Target detection method and system based on remote sensing image

Abstract

The invention provides a target detection method and system based on a remote sensing image, and belongs to the technical field of radio detection, and the method specifically comprises the steps: carrying out the determination of a detection deviation target in detection targets through a detection deviation condition, and obtaining the distribution data of the detection deviation target in a target region, and combining detection deviation conditions of different detection deviation targets to determine that the detection accuracy of the target area does not meet requirements, combining different types of spectrums to construct a plurality of spectrum detection combinations, and obtaining the detection deviation conditions of the detection deviation targets in different spectrum detection combinations. And the target detection strategy of the target area is determined by using the detection deviation conditions of different spectrum detection combinations and the spectrum composition data, so that the accuracy of target detection processing is improved.

Description

Technical Field

[0001] The present invention belongs to the field of radio detection technology, and in particular relates to a target detection method and system based on remote sensing images. Background Art

[0002] The remote sensing images of satellite devices can be used to quickly and easily detect and process ground targets. Specifically, in the invention patent application CN202010723927.3 "Satellite Image Processor for Remote Sensing Image Target Feature Recognition", the real-time remote sensing image data of the detection area is received and output, and target detection, feature extraction and positioning are performed based on the output remote sensing image data, thereby achieving accurate detection and recognition of the target. However, the above technical solution has the following problems: In the process of detecting and processing targets using remote sensing images, existing technical solutions often use a single spectrum or multiple spectra to detect targets. Using a single spectrum may make it difficult to meet the detection accuracy requirements in some cases, while using multiple spectra will further increase the complexity of data analysis and processing. Therefore, how to generate differentiated detection and processing strategies based on the distribution data of targets in the detection target area has become a technical problem that needs to be solved urgently.

[0003] In response to the above technical problems, the present application specifically provides a target detection method and system based on remote sensing images. Summary of the invention

[0004] To achieve the purpose of the present invention, the present invention adopts the following technical solutions: In a first aspect, the present application provides a target detection method based on remote sensing images, specifically comprising: S1 uses a single spectrum to obtain remote sensing images of the target area to obtain detection data, and uses the analysis results of the detection data to determine the distribution data of different types of detection targets in the target area. When it is determined based on the distribution data that the analysis complexity of the target area does not meet the requirements, proceed to the next step; S2 determines the detection deviation of different types of detection targets based on the historical detection data of different types of detection targets in the remote sensing image, and uses the detection deviation to determine the detection deviation target in the detection target; S3 obtains the distribution data of the detection deviation targets in the target area, and when it is determined that the detection accuracy of the target area does not meet the requirements based on the detection deviation conditions of different detection deviation targets, proceeds to the next step; S4 combines different types of spectra to obtain a variety of spectral detection combinations, obtains the detection deviation of the detection deviation target in different spectral detection combinations, and uses the detection deviation in different spectral detection combinations and spectral composition data to determine the target detection strategy for the target area.

[0005] The beneficial effects of the present invention are: Whether the parsing complexity of the target area meets the requirements is determined based on the distribution data of different types of detection targets. Not only the differences in the difficulty of identifying and processing the detection targets in the target area due to the differences in the number of different types of detection targets, but also the differences in the difficulty of identifying and processing the detection targets in the target area due to the differences in the distribution and aggregation levels of different types of detection targets are taken into account. This realizes the screening of target areas with greater identification and processing difficulties from multiple angles, and also lays the foundation for adopting differentiated target detection strategies according to the differences in identification and processing difficulties.

[0006] The target detection strategy of the target area is determined by utilizing the detection deviation of different spectral detection combinations and the spectral composition data. The recognition accuracy of targets with detection deviations in different spectral detection combinations is fully considered to ensure the accuracy of target detection in the target area. At the same time, it avoids the emergence of technical problems that make recognition and processing more difficult due to the use of the full spectrum approach, thereby improving the efficiency and accuracy of the analysis and processing of multi-spectral remote sensing images.

[0007] A further technical solution is that the types of the detection targets are divided according to the building types of the detection targets.

[0008] A further technical solution is that the distribution data of the detection targets include distribution areas of different detection targets and spacing distances between distribution areas of other detection targets.

[0009] A further technical solution is to determine that the resolution complexity of the target area does not meet the requirements, specifically including: Determining the number of different types of detection targets in the target area based on the distribution data of different types of detection targets in the target area; Acquire the number of different types of detection targets in different unit area regions in the target region, and determine the aggregation region in the unit area region using the number of different types of detection targets; It is determined whether the resolution complexity of the target area meets the requirement according to the number of clustered areas.

[0010] A further technical solution is that the gathering area is a unit area where the total number of different types of detection targets is greater than a preset number threshold.

[0011] A further technical solution is that, when the number of the clustered areas is greater than a preset number of clustered areas, it is determined that the analysis complexity of the target area does not meet the requirements.

[0012] A further technical solution is that the method for determining the target detection strategy of the target area is: Determine the detection deviation times of different detection deviation targets in different spectral detection combinations based on the detection deviation situations of different detection deviation targets in different spectral detection combinations, and determine the target deviation coefficients of different detection deviation targets in different spectral detection combinations using the preset deviation coefficients corresponding to the detection deviation times; Determining target weight coefficients of different detection deviation targets based on the number proportions of different detection deviation targets in the target area; The detection deviation values ​​of different spectral detection combinations are determined according to the target weight coefficients of different detection deviation targets and the target deviation coefficients of different detection deviation targets in different spectral detection combinations, and the matching spectral detection combination of the target area is determined in combination with the number of spectrum types in the different spectral detection combinations, and the detection processing of the detection targets in the target area is performed using the matching spectral detection combination.

[0013] A further technical solution is that the method for determining the matching spectral detection combination of the target area is: Determine preset analytical complexity coefficients corresponding to different spectral detection combinations according to the number of types of spectra in different spectral detection combinations; A matching deviation value is determined according to the detection deviation values ​​of different spectral detection combinations and an average value of a preset analytical complexity coefficient, and the matching spectral detection combination of the target area is determined using the matching deviation value.

[0014] A further technical solution is that the matching spectral detection combination of the target area is a spectral detection combination with a minimum matching deviation value.

[0015] In a second aspect, the present invention provides a computer system comprising: a memory and a processor that are communicatively connected, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-mentioned target detection method based on remote sensing images when running the computer program.

[0016] Other features and advantages will be described in the following description, and partly become apparent from the description, or understood by practicing the invention. The purpose and other advantages of the invention are realized and obtained by the structures particularly pointed out in the description and the drawings.

[0017] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings.

[0019] Figure 1 It is a flow chart of a target detection method based on remote sensing images; Figure 2 It is a flow chart to determine that the analytical complexity of the target area does not meet the requirements; Figure 3 is a flow chart of a method for detecting a determination of a deviation target; Figure 4 It is a flow chart of a method for determining a target detection strategy for a target area. DETAILED DESCRIPTION

[0020] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that the present invention will be comprehensive and complete and fully convey the concepts of the example embodiments to those skilled in the art. The same reference numerals in the figures represent the same or similar structures, and thus their detailed description will be omitted.

[0021] The terms "a", "an", "the", and "said" are used to indicate the presence of one or more elements / components / etc.; the terms "comprising" and "having" are used to express an open-ended inclusive meaning and mean that additional elements / components / etc. may be present in addition to the listed elements / components / etc.

[0022] Example 1 To solve the above problems, according to one aspect of the present invention, Figure 1 As shown, according to one aspect of the present invention, a first aspect is provided. The present application provides a target detection method based on remote sensing images, specifically comprising: S1 uses a single spectrum to obtain remote sensing images of the target area to obtain detection data, and uses the analysis results of the detection data to determine the distribution data of different types of detection targets in the target area. When it is determined based on the distribution data that the analysis complexity of the target area does not meet the requirements, proceed to the next step; Furthermore, the types of the detection targets are divided according to the building types of the detection targets.

[0023] It should be noted that the distribution data of the detection targets include distribution areas of different detection targets and interval distances between distribution areas of other detection targets.

[0024] It is understandable that if Figure 2 As shown, it is determined that the analysis complexity of the target area does not meet the requirements, specifically including: Determining the number of different types of detection targets in the target area based on the distribution data of different types of detection targets in the target area; Acquire the number of different types of detection targets in different unit area regions in the target region, and determine the aggregation region in the unit area region using the number of different types of detection targets; It is determined whether the resolution complexity of the target area meets the requirement according to the number of clustered areas.

[0025] It should also be noted that the aggregation area is a unit area where the total number of different types of detection targets is greater than a preset number threshold.

[0026] It can be understood that when the number of the clustering regions is greater than the preset number of clustering regions, it is determined that the parsing complexity of the target region does not meet the requirement.

[0027] Specifically, when the analysis complexity of the target area meets the requirements, the target area is detected by using the full spectrum method.

[0028] In another possible embodiment, determining that the resolution complexity of the target area does not meet the requirement specifically includes: Determining the number of different types of detection targets in the target area based on the distribution data of different types of detection targets in the target area, and when the total number of different types of detection targets in the target area is greater than a preset number of targets, determining that the resolution complexity of the target area does not meet the requirements; When the total number of different types of detection targets in the target area is not greater than the preset number of targets: Determining a basic analytical complexity coefficient of the detection target in the target area based on the number of different types of detection targets in the target area, and determining that the analytical complexity of the target area does not meet the requirement when the basic analytical complexity coefficient of the detection target in the target area does not meet the requirement; When the basic analytical complexity coefficient of the detection target in the target area is within the preset complexity coefficient interval: it is determined that the analytical complexity of the target area meets the requirements; When the basic analytical complexity coefficient of the detection target in the target area is not within the preset complexity coefficient range: Acquire the number of different types of detection targets in different unit area areas of the target area, and when the total number of different types of detection targets in different unit area areas is less than a preset number threshold, determine that the resolution complexity of the target area meets the requirement; When there is a unit area where the total number of different types of detection targets is not less than the preset number threshold: A unit area region in which the total number of different types of detection targets is not less than a preset number threshold is used as a clustering region, and when the number of the clustering regions does not meet the requirement, it is determined that the resolution complexity of the target region does not meet the requirement; When the number of cluster areas meets the requirement: Determine the basic analytical complexity coefficients of the detection targets in different unit area areas according to the number of different types of detection targets in different unit area areas; when the number of unit area areas whose basic analytical complexity coefficients of the detection targets are not within a preset complexity coefficient interval does not meet the requirement, it is determined that the analytical complexity of the target area does not meet the requirement; When the number of unit area regions where the basic analytical complexity coefficient of the detection target is not within the preset complexity coefficient range meets the requirements: Based on the basic analytical complexity coefficients of the detection targets in different unit area regions, the complexity coefficient evaluation amount is determined, and the complexity coefficient evaluation amount is used to determine whether the analytical complexity of the target area meets the requirements.

[0029] S2 determines the detection deviation of different types of detection targets based on the historical detection data of different types of detection targets in the remote sensing image, and uses the detection deviation to determine the detection deviation target in the detection target; Furthermore, the detection deviation of the detection target includes the number of detection deviations of the detection target and detection deviation types of different detection deviation numbers.

[0030] It should be noted that the detection deviation types include target type recognition deviation, target area recognition deviation and target height distribution recognition deviation.

[0031] It is understandable that if Figure 3 As shown, the method for determining the detection deviation target is: Determining the detection deviation times of the detection deviation target and the detection deviation types of different detection deviation times based on the detection deviation situation of the detection target; Determine the detection deviation type whose detection deviation number is greater than the preset deviation number based on the detection deviation number of different detection deviation types, and use it as the abnormal detection type; Whether the detection target is a detection deviation target is determined by the number of the abnormal detection types.

[0032] Furthermore, when the number of the abnormal detection types does not meet the requirement, it is determined that the detection target belongs to the detection deviation target.

[0033] Optionally, the method for determining the detection deviation target is: Determining the detection deviation times of the detection deviation target and the detection deviation types of different detection deviation times based on the detection deviation situation of the detection target; Determining detection bias probabilities of different detection bias types based on proportions of detection bias times of different detection bias types in detection times of the detection target; Whether the detection target is a detection deviation target is determined by the detection deviation probabilities of different detection deviation types.

[0034] Further, when there is a detection deviation type whose detection deviation probability is greater than a preset deviation probability, the detection target is determined to be a detection deviation target.

[0035] In another possible embodiment, the method for determining the detection deviation target is: S21 determines the detection deviation times of the detection deviation target and the detection deviation types of different detection deviation times according to the detection deviation situation of the detection target; S22 obtains the proportion of the number of detection deviations of different detection deviation types in the number of detections of the detection target, and determines the detection abnormality values ​​of different detection deviation types in combination with the number of detection deviations corresponding to the different detection deviation types; S23 determines the target detection deviation probability of the detection target through detection abnormal values ​​of different detection deviation types, and determines whether the detection target is a detection deviation target by using the target detection deviation probability.

[0036] Furthermore, the target detection deviation probability of the detection target is determined according to the weighted sum of detection anomalies of different detection deviation types.

[0037] Specifically, the target detection deviation probability of the detection target ranges from 0 to 1, wherein when the target detection deviation probability of the detection target is greater than a preset deviation probability threshold, the detection target is determined to be a detection deviation target.

[0038] Optionally, the above step S21 includes the following contents: S211 determines the detection deviation times of the detection deviation target according to the detection deviation of the detection target. When the detection deviation times of the detection deviation target does not meet the requirement, it is determined that the detection target belongs to the detection deviation target. When the detection deviation times of the detection deviation target meets the requirement, it proceeds to step S212. S212 determines a detection deviation ratio based on the ratio of the detection deviation times of the detection deviation target to the detection times of the detection deviation target. When the detection deviation ratio is less than a preset ratio threshold, the process proceeds to step S22. When the detection deviation ratio is not less than the preset ratio threshold, the process proceeds to step S213. S213: When the detection deviation times of the detection deviation target are within the preset deviation times interval, it is determined that the detection target belongs to the detection deviation target; when the detection deviation times of the detection deviation target are not within the preset deviation times interval, the process proceeds to step S22.

[0039] Optionally, the above step S22 includes the following contents: S221 obtains the detection deviation times of different detection deviation types. When there is a detection deviation type whose corresponding detection deviation times do not meet the requirements, the process proceeds to step S222. When there is no detection deviation type whose corresponding detection deviation times do not meet the requirements, the process proceeds to step S223. S222: when the number of detection deviation types whose corresponding detection deviation times do not meet the requirements is greater than the preset number of deviation types, it is determined that the detection target belongs to the detection deviation target; when the number of detection deviation types whose corresponding detection deviation times do not meet the requirements is not greater than the preset number of deviation types, the process proceeds to step S223; S223 obtains the proportion of the number of detection deviations of different detection deviation types in the number of detections of the detection target, and determines the detection abnormality values ​​of different detection deviation types in combination with the detection deviation numbers corresponding to different detection deviation types. When there is a detection abnormality value that does not meet the required detection deviation type, it is determined that the detection target belongs to the detection deviation target. When there is no detection abnormality value that does not meet the required detection deviation type, the process proceeds to step S224. S224: When the detection abnormality values ​​of different detection deviation types are all less than the preset abnormality threshold, it is determined that the detection target does not belong to the detection deviation target. When there is a detection deviation type whose detection abnormality value is not less than the preset abnormality threshold, the process proceeds to step S225; S225 obtains the number of detection deviation types whose detection abnormality values ​​are not less than the preset abnormality threshold. When the number of detection deviation types whose detection abnormality values ​​are not less than the preset abnormality threshold does not meet the requirement, it is determined that the detection target belongs to the detection deviation target. When the number of detection deviation types whose detection abnormality values ​​are not less than the preset abnormality threshold meets the requirement, proceed to step S23.

[0040] S3 obtains the distribution data of the detection deviation targets in the target area, and when it is determined that the detection accuracy of the target area does not meet the requirements based on the detection deviation conditions of different detection deviation targets, proceeds to the next step; Specifically, determining that the detection accuracy of the target detection area does not meet the requirement specifically includes: Determine the number of different detection deviation targets in the target area based on the distribution data of the detection deviation targets in the target area, and determine the weight values ​​of different detection deviation targets using the preset weight values ​​corresponding to the numbers of different detection deviation targets; According to the detection deviation conditions of different detection deviation targets, the proportion of the detection deviation times of different detection deviation targets in the detection times is determined, and the proportion is used as the target detection deviation probability; Based on the target detection deviation probabilities and weight values ​​of different detection deviation targets, the sum of the weight values ​​of the target detection deviation probabilities of different detection deviation targets is determined, and used as a comprehensive detection deviation value. The comprehensive detection deviation value is used to determine whether the detection accuracy of the target detection area meets the requirements.

[0041] Further, when the comprehensive detection deviation value is greater than a preset deviation threshold, it is determined that the detection accuracy of the target detection area does not meet the requirement.

[0042] It should also be noted that when the detection accuracy of the target detection area meets the requirement, it is only necessary to use a single spectrum to perform target detection in the target area.

[0043] Optionally, determining that the detection accuracy of the target detection area does not meet the requirement specifically includes: Determine the number of different detection deviation targets in the target area based on the distribution data of the detection deviation targets in the target area, and when the total number of different detection deviation targets in the target area is not less than a preset deviation target number threshold, determine that the detection accuracy of the target detection area does not meet the requirement; When the total number of different detected deviation targets in the target area is less than a preset deviation target number threshold: When the proportion of the number of detected targets in the target area with detected deviation targets is greater than the proportion of the number of preset deviation targets, it is determined that the detection accuracy of the target detection area does not meet the requirement; When the proportion of the number of detected deviation targets in the target area is not greater than the proportion of the number of preset deviation targets: Determine the weight values ​​of different detection deviation targets based on the proportion of the number of detection deviation targets in the target area and the number of detection deviation targets in the target area, and when the sum of the weight values ​​of different detection deviation targets does not meet the requirement, determine that the detection accuracy of the target detection area does not meet the requirement; When the sum of the weights of different detection deviation targets meets the requirements: According to the detection deviation of different detection deviation targets, the proportion of the detection deviation times of different detection deviation targets in the detection times is determined, and the proportion is used as the target detection deviation probability, and the corrected deviation probabilities of different detection deviation targets are determined based on the product of the target detection deviation probabilities of different detection deviation targets and the weight values. When there is a detection deviation target whose corrected deviation probability does not meet the requirements, it is determined that the detection accuracy of the target detection area does not meet the requirements; When there is no correction bias probability that does not meet the required detection bias target: Based on the target detection deviation probabilities and weight values ​​of different detection deviation targets, the sum of the weight values ​​of the target detection deviation probabilities of different detection deviation targets is determined, and used as a comprehensive detection deviation value. The comprehensive detection deviation value is used to determine whether the detection accuracy of the target detection area meets the requirements.

[0044] S4 combines different types of spectra to obtain a variety of spectral detection combinations, obtains the detection deviation of the detection deviation target in different spectral detection combinations, and uses the detection deviation in different spectral detection combinations and spectral composition data to determine the target detection strategy for the target area.

[0045] Further, such as Figure 4 As shown, the method for determining the target detection strategy of the target area is: Determine the detection deviation times of different detection deviation targets in different spectral detection combinations based on the detection deviation situations of different detection deviation targets in different spectral detection combinations, and determine the target deviation coefficients of different detection deviation targets in different spectral detection combinations using the preset deviation coefficients corresponding to the detection deviation times; Determining target weight coefficients of different detection deviation targets based on the number proportions of different detection deviation targets in the target area; The detection deviation values ​​of different spectral detection combinations are determined according to the target weight coefficients of different detection deviation targets and the target deviation coefficients of different detection deviation targets in different spectral detection combinations, and the matching spectral detection combination of the target area is determined in combination with the number of spectrum types in the different spectral detection combinations, and the detection processing of the detection targets in the target area is performed using the matching spectral detection combination.

[0046] It should be noted that the method for determining the matching spectral detection combination of the target area is: Determine preset analytical complexity coefficients corresponding to different spectral detection combinations according to the number of types of spectra in different spectral detection combinations; A matching deviation value is determined according to the detection deviation values ​​of different spectral detection combinations and an average value of a preset analytical complexity coefficient, and the matching spectral detection combination of the target area is determined using the matching deviation value.

[0047] It can be understood that the matching spectral detection combination of the target area is the spectral detection combination with the smallest matching deviation value.

[0048] Example 2 In a second aspect, the present invention provides a computer system comprising: a memory and a processor that are communicatively connected, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-mentioned target detection method based on remote sensing images when running the computer program.

[0049] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0050] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0051] The above description is only one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of the claims of this specification.

Claims

1. A target detection method based on remote sensing images, characterized in that: Specifically include: Acquiring remote sensing images of the target area using a single spectrum to obtain detection data, determining distribution data of different types of detection targets in the target area using the analysis results of the detection data, and when it is determined based on the distribution data that the analysis complexity of the target area does not meet the requirements, proceeding to the next step; Determine the detection deviation of different types of detection targets based on the historical detection data of different types of detection targets in the remote sensing image, and use the detection deviation to determine the detection deviation target in the detection target; Obtaining distribution data of detection deviation targets in the target area, and combining detection deviation conditions of different detection deviation targets, when it is determined that the detection accuracy of the target area does not meet the requirements, proceeding to the next step; Different types of spectra are combined to construct a variety of spectral detection combinations, the detection deviation of the detection deviation target in different spectral detection combinations is obtained, and the target detection strategy of the target area is determined using the detection deviation in different spectral detection combinations and spectral composition data.

2. The target detection method based on remote sensing images according to claim 1, characterized in that: The types of the detection targets are divided according to the building types of the detection targets.

3. The target detection method based on remote sensing images according to claim 1, characterized in that: The distribution data of the detection targets include distribution areas of different detection targets and interval distances between distribution areas of other detection targets.

4. The target detection method based on remote sensing images according to claim 1, characterized in that: Determining that the resolution complexity of the target area does not meet the requirements includes: Determining the number of different types of detection targets in the target area based on the distribution data of different types of detection targets in the target area; Acquire the number of different types of detection targets in different unit area regions in the target region, and determine the aggregation region in the unit area region using the number of different types of detection targets; It is determined whether the resolution complexity of the target area meets the requirement according to the number of clustered areas.

5. The target detection method based on remote sensing images according to claim 4, characterized in that: The gathering area is a unit area where the total number of different types of detection targets is greater than a preset number threshold.

6. The target detection method based on remote sensing images according to claim 1, characterized in that: When the analysis complexity of the target area meets the requirements, the target area is detected by using the full spectrum method.

7. The target detection method based on remote sensing images according to claim 1, characterized in that: The method for determining the target detection strategy of the target area is: Determine the detection deviation times of different detection deviation targets in different spectral detection combinations based on the detection deviation situations of different detection deviation targets in different spectral detection combinations, and determine the target deviation coefficients of different detection deviation targets in different spectral detection combinations using the preset deviation coefficients corresponding to the detection deviation times; Determining target weight coefficients of different detection deviation targets based on the number proportions of different detection deviation targets in the target area; The detection deviation values ​​of different spectral detection combinations are determined according to the target weight coefficients of different detection deviation targets and the target deviation coefficients of different detection deviation targets in different spectral detection combinations, and the matching spectral detection combination of the target area is determined in combination with the number of spectrum types in the different spectral detection combinations, and the detection processing of the detection targets in the target area is performed using the matching spectral detection combination.

8. The target detection method based on remote sensing images according to claim 7, characterized in that: The method for determining the matching spectral detection combination of the target area is: Determine preset analytical complexity coefficients corresponding to different spectral detection combinations according to the number of types of spectra in different spectral detection combinations; A matching deviation value is determined according to the detection deviation values ​​of different spectral detection combinations and an average value of a preset analytical complexity coefficient, and the matching spectral detection combination of the target area is determined using the matching deviation value.

9. The target detection method based on remote sensing images according to claim 7, characterized in that: The matching spectral detection combination of the target area is a spectral detection combination with a minimum matching deviation value.

10. A computer system comprising: A memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that when the processor runs the computer program, a target detection method based on remote sensing images as described in any one of claims 1-9 is executed.

Images