Target extraction method and device for indoor simulation measurement of visible light image

Abstract

The invention discloses a target extraction method and device for indoor simulation measurement of a visible light image. The method comprises the following steps: acquiring a target image sequence under different solar incident angles and detection angles; for each target image in the target image series, carrying out frame selection on an effective area of a target in the image to obtain a first image; extracting a target edge in the first image based on a preset algorithm, and determining a second image based on an edge extraction result; and based on imaging features of a supporting structure in the indoor simulation measurement system, removing the supporting structure in the second image to obtain a final target extraction result. According to the invention, the target in the visible light image can be accurately extracted.

Description

Technical Field

[0001] This invention relates to the field of image analysis technology, and in particular to a method and apparatus for target extraction from indoor simulated measurement visible light images. Background Technology

[0002] Indoor simulation measurement allows for the measurement of targets under darkened conditions, simulating a deep-space background, and obtaining the target's characteristics in the visible light band. By varying the angle of the measurement system, it is possible to measure the target's characteristics at all angles, covering different solar incidence and detection angles.

[0003] Because simulation measurements are conducted in a dark room, the deep-space background cannot be fully reproduced, leading to interference from the background environment on the target at certain angles. This hinders the effective extraction of target characteristics from the image, causing difficulties in image processing. Currently, existing image processing methods use region thresholding, selecting a background threshold for the target region, retaining pixel values ​​above the threshold as target data, and removing those below as background. Furthermore, the support structure of the measurement system is connected to the target, and is treated as part of the target during image processing. However, this method cannot accurately extract the target due to the inability to select a suitable background threshold, resulting in low measurement accuracy. Therefore, there is an urgent need for a target extraction method for indoor simulation measurements of visible light images to address these problems. Summary of the Invention

[0004] This invention provides a method and apparatus for target extraction from visible light images obtained through indoor simulated measurement, which can accurately extract targets from visible light images. The technical solution is as follows:

[0005] On the one hand, a method for target extraction from indoor simulated measurement visible light images is provided, the method comprising:

[0006] Acquire target image sequences under different solar incidence and detection angles;

[0007] For each target image in the target image series, the effective region of the target in the image is selected to obtain the first image;

[0008] The target edges in the first image are extracted based on a preset algorithm, and the second image is determined based on the edge extraction results;

[0009] Based on the imaging characteristics of the support structure in the indoor simulation measurement system, the support structure in the second image is removed to obtain the final target extraction result.

[0010] On the other hand, a target extraction device for indoor simulated measurement of visible light images is provided, the device comprising:

[0011] The acquisition unit is used to acquire target image sequences under different solar incidence angles and detection angles;

[0012] The selection unit is used to select the effective area of ​​the target in each target image in the target image series to obtain the first image;

[0013] An extraction unit is used to extract target edges in the first image based on a preset algorithm, and to determine a second image based on the edge extraction results;

[0014] The elimination unit is used to eliminate the supporting structure in the second image based on the imaging features of the supporting structure in the indoor simulation measurement system, so as to obtain the final target extraction result.

[0015] On the other hand, a computer device is provided, the computer device including a memory and a processor, the memory for storing computer programs, and the processor for executing the computer programs stored in the memory to implement the steps of the target extraction method for indoor simulated measurement of visible light images described above.

[0016] On the other hand, a computer-readable storage medium is provided, wherein a computer program is stored therein, and when executed by a processor, the computer program implements the steps of the target extraction method for indoor simulated measurement of visible light images described above.

[0017] On the other hand, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the target extraction method for indoor simulated measurement of visible light images described above.

[0018] This invention provides a target extraction method for indoor simulated measurement of visible light images. Through processing steps such as target region selection, edge extraction, and removal of system support structures, the actual image area occupied by the target can be obtained, solving the problem of low image processing accuracy in traditional methods. Simultaneously, based on the image characteristics of the system support structures, the support structures in the target region are removed, resolving the problem of the target and support structures being mixed together in optical simulation measurement, and improving the ability to extract target image features in simulated measurement. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1This is a flowchart of a target extraction method for indoor simulated measurement of visible light images provided by an embodiment of the present invention;

[0021] Figure 2 This is a structural diagram of a target extraction device for indoor simulated measurement of visible light images provided in an embodiment of the present invention;

[0022] Figure 3 This is a hardware architecture diagram of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0024] The specific implementation of the method in this application is described in detail below.

[0025] Please refer to Figure 1 This invention provides a target extraction method for indoor simulated measurement of visible light images, the method comprising:

[0026] Step 100: Obtain target image sequences under different solar incidence angles and detection angles;

[0027] Step 102: For each target image in the target image series, the effective area of ​​the target in the image is selected to obtain the first image;

[0028] Step 104: Extract the target edges in the first image based on a preset algorithm, and determine the second image based on the edge extraction results;

[0029] Step 106: Based on the imaging features of the support structure in the indoor simulation measurement system, remove the support structure from the second image to obtain the final target extraction result.

