A method and system for rapid detection and positioning of high-value targets based on ultra-wide-width rotary scanning remote sensing images

Abstract

A method and system for rapid detection and positioning of high-value targets based on ultra-wide-width rotary scanning remote sensing images belongs to the field of computer algorithm technology and is used to rapidly identify and locate high-value targets in remote sensing images. The method comprises: acquiring an ultra-wide-width swing-scan remote sensing image and the timestamp, remote sensing satellite orbit data, and swing-scan camera parameters corresponding to each pixel column in the image; using this data, calculating the overlap ratio required for each pixel position in real time, and segmenting the ultra-wide-width swing-scan remote sensing image into slices of various sizes; using the slices as input to a detector, which outputs a target detection frame and maps the detection frame back to the ultra-wide-width remote sensing image based on the slice's position in the original image; using the pixel coordinates of the target detection frame's center as the target's image position, and mapping the target pixel coordinates to WGS84 coordinates to complete the detection and positioning of high-value targets. The method is suitable for rapid identification and positioning of high-value targets in remote sensing images.

Description

Technical Field

[0001] The present invention belongs to the field of computer algorithm technology, and specifically relates to a high-value target rapid detection and positioning algorithm based on ultra-wide sweep remote sensing images, which realizes rapid recognition and positioning of high-value targets in remote sensing images. Background Art

[0002] In the field of remote sensing, high-resolution imaging systems play a critical role in acquiring detailed and accurate spatial information about the Earth's surface. Among these systems, rotary sweep cameras, a key innovation, offer the unique advantage of capturing wide ground coverage areas with high precision. Swing sweep cameras are designed to scan wide areas, capturing sequential images using a rotating mechanism. These images are then stitched together to form a continuous panoramic view of the target area. This imaging method enables the acquisition of regional information over a large area in a single pass, easily covering swaths of thousands of kilometers. This significantly reduces revisit times and enhances the ability to rapidly detect ships, aircraft, and ground targets. However, remote sensing images obtained using this imaging method face several key challenges. First, as the swath width increases, image resolution also increases significantly. This makes inputting ultra-wide remote sensing images into detectors a primary challenge for target detection in remote sensing images. Second, as the swing sweep angle increases, the distance between object points and the image plane also increases, resulting in a sharp decrease in the ground sampling distance. This results in sub-pixelization of the edges of the imaged area along the track, and compression of objects on both sides of the image plane along the track. Furthermore, in side-view scenarios (i.e., those with large panning angles), the target object exhibits different characteristic information than in top-down scenarios and causes greater geometric distortion, which further complicates target detection in remote sensing images. Overcoming these difficulties and achieving rapid detection and localization of high-value targets in ultra-wide-panning panning remote sensing images is a crucial research topic due to its widespread real-world applications.

[0003] With the rapid development of deep learning technology and the emergence of large-scale labeled remote sensing image datasets in recent years, object detection in remote sensing images has seen significant improvements in both accuracy and speed. However, achieving efficient object detection in ultra-wide remote sensing images still faces a significant challenge: unlike general object detection tasks where images are directly fed into the detector, ultra-wide remote sensing images cannot be directly fed into the detector due to the memory limitations of the graphics processing unit (GPU). Furthermore, downsampling ultra-wide remote sensing images to a size suitable for detector input results in information loss due to the reduced resolution, especially for small-sized object detection. The current paradigm proposed to address this problem is to crop the ultra-wide image to a size suitable for detector input (e.g., 800×800 pixels) using a sliding window