Unmanned aerial vehicle image panoramic display method and system

Abstract

The invention is suitable for the technical field of image processing, and provides an unmanned aerial vehicle image panoramic display method and system. Comparing the position information with the detection area, judging a display mode according to a comparison position result, obtaining task requirements, and matching display contents according to the task requirements; the method comprises the steps of obtaining multiple pieces of display content, extracting key feature points in the display content, finding out a corresponding relation between images according to the key feature points, aligning the multiple pieces of display content through the corresponding relation, splicing the multiple pieces of display content, obtaining a user instruction, and adjusting the display content in real time according to the user instruction. Real-time data are obtained through an illumination intensity sensor, the exposure degree of the image is adjusted, and image data of the multiple unmanned aerial vehicles are processed through a chromatic aberration compensation and contrast optimization algorithm based on image analysis, so that the accuracy and efficiency of task execution are remarkably improved; and it is ensured that the displayed content is always highly matched with the task requirement and the user instruction.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of image processing, and particularly relates to a method and system for panoramic display of images of unmanned aerial vehicles. BACKGROUND

[0002] With the rapid development of unmanned aerial vehicle technology, its application in environmental monitoring, post-disaster assessment, agricultural inspection, urban management and other fields is gradually widespread. In these application scenarios, unmanned aerial vehicle image display technology plays an important role, especially in image acquisition, stitching, processing and display, which becomes the key to task execution and decision support. However, the traditional unmanned aerial vehicle image display technology still faces some challenges, especially in the changing flight environment and complex task requirements, how to ensure the accuracy, clarity and real-time of the display content has become a technical bottleneck in the field of unmanned aerial vehicle image display.

[0003] In the prior art, although there are image stitching-based technical methods, in the dynamic flight environment, the accuracy of image stitching and the adjustment of display content still have certain problems. For example, due to changes in light, flight angle and height, traditional image display methods often have problems such as uneven exposure, excessive color difference, unnatural image stitching, etc. In addition, the real-time adjustment capability of the existing technology for display content is relatively limited, users need to constantly adjust the viewing angle, area and resolution through manual operation, and it is difficult to adapt to environmental changes and task requirements in real time. Therefore, how to optimize image display through intelligent technology and dynamically adjust it according to flight path, task target and environmental changes is a key problem to be solved in the current unmanned aerial vehicle image display technology.

[0004] The background technology of the present application aims to solve the deficiencies in the existing unmanned aerial vehicle image display technology, and realizes high-quality image display through multi-sensor data fusion, real-time image optimization, intelligent display adjustment and other technical means, to meet the display requirements in different tasks and environments. By introducing light intensity sensors, depth sensors, meteorological sensors and other devices, combined with flight path data, task requirements and user instructions, automatic optimization and accurate adjustment of images are realized, which improves the real-time, accuracy and flexibility of image display, and promotes the further development of unmanned aerial vehicle image display technology. SUMMARY

[0005] The purpose of the embodiment of the present application is to provide a method for panoramic display of images of unmanned aerial vehicles, which aims to solve the problems raised in the third part of the background technology.

[0006] The embodiment of the present application is implemented as follows: a method for panoramic display of images of unmanned aerial vehicles, the method comprising: Obtaining sensor types, including RGB cameras, depth sensors, and weather sensors, which are used to collect data along the flight path, including location information, flight angle, flight speed, height, and environmental data. Comparing the location information with the detection area, determining the display method based on the comparison result, obtaining the task requirements, and matching the display content based on the task requirements. Obtaining multiple display contents, extracting key feature points in the display contents, finding corresponding relationships between images based on the key feature points, aligning multiple display contents based on the corresponding relationships, stitching multiple display contents, obtaining user instructions, and adjusting display contents in real time based on user instructions. Adjusting the exposure of the image based on real-time data obtained by the light intensity sensor, color difference compensation and contrast optimization algorithms based on image analysis, and processing image data from multiple drones.

[0007] Preferably, the step of comparing the location information with the detection area, determining the display method based on the comparison result, obtaining the task requirements, and matching the display content based on the task requirements, specifically includes: Obtaining key detection area information, comparing the location information with the detection area, and identifying the key features of the area if the drone is determined to be located in the key detection area. Obtaining the display method, which includes panoramic display and specific area display, determining the display method based on the comparison result, obtaining the task requirements, which include environmental monitoring, post-disaster evaluation, and inspection. Matching the display content based on the task requirements, which includes zooming in on details, real-time flight angle, and real-time flight height.

[0008] Preferably, the step of obtaining multiple display contents, extracting key feature points in the display contents, finding corresponding relationships between images based on the key feature points, aligning multiple display contents based on the corresponding relationships, stitching multiple display contents, obtaining user instructions, and adjusting display contents in real time based on user instructions, specifically includes: Obtaining multiple display contents, including different angles, different flight heights, and different lighting conditions, and extracting key feature points in the display contents. Finding corresponding relationships between images based on the key feature points, aligning multiple display contents based on the corresponding relationships, stitching multiple display contents, obtaining user instructions, which include voice instructions, gesture control, or APP adjustments. Adjusting display contents in real time based on user instructions, including adjusting the viewing angle, display area, and display content.

[0009] Preferably, the step of processing image data of multiple unmanned aerial vehicles through real-time data acquisition by a light intensity sensor, adjusting exposure of the image, color difference compensation and contrast optimization algorithm based on image analysis, specifically comprises: real-time data acquisition by a light intensity sensor, adjusting exposure of the image, color difference compensation and contrast optimization algorithm based on image analysis, wherein the optimization algorithm is adjusting hue, saturation and contrast of the image; adjusting resolution of the image according to requirements of the flight path and the task target, wherein the adjustment mode is improving resolution in a key area and reducing resolution in a non-key area; processing image data of multiple unmanned aerial vehicles, wherein the processing includes cooperative processing and storage, and optimizing display content according to historical task data and real-time environmental changes.

[0010] Preferably, the environmental data includes light and climate changes.

[0011] Another object of the embodiment of the application is to provide a panoramic display system for images of unmanned aerial vehicles, which comprises: a basic information acquisition module, which acquires types of sensors, wherein the sensors include an RGB camera, a depth sensor and a meteorological sensor, and the sensors are used to collect data in a flight path, and the sensor data includes position information, flight angle, flight speed, height and environmental data; a display module, which compares the position information with a detection area, judges a display mode according to a comparison result, acquires task requirements, and matches display content according to the task requirements; a content adjustment module, which acquires multiple display contents, extracts key feature points in the display contents, finds out corresponding relationships between images according to the key feature points, aligns the multiple display contents through the corresponding relationships, splices the multiple display contents, acquires user instructions, and adjusts the display contents in real time according to the user instructions; an optimization module, which acquires real-time data through a light intensity sensor, adjusts exposure of the image, and processes image data of multiple unmanned aerial vehicles through color difference compensation and contrast optimization algorithm based on image analysis.