[0030] In this embodiment, by performing processing steps such as target region selection, edge extraction, and removal of system support structures, the actual image area occupied by the target can be obtained, solving the problem of low image processing accuracy in traditional methods. Simultaneously, based on the image characteristics of the system support structures, the support structures of the target region are removed, resolving the problem of the target and support structures being mixed together in optical simulation measurements, and improving the ability to extract target image features in simulation measurements.

[0031] The following description Figure 1 The execution method for each step is shown.

[0032] First, regarding step 100:

[0033] In this step, the input parameters of the simulation measurement system are first determined. By acquiring target image sequences under different solar incidence angles and detection angles, a series of target images with different attitudes and different brightness conditions can be obtained.

[0034] Regarding step 102:

[0035] In the target image sequence obtained in step 100, the area occupied by the target in each image is different, and the background of the darkroom is not a completely dark background. Therefore, by selecting the effective area of ​​the target, some background interference factors can be removed.

[0036] Furthermore, when selecting the effective area of ​​the target, a uniform selection shape size is chosen to ensure that the target is completely covered for all images in the sequence, facilitating subsequent automatic image processing. Selection methods include rectangular, circular, elliptical, and polygonal selections, which users can choose according to the target characteristics; this application does not impose specific limitations.

[0037] Regarding step 104:

[0038] In the first image, a portion of the background environment still exists around the target, and therefore needs to be removed in step 104. In step 104, the preset algorithm is one of the Canny algorithm, Sobel algorithm, and Prewitt algorithm. Of course, users can also use other algorithms; this application does not impose specific limitations.

[0039] In some implementations, determining the second image based on the edge extraction results includes:

[0040] Determine the outermost edge point;

[0041] Connect each outermost edge point to obtain a closed region;

[0042] The portion containing the enclosed area is designated as the second image.

[0043] In this step, the first image is a grayscale image. Generally, the grayscale value of the target area is higher, while the grayscale value of the background area is lower, with a clear boundary between the two. Therefore, the edge contour of the target can be analyzed based on this characteristic. However, since the intensity of the actual target area is not uniformly distributed and there are certain variations in brightness, the target edge after processing by the above method is a curve or a discrete closed region. By statistically analyzing the coordinate positions of the curve or closed region, the positions of the points closest to the image edge are calculated and arranged. Connecting these points yields a closed region, which is the actual area occupied by the target after removing the background environment.

[0044] Regarding step 106: The imaging feature of the support structure in the image is a rectangle of fixed width, and one short side of the rectangle is connected to the target;

[0045] In some implementations, step 106 includes:

[0046] The corner features of the supporting structure in the second image were obtained based on the Harris corner detection algorithm, resulting in four corner points.

[0047] Using the four corner points as the four vertices of a rectangle, we obtain a rectangular region;

[0048] The rectangular region is removed from the second image to obtain the final target extraction result.

[0049] In this embodiment, the second image contains not only the target but also the feature information of the system support structure. Since the system support structure is fixed and the measurement distance is fixed, the image features of the system support structure remain unchanged in the sequence of target images obtained after step 104, existing only at different positions in the image under different measurement angles. The system support structure in the image is a rectangle of fixed width with an aspect ratio greater than 1, and it is connected to the target. Therefore, the combined features of the second image are the target region features plus a rectangular feature. The two long sides of the rectangle can be extracted from the second image; their features are two long straight lines connected at their vertices, one end at the image edge and the other connected to the target. Both ends of the long straight lines are abrupt corner points, and corner features can be obtained using algorithms such as Harris corner detection. The connected region of the four corner points on the two straight lines is the image region occupied by the system support structure; removing it from the second image yields the final target image.

[0050] like Figure 2 , Figure 3 As shown, this embodiment of the invention provides a target extraction device for indoor simulated measurement of visible light images. The device embodiment can be implemented through software, hardware, or a combination of both. From a hardware perspective, such as... Figure 2 The diagram shown is a hardware architecture diagram of a computing device housing a target extraction device for indoor simulated measurement of visible light images provided in an embodiment of the present invention. (Except for...) Figure 2 In addition to the processor, memory, network interface, and non-volatile memory shown, the computing device in the embodiment may also include other hardware, such as a forwarding chip responsible for processing packets. Taking software implementation as an example, such as... Figure 3 As shown, a device in a logical sense is formed by the CPU of the computing device in which it is located reading the corresponding computer program from the non-volatile memory into the memory for execution.

[0051] Please refer to Figure 3 This invention provides a target extraction device for indoor simulated measurement of visible light images, the device comprising:

[0052] The acquisition unit 300 is used to acquire target image sequences under different solar incidence angles and detection angles;

[0053] The selection unit 302 is used to select the effective area of ​​the target in each target image in the target image series to obtain the first image;

[0054] Extraction unit 304 is used to extract target edges in the first image based on a preset algorithm, and to determine the second image based on the edge extraction results;

[0055] The elimination unit 306 is used to eliminate the supporting structure in the second image based on the imaging features of the supporting structure in the indoor simulation measurement system, so as to obtain the final target extraction result.

[0056] In some implementations, determining the second image based on the edge extraction results includes:

[0057] Determine the outermost edge point;

[0058] Connect each outermost edge point to obtain a closed region;

[0059] The portion containing the enclosed area is designated as the second image.

[0060] In some implementations, the preset algorithm is one of the Canny algorithm, Sobel algorithm, and Prewitt algorithm.

[0061] In some implementations, the imaging feature of the support structure in the image is a rectangle of fixed width, and one short side of the rectangle is connected to the target.

[0062] The rejection unit 306 is used to perform the following operations:

[0063] The corner features of the supporting structure in the second image were obtained based on the Harris corner detection algorithm, resulting in four corner points.

[0064] Using the four corner points as the four vertices of a rectangle, we obtain a rectangular region;

[0065] The rectangular region is removed from the second image to obtain the final target extraction result.

[0066] It should be noted that the target extraction device for indoor simulated measurement of visible light images provided in the above embodiments is only an example of the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the target extraction device for indoor simulated measurement of visible light images provided in the above embodiments and the target extraction method embodiments for indoor simulated measurement of visible light images belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be repeated here.

[0067] Embodiments of this application also provide a computer device, please refer to... Figure 3 The computer device includes a processor and a memory, the memory storing at least one instruction, at least one program, code set or instruction set, the at least one instruction, at least one program, code set or instruction set being loaded and executed by the processor to implement the target extraction method for indoor simulated measurement of visible light images provided in the above-described method embodiments.

[0068] Embodiments of this application also provide a computer-readable storage medium storing at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, at least one program, code set, or instruction set is loaded and executed by a processor to implement the target extraction method for indoor simulated measurement of visible light images provided in the above-described method embodiments.

[0069] Embodiments of this application also provide a computer program product, which includes a computer program. A processor of a computer device reads the computer program from a computer-readable storage medium and executes the computer program, causing the computer device to perform the target extraction method for indoor simulated measurement of visible light images as described in any of the above embodiments.

[0070] For ease of description, the above systems or devices are described separately as various modules or units based on their functions. Of course, in implementing this application, the functions of each unit can be implemented in one or more software and / or hardware components.

[0071] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0072] Finally, it should be noted that in this document, relational terms such as first, second, third, and fourth are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0073] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for target extraction from indoor simulated visible light images, characterized in that, The method includes: Acquire target image sequences under different solar incidence and detection angles; For each target image in the target image series, the effective region of the target in the image is selected to obtain the first image; The target edges in the first image are extracted based on a preset algorithm, and the second image is determined based on the edge extraction results; Based on the imaging characteristics of the support structure in the indoor simulation measurement system, the support structure in the second image is removed to obtain the final target extraction result.

2. The method according to claim 1, characterized in that, The process of determining the second image based on edge extraction results includes: Determine the outermost edge point; Connect each outermost edge point to obtain a closed region; The portion containing the enclosed area is designated as the second image.

3. The method according to claim 1, characterized in that, The preset algorithm is one of the Canny algorithm, Sobel algorithm, and Prewitt algorithm.

4. The method according to claim 1, characterized in that, The imaging feature of the support structure in the image is a rectangle of fixed width, and one of the short sides of the rectangle is connected to the target. The imaging features of the support structure in the indoor simulation measurement system are used to remove the support structure from the second image, resulting in the final target extraction result, including: The corner features of the support structure in the second image are obtained based on the Harris corner detection algorithm, resulting in four corner points; Using the four corner points as the four vertices of a rectangle, a rectangular region is obtained; The rectangular region is removed from the second image to obtain the final target extraction result.

5. A target extraction device for indoor simulated measurement of visible light images, characterized in that, The device includes: The acquisition unit is used to acquire target image sequences under different solar incidence angles and detection angles; The selection unit is used to select the effective area of ​​the target in each target image in the target image series to obtain the first image; An extraction unit is used to extract target edges in the first image based on a preset algorithm, and to determine a second image based on the edge extraction results; The elimination unit is used to eliminate the supporting structure in the second image based on the imaging features of the supporting structure in the indoor simulation measurement system, so as to obtain the final target extraction result.

6. The apparatus according to claim 5, characterized in that, The process of determining the second image based on edge extraction results includes: Determine the outermost edge point; Connect each outermost edge point to obtain a closed region; The portion containing the enclosed area is designated as the second image.

7. The apparatus according to claim 5, characterized in that, The preset algorithm is one of the Canny algorithm, Sobel algorithm, and Prewitt algorithm.

8. The apparatus according to claim 5, characterized in that, The imaging feature of the support structure in the image is a rectangle of fixed width, and one of the short sides of the rectangle is connected to the target. The imaging features of the support structure in the indoor simulation measurement system are used to remove the support structure from the second image, resulting in the final target extraction result, including: The corner features of the support structure in the second image are obtained based on the Harris corner detection algorithm, resulting in four corner points; Using the four corner points as the four vertices of a rectangle, a rectangular region is obtained; The rectangular region is removed from the second image to obtain the final target extraction result.

9. A computer device, characterized in that, The computer device includes a memory and a processor. The memory is used to store computer programs, and the processor is used to execute the computer programs stored in the memory to implement the steps of the method according to any one of claims 1-4.

10. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the steps of the method described in any one of claims 1-4.

Images