is enhanced by using the algorithm, the brightness is adjusted under the condition of changing the color space aiming at the condition of uneven brightness generated by enhancement, so that a high-quality image is finally formed, and a reliable data basis is provided for the development of subsequent work.
Drawings
Fig. 1 is a flowchart of a method for removing an image shadow of an unmanned aerial vehicle according to an embodiment of the present invention;
FIG. 2 is a comparison diagram of different enhancement algorithms of a method for removing shadows from images of an unmanned aerial vehicle according to an embodiment of the present invention;
fig. 3 is an original image and an image feature edge extraction diagram of an image after being enhanced by a Retinex algorithm of a method for removing an image shadow of an unmanned aerial vehicle according to an embodiment of the present invention;
fig. 4 is an original image acquired by the unmanned aerial vehicle according to the embodiment of the present invention;
fig. 5 is a diagram of an original image acquired by an unmanned aerial vehicle according to the embodiment of the present invention after image enhancement by a Retinex algorithm;
fig. 6 is a diagram of an original image acquired by an unmanned aerial vehicle according to an embodiment of the present invention after being processed by an improved Retinex algorithm;
fig. 7 is a diagram of the original image acquired by the unmanned aerial vehicle and the image processed by the improved Retinex algorithm after feature extraction of the feature edge.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
In the description of the embodiments of the present application, it is to be understood that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", and the like, refer to the orientation or positional relationship as shown in the drawings, or as conventionally placed in use of the product of the application, or as conventionally understood by those skilled in the art, and are used merely for convenience of description and for simplicity of description, and do not indicate or imply that the referenced device or element must have a particular orientation, be constructed in a particular orientation, and be operated, and therefore should not be considered as limiting the present application.
In the description of the embodiments of the present application, it should also be noted that, unless otherwise explicitly stated or limited, the terms "disposed," "mounted," "connected," and "connected" are to be construed broadly and may, for example, be fixedly connected, detachably connected, or integrally connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present application can be understood in a specific case by those of ordinary skill in the art.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
The technical solution in the present application will be described below with reference to the accompanying drawings.
Referring to fig. 1, fig. 1 is a flowchart illustrating a method for removing an image shadow of an unmanned aerial vehicle according to an embodiment of the present invention.
The embodiment provides a method for removing an unmanned aerial vehicle image shadow, which specifically comprises the following steps:
s1: and acquiring images, and acquiring original images by adopting an unmanned aerial vehicle to acquire high-altitude images.
The camera carried by the unmanned aerial vehicle is used for shooting the set area at high altitude so as to obtain the original image. The initial parameters of the raw imagery are determined based on the performance parameters of the cameras, the altitude and position of the drone and the operational needs. In this embodiment, the original image obtained is an image of 2000 ten thousand pixels with a resolution of 5472 × 3648.
S2: and (5) image enhancement, namely enhancing the original image by utilizing an enhancement algorithm to form an enhanced image.
The enhancement algorithm is mainly used for enhancing the brightness of the image, so that the shadow area can express related objects, such as houses, roads, slopes and the like, and can be clearly identified. There are various image enhancement algorithms, in this embodiment, a Retinex algorithm is used for enhancement, and in order to show that the effect of enhancement by the Retinex algorithm is better than that of other enhancement methods, this embodiment also compares an original image, an image processed by a histogram equalization enhancement algorithm, an image enhanced by the Retinex algorithm, and an image enhanced by Mask light equalization. The result is shown in fig. 2, in which 2.1 is the original image, 2.2 is the image processed by histogram equalization enhancement algorithm, 2.3 is the image enhanced by Retinex algorithm, and 2.4 is the image enhanced by Mask dodging. Compared with other influences, the influence obtained by adopting the Retinex algorithm is greatly improved in quality, buildings in shadow areas are clearly visible, and the outline of a target object is clear.
Meanwhile, quantitative analysis is performed on the four influences, and comparison after image enhancement is performed by respectively adopting the average gradient value, the variance and the information entropy, and the result is shown in table 1.
TABLE 1
Thus, the following steps are carried out: due to underexposure of the original image, the texture information is compressed, and the average gradient value, variance and information entropy of the image are relatively low. The image is enhanced by three classical enhancement algorithms, three indexes are greatly improved, wherein the S value, the IE value and the MG value of the image after the image is enhanced by the Retinex algorithm are the largest in the three methods, which shows that the Retinex algorithm is optimal, the image after the image is enhanced has clear ground object targets, the landslide reinforcement position and the texture of the building are also clear, and the vegetation texture on the mountain is relatively clear compared with the other three algorithms.
Meanwhile, the LOG operator is used to extract the feature of the feature edge of the original image and the image enhanced by the Retinex algorithm, and the result is shown in fig. 3, where 3.1 is the feature map of the feature edge of the feature extracted from the original image, and 3.2 is the feature map of the feature edge of the feature extracted from the image enhanced by the Retinex algorithm.
Therefore, the following steps are carried out: the original image ground object edge feature extraction is poor, and large-area cavities appear in mountains. The Retinex algorithm is used for image enhancement, the condition of insufficient image exposure under a weak light source can be improved, the recognition degree of image features is improved, the extracted edge features are rich, and a large amount of edge information is extracted from mountains.
S3: and color transformation, namely transforming the color space of the enhanced image to form a transformed image.
The image after enhancement has uneven brightness, and further processing is required to improve the quality of the image. In this embodiment, the color space of the enhanced image is first converted from RGB to HSV, so as to complete the conversion of the color space and prepare for the next adjustment of the brightness.
S4: and color correction, namely performing color correction on the converted image by using a processing function to form a corrected image.
The color correction is to adjust the brightness of the image to eliminate the non-uniformity of the brightness, so that the brightness of the whole image is smooth, which is beneficial to target finding and further data processing. The color correction method includes various methods, including processing by using an arithmetic function, in this embodiment, a two-dimensional gamma function is used to process the transformed image.
S5: and (5) image inversion, namely performing color inverse transformation on the corrected image to form a final image.
After the brightness adjustment is completed, the color of the corrected image is converted from HSV color space to RGB color space, and the final image is synthesized.
The present embodiment provides a specific implementation:
the image is obtained by adopting a Dajiang eidolon 4Pro unmanned aerial vehicle (the flying platform of the unmanned aerial vehicle is relatively stable compared with other unmanned aerial vehicles and is convenient to operate and control), the takeoff weight is 1388g, the maximum flight time is about 23 minutes, the number of 1-inch CMOS effective pixels is 2000 ten thousand, the image resolution is 5472 multiplied by 3648, the lens focal length is 35mm, the aperture f/2.8-f/11 has automatic focusing, the maximum rising speed is 6m/s, the maximum flight height is 6000m, and the GPS/GLONASS dual-mode satellite positioning mode is adopted. Unmanned aerial vehicle is at the flight in-process, because sheltering from of massif, the shadow exists in the unmanned aerial vehicle image of acquireing.
The unmanned aerial vehicle image is loaded, as the original image shown in fig. 4, and image enhancement is performed by using a Retinex algorithm, and the enhancement result is shown in fig. 5. In the enhanced unmanned aerial vehicle image, the shadow area is improved greatly, the brightness of the image in the shadow area is improved greatly, the target object in the shadow area can be identified clearly, but the enhanced image has the phenomena of texture distortion and color distortion. The enhanced unmanned aerial vehicle image is subjected to color conversion, RGB (red, green, blue) colors are converted into HSV (hue, saturation, value) components, the converted brightness image is subjected to color correction, the image subjected to color correction is subjected to inverse operation and synthesized into a new image, as shown in figure 6, the image subjected to two-dimensional gamma function correction has uniform brightness, and the texture features of the image are clear.
The feature edge feature extraction is performed on the image after the brightness correction by using the gaussian-laplacian operator, and simultaneously the feature edge is compared with the edge feature of the original image, as shown in fig. 7, where fig. 7.1 is the edge feature of the original image, and fig. 7.2 is the edge feature of the image after the brightness correction.
As can be seen from fig. 7.1, the original image has no shadow region, rich texture, obvious edge features, and the shadow region, and the extracted edge features show holes, which indicates that the edge features are not clear and the contour of the target object cannot be extracted. As can be seen from fig. 7.2, the corrected image of the unmanned aerial vehicle, which is the image of the original shadow region, can now extract more obvious edge features, which indicates that the method for removing the shadow region and correcting the brightness has an obvious effect.