[0012] Preferably, the display module comprises: a region comparison unit, which acquires information of a key detection area, compares the position information with the detection area, and identifies key features of the area if it is determined that the unmanned aerial vehicle is located in the key detection area; a display unit, which acquires a display mode, wherein the display mode includes panoramic display and specific area display, judges the display mode according to a comparison result, and acquires task requirements, wherein the task requirements include environmental monitoring, post-disaster evaluation and inspection; The display content selection unit matches display content according to task requirements, and the display content includes zoomed-in details, real-time flight angles, and real-time flight heights.

[0013] Preferably, the content adjustment module comprises: The display feature point unit acquires a plurality of display contents, the plurality of display contents including different angles, different flight heights, and different lighting conditions, and extracts key feature points in the display contents. The content splicing unit finds out the corresponding relationship between images according to the key feature points, aligns the plurality of display contents through the corresponding relationship, splices the plurality of display contents, and acquires user instructions, the user instructions including voice instructions, gesture controls, or APP adjustments. The content adjustment unit adjusts the display content in real time according to the user instructions, and the adjustment mode includes adjusting a viewing angle, a display area, and the display content.

[0014] Preferably, the optimization module comprises: The chromatic aberration optimization unit acquires real-time data through a lighting intensity sensor, adjusts the exposure of an image, and performs chromatic aberration compensation and contrast optimization algorithms based on image analysis, the optimization algorithms being adjustment of hue, saturation, and contrast of the image. The resolution optimization unit adjusts the resolution of the image according to the requirements of a flight path and a task target, and the adjustment mode is to increase the resolution in a key area and to reduce the resolution in a non-key area. The image processing unit processes image data of a plurality of unmanned aerial vehicles, the processing including cooperative processing and storage, and optimizes display content according to historical task data and real-time environmental changes.

[0015] Preferably, the environmental data includes lighting and climate changes.

[0016] The unmanned aerial vehicle image panoramic display method provided by the embodiment of the application realizes intelligent adjustment and optimization of image display content by comprehensively applying various technical means such as a lighting intensity sensor, a depth sensor, and a meteorological sensor, in combination with flight path data, task requirements, and user interaction instructions. Through real-time adjustment of multiple dimensions such as exposure, chromatic aberration, and contrast of the image, it is ensured that the image display always maintains high quality under different environmental conditions. At the same time, based on real-time feedback of the flight path, the task target, and the user requirements, the resolution and the display area of the image can be accurately controlled, the display precision of the key area is improved, and the processing burden of the non-key area is reduced, thereby optimizing the data processing and storage efficiency.

[0017] The cooperative work of multiple drones not only improves the efficiency of data processing, but also optimizes the display content in real time through cloud cooperation and big data analysis, ensures detailed display in key task areas, and intelligently adjusts according to historical task data and real-time environmental changes. This dynamic and intelligent image display optimization method significantly improves the accuracy and efficiency of task execution, ensures that the display content is highly consistent with task requirements and user instructions at all times, and has a wide application prospect. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 A flowchart of a method for panoramic display of images by a drone is provided for embodiments of the present application; Figure 2 A flowchart of the steps of comparing position information with a detection area, determining a display method according to the comparison result, and matching display content according to task requirements is provided for embodiments of the present application; Figure 3 A flowchart of the steps of finding the corresponding relationship between images according to key feature points, splicing multiple display contents, and adjusting display contents in real time according to user instructions is provided for embodiments of the present application; Figure 4 A flowchart of the steps of adjusting the exposure of images, using color difference compensation and contrast optimization algorithms based on image analysis, and processing image data from multiple drones is provided for embodiments of the present application; Figure 5 An architectural diagram of a panoramic display system for images by a drone is provided for embodiments of the present application; Figure 6 An architectural diagram of a display module is provided for embodiments of the present application; Figure 7 An architectural diagram of a content adjustment module is provided for embodiments of the present application; Figure 8 An architectural diagram of an optimization module is provided for embodiments of the present application. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solutions and advantages of the present application clearer and more apparent, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0020] It can be understood that the terms "first", "second", etc. used in the present application can be used herein to describe various elements, but unless specifically stated, these elements are not limited by these terms. These terms are only used to distinguish the first element from another element. For example, without departing from the scope of the present application, the first xx script can be referred to as the second xx script, and similarly, the second xx script can be referred to as the first xx script.

[0021] As Figure 1 shown, a method for displaying panoramic images of a UAV provided by an embodiment of the application, the method comprising: S100, acquiring sensor types, the sensors including an RGB camera, a depth sensor, and a weather sensor, the sensors being used to collect data in the flight path, the sensor data including position information, flight angle, flight speed, height, and environmental data.

[0022] In this step, the types of sensors are acquired, including an RGB camera, a depth sensor, and a weather sensor, which can comprehensively collect key data in the flight path of the UAV. The RGB camera is responsible for capturing environmental images in the flight path, providing high-definition two-dimensional image data, supporting image stitching and panoramic display. The camera can collect multiple images and synthesize them to generate a comprehensive image view according to different flight angles and perspectives, and is widely used in environmental monitoring and urban inspection tasks. The depth sensor captures three-dimensional information of the scene in real time through laser radar or stereo vision technology, including the elevation of ground objects and the position of objects, enhancing the depth perception of the image. For example, in urban construction monitoring or post-disaster assessment tasks, the depth sensor can provide accurate three-dimensional data to help generate more detailed and accurate environmental models, improving the accuracy and spatial perception of the image.

[0023] The weather sensor is used to collect environmental data in the flight path, such as temperature, humidity, air pressure, and light intensity, providing real-time key data about the flight environment. By collecting light intensity, the image exposure can be adjusted to ensure image clarity under different lighting conditions; temperature and humidity data can be used to adjust image color and contrast to optimize display effects. In the flight path, real-time collection of UAV position information, flight angle, flight speed, and height data is also included, which provides accurate flight trajectory for image display, supports dynamic adjustment of display content according to task requirements, and ensures that image display is synchronized with flight tasks. Through the integration of sensor data, image display content can be automatically optimized according to flight path and environmental changes, ensuring that display effects always maintain high quality and accuracy during the task process.

[0024] S200, comparing position information with detection area, determining display method according to comparison result, acquiring task requirements, and matching display content according to task requirements.

[0025] In this step, the position information is compared with the detection area, and the position information of the flight path is compared with the detection area based on the position information of the unmanned aerial vehicle to determine the display mode of the display content. The position information in the flight path is collected in real time by multiple sensors, including GPS positioning data, flight angle, speed, etc. By comparing with the pre-defined task detection area, when the unmanned aerial vehicle enters a specific area, the content to be displayed can be automatically determined according to the comparison result. For example, in an environmental monitoring task, when the unmanned aerial vehicle flies to a pollution source area, the position information will be matched with the coordinates of the area. If the matching is successful, the display content will automatically switch to the detailed display mode of the local area, focusing on displaying the real-time environmental data of the area, such as pollution index, temperature, etc., and increasing the resolution of the image of the area to clearly display the detailed situation of the target area.

[0026] According to the obtained task requirements, the display content will automatically match the task target. The task requirements usually include the priority of the task target area, the required display details and the accuracy of the display. In a post-disaster assessment task, for example, when the unmanned aerial vehicle flies to a severely affected area, the task requirements may specify the display of the building damage in the area, the degree of road damage, etc., to ensure that the detailed information of the affected area can be clearly presented. By comparing the task requirements with the position information in the real-time flight path, the display content can be dynamically optimized during the task execution, such as adjusting the display area range, switching the display mode, increasing the image resolution, etc., to meet the specific needs of the task, ensuring that the display content always matches the needs of the flight target, providing accurate task support and decision basis.

[0027] S300, obtaining a plurality of display contents, extracting key feature points in the display contents, finding corresponding relationships between images according to the key feature points, aligning the plurality of display contents through the corresponding relationships, and splicing the plurality of display contents.

[0028] In this step, a plurality of display contents are obtained, and the plurality of display contents are aligned and spliced by extracting key feature points. First, representative key feature points are extracted from each display content, including corner points, edge points or other significant feature points in the image. By comparing the feature points in different display contents, the corresponding relationships between images can be found. According to these corresponding relationships, the images will be accurately aligned to ensure seamless transition of the spliced image. This process uses high-precision feature point matching algorithms such as SIFT, SURF, etc., to ensure consistent visual effects and details when splicing images.

[0029] After the alignment is completed, multiple display contents will be spliced into a complete image, presenting a wide field of view. During the splicing process, the boundaries and seams of the images will be optimized through smoothing and color correction, eliminating the seams or distortion phenomena caused by image inconsistency, ensuring the smoothness and naturalness of the display effect. On this basis, according to the user's instructions, the display content will be adjusted in real time. For example, the user can request to display detailed content of a specific area through voice commands, gestures or other input methods. According to the user's instructions, the image will automatically zoom, move or switch the perspective to display more accurate information.

[0030] S400, real-time data is obtained through the light intensity sensor, the exposure of the image is adjusted, the color difference compensation and contrast optimization algorithm based on image analysis is used to process the image data of multiple unmanned aerial vehicles.

[0031] In this step, real-time data is obtained through the light intensity sensor, and the exposure of the image is automatically adjusted to ensure that the image always maintains the best display effect under different lighting conditions. The light intensity sensor can accurately measure the change of ambient light, and when the ambient light changes during flight, the exposure value of the image will automatically adjust accordingly to avoid overexposure or underexposure. This adjustment mechanism can maintain the balanced brightness of the image in strong light or shadow environment, ensuring the clear presentation of image details and improving the quality of display effect.

[0032] In addition, image analysis technology further improves the visual effect of the image through color difference compensation and contrast optimization algorithm. By analyzing and correcting the color difference of different areas in the image in real time, color distortion caused by environmental changes can be effectively eliminated, ensuring the consistency of color tones in the image. The contrast optimization algorithm automatically enhances the contrast of the image according to the distribution of image content, making the details more clearly visible, and avoiding visual blur problems caused by insufficient light or single image content.

[0033] To improve the accuracy of the display effect, the application also processes the image data of multiple unmanned aerial vehicles. Through multi-machine cooperation and image data fusion, image information from different flight paths and different perspectives can be integrated, and further optimization can be performed during splicing and display to ensure that the final image has uniform and consistent color, exposure and contrast in each area, presenting a most real and high-quality panoramic image.

[0034] As shown in Figure 2 As a preferred embodiment of the present application, the comparison position information and the detection area, according to the comparison position result to judge the display mode, obtain the task requirement, and according to the task requirement to match the display content, the steps specifically include: S201: Obtain information on key detection areas, compare the location information with the detection area, and if it is determined that the UAV is located within the key detection area, identify the key features of that area.

[0035] In this step, key detection area information is acquired by comparing the location information along the flight path with the key detection area in real time. When the drone flies to the predetermined key detection area, its location information is compared with the coordinates of that area to determine whether it has entered the area. If the drone is determined to be within the key detection area, the system will automatically identify the key features of that area. These key features can be buildings, equipment, or other significant geographical features in the image. Especially in tasks such as inspection and environmental monitoring, these areas typically require higher precision display and detailed monitoring.

[0036] Once the drone is located within the key detection area, the next step is to conduct a detailed analysis of that area to extract its key features. Image processing algorithms can identify important objects or structures within the area and extract their shape, location, size, and other feature data. These key features are crucial for mission execution, providing more accurate image visualization and analysis. Especially in disaster assessment, building inspection, or environmental monitoring, detailed information about key areas is essential for decision-making.

[0037] This technology, which compares location information with key detection areas, ensures that drones can intelligently and accurately locate important areas and extract crucial data during missions, providing efficient support for image display, problem diagnosis, and mission execution. This optimization not only improves mission efficiency but also ensures the accuracy of displayed content, avoids interference from non-critical areas, and concentrates resources and processing power on truly important mission areas.

[0038] S202, Obtain the display method, which includes panoramic display and specific area display. Determine the display method based on the comparison location results, and obtain the task requirements, which include environmental monitoring, post-disaster assessment, and inspection.

[0039] In this step, the display mode is determined in real time based on the drone's location information and flight path. Two display modes are available: panoramic display and specific area display. By comparing the current location with the predetermined detection area, it is determined whether the drone is located in a key monitoring area or a critical area required by the mission. If the drone is in an area requiring focused attention, the display mode will automatically switch to specific area display mode, focusing on that area and improving its display accuracy; if the drone is in other areas, panoramic display mode will be used to show a wider range of environmental information, ensuring comprehensive monitoring of the mission area.

[0040] The display method will be further adjusted according to the task requirements to adapt to different task needs. Task requirements may include different types such as environmental monitoring, post-disaster assessment, and inspection. In environmental monitoring tasks, the focus is on displaying the environmental status and changes of the area. In post-disaster assessment tasks, the system automatically identifies the affected areas and uses a specific area display mode to provide detailed information about the disaster area, such as building damage and traffic disruptions, to help users quickly assess the disaster situation. For inspection tasks, the display method is optimized according to the focus of the inspection area, providing clear and accurate local area displays to ensure that details of key parts are fully presented.

[0041] S203, Match the display content according to the task requirements, the display content includes magnified details, real-time flight angle and real-time flight altitude.

[0042] In this step, the displayed content is matched and adjusted automatically according to the task requirements to ensure it aligns with the mission needs. The displayed content includes magnified details, real-time flight angle, and real-time flight altitude. For different types of tasks, such as environmental monitoring, post-disaster assessment, or inspection, the displayed content will be dynamically adjusted based on the task's focus. For example, in a post-disaster assessment task, when the drone flies over a damaged area, the displayed content will automatically switch to magnified detail mode, highlighting high-definition images of damaged buildings, roads, and other areas, ensuring users can clearly see the situation in key areas.

[0043] Furthermore, the displayed content is optimized and adjusted synchronously based on changes in real-time flight angle and altitude. When the drone's flight angle changes, the viewing angle of the image display adjusts accordingly to ensure that the displayed content remains consistent with the flight path. For example, during flight, if the drone needs to inspect the details of a certain area, the displayed content will automatically zoom in on that area and adjust the viewing angle to ensure that the key features of that area are accurately displayed. Similarly, real-time flight altitude data also affects the displayed content, ensuring that images acquired at different altitudes have appropriate clarity and display range.

[0044] like Figure 3 As shown, in a preferred embodiment of the present invention, the steps of acquiring multiple display contents, extracting key feature points from the display contents, finding the correspondence between images based on the key feature points, aligning the multiple display contents through the correspondence, stitching the multiple display contents together, acquiring user instructions, and adjusting the display contents in real time according to the user instructions specifically include: S301, acquire multiple display contents, including different angles, different flight altitudes, and different lighting conditions, and extract key feature points from the display contents.

[0045] This step involves acquiring multiple display elements, including images taken from different shooting angles, at different flight altitudes, and under varying lighting conditions, comprehensively collecting image data along the flight path. These display elements, obtained through image acquisition from different perspectives and under different flight conditions, provide richer environmental information. For example, images at different flight altitudes can reveal different levels of geographical features, while images under different lighting conditions can reflect detailed changes in the environment under varying lighting conditions. These display elements provide multi-dimensional data support for subsequent image processing and display.

[0046] During the extraction of image display content, a feature point detection algorithm is applied to automatically extract key feature points from each display item. These feature points include corner points, edge points, and other salient features in the image, representing important regions and structural information within the image. By comparing feature points in different display items, the correlation between different images can be identified, thus providing a basis for image stitching, alignment, and optimization. For example, in image stitching, feature point matching ensures accurate alignment of images taken under different flight angles, altitudes, and lighting conditions, avoiding seams or distortion.

[0047] By extracting key feature points and utilizing feature point matching algorithms, image stitching and content display optimization can be effectively performed, ensuring the accuracy and coherence of the images. This method not only improves the quality and accuracy of image display but also provides more precise data support for UAV mission execution in complex environments, ensuring clearer and more accurate display of the mission target area.

[0048] S302, find the correspondence between images based on key feature points, align multiple display contents through the correspondence, stitch the multiple display contents together, and obtain user instructions, including voice instructions, gesture control or APP adjustment.

[0049] In this step, correspondences between images are identified based on key feature points. Using key feature points extracted from multiple display contents, a feature point matching algorithm is employed to find these correspondences between different images. These feature points include corner points, edge points, and other salient features in the images, effectively describing important elements within the images. By analyzing these correspondences, images can be precisely aligned, ensuring seamless stitching of images acquired from different angles, flight altitudes, and lighting conditions. This image alignment process ensures the continuity and consistency of the displayed content after stitching, avoiding seams or distortion at the stitching points and enhancing the naturalness and realism of the display effect.

[0050] After image alignment and stitching are completed, the displayed content will be adjusted in real time according to user commands. Users can adjust the display method of the content through voice commands, gesture control, or the app interface. For example, users can use voice commands to request zooming in on a certain area of ​​the image, or use gesture control to rotate the image to view different angles, or even make detailed adjustments and switch perspectives through the app. These interaction methods enable users to dynamically adjust the displayed content according to specific needs, ensuring that the displayed images accurately match task requirements and environmental changes.

[0051] S303, Real-time adjustment of the displayed content according to user instructions, the adjustment methods include adjusting the viewing angle, display area and display content.

[0052] In this step, the displayed content is adjusted in real time according to user instructions. Adjustments include flexible control over the viewing angle, display area, and content. When the user inputs adjustment commands via voice commands, gestures, or the app interface, the displayed content responds immediately and automatically changes its viewing angle. For example, the user can command to rotate an image to a specific angle or zoom in on a portion of the image to view details more clearly. In this way, the display perspective can switch in real time according to user needs, ensuring that the displayed content always meets the task requirements and the user's specific needs.

[0053] In addition to adjusting the viewing angle, the display area can also be dynamically switched based on user commands. When a user focuses on a specific area, they can select that area using control commands, and the displayed content will automatically focus on that area, improving display accuracy. For large-scale panoramic displays, users can zoom or adjust the display area using commands, making the key areas of interest stand out more, while ensuring that other less important areas are appropriately shrunk or hidden in the image. This area adjustment function enhances the flexibility of image display, allowing users to quickly focus on the critical areas required for the task.

[0054] Furthermore, the displayed content can be fully adjusted according to user needs. In different task scenarios, users may require different levels of information display. For example, in inspection tasks, users may require displaying detailed equipment status, while in environmental monitoring tasks, they may need to highlight a specific geographical area or environmental variable. By adjusting the displayed content in real time, the execution of each task can be made more efficient and accurate, while enhancing the user's control over image information.

[0055] like Figure 4 As shown, in a preferred embodiment of the present invention, the steps of acquiring real-time data through a light intensity sensor, adjusting the image exposure, and processing image data from multiple drones based on image analysis-based color difference compensation and contrast optimization algorithms specifically include: S401: Real-time data is acquired through a light intensity sensor, and the exposure of the image is adjusted. A color difference compensation and contrast optimization algorithm based on image analysis is used, wherein the optimization algorithm adjusts the hue, saturation and contrast of the image.

[0056] In this step, real-time data is acquired using a light intensity sensor, and the image exposure is automatically adjusted based on changes in lighting conditions. During flight, light intensity may vary significantly, causing overexposure or underexposure in certain areas of the image. By utilizing real-time light intensity data, the image exposure can be dynamically adjusted according to the ambient light intensity, ensuring uniform brightness under various lighting conditions and avoiding overly bright or dark areas, thereby improving the overall image clarity and visibility.

[0057] Image analysis-based color difference compensation and contrast optimization algorithms can further optimize image display. This optimization algorithm automatically adjusts the image's hue, saturation, and contrast by analyzing the color distribution and contrast within the image. The color difference compensation function eliminates color differences caused by variations in lighting or shooting angles, ensuring consistent color across different environments. The contrast optimization algorithm adjusts the contrast based on the image content, enhancing the visibility of details, especially in low-contrast areas, improving the image's depth and detail clarity.

[0058] This combination of exposure adjustment, color difference compensation, and contrast optimization technologies ensures high-quality image display under various environmental and lighting conditions. By automatically optimizing the visual effects of images, accurate, clear, and consistent content can be provided in a variety of complex flight missions, meeting the needs of users in different tasks.

[0059] S402, adjust the image resolution according to the requirements of the flight path and mission objectives. The adjustment method is to increase the resolution in critical areas and decrease the resolution in non-critical areas.

[0060] In this step, the image resolution is intelligently adjusted based on the flight path and mission objectives. During mission execution, the image resolution of key areas is automatically increased to ensure that critical parts of the mission are clearly displayed. For example, in inspection missions, when the drone flies near equipment or facilities, the image resolution automatically increases to highlight equipment details and potential problems; while during environmental monitoring, the image resolution near important geographical areas or pollution sources is also improved to ensure that users can clearly see changes in key areas.

[0061] For non-critical areas, the image resolution will be appropriately reduced to optimize processing efficiency and storage resources. When the focus of the flight path or mission requirements is not on certain areas, the image resolution will be automatically reduced to decrease the amount of data and speed up the processing. This adjustment method effectively reduces the burden of image processing and storage while ensuring that core information in the flight mission is prioritized for display, meeting the specific needs of the mission.

[0062] S403 processes image data from multiple drones, including collaborative processing and storage, and optimizes the displayed content based on historical mission data and real-time environmental changes.

[0063] In this step, image data from multiple drones is processed, integrated, and optimized through collaborative processing and storage. When multiple drones perform tasks simultaneously, the image data collected by each drone can be collaboratively processed in the cloud or locally, integrating data from different flight paths and perspectives to ensure comprehensive display of key information in the mission. Collaborative processing not only improves data processing efficiency but also enables precise monitoring and detailed presentation of the mission area by analyzing image information acquired by different drones. This collaborative approach significantly improves mission execution efficiency, especially in large-scale environmental monitoring and complex tasks, ensuring that image data from each drone provides valuable support for the final presentation.

[0064] By optimizing storage and management, historical task data and real-time environmental changes allow for further adjustments to the displayed content. Historical data provides valuable reference for display optimization, helping to determine the changing trends of specific areas or tasks. For example, in environmental monitoring tasks, historical data can reveal long-term patterns of change in certain areas, while real-time environmental data provides dynamic information about current changes. By combining this data, the displayed content can more accurately reflect task requirements, automatically adjusting the displayed areas and details to highlight changes or anomalies in key areas, ensuring that the final image display always meets the task objectives.

[0065] like Figure 5 As shown, an embodiment of the present invention provides a panoramic image display system for unmanned aerial vehicles (UAVs), the system comprising: The basic information acquisition module 100 is used to acquire sensor types, including an RGB camera, a depth sensor, and a weather sensor. The sensors are used to collect data along the flight path, and the sensor data includes position information, flight angle, flight speed, altitude, and environmental data.

[0066] In this system, the basic information acquisition module 100 acquires sensor types, including RGB cameras, depth sensors, and meteorological sensors, enabling comprehensive collection of key data along the drone's flight path. The RGB camera captures environmental images along the flight path, providing high-definition two-dimensional image data and supporting image stitching and panoramic display. This camera can acquire multiple images and synthesize them based on different flight angles and perspectives to generate a comprehensive image view, widely used in tasks such as environmental monitoring and urban inspection. The depth sensor, through LiDAR or stereo vision technology, captures real-time three-dimensional information of the scene, including ground feature elevation and object position, enhancing image depth perception. For example, in urban construction monitoring or post-disaster assessment tasks, the depth sensor can provide accurate three-dimensional data, helping to generate more detailed and accurate environmental models, improving image accuracy and spatial perception.

[0067] Weather sensors are used to collect environmental data along the flight path, such as temperature, humidity, air pressure, and light intensity, providing real-time key data about the flight environment. By collecting light intensity data, image exposure can be adjusted to ensure image clarity under different lighting conditions; while temperature and humidity data can be used to adjust image color and contrast, optimizing the display effect. The flight path also includes real-time collection of the drone's position, flight angle, flight speed, and altitude data. This data provides a precise flight trajectory for image display, supporting dynamic adjustments to the display content according to mission requirements, ensuring that the image display is synchronized with the flight mission. Through the integration of sensor data, the image display content can be automatically optimized based on changes in the flight path and environment, ensuring that the display effect maintains high quality and accuracy throughout the mission.

[0068] The display module 200 is used to compare location information with the detection area, determine the display method based on the comparison results, obtain task requirements, and match display content according to the task requirements.

[0069] In this system, the display module 200 compares the location information with the detection area. Based on the UAV's location information, the module determines the display method for the content. The location information along the flight path is collected in real time by multiple sensors, including GPS positioning data, flight angle, and speed. By comparing it with a predefined task detection area, when the UAV enters a specific area, the system automatically determines the content to be displayed based on the comparison results. For example, in an environmental monitoring task, when the UAV flies to a pollution source area, its location information is matched with the coordinates of that area. If the match is successful, the display content automatically switches to a detailed display mode for that specific area, highlighting real-time environmental data such as pollution index and temperature, and increasing the resolution of the image to clearly show the detailed conditions of the target area.

[0070] Based on the acquired task requirements, the displayed content is automatically matched with the task objectives. Task requirements typically include the priority of the target area, the required display details, and the accuracy of the display. In post-disaster assessment tasks, for example, when a drone flies over a severely affected area, the task requirements might specify displaying the extent of building damage, road damage, etc., ensuring that detailed information about the affected area is clearly presented. By comparing the task requirements with the location information in the real-time flight path, the displayed content can be dynamically optimized during task execution, such as adjusting the displayed area, switching display modes, and increasing image resolution, to meet the specific needs of the task and ensure that the displayed content always matches the needs of the flight objective, providing accurate task support and decision-making basis.

[0071] The content adjustment module 300 is used to acquire multiple display contents, extract key feature points from the display contents, find the correspondence between images based on the key feature points, align multiple display contents through the correspondence, stitch the multiple display contents together, acquire user instructions, and adjust the display contents in real time according to the user instructions.

[0072] In this system, the content adjustment module 300 The optimization module 400 is used to acquire real-time data through a light intensity sensor, adjust the exposure of the image, and process the image data of multiple drones based on color difference compensation and contrast optimization algorithms based on image analysis.

[0073] In this system, the optimization module 400 acquires real-time data through a light intensity sensor and automatically adjusts the image exposure to ensure optimal display quality under varying lighting conditions. The light intensity sensor accurately measures changes in ambient light. During flight, when ambient light changes, the image exposure value is automatically adjusted to prevent overexposure or underexposure. This adjustment mechanism maintains balanced image brightness in both bright and shadowy environments, ensuring clear detail and improving display quality.

[0074] Furthermore, image analysis technology further improves the visual effect of images through color difference compensation and contrast optimization algorithms. By analyzing and correcting color differences in different areas of an image in real time, color distortion caused by environmental changes can be effectively eliminated, ensuring the consistency of tones in the image. The contrast optimization algorithm automatically enhances the contrast of the image based on the distribution of image content, making details more clearly visible and avoiding visual blurring caused by insufficient lighting or monotonous image content.

[0075] To improve the accuracy of the display effect, this invention also incorporates image data from multiple drones. Through multi-drone collaboration and image data fusion, image information from different flight paths and perspectives can be integrated and further optimized during stitching and display to ensure that the final image has uniform color, exposure, and contrast in all areas, presenting the most realistic and high-quality panoramic image.

[0076] like Figure 6 As shown, in a preferred embodiment of the present invention, the display module 200 includes: The area comparison unit 201 is used to obtain information on key detection areas, compare the location information with the detection area, and identify the key features of the area if it is determined that the UAV is located in the key detection area.

[0077] In this module, the area comparison unit 201 acquires key detection area information and compares its position information along the flight path with the key detection area in real time. When the UAV flies to the predetermined key detection area, its position information is compared with the coordinates of that area to determine whether it has entered the area. If the UAV is determined to be within the key detection area, the system will automatically identify the key features of that area. These key features can be buildings, equipment, or other significant ground features in the image. Especially in tasks such as inspection and environmental monitoring, these areas typically require higher precision display and detailed monitoring.

[0078] Once the drone is located within the key detection area, the next step is to conduct a detailed analysis of that area to extract its key features. Image processing algorithms can identify important objects or structures within the area and extract their shape, location, size, and other feature data. These key features are crucial for mission execution, providing more accurate image visualization and analysis. Especially in disaster assessment, building inspection, or environmental monitoring, detailed information about key areas is essential for decision-making.

[0079] This technology, which compares location information with key detection areas, ensures that drones can intelligently and accurately locate important areas and extract crucial data during missions, providing efficient support for image display, problem diagnosis, and mission execution. This optimization not only improves mission efficiency but also ensures the accuracy of displayed content, avoids interference from non-critical areas, and concentrates resources and processing power on truly important mission areas.

[0080] The display unit 202 is used to obtain the display method, which includes panoramic display and specific area display. The display method is determined based on the comparison position results, and the task requirements are obtained, which include environmental monitoring, post-disaster assessment and inspection.

[0081] In this module, the display unit 202 acquires the display mode and determines it in real time based on the UAV's location information and flight path. The display modes include panoramic display and specific area display. By comparing the current location with the predetermined detection area, it determines whether the UAV is located in a key monitoring area or a critical area required by the mission. If the UAV is in an area requiring focused attention, the display mode automatically switches to specific area display mode, focusing on that area and improving its display accuracy; if the UAV is in other areas, the panoramic display mode is used to show a wider range of environmental information, ensuring comprehensive monitoring of the mission area.

[0082] The display method will be further adjusted according to the task requirements to adapt to different task needs. Task requirements may include different types such as environmental monitoring, post-disaster assessment, and inspection. In environmental monitoring tasks, the focus is on displaying the environmental status and changes of the area. In post-disaster assessment tasks, the system automatically identifies the affected areas and uses a specific area display mode to provide detailed information about the disaster area, such as building damage and traffic disruptions, to help users quickly assess the disaster situation. For inspection tasks, the display method is optimized according to the focus of the inspection area, providing clear and accurate local area displays to ensure that details of key parts are fully presented.

[0083] The content selection unit 203 is used to match the content to be displayed according to the task requirements. The content to be displayed includes magnified details, real-time flight angle and real-time flight altitude.

[0084] In this module, the content selection unit 203 matches the displayed content according to the task requirements. The displayed content is automatically matched and adjusted to ensure that it conforms to the task needs. The displayed content includes magnified details, real-time flight angle, and real-time flight altitude. For different types of tasks, such as environmental monitoring, post-disaster assessment, or inspection tasks, the displayed content will be dynamically adjusted according to the task's focus. For example, in a post-disaster assessment task, when the drone flies over the damaged area, the displayed content will automatically switch to magnified detail mode, highlighting high-definition images of damaged buildings, roads, and other areas, ensuring that users can clearly see the situation in key areas.

[0085] Furthermore, the displayed content is optimized and adjusted synchronously based on changes in real-time flight angle and altitude. When the drone's flight angle changes, the viewing angle of the image display adjusts accordingly to ensure that the displayed content remains consistent with the flight path. For example, during flight, if the drone needs to inspect the details of a certain area, the displayed content will automatically zoom in on that area and adjust the viewing angle to ensure that the key features of that area are accurately displayed. Similarly, real-time flight altitude data also affects the displayed content, ensuring that images acquired at different altitudes have appropriate clarity and display range.

[0086] like Figure 7As shown, in a preferred embodiment of the present invention, the content adjustment module 300 includes: The feature point unit 301 is used to acquire multiple display contents, including different angles, different flight altitudes, and different lighting conditions, and to extract key feature points from the display contents.

[0087] In this module, the feature point unit 301 acquires multiple display contents, including images from different shooting angles, flight altitudes, and lighting conditions, comprehensively collecting image data along the flight path. These display contents, acquired through image acquisition from different perspectives and under different flight conditions, provide richer environmental information. For example, images at different flight altitudes can display different levels of geographical features, while images under different lighting conditions can reflect detailed changes in the environment under varying lighting conditions. These display contents provide multi-dimensional data support for subsequent image processing and display.

[0088] During the extraction of image display content, a feature point detection algorithm is applied to automatically extract key feature points from each display item. These feature points include corner points, edge points, and other salient features in the image, representing important regions and structural information within the image. By comparing feature points in different display items, the correlation between different images can be identified, thus providing a basis for image stitching, alignment, and optimization. For example, in image stitching, feature point matching ensures accurate alignment of images taken under different flight angles, altitudes, and lighting conditions, avoiding seams or distortion.

[0089] By extracting key feature points and utilizing feature point matching algorithms, image stitching and content display optimization can be effectively performed, ensuring the accuracy and coherence of the images. This method not only improves the quality and accuracy of image display but also provides more precise data support for UAV mission execution in complex environments, ensuring clearer and more accurate display of the mission target area.

[0090] The content splicing unit 302 is used to find the correspondence between images based on key feature points, align multiple display contents through the correspondence, splice the multiple display contents, and obtain user instructions, including voice instructions, gesture control, or APP adjustments.

[0091] In this module, the content stitching unit 302 identifies the correspondence between images based on key feature points. Using a feature point matching algorithm, it finds the correspondence between different images based on key feature points extracted from multiple display contents. These feature points include corner points, edge points, and other salient features in the images, effectively describing important elements within the images. By analyzing these correspondences, the images can be precisely aligned, ensuring seamless stitching of images acquired from different angles, flight altitudes, and lighting conditions. The image alignment process ensures the continuity and consistency of the displayed content after stitching, avoiding seams or distortion at the stitching points and enhancing the naturalness and realism of the display effect.

[0092] After image alignment and stitching are completed, the displayed content will be adjusted in real time according to user commands. Users can adjust the display method of the content through voice commands, gesture control, or the app interface. For example, users can use voice commands to request zooming in on a certain area of ​​the image, or use gesture control to rotate the image to view different angles, or even make detailed adjustments and switch perspectives through the app. These interaction methods enable users to dynamically adjust the displayed content according to specific needs, ensuring that the displayed images accurately match task requirements and environmental changes.

[0093] The content adjustment unit 303 is used to adjust the displayed content in real time according to user instructions. The adjustment methods include adjusting the viewing angle, display area, and display content.

[0094] In this module, the content adjustment unit 303 adjusts the displayed content in real time according to user instructions. Adjustments include flexible control over the viewing angle, display area, and content. When the user inputs adjustment commands via voice commands, gesture control, or the app interface, the displayed content responds immediately and automatically changes the viewing angle. For example, the user can command to rotate an image to a specific angle or zoom in on a portion of the image to view details more clearly. In this way, the display perspective can switch in real time according to user needs, ensuring that the displayed content always meets task requirements and the user's specific needs.

[0095] In addition to adjusting the viewing angle, the display area can also be dynamically switched based on user commands. When a user focuses on a specific area, they can select that area using control commands, and the displayed content will automatically focus on that area, improving display accuracy. For large-scale panoramic displays, users can zoom or adjust the display area using commands, making the key areas of interest stand out more, while ensuring that other less important areas are appropriately shrunk or hidden in the image. This area adjustment function enhances the flexibility of image display, allowing users to quickly focus on the critical areas required for the task.

[0096] Furthermore, the displayed content can be fully adjusted according to user needs. In different task scenarios, users may require different levels of information display. For example, in inspection tasks, users may require displaying detailed equipment status, while in environmental monitoring tasks, they may need to highlight a specific geographical area or environmental variable. By adjusting the displayed content in real time, the execution of each task can be made more efficient and accurate, while enhancing the user's control over image information.

[0097] like Figure 8 As shown, in a preferred embodiment of the present invention, the optimization module 400 includes: The color difference optimization unit 401 is used to acquire real-time data through a light intensity sensor, adjust the exposure of the image, and implement a color difference compensation and contrast optimization algorithm based on image analysis. The optimization algorithm adjusts the hue, saturation, and contrast of the image.

[0098] In this module, the color difference optimization unit 401 acquires real-time data through a light intensity sensor and automatically adjusts the image exposure according to changes in lighting conditions. During flight, light intensity may change significantly, causing overexposure or underexposure in certain areas of the image. By utilizing real-time light intensity data, the image exposure can be dynamically adjusted according to the ambient light intensity, ensuring that the image maintains uniform brightness under various lighting conditions, avoiding overly bright or dark areas, thereby improving the overall image clarity and visual effect.

[0099] Image analysis-based color difference compensation and contrast optimization algorithms can further optimize image display. This optimization algorithm automatically adjusts the image's hue, saturation, and contrast by analyzing the color distribution and contrast within the image. The color difference compensation function eliminates color differences caused by variations in lighting or shooting angles, ensuring consistent color across different environments. The contrast optimization algorithm adjusts the contrast based on the image content, enhancing the visibility of details, especially in low-contrast areas, improving the image's depth and detail clarity.

[0100] This combination of exposure adjustment, color difference compensation, and contrast optimization technologies ensures high-quality image display under various environmental and lighting conditions. By automatically optimizing the visual effects of images, accurate, clear, and consistent content can be provided in a variety of complex flight missions, meeting the needs of users in different tasks.

[0101] The resolution optimization unit 402 is used to adjust the resolution of the image according to the requirements of the flight path and mission objectives. The adjustment method is to increase the resolution in critical areas and decrease the resolution in non-critical areas.

[0102] In this module, the resolution optimization unit 402 intelligently adjusts the image resolution according to the requirements of the flight path and mission objectives. During mission execution, the image resolution of key areas is automatically increased to ensure that critical parts of the mission are clearly displayed. For example, in inspection missions, when the drone flies near equipment or facilities, the image resolution automatically increases to highlight equipment details and potential problems; while during environmental monitoring, the image resolution near important geographical areas or pollution sources is also improved to ensure that users can clearly see changes in key areas.

[0103] For non-critical areas, the image resolution will be appropriately reduced to optimize processing efficiency and storage resources. When the focus of the flight path or mission requirements is not on certain areas, the image resolution will be automatically reduced to decrease the amount of data and speed up the processing. This adjustment method effectively reduces the burden of image processing and storage while ensuring that core information in the flight mission is prioritized for display, meeting the specific needs of the mission.

[0104] The image processing unit 403 is used to process image data from multiple drones. The processing includes collaborative processing and storage, and optimizes the displayed content based on historical mission data and real-time environmental changes.

[0105] In this module, the image processing unit 403 processes image data from multiple drones. This image data is integrated and optimized through collaborative processing and storage. When multiple drones perform tasks simultaneously, the image data collected by each drone can be collaboratively processed in the cloud or locally, integrating data from different flight paths and perspectives to ensure comprehensive display of key information in the mission. Collaborative processing not only improves data processing efficiency but also enables precise monitoring and detailed presentation of the mission area by analyzing image information acquired by different drones. This collaborative approach significantly improves mission execution efficiency, especially in large-scale environmental monitoring and complex tasks, ensuring that the image data from each drone provides valuable support for the final presentation.

[0106] By optimizing storage and management, historical task data and real-time environmental changes allow for further adjustments to the displayed content. Historical data provides valuable reference for display optimization, helping to determine the changing trends of specific areas or tasks. For example, in environmental monitoring tasks, historical data can reveal long-term patterns of change in certain areas, while real-time environmental data provides dynamic information about current changes. By combining this data, the displayed content can more accurately reflect task requirements, automatically adjusting the displayed areas and details to highlight changes or anomalies in key areas, ensuring that the final image display always meets the task objectives.

[0107] In one embodiment, a computer device is provided, the computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps: The types of sensors are identified, including an RGB camera, a depth sensor, and a weather sensor. These sensors are used to collect data along the flight path, and the sensor data includes position information, flight angle, flight speed, altitude, and environmental data. Compare location information with the detection area, determine the display method based on the comparison results, obtain task requirements, and match display content according to the task requirements; The system acquires multiple display contents, extracts key feature points from the display contents, finds the correspondence between images based on the key feature points, aligns multiple display contents based on the correspondence, stitches the multiple display contents together, acquires user commands, and adjusts the display contents in real time according to the user commands. Real-time data is acquired through a light intensity sensor, and the exposure of the image is adjusted. Based on image analysis, color difference compensation and contrast optimization algorithms are used to process image data from multiple drones.

[0108] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, causes the processor to perform the following steps: The types of sensors are identified, including an RGB camera, a depth sensor, and a weather sensor. These sensors are used to collect data along the flight path, and the sensor data includes position information, flight angle, flight speed, altitude, and environmental data. Compare location information with the detection area, determine the display method based on the comparison results, obtain task requirements, and match display content according to the task requirements; The system acquires multiple display contents, extracts key feature points from the display contents, finds the correspondence between images based on the key feature points, aligns multiple display contents based on the correspondence, stitches the multiple display contents together, acquires user commands, and adjusts the display contents in real time according to the user commands. Real-time data is acquired through a light intensity sensor, and the exposure of the image is adjusted. Based on image analysis, color difference compensation and contrast optimization algorithms are used to process image data from multiple drones.

[0109] It should be understood that although the steps in the flowcharts of the various embodiments of the present invention are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the various embodiments may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps. Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0110] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0111] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

[0112] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for drone image panoramic presentation, characterized in that, The method comprises: acquiring sensor categories, the sensors including RGB cameras, depth sensors, and weather sensors, the sensors being used to collect data in a flight path, the sensor data including position information, flight angle, flight speed, height, and environmental data; comparing the position information with a detection area, determining a display mode according to a comparison result, acquiring task requirements, and matching display content according to the task requirements; acquiring multiple display contents, extracting key feature points in the display contents, finding corresponding relationships between images according to the key feature points, aligning the multiple display contents through the corresponding relationships, splicing the multiple display contents, acquiring user instructions, and adjusting the display contents in real time according to the user instructions; acquiring real-time data through a light intensity sensor, adjusting the exposure of images, and processing image data of multiple unmanned aerial vehicles based on color difference compensation and contrast optimization algorithms of image analysis.

2. The method of claim 1, wherein, The steps of comparing the position information with the detection area, determining the display mode according to the comparison result, acquiring the task requirements, and matching the display content according to the task requirements specifically comprise: acquiring key detection area information, comparing the position information with the detection area, and identifying key features of the area if it is determined that the unmanned aerial vehicle is located in the key detection area; acquiring a display mode, the display mode including panoramic display and specific area display, determining the display mode according to the comparison result, acquiring task requirements, and the task requirements including environmental monitoring, post-disaster evaluation, and inspection; matching the display content according to the task requirements, and the display content including magnified details, real-time flight angle, and real-time flight height.

3. The method of claim 2, wherein, The steps of acquiring the multiple display contents, extracting key feature points in the display contents, finding corresponding relationships between images according to the key feature points, aligning the multiple display contents through the corresponding relationships, splicing the multiple display contents, acquiring user instructions, and adjusting the display contents in real time according to the user instructions specifically comprise: acquiring the multiple display contents, the multiple display contents including different angles, different flight heights, and different light conditions, and extracting key feature points in the display contents; finding corresponding relationships between images according to the key feature points, aligning the multiple display contents through the corresponding relationships, splicing the multiple display contents, acquiring user instructions, and the user instructions including voice instructions, gesture control, or APP adjustment; adjusting the display contents in real time according to the user instructions, and the adjustment mode including adjusting a viewing angle, a display area, and display content.

4. The method of claim 3, wherein, The steps of acquiring real-time data through a light intensity sensor, adjusting the exposure of images, and processing image data of multiple unmanned aerial vehicles based on color difference compensation and contrast optimization algorithms of image analysis specifically comprise: acquiring real-time data through a light intensity sensor, adjusting the exposure of images, and based on color difference compensation and contrast optimization algorithms of image analysis, the optimization algorithm being an algorithm for adjusting the hue, saturation, and contrast of images; adjusting the resolution of images according to requirements of a flight path and a task target, and the adjustment mode being increasing the resolution in a key area and decreasing the resolution in a non-key area. Image data of multiple unmanned aerial vehicles is processed, the processing including cooperative processing and storage, and display content is optimized according to historical task data and real-time environmental changes.

5. The method of claim 1, wherein, The environmental data includes illumination and climate changes.

6. A drone image panoramic presentation system, characterized in that, The system includes: a basic information acquisition module that acquires sensor types, the sensors including RGB cameras, depth sensors, and weather sensors, the sensors being used to collect data in a flight path, the sensor data including position information, flight angles, flight speeds, heights, and environmental data; a display module that compares the position information with detection areas, determines a display mode according to the comparison result, acquires task requirements, and matches display content according to the task requirements; a content adjustment module that acquires multiple display contents, extracts key feature points in the display contents, finds corresponding relationships between images according to the key feature points, aligns the multiple display contents through the corresponding relationships, performs splicing on the multiple display contents, acquires user instructions, and adjusts the display contents in real time according to the user instructions; an optimization module that acquires real-time data through an illumination intensity sensor, adjusts exposure of images, and processes image data of multiple unmanned aerial vehicles based on color difference compensation and contrast optimization algorithms of image analysis.

7. The unmanned aerial vehicle image panorama presentation system of claim 6, wherein, The display module includes: a region comparison unit that acquires key detection area information, compares position information with detection areas, and identifies key features of the areas if it is determined that the unmanned aerial vehicles are located in the key detection areas; a display unit that acquires a display mode, the display mode including panoramic display and specific area display, determines the display mode according to the comparison result, acquires task requirements, and the task requirements including environmental monitoring, post-disaster evaluation, and inspection; a display content selection unit that matches display content according to the task requirements, the display content including magnified details, real-time flight angles, and real-time flight heights.

8. The unmanned aerial vehicle image panorama presentation system of claim 7, wherein, The content adjustment module includes: a display feature point unit that acquires multiple display contents, the multiple display contents including different angles, different flight heights, and different illumination conditions, and extracts key feature points in the display contents; a content splicing unit that finds corresponding relationships between images according to the key feature points, aligns the multiple display contents through the corresponding relationships, splices the multiple display contents, and acquires user instructions, the user instructions including voice instructions, gesture controls, or APP adjustments; a content adjustment unit that adjusts the display contents in real time according to the user instructions, the adjustment mode including adjustment of viewing angles, display areas, and display contents.

9. The unmanned aerial vehicle image panorama presentation system of claim 8, wherein, The optimization module includes: a color difference optimization unit that acquires real-time data through an illumination intensity sensor, adjusts exposure of images, and processes image data of multiple unmanned aerial vehicles based on color difference compensation and contrast optimization algorithms of image analysis, the optimization algorithms being used to adjust hues, saturation, and contrast of the images; a resolution optimization unit that adjusts resolution of images according to requirements of flight paths and task targets, the adjustment mode being to increase resolution in key areas and to decrease resolution in non-key areas; an image processing unit that processes image data of multiple unmanned aerial vehicles, the processing including cooperative processing and storage, and display content is optimized according to historical task data and real-time environmental changes.

10. The unmanned aerial vehicle image panorama presentation system of claim 9, wherein, The environmental data includes lighting and weather changes.

Images