Image processing method and system for remote-sensing unmanned aerial vehicle for intelligent transportation construction data collection

Abstract

The present application relates to the technical field of transportation construction, and relates to an image processing method and system for a remote-sensing unmanned aerial vehicle for intelligent transportation construction data collection. The method comprises: acquiring first image information and construction requirement information; on the basis of the construction requirement information, retrieving image requirement benchmark information corresponding to the construction requirement information; on the basis of a preset image feature extraction method, performing analysis processing on the image requirement benchmark information, so as to form benchmark image feature information; on the basis of a preset image feature comparison method, performing analysis processing on image information collected by an unmanned aerial vehicle and the benchmark image feature information, so as to form collected-image comparison result information; and on the basis of a preset image output analysis method, performing analysis processing on the collected-image comparison result information, so as to output successfully-compared image output information. The present application has the effect of facilitating the subsequent rapid analysis of images collected by a remote-sensing unmanned aerial vehicle.

Description

Remote sensing drone image processing method and system for smart transportation construction data collection

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on October 7, 2023, with application number 2023112877263 and invention name “Remote Sensing UAV Image Processing Method and System for Smart Transportation Construction Data Collection”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of traffic construction technology, and in particular to a remote sensing drone image processing method and system for collecting data for smart traffic construction. Background Art

[0003] Transportation construction refers to the construction, building, maintenance, and management of transportation infrastructure, including roads, railways, pipelines, cableways, bridges, and tunnels. Smart transportation construction refers to the application of unmanned, intelligent construction to transportation infrastructure projects.

[0004] In related technologies, due to the advantages of drones such as maneuverability, flexibility, precision, thoroughness and detailed measurement, remote sensing drones are generally used for road measurement during smart transportation construction. Remote sensing drones collect a large number of images of road conditions in different terrains from various angles. After the remote sensing drones transmit the collected images to the processing system, the processing system processes the collected data and construction requirements, and plans the optimal plan to facilitate subsequent construction.

[0005] Regarding the above-mentioned related technologies, the applicant found the following defects: when remote sensing drones are used in the process of smart transportation construction, images are generally collected by the remote sensing drones and transmitted to the processing system, and then the processing system processes the images. The number of images collected by the remote sensing drones generally increases with time, which causes the processing system to need to analyze a large number of images, which makes it inconvenient to quickly analyze the images collected by the remote sensing drones.

[0006] Summary of the Invention

[0007] In order to facilitate the subsequent rapid analysis of images collected by remote sensing drones, this application provides a remote sensing drone image processing method and system for smart transportation construction data collection.

[0008] In the first aspect, this application provides a remote sensing drone image processing method for smart transportation construction data collection, which adopts the following technical solutions:

[0009] A remote sensing drone image processing method for collecting smart transportation construction data includes:

[0010] The drone collects image information, and uses the image information collected by the drone as the first image information;

[0011] The first image information and the construction requirement information are input into an image processing device including a memory and a processor, so as to:

[0012] Retrieving image requirement benchmark information corresponding to the construction requirement information according to the construction requirement information;

[0013] Analyzing and processing the image requirement reference information according to a preset image feature extraction method to form reference image feature information;

[0014] Analyzing and processing the first image information and the reference image feature information according to a preset image feature comparison method to generate collected image comparison result information;

[0015] The collected image comparison result information is analyzed and processed according to a preset image output analysis method to obtain successful comparison image output information, and the image processing device outputs the successful comparison image output information.

[0016] By adopting the above technical solution, the image information and construction requirement information collected by the UAV are acquired, the image requirement benchmark information is retrieved through the construction requirement information, the image requirement benchmark information is analyzed and processed by the image feature extraction method to form the benchmark image feature information, the image information collected by the UAV and the benchmark image feature information are analyzed and processed by the image feature comparison method to form the collected image comparison result information, and the collected image comparison result information is analyzed and processed by the image output analysis method to output the comparison successful image output information and output it, thereby facilitating the subsequent rapid analysis of the images collected by the remote sensing UAV.

[0017] Secondly, this application provides a remote sensing drone image processing system for smart transportation construction data collection, which adopts the following technical solutions:

[0018] Remote sensing drone image processing system for smart transportation construction data collection, including:

[0019] The acquisition module is used to obtain the image information collected by the drone, construction demand information and the flight status information of the drone;

[0020] A memory for storing a program of the remote sensing drone image processing method for intelligent transportation construction data collection as described in any one of the first aspects;

[0021] The processor and the program in the memory can be loaded and executed by the processor and implement the remote sensing drone image processing method for smart transportation construction data collection as described in any one of the first aspects.

[0022] In summary, this application includes at least one of the following beneficial technical effects:

[0023] 1. Acquire image information and construction requirement information collected by the UAV, retrieve image requirement benchmark information based on the construction requirement information, analyze and process the image requirement benchmark information using an image feature extraction method to form benchmark image feature information, analyze and process the image information collected by the UAV and the benchmark image feature information using an image feature comparison method to form collected image comparison result information, analyze and process the collected image comparison result information using an image output analysis method to output successful comparison image output information, thereby facilitating subsequent rapid analysis of images collected by the remote sensing UAV;

[0024] 2. Retrieve image requirement device type information and image requirement environment information based on image requirement benchmark information, obtain device type feature information through analysis of image requirement device type information, obtain environment feature information through analysis of image requirement environment information, obtain benchmark image comprehensive feature information through analysis of device type feature information and image type feature information, and use the benchmark image comprehensive feature information as benchmark image feature information, thereby improving the accuracy of the obtained benchmark image feature information;

[0025] 3. By acquiring the UAV flight status information, and analyzing and processing the UAV flight status information through the flight status impact analysis method to form the flight status impact feature information, the flight status impact feature information is compared and deleted through the UAV collected image information and the collected image impact adjustment information is generated, and the baseline image feature information and the collected image impact adjustment information are analyzed and processed through the image feature similarity analysis method to form the collected image feature similarity, and then it is judged whether the collected image feature similarity is less than the preset feature baseline similarity. When it is less than, the preset image no similarity result information is output and used as the collected image comparison result information. When it is not less than, the collected image similarity result information is obtained through the collected image feature similarity and the UAV collected image information analysis, and the collected image similarity result information is used as the collected image comparison result information, thereby improving the accuracy of the obtained collected image comparison result information.

[0026] Figures in the specification

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0028] Figure 1 is a flow chart of a method for remote sensing drone image processing for smart transportation construction data collection according to an embodiment of the present application.

[0029] FIG2 is a flow chart of a method for analyzing and processing image requirement reference information to form reference image feature information according to a preset image feature extraction method in an embodiment of the present application.

[0030] FIG3 is a flow chart of a method for analyzing and processing drone-collected image information and reference image feature information according to a preset image feature comparison method to form collected image comparison result information according to an embodiment of the present application.

[0031] FIG4 is a flow chart of a method for analyzing and processing UAV flight status information to form flight status impact characteristic information according to a preset flight status impact analysis method in an embodiment of the present application.

[0032] FIG5 is a flow chart of a method for analyzing and processing reference image feature information and captured image impact adjustment information to form captured image feature similarity according to a preset image feature similarity analysis method in an embodiment of the present application.

[0033] FIG6 is a flow chart of a method for analyzing and processing collected image comparison result information according to a preset image output analysis method to output comparison successful image output information in an embodiment of the present application.

[0034] FIG7 is a flow chart of a method for analyzing and processing similar feature type information and collected image comparison result information according to a preset feature type output analysis method in an embodiment of the present application to form feature type output information.

[0035] FIG8 is a flow chart of a method for analyzing and processing similar feature type information to form single type construction type information according to a preset single type construction type analysis method in an embodiment of the present application.

[0036] FIG9 is a flow chart of a method for analyzing and processing similar feature category information and single-category construction category information to form construction category composite information according to a preset construction category composite analysis method in an embodiment of the present application.

[0037] Figure 10 is a system flow chart of remote sensing drone image processing for smart transportation construction data collection in an embodiment of the present application.

[0038] Reference numerals: 1, acquisition module; 2, memory; 3, processor. DETAILED DESCRIPTION

[0039] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0040] 1 , the present application discloses a remote sensing drone image processing method for collecting smart traffic construction data, which includes:

[0041] Step S100: The drone collects image information, uses the image information collected by the drone as first image information, and inputs the first image information and construction requirement information into an image processing device including a memory and a processor, so that the image processing device executes subsequent steps S200 to S500.

[0042] Among them, the image information collected by drones refers to the image information collected by remote sensing drones that collect data when conducting smart transportation construction. The image information collected by drones is collected and obtained by remote sensing drones. The construction demand information refers to the current demand information when conducting smart transportation construction. The construction demand information is obtained through pre-input by the operator.

[0043] Step S200: Retrieve image requirement benchmark information corresponding to the construction requirement information according to the construction requirement information.

[0044] The image requirement benchmark information refers to the benchmark image information currently required for smart transportation construction. This image requirement benchmark information is retrieved from a database that stores this information. Retrieving this image requirement benchmark information facilitates subsequent use.

[0045] Step S300: analyzing and processing the image requirement reference information according to a preset image feature extraction method to form reference image feature information.

[0046] The reference image feature information refers to the reference feature information in the currently required reference image, and the image feature extraction method refers to a method for extracting features in an image. The image feature extraction method is obtained by querying a database storing image feature extraction methods.

[0047] The image requirement benchmark information is analyzed and processed by the image feature extraction method to form benchmark image feature information, which is convenient for subsequent use of the benchmark image feature information.

[0048] Step S400: analyzing and processing the first image information and the reference image feature information according to a preset image feature comparison method to generate collected image comparison result information.

[0049] Among them, the collected image comparison result information refers to the result information after the collected image is compared with the features, the image feature comparison method refers to the method used to compare the features of the image, and the image feature comparison method is queried and obtained from a database storing the image feature comparison method.

[0050] The image feature comparison method is used to analyze and process the image information collected by the drone and the reference image feature information, thereby forming the collected image comparison result information, which is convenient for subsequent use.

[0051] Step S500: analyzing and processing the collected image comparison result information according to a preset image output analysis method to obtain successful comparison image output information, and the image processing device outputs the successful comparison image output information.

[0052] The image output analysis method refers to an analysis method for outputting an image, and the image output analysis method is retrieved from a database storing image output analysis methods. The successfully compared image output information refers to output information for outputting a successfully compared image.

[0053] The collected image comparison result information is analyzed and processed by the image output analysis method, so as to output the successful comparison image output information, thereby performing pre-feature comparison processing on the images collected by the remote sensing UAV, and outputting the successfully compared images, thereby facilitating the subsequent rapid analysis of the images collected by the remote sensing UAV.

[0054] In step S300 shown in FIG1 , in order to further ensure the rationality of the reference image feature information, it is necessary to perform further separate analysis and calculation on the reference image feature information, which is specifically described in detail through the steps shown in FIG2 .

[0055] 2 , analyzing and processing the image requirement reference information according to the preset image feature extraction method to form reference image feature information includes the following steps:

[0056] Step S310: Retrieve image requirement device type information and image requirement environment information corresponding to the image requirement benchmark information according to the image requirement benchmark information.

[0057] The image-required device type information refers to the type of equipment currently required for smart transportation construction, and is retrieved from a database storing such information. The image-required environment information refers to the environment currently required for smart transportation construction, and is retrieved from a database storing such information.

[0058] The image requirement device type information and the image requirement environment information are retrieved through the image requirement benchmark information, thereby facilitating the subsequent acquisition of the image requirement device type information and the image requirement environment information.

[0059] Step S320: Analyze and obtain device type feature information corresponding to the image requirement device type information based on the correspondence between the image requirement device type information and the preset device type feature information.

[0060] The device type characteristic information refers to characteristic information used to indicate the currently required device, and the device type characteristic information is obtained by querying from a database storing the device type characteristic information.

[0061] The device type feature information is obtained by analyzing the device type information required by the image, so as to facilitate the subsequent use of the device type feature information.

[0062] Step S330: Analyze and obtain environmental feature information corresponding to the image requirement environmental information according to the correspondence between the image requirement environmental information and the preset environmental feature information.

[0063] The environmental characteristic information refers to characteristic information of the current demand environment, and the environmental characteristic information is obtained by querying a database storing the environmental characteristic information.

[0064] The environmental feature information is obtained by analyzing the image requirement environmental information, so as to facilitate the subsequent use of the image requirement environmental information.

[0065] Step S340: According to the correspondence between the device type feature information, the environment feature information and the preset reference image comprehensive feature information, analyze and obtain the reference image comprehensive feature information corresponding to the device type feature information and the environment feature information, and use the reference image comprehensive feature information as the reference image feature information.

[0066] The reference image comprehensive feature information refers to comprehensive feature information in the reference image, and the reference image comprehensive feature information is obtained by querying from a database storing the reference image comprehensive feature information.

[0067] The comprehensive feature information of the benchmark image is obtained by analyzing the device type feature information and the image type feature information, and the comprehensive feature information of the benchmark image is used as the benchmark image feature information, so that the obtained benchmark image feature information is affected by the device type and environment, thereby improving the accuracy of the obtained benchmark image feature information.

[0068] In step S400 shown in FIG1 , in order to further ensure the rationality of the collected image comparison result information, it is necessary to perform further separate analysis and calculation on the collected image comparison result information, which is specifically described in detail through the steps shown in FIG3 .

[0069] 3 , analyzing and processing the first image information and the reference image feature information according to the preset image feature comparison method to generate collected image comparison result information includes the following steps:

[0070] Step S410: Obtain the UAV flight status information.

[0071] Among them, the drone flight status information refers to the flight status information used to indicate the remote sensing drone when collecting data. The drone flight status information is detected and obtained through sensors preset on the remote sensing drone.

[0072] Step S420: Analyze and process the UAV flight status information according to a preset flight status impact analysis method to form flight status impact characteristic information.

[0073] Among them, the flight state impact characteristic information refers to the impact characteristic information caused by the flight state of the remote sensing UAV when collecting data, and the flight state impact analysis method refers to an analysis method used to analyze the impact caused by the flight state of the remote sensing UAV when collecting data. The flight state impact analysis method is queried and obtained from a database storing the flight state impact analysis method.

[0074] The flight status information of the UAV is analyzed and processed through the flight status impact analysis method to form flight status impact feature information, which is convenient for subsequent use of the flight status impact feature information.

[0075] Step S430: comparing the flight status impact characteristic information based on the first image information and deleting the second image information that is consistent with the flight status impact characteristic information, and using the third image information after deleting the second image information as the collected image impact adjustment information.

[0076] Among them, by comparing the image information collected by the drone with the flight status impact characteristic information, and deleting the image information consistent with the flight status impact characteristic information in the image information collected by the drone, and using the image information collected by the drone after deleting the image information as the collected image impact adjustment information, it is convenient to use the collected image impact adjustment information later.

[0077] Step S440: analyzing and processing the reference image feature information and the collected image impact adjustment information according to a preset image feature similarity analysis method to form a collected image feature similarity.

[0078] Among them, the captured image feature similarity refers to the similarity when the features in the captured image are similar to the features in the reference image, the image feature similarity analysis method refers to the analysis method used to analyze the feature similarity in the image, and the image feature similarity analysis method refers to querying and obtaining from a database storing the image feature similarity analysis method.

[0079] The reference image feature information and the acquired image impact adjustment information are analyzed and processed by the image feature similarity analysis method, thereby forming the acquired image feature similarity for subsequent use.

[0080] Step S450: Determine whether the similarity of the collected image features is less than a preset feature reference similarity. If yes, proceed to step S460; if not, proceed to step S470.

[0081] The feature baseline similarity refers to the baseline similarity when features are similar, and the feature baseline similarity is obtained by querying a database storing the feature baseline similarity.

[0082] By judging whether the feature similarity of the collected image is less than the preset feature reference similarity, it is judged whether the collected image meets the current requirements.

[0083] Step S460: Outputting the preset image no similarity result information as the collected image comparison result information.

[0084] The image no similarity result information refers to result information indicating that no similarity exists between the images. The image no similarity result information is obtained by querying a database storing the image no similarity result information.

[0085] When the feature similarity of the acquired image is less than the preset feature baseline similarity, it means that the image acquired at this time does not meet the current requirements, so the preset image no similarity result information is output and used as the acquired image comparison result information, thereby improving the accuracy of the acquired image comparison result information.

[0086] Step S470: According to the correspondence between the acquired image feature similarity, the first image information and the preset acquired image similarity result information, the acquired image similarity result information corresponding to the acquired image feature similarity and the first image information is analyzed and obtained, and the acquired image similarity result information is used as the acquired image comparison result information.

[0087] The collected image similarity result information refers to result information indicating that similarity exists between the collected images. The collected image similarity result information is obtained by querying a database storing the collected image similarity result information.

[0088] When the similarity of the collected image features is not less than the preset feature baseline similarity, it means that the image collected at this time meets the current requirements. Therefore, the collected image similarity result information is obtained by analyzing the collected image feature similarity and the drone collected image information, and the collected image similarity result information is used as the collected image comparison result information, thereby improving the accuracy of the obtained collected image comparison result information.

[0089] The flight status information of the UAV is acquired, and the flight status information of the UAV is analyzed and processed by a flight status impact analysis method to form flight status impact feature information. The flight status impact feature information is compared and deleted by the UAV collected image information to generate collected image impact adjustment information. The benchmark image feature information and the collected image impact adjustment information are analyzed and processed by an image feature similarity analysis method to form collected image feature similarity. Then, it is judged whether the collected image feature similarity is less than a preset feature benchmark similarity. When it is less than, the preset image no similarity result information is output as the collected image comparison result information. When it is not less than, the collected image similarity result information is obtained by analyzing the collected image feature similarity and the UAV collected image information, and the collected image similarity result information is used as the collected image comparison result information, thereby improving the accuracy of the obtained collected image comparison result information.

[0090] In step S420 shown in FIG3 , in order to further ensure the rationality of the flight status impact characteristic information, it is necessary to perform further separate analysis and calculation on the flight status impact characteristic information, which is specifically described in detail through the steps shown in FIG4 .

[0091] 4 , analyzing and processing the UAV flight state information according to the preset flight state impact analysis method to form flight state impact characteristic information includes the following steps:

[0092] Step S421: retrieve the current weather condition information and the current altitude value corresponding to the UAV flight status information according to the UAV flight status information.

[0093] The drone's flight status information includes the current weather information and the current altitude. The current weather information refers to the weather information at the remote sensing drone's current location, which is retrieved from a database storing current weather information. The current altitude refers to the altitude at the remote sensing drone's current location, which is retrieved from a database storing current altitude values.

[0094] The current weather condition information and the current altitude value are retrieved through the UAV flight status information, so as to facilitate the subsequent use of the current weather condition information and the current altitude value.

[0095] Step S422: Analyze and obtain the current weather impact characteristic information corresponding to the current weather condition information based on the correspondence between the current weather condition information and the preset current weather impact characteristic information.

[0096] The current weather impact characteristic information refers to the impact characteristic information generated by the weather at the current time, and the current weather impact characteristic information is obtained by querying from a database storing the current weather impact characteristic information.

[0097] The current weather condition information is analyzed to obtain the current weather impact characteristic information, thereby facilitating the subsequent use of the current weather impact characteristic information.

[0098] Step S423: Analyze and obtain the altitude impact characteristic information corresponding to the current altitude value according to the corresponding relationship between the current altitude value and the preset altitude impact characteristic information.

[0099] The height impact characteristic information refers to the impact characteristic information generated by the height of the remote sensing UAV's location at the current time, and the height impact characteristic information is obtained by querying a database storing the height impact characteristic information.

[0100] The height impact characteristic information is obtained by analyzing the current height value, so as to facilitate the subsequent use of the height impact characteristic information.

[0101] Step S424: According to the correspondence between the current weather impact characteristic information, the altitude impact characteristic information and the preset UAV comprehensive impact characteristic information, analyze and obtain the UAV comprehensive impact characteristic information corresponding to the current weather impact characteristic information and the altitude impact characteristic information, and use the UAV comprehensive impact characteristic information as the flight status impact characteristic information.

[0102] Among them, the comprehensive impact characteristic information of drones refers to the comprehensive impact characteristic information generated by remote sensing drones when collecting data. The comprehensive impact characteristic information of drones is queried and obtained from a database that stores the comprehensive impact characteristic information of drones.

[0103] The comprehensive impact characteristic information of the UAV is obtained by analyzing the current weather impact characteristic information and the altitude impact characteristic information, and the comprehensive impact characteristic information of the UAV is used as the flight status impact characteristic information, so that the obtained flight status impact characteristic information is affected by the weather and altitude, thereby improving the accuracy of the obtained flight status impact characteristic information.

[0104] In step S440 shown in FIG3 , in order to further ensure the rationality of the similarity of the collected image features, it is necessary to perform further separate analysis and calculation on the similarity of the collected image features, which is specifically described in detail through the steps shown in FIG5 .

[0105] 5 , analyzing and processing the reference image feature information and the collected image influence adjustment information according to the preset image feature similarity analysis method to form the collected image feature similarity includes the following steps:

[0106] Step S441: comparing the reference image feature information with the acquired image impact adjustment information, and analyzing and obtaining the similarity between the reference image feature information and the acquired image impact adjustment information as the initial feature similarity.

[0107] Among them, the feature initial similarity refers to the initial similarity when there is similarity in the features. By comparing the baseline image feature information with the acquired image impact adjustment information, the similarity between the baseline image feature information and the acquired image impact adjustment information is analyzed and obtained and used as the feature initial similarity, thereby facilitating the subsequent use of the feature initial similarity.

[0108] Step S442: Determine whether the initial feature similarity is greater than a preset feature reference similarity. If yes, proceed to step S443; if no, proceed to step S444.

[0109] Here, by judging whether the initial similarity of the features is greater than the preset feature reference similarity, it is judged whether the similarity reference requirement is met when the features are similar.

[0110] Step S443: taking the initial feature similarity as the captured image feature similarity.

[0111] Among them, when the initial feature similarity is greater than the preset feature baseline similarity, it means that the features are similar and meet the similarity baseline requirements. Therefore, the initial feature similarity is used as the feature similarity of the acquired image, thereby improving the accuracy of the acquired feature similarity of the acquired image.

[0112] Step S444: Compare the baseline image feature information with the acquired image impact adjustment information, analyze and obtain the similar area between the baseline image feature information and the acquired image impact adjustment information as the actual similar area information of the acquired image, and use the similar baseline image feature information as the baseline image similar feature information.

[0113] The actual similar region information of the acquired image refers to the region information corresponding to the actual similarity when similarity exists in the acquired image, and the similar feature information of the reference image refers to the reference feature information corresponding to the similarity when similarity exists in the acquired image.

[0114] When the initial similarity of the feature is not greater than the preset feature baseline similarity, it means that the similarity of the features at this time has not yet met the similarity baseline requirements. Therefore, by comparing the baseline image feature information with the acquired image impact adjustment information, the similar area between the baseline image feature information and the acquired image impact adjustment information is analyzed and obtained as the actual similar area information of the acquired image, and the similar baseline image feature information is used as the baseline image similar feature information, so as to facilitate the subsequent use of the actual similar area information of the acquired image and the baseline image similar feature information.

[0115] Step S445: Analyze and obtain the similar feature remaining area information corresponding to the actual similar area information of the captured image and the similar feature information of the reference image based on the correspondence between the actual similar area information of the captured image, the similar feature information of the reference image and the preset similar feature remaining area information.

[0116] The similar feature remaining area information refers to the remaining area information of the reference feature when it is similar to the captured image feature except for the actual similarity. The similar feature remaining area information is obtained by querying a database storing similar feature remaining area information.

[0117] By collecting the actual similar area information of the image and analyzing the similar feature information of the reference image, the similar feature remaining area information is obtained, thereby facilitating the subsequent use of the similar feature remaining area information.

[0118] Step S446: according to the similar feature remaining region information, retrieve the similar feature remaining region area value corresponding to the similar feature remaining region information.

[0119] The area value of the remaining region with similar features refers to the area value corresponding to the remaining region when similar features exist, and the area value of the remaining region with similar features is obtained by querying a database storing the area values ​​of the remaining regions with similar features.

[0120] The area value of the similar feature remaining region is retrieved through the similar feature remaining region information, thereby facilitating the subsequent use of the similar feature remaining region area value.

[0121] Step S447: Retrieve the flight state impact characteristic area value corresponding to the flight state impact characteristic information according to the flight state impact characteristic information.

[0122] The flight state impact characteristic area value refers to the area value corresponding to the impact characteristic of the flight state of the remote sensing UAV, and the flight state impact characteristic area value is obtained by querying from a database storing the flight state impact characteristic area values.

[0123] The flight status impact characteristic area value is retrieved through the flight status impact characteristic information, thereby facilitating subsequent use of the flight status impact characteristic area value.

[0124] Step S448: According to the correspondence between the similar feature remaining area value, the flight status influence feature area value and the preset similar feature remaining area influence value, analyze and obtain the similar feature remaining area influence value corresponding to the similar feature remaining area value and the flight status influence feature area value.

[0125] The similar feature residual region influence value refers to the influence degree value when the residual region has an influence, and the similar feature residual region influence value is obtained by querying from a database storing similar feature residual region influence values.

[0126] The similar feature remaining area impact value is obtained by analyzing the similar feature remaining area value and the flight status impact feature area value, which is convenient for subsequent use.

[0127] Step S449: According to the correspondence between the residual area influence value of the similar feature, the initial feature similarity and the preset feature influence adjustment similarity, analyze and obtain the feature influence adjustment similarity corresponding to the residual area influence value of the similar feature and the initial feature similarity, and use the feature influence adjustment similarity as the feature similarity of the acquired image.

[0128] The feature impact adjusted similarity refers to the similarity after the similarity is adjusted when the remaining area has an impact, and the feature impact adjusted similarity is obtained by querying a database storing the feature impact adjusted similarity.

[0129] The feature influence adjustment similarity is obtained by analyzing the residual area influence value of similar features and the initial similarity of features, and the feature influence adjustment similarity is used as the feature similarity of the acquired image. Therefore, when the features are similar but have not yet met the similarity benchmark requirements, the influence of the residual area influence value of similar features is analyzed and obtained, thereby reducing the influence of the flight status on the feature information, thereby improving the accuracy of the acquired image feature similarity.

[0130] In step S500 shown in FIG. 1 , in order to further ensure the rationality of the output information of the successfully compared image, further separate analysis and calculation are required for the output information of the successfully compared image, which is specifically described in detail through the steps shown in FIG. 6 .

[0131] 6 , analyzing and processing the collected image comparison result information according to the preset image output analysis method to output the comparison successful image output information includes the following steps:

[0132] Step S510: Determine whether the collected image comparison result information is the preset image no similarity result information. If yes, execute step S520; if not, execute step S530.

[0133] Here, by judging whether the collected image comparison result information is the preset image no-similar result information, it is judged whether further processing is required when outputting.

[0134] Step S520: Continue to obtain image information collected by the drone.

[0135] When the collected image comparison result information indicates that there is no similar result information for the preset image, it indicates that no further processing is required when outputting the image, so the first image information is continuously acquired.

[0136] Step S530: Retrieve the collected image comparison similarity feature information corresponding to the collected image comparison result information according to the collected image comparison result information.

[0137] The collected image comparison similarity feature information refers to similarity feature information when similarity exists after the collected images are compared. The collected image comparison similarity feature information is obtained by querying a database storing the collected image comparison similarity feature information.

[0138] When the collected image comparison result information is not the preset image no similarity result information, it means that further processing is required when outputting at this time. Therefore, the collected image comparison similarity feature information is retrieved through the collected image comparison result information, so as to facilitate the subsequent use of the collected image comparison similarity feature information.

[0139] Step S540: Retrieve similar feature category information corresponding to the similar feature information of the collected image comparison according to the similar feature information of the collected image comparison.

[0140] The similar feature category information refers to category information corresponding to similar features, and the similar feature category information is obtained by querying from a database storing similar feature category information.

[0141] By collecting images and comparing similar feature information, similar feature type information is retrieved, thereby facilitating subsequent use of the similar feature type information.

[0142] Step S550: Analyze and process the similar feature type information and the collected image comparison result information according to a preset feature type output analysis method to form feature type output information, and use the feature type output information as the successfully compared image output information.

[0143] Among them, feature type output information refers to output information used for output based on feature types, feature type output analysis method refers to an analysis method used for analyzing feature type output information, and the feature type output analysis method is obtained by querying a database storing feature type output analysis methods.

[0144] The similar feature type information and the collected image comparison result information are analyzed and processed by the feature type output analysis method to form feature type output information, and the feature type output information is used as the successful comparison image output information, so that the obtained successful comparison image output information is affected by the similar feature type information, thereby improving the accuracy of the obtained successful comparison image output information.

[0145] In step S550 shown in FIG6 , in order to further ensure the rationality of the feature type output information, it is necessary to perform further separate analysis and calculation on the feature type output information, which is specifically described in detail through the steps shown in FIG7 .

[0146] 7 , analyzing and processing similar feature type information and collected image comparison result information according to a preset feature type output analysis method to form feature type output information includes the following steps:

[0147] Step S551: Determine whether there is only one similar feature type information. If yes, execute step S552; if no, execute step S553.

[0148] Here, by judging whether there is only one similar feature type information, it is judged whether the output information needs to be further processed.

[0149] Step S552: According to the correspondence between the similar feature category information, the collected image comparison result information and the preset single category output information, analyze and obtain the single category output information corresponding to the similar feature category information and the collected image comparison result information, and use the single category output information as the feature category output information.

[0150] The single-type output information refers to output information for instructing to perform a single-type output, and the single-type output information is retrieved from a database storing the single-type output information.

[0151] When there is only one similar feature type information, it means that no further processing of the output information is required at this time. Therefore, single type output information is obtained by analyzing the similar feature type information and the collected image comparison result information, and the single type output information is used as the feature type output information, thereby improving the accuracy of the obtained feature type output information.

[0152] Step S553: ​​Analyze and process the similar feature category information according to a preset single-category construction category analysis method to form single-category construction category information.

[0153] Among them, single-type construction category information refers to the construction category information corresponding to the characteristics of a single type, and the single-type construction category analysis method refers to the analysis method used to analyze the single-type construction category information. The single-type construction category analysis method is queried and obtained from a database storing the single-type construction category analysis method.

[0154] When there is more than one similar feature type information, it means that the output information needs to be further processed. Therefore, the similar feature type information is analyzed and processed through a single type construction category analysis method to form a single type construction category information for subsequent use.

[0155] Step S554 : Analyze and process the similar feature category information and the single-category construction category information according to a preset construction category composite analysis method to generate construction category composite information.

[0156] Among them, the construction category type composite information refers to the information after the types are composited according to the construction category, the construction category type composite analysis method refers to the analysis method used to analyze the construction category type composite information, and the construction category type composite analysis method is queried and obtained from a database storing the construction category type composite analysis method.

[0157] The similar feature type information and single type construction type information are analyzed and processed by the construction type composite analysis method, thereby forming construction type composite information, which is convenient for subsequent use of the construction type composite information.

[0158] Step S555: According to the correspondence between the composite information of the construction category type, the collected image comparison result information and the preset composite type construction output information, analyze and obtain the composite type construction output information corresponding to the composite information of the construction category type and the collected image comparison result information, and use the composite type construction output information as the feature type output information.

[0159] The composite type construction output information refers to output information that is output based on a composite type of construction category, and the composite type construction output information is obtained by querying a database storing the composite type construction output information.

[0160] Composite type construction output information is obtained by analyzing the composite information of construction category types and the collected image comparison result information, and the composite type construction output information is used as the feature type output information, so that the obtained feature type output information is affected by the composite information of construction category types, thereby improving the accuracy of the obtained feature type output information. In other words, by determining whether there is only one similar feature type information, when there is only one, single type output information is obtained by analyzing the similar feature type information and the collected image comparison result information, and the single type output information is used as the feature type output information; when there is more than one, the similar feature type information is analyzed and processed using a single type construction category analysis method to form single type construction category information, the similar feature type information and the single type construction category information are analyzed and processed using a construction category composite analysis method to form construction category composite information, the composite type construction output information is obtained by analyzing the composite information of construction category types and the collected image comparison result information, and the composite type construction output information is used as the feature type output information, thereby improving the accuracy of the obtained feature type output information.

[0161] In step S553 shown in FIG7 , in order to further ensure the rationality of the single type of construction category information, it is necessary to perform further separate analysis and calculation on the single type of construction category information, which is specifically explained in detail through the steps shown in FIG8 .

[0162] 8 , analyzing and processing similar feature type information to form single type construction type information according to a preset single type construction type analysis method includes the following steps:

[0163] Step S5531: arbitrarily select one of the similar feature category information as the similar feature single category information, and use the remaining similar feature category information as the similar feature remaining category information.

[0164] The similar feature single category information refers to category information used to indicate a single category in the similar feature, and the similar feature remaining category information refers to other remaining category information in the similar feature category information except the similar feature single category information.

[0165] By arbitrarily selecting one of the similar feature category information and using it as the similar feature single category information, and using the remaining similar feature category information as the similar feature remaining category information, the subsequent use of the similar feature single category information and the similar feature remaining category information is facilitated.

[0166] Step S5532: Retrieve the single-category initial construction category information corresponding to the similar feature single-category information according to the similar feature single-category information.

[0167] The single-category initial construction category information refers to initial category information for indicating a construction category corresponding to a single category, and the single-category initial construction category information is obtained by querying from a database storing the single-category initial construction category information.

[0168] The single-category initial construction category information is obtained through the single-category information with similar characteristics, thereby facilitating the subsequent use of the single-category initial construction category information.

[0169] Step S5533: Retrieve the initial category number value corresponding to the single category initial category information according to the single category initial category information.

[0170] The initial category type value refers to the type value of the types included in the initial category, and the initial category type value is obtained by querying a database storing the initial category type value.

[0171] The initial category type value is retrieved through the single category initial category information, so as to facilitate the subsequent use of the initial category type value.

[0172] Step S5534: according to the similar feature type information, retrieve the similar feature type value corresponding to the similar feature type information.

[0173] The number of similar feature types refers to the number of all types of similar features, and the number of similar feature types is obtained by querying a database storing the number of similar feature types.

[0174] The numerical values ​​of similar feature types are retrieved through similar feature type information, thereby facilitating the subsequent use of the numerical values ​​of similar feature types.

[0175] Step S5535: According to the correspondence between the numerical value of the number of similar feature types and the preset reference value of the number of types, the reference value of the number of types corresponding to the numerical value of the number of similar feature types is analyzed and obtained.

[0176] The reference value of the number of types refers to the reference value of the number of types corresponding to the tolerable construction category among all types in the similar features, and the reference value of the number of types is obtained by querying from a database storing the reference values ​​of the number of types.

[0177] The number of categories is analyzed by numerical analysis of similar feature categories to obtain the category number benchmark value, which is convenient for subsequent use of the category number benchmark value.

[0178] Step S5536: Determine whether the initial number of categories is greater than the reference number of categories. If yes, proceed to step S5537; if no, proceed to step S5538.

[0179] Among them, by judging whether the value of the initial category number is greater than the category number benchmark value, it is judged whether the initial construction category information of a single category meets the requirements.

[0180] Step S5537: Use the single-type initial construction category information as the single-type construction category information.

[0181] Among them, when the value of the number of initial categories is greater than the reference value of the number of categories, it means that the single-category initial construction category information meets the requirements at this time, so the single-category initial construction category information is used as the single-category construction category information.

[0182] Step S5538: reselect one of the similar feature category information as the similar feature single category information, and use the remaining similar feature category information as the similar feature remaining category information.

[0183] If the initial number of categories is less than the category number reference value, it indicates that the single-category initial construction category information does not meet the requirements. Therefore, one of the similar feature category information is reselected as the single similar feature category information, and the remaining similar feature category information is used as the remaining similar feature category information, thereby improving the accuracy of the acquired single-category construction category information. In step S554 shown in FIG7 , to further ensure the rationality of the composite construction category information, further separate analysis and calculation of the composite construction category information is required, as detailed in the steps shown in FIG9 .

[0184] 9 , analyzing and processing similar feature type information and single type construction type information according to a preset construction type composite analysis method to form construction type composite information includes the following steps:

[0185] Step S5541: retrieve the single-type construction requirement feature category information corresponding to the single-type construction category information according to the single-type construction category information.

[0186] The single-category construction requirement feature category information refers to the category information included in the construction category corresponding to the single-category feature, and the single-category construction requirement feature category information is queried and obtained from a database storing the single-category construction requirement feature category information.

[0187] The single type of construction demand feature type information is retrieved through the single type of construction category information, thereby facilitating the subsequent use of the single type of construction demand feature type information.

[0188] Step S5542: Determine whether the category information of the single construction requirement feature is consistent with the category information of the remaining similar features. If yes, execute step S5543; if not, execute step S5546.

[0189] Here, by judging whether there is consistency between the type information of a single type of construction requirement feature and the remaining type information of similar features, it is judged whether the features in the same construction requirement can be output simultaneously.

[0190] Step S5543: The category information in the category information of the single-category construction requirement feature that is consistent with the category information of the remaining category information of similar features is used as the category information with consistent features.

[0191] Consistent feature category information refers to category information when features are consistent. When a single-category construction requirement feature category information is consistent with the remaining category information for similar features, it indicates that the features of the same construction requirement can be output simultaneously. Therefore, the consistent category information between the single-category construction requirement feature category information and the remaining category information for similar features is treated as consistent feature category information, facilitating subsequent use of the consistent feature category information.

[0192] Step S5544: according to the correspondence between the similar feature remaining category information, the feature consistent category information and the preset feature distinguishing category information, analyze and obtain the feature distinguishing category information corresponding to the similar feature remaining category information and the feature consistent category information.

[0193] The feature-distinguishing category information refers to other category information in the remaining category information of similar features except for the feature-identical category information. The feature-distinguishing category information is obtained by querying a database storing the feature-distinguishing category information.

[0194] The feature distinguishing category information is obtained by analyzing the similar feature remaining category information and the feature consistent category information, so as to facilitate the subsequent use of the feature distinguishing category information.

[0195] Step S5545: According to the correspondence between the feature consistent category information, the feature distinguishing category information and the preset feature category composite information, analyze and obtain the feature category composite information corresponding to the feature consistent category information and the feature distinguishing category information, and use the feature category composite information as the construction category category composite information.

[0196] The feature type compound information refers to type information indicating the types of features after compounding, and the feature type compound information is obtained by querying from a database storing the feature type compound information.

[0197] Feature type composite information is obtained by analyzing feature consistent type information and feature distinguishing type information, and the feature type composite information is used as construction category type composite information, thereby improving the accuracy of the obtained construction category type composite information.

[0198] Step S5546: Jump to execute step S5538.

[0199] Among them, when there is no consistency between the type information of a single type of construction requirement feature and the remaining type information of similar features, it means that the features in the same construction requirement cannot be output at the same time, so the process jumps to step S5538.

[0200] The present application also provides an application scenario, which applies the above-mentioned remote sensing drone image processing method for smart transportation construction data collection. Specifically: the remote sensing drone image processing method for smart transportation construction data collection provided by this embodiment can be applied in the remote sensing drone image collection and processing scenario. The image collection and processing scenario includes an image collection link and an image processing link; the image enters the image processing link from the collection link, and the remote sensing drone image processing method for smart transportation construction data collection provided by this embodiment belongs to the image processing link. Specifically, in the image processing process, the drone is used to collect image information and construction demand information to obtain the image demand benchmark information, the image demand benchmark information is retrieved through the construction demand information, the image feature extraction method is used to analyze and process the image demand benchmark information to form benchmark image feature information, the image feature comparison method is used to analyze and process the drone collected image information and the benchmark image feature information to form collected image comparison result information, and the image output analysis method is used to analyze and process the collected image comparison result information to output the successfully compared image output information and output it.

[0201] 10 , based on the same inventive concept, an embodiment of the present invention provides a remote sensing drone image processing system for collecting smart transportation construction data, comprising:

[0202] A drone, configured to collect first image information;

[0203] Image processing equipment, including:

[0204] Acquisition module 1, used to acquire first image information, construction requirement information and UAV flight status information;

[0205] Memory 2, used to store a program of a remote sensing drone image processing method for intelligent transportation construction data collection as shown in any one of Figures 1 to 9;

[0206] Processor 3, the program in the memory can be loaded and executed by the processor and realize the remote sensing drone image processing method for smart transportation construction data collection as shown in any one of Figures 1 to 9.

[0207] By adopting the above technical solution, the acquisition module is used to obtain the image information, construction demand information and flight status information collected by the drone, and the processor is used to load and execute the program in the memory, thereby facilitating the subsequent rapid analysis of the images collected by the remote sensing drone.

[0208] Those skilled in the art will clearly understand that for the sake of convenience and brevity, the division of the above-mentioned functional modules is only used as an example for illustration. In actual applications, the above-mentioned 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. The specific working processes of the above-mentioned systems, devices, and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0209] The above are all preferred embodiments of the present application and are not intended to limit the scope of protection of this application. Unless otherwise stated, any feature disclosed in this specification (including the abstract and drawings) may be replaced by other equivalent or similar features. In other words, unless otherwise stated, each feature is merely an example of a series of equivalent or similar features.

Claims

1. A remote sensing drone image processing method for intelligent transportation construction data collection, characterized in that: include: The drone collects image information, uses the image information collected by the drone as first image information, and inputs the first image information and construction requirement information into an image processing device including a memory and a processor, so as to: Retrieving image requirement benchmark information corresponding to the construction requirement information according to the construction requirement information; Analyzing and processing the image requirement reference information according to a preset image feature extraction method to form reference image feature information; Analyzing and processing the first image information and the reference image feature information according to a preset image feature comparison method to form collected image comparison result information; The collected image comparison result information is analyzed and processed according to a preset image output analysis method to obtain successfully compared image output information, and the image processing device outputs the successfully compared image output information.

2. The remote sensing drone image processing method for intelligent transportation construction data collection according to claim 1 is characterized in that: Analyzing and processing the image requirement reference information according to the preset image feature extraction method to form reference image feature information includes: According to the image requirement benchmark information, image requirement device type information and image requirement environment information corresponding to the image requirement benchmark information are retrieved; According to the correspondence between the image requirement device type information and the preset device type characteristic information, the device type characteristic information corresponding to the image requirement device type information is analyzed and obtained; wherein the device type characteristic information is obtained by querying a database storing the device type characteristic information; According to the correspondence between the image requirement environment information and the preset environment feature information, the environment feature information corresponding to the image requirement environment information is analyzed and obtained; wherein the environment feature information is obtained by querying a database storing the environment feature information; According to the correspondence between the device type feature information, the environment feature information and the preset baseline image comprehensive feature information, the baseline image comprehensive feature information corresponding to the device type feature information and the environment feature information is analyzed and obtained, and the baseline image comprehensive feature information is used as the baseline image feature information; wherein the baseline image comprehensive feature information is queried and obtained from a database storing the baseline image comprehensive feature information.

3. The remote sensing drone image processing method for intelligent transportation construction data collection according to claim 2 is characterized in that: Analyzing and processing the first image information and the reference image feature information according to a preset image feature comparison method to form collected image comparison result information includes: Get the UAV flight status information; Analyze and process the UAV flight status information according to the preset flight status impact analysis method to form flight status impact characteristic information; Based on the first image information, the flight status affecting characteristic information is compared and the second image information that is consistent with the flight status affecting characteristic information is deleted, and the second image information is deleted. The third image information after the information is used as the acquisition image impact adjustment information; Analyze and process the reference image feature information and the collected image influence adjustment information according to a preset image feature similarity analysis method to form a collected image feature similarity; Determine whether the similarity of the collected image features is less than a preset feature reference similarity; If yes, the preset image has no similarity result information and is output as the collected image comparison result information; If not, then based on the correspondence between the acquired image feature similarity, the first image information and the preset acquired image similarity result information, analyze and obtain the acquired image similarity result information corresponding to the acquired image feature similarity and the first image information, and use the acquired image similarity result information as the acquired image comparison result information.

4. The remote sensing drone image processing method for intelligent transportation construction data collection according to claim 3 is characterized in that: The flight state information of the UAV is analyzed and processed according to the preset flight state impact analysis method to form the flight state impact characteristic information including: According to the UAV flight status information, retrieve the current weather condition information and the current altitude value corresponding to the UAV flight status information; According to the correspondence between the current weather condition information and the preset current weather impact characteristic information, analyzing and obtaining the current weather impact characteristic information corresponding to the current weather condition information; According to the correspondence between the current altitude value and the preset altitude influence characteristic information, analyzing and obtaining the altitude influence characteristic information corresponding to the current altitude value; According to the correspondence between the current weather impact characteristic information, the altitude impact characteristic information and the preset UAV comprehensive impact characteristic information, the UAV comprehensive impact characteristic information corresponding to the current weather impact characteristic information and the altitude impact characteristic information is analyzed and obtained, and the UAV comprehensive impact characteristic information is used as the flight status impact characteristic information.

5. The remote sensing drone image processing method for intelligent transportation construction data collection according to claim 3 is characterized in that: Analyzing and processing the reference image feature information and the collected image influence adjustment information according to the preset image feature similarity analysis method to form the collected image feature similarity includes: Based on the comparison between the reference image feature information and the acquired image impact adjustment information, the similarity between the reference image feature information and the acquired image impact adjustment information is analyzed and obtained as the feature initial similarity; Determine whether the initial feature similarity is greater than a preset feature baseline similarity; If yes, the initial feature similarity is used as the feature similarity of the acquired image; If not, then compare the reference image feature information with the acquired image impact adjustment information, analyze and obtain the similar area between the reference image feature information and the acquired image impact adjustment information as the actual similar area information of the acquired image, and use the similar reference image feature information as the reference image similar feature information; According to the correspondence between the actual similar area information of the acquired image, the similar feature information of the reference image and the preset similar feature residual area information, the actual similar area information of the acquired image is analyzed and obtained. and similar feature remaining area information corresponding to similar feature information of the reference image; According to the similar feature remaining area information, the similar feature remaining area value corresponding to the similar feature remaining area information is retrieved; Retrieving the flight state impact characteristic area value corresponding to the flight state impact characteristic information according to the flight state impact characteristic information; According to the corresponding relationship between the area value of the similar feature remaining area, the area value of the flight state influence feature and the preset similar feature remaining area influence value, the similar feature remaining area influence value corresponding to the area value of the similar feature remaining area and the area value of the flight state influence feature is analyzed and obtained; According to the correspondence between the residual area influence value of similar features, the initial feature similarity and the preset feature influence adjustment similarity, the feature influence adjustment similarity corresponding to the residual area influence value of similar features and the initial feature similarity is analyzed and obtained, and the feature influence adjustment similarity is used as the feature similarity of the acquired image.

6. The remote sensing drone image processing method for intelligent transportation construction data collection according to claim 3 is characterized in that: Analyzing and processing the collected image comparison result information according to the preset image output analysis method to output the comparison successful image output information includes: Determine whether the collected image comparison result information is the preset image without similar result information; If yes, continue to obtain the first image information; If not, then retrieve the collected image comparison similarity feature information corresponding to the collected image comparison result information according to the collected image comparison result information; Retrieving similar feature type information corresponding to the similar feature information compared with the collected image according to the similar feature information compared with the collected image; According to the preset feature type output analysis method, similar feature type information and collected image comparison result information are analyzed and processed to form feature type output information, and the feature type output information is used as the comparison successful image output information.

7. The remote sensing drone image processing method for intelligent transportation construction data collection according to claim 6 is characterized in that: Analyzing and processing similar feature type information and collected image comparison result information according to a preset feature type output analysis method to form feature type output information includes: Determine whether there is only one type of similar feature information; If yes, then according to the correspondence between the similar feature category information, the collected image comparison result information and the preset single category output information, analyze and obtain the single category output information corresponding to the similar feature category information and the collected image comparison result information, and use the single category output information as the feature category output information; If not, the similar feature type information is analyzed and processed according to the preset single type construction category analysis method to form single type construction category information; Analyze and process similar feature type information and single type construction type information according to a preset construction type composite analysis method to form construction type composite information; According to the composite information of construction category, the collected image comparison result information and the preset composite type The correspondence between the type of construction output information is analyzed to obtain the composite type of construction output information corresponding to the composite information of the construction category and the collected image comparison result information, and the composite type of construction output information is used as the feature type output information.

8. The remote sensing drone image processing method for intelligent transportation construction data collection according to claim 7 is characterized in that: According to the preset single-type construction category analysis method, similar feature category information is analyzed and processed to form single-type construction category information including: Randomly select one of the similar feature category information as the similar feature single category information, and use the remaining similar feature category information as the similar feature remaining category information; Retrieving the single-category initial construction category information corresponding to the single-category information of similar characteristics according to the single-category information of similar characteristics; According to the single-category initial category information, the initial category type number value corresponding to the single-category initial category information is retrieved; Retrieving the similar feature type number value corresponding to the similar feature type information according to the similar feature type information; According to the correspondence between the number of similar feature types and the preset number of types reference value, analyzing and obtaining the number of types reference value corresponding to the number of similar feature types; Determine whether the initial category number value is greater than the category number benchmark value; If yes, the single-type initial construction category information is used as the single-type construction category information; If not, one of the similar feature category information is reselected and used as the similar feature single category information, and the remaining similar feature category information is used as the similar feature remaining category information.

9. The remote sensing drone image processing method for intelligent transportation construction data collection according to claim 7 is characterized in that: According to the preset construction category composite analysis method, similar feature category information and single type construction category information are analyzed and processed to form construction category composite information including: Retrieving single-type construction demand feature category information corresponding to the single-type construction category information according to the single-type construction category information; Determine whether there is a consistency between the type information of a single type of construction demand feature and the remaining type information of similar features; If yes, the category information in the category information of the single type of construction demand feature that is consistent with the category information of the remaining similar features is taken as the category information with consistent features; According to the correspondence between the similar feature remaining category information, the feature consistent category information and the preset feature distinguishing category information, analyzing and obtaining the feature distinguishing category information corresponding to the similar feature remaining category information and the feature consistent category information; According to the correspondence between the feature consistent category information, the feature distinguishing category information and the preset feature category composite information, the feature category composite information corresponding to the feature consistent category information and the feature distinguishing category information is analyzed and obtained, and the feature category composite information is used as the construction category category composite information; If not, the process jumps to reselect one of the similar feature category information as the similar feature single category information, and uses the remaining similar feature category information as the similar feature remaining category information.

10. A remote sensing drone image processing system for intelligent transportation construction data collection, characterized in that: include: A drone, used for collecting first image information; Image processing equipment, including: An acquisition module (1) is used to acquire the first image information, construction requirement information and UAV flight status information; A memory (2) for storing a program of a remote sensing drone image processing method for intelligent transportation construction data collection according to any one of claims 1 to 9; A processor (3), wherein the program in the memory can be loaded and executed by the processor and implement the remote sensing drone image processing method for intelligent transportation construction data collection as described in any one of claims 1 to 9.

Images