In summary, the embodiments provided by the present invention have the following main effective effects:
by adopting the improved Retinex algorithm to carry out combined image processing, after the Retinex algorithm is used for enhancement, the brightness is adjusted under the condition of changing color space aiming at the condition of uneven brightness generated by enhancement, and finally a high-quality image is formed, thereby providing a reliable data basis for the development of subsequent work.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only show several embodiments of the present invention, and the description thereof is specific and detailed, but not to be construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (8)
1. A method for removing the shadow of the image of an unmanned aerial vehicle is characterized by comprising the following steps:
acquiring an image, and acquiring an original image by adopting an unmanned aerial vehicle to acquire an overhead image;
enhancing the image, namely enhancing the original image to form an enhanced image;
color transformation, namely transforming the color space of the enhanced image to form a transformed image;
color correction, which is to perform color correction on the transformed image to form a corrected image;
and image inversion, namely performing color inverse transformation on the corrected image to form a final image.
2. The method as claimed in claim 1, wherein in the step of obtaining the image, the original image obtained is an image with a resolution of 5472 x 3648 and 2000 ten thousand pixels.
3. The method as claimed in claim 1, wherein in the image enhancement step, an enhancement algorithm is used to perform a brightness enhancement process on the original image.
4. The method as claimed in claim 3, wherein in the image enhancement step, the enhancement algorithm employs a Retinex algorithm.
5. The method of claim 1, wherein the color transformation step transforms the enhanced image from an RGB color space to an HSV color space.
6. The method of claim 1, wherein the color correction step uses a function to process the transformed image.
7. The method of claim 6, wherein in the color correction step, the function is a two-dimensional gamma function.
8. The method of claim 1, wherein in the image inverting step, the color of the corrected image is converted from HSV color space to RGB color space.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111622343.8A CN115375558A (en) | 2021-12-28 | 2021-12-28 | Method for removing image shadow of unmanned aerial vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111622343.8A CN115375558A (en) | 2021-12-28 | 2021-12-28 | Method for removing image shadow of unmanned aerial vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115375558A true CN115375558A (en) | 2022-11-22 |
Family
ID=84060204
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111622343.8A Pending CN115375558A (en) | 2021-12-28 | 2021-12-28 | Method for removing image shadow of unmanned aerial vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115375558A (en) |
-
2021
- 2021-12-28 CN CN202111622343.8A patent/CN115375558A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021120406A1 (en) | Infrared and visible light fusion method based on saliency map enhancement | |
| CN110660088B (en) | Image processing method and device | |
| CN104683767B (en) | Penetrating Fog image generating method and device | |
| CN106462944B (en) | High-resolution panorama VR generator and method | |
| US10699395B2 (en) | Image processing device, image processing method, and image capturing device | |
| CN110827218B (en) | Airborne image defogging method based on weighted correction of HSV (hue, saturation, value) transmissivity of image | |
| DE102018119625A1 (en) | Reduction of structured IR patterns in stereoscopic depth sensor imaging | |
| TWI760782B (en) | System and method for orchard recognition on geographic area | |
| Sidike et al. | Adaptive trigonometric transformation function with image contrast and color enhancement: Application to unmanned aerial system imagery | |
| US10951817B2 (en) | Compound-eye imaging device, image processing method, and recording medium | |
| CN107274441B (en) | Wave band calibration method and system for hyperspectral image | |
| US11763432B2 (en) | Multi-exposure image fusion method based on feature distribution weight of multi-exposure image | |
| CN106683056A (en) | Airborne photoelectric infrared digital image processing method and apparatus thereof | |
| CN109886883A (en) | Real-time polarization fog-penetrating imaging image enhancement processing method | |
| CN110533600A (en) | A kind of same/heterogeneous remote sensing image high-fidelity broad sense sky-spectrum fusion method | |
| CN110163807A (en) | A kind of enhancement method of low-illumination image based on the bright channel of expectation | |
| CN109738069A (en) | The method that multispectral imaging illuminates spatial heterogeneity correction | |
| CN108537744A (en) | A kind of coloured image luminance component homomorphic filtering defogging method | |
| US20240185561A1 (en) | Aerial image change detection apparatus | |
| JP4624884B2 (en) | Image processing device for work vehicles | |
| CN112243584A (en) | Image color correction method, shooting device and image color correction system | |
| CN107507151B (en) | Multispectral remote sensing image real color restoration method and system | |
| US8854501B2 (en) | Image processing apparatus and image processing method for processing spectral image data | |
| CN115375558A (en) | Method for removing image shadow of unmanned aerial vehicle | |
| KR20210096925A (en) | Flexible Color Correction Method for Massive Aerial Orthoimages |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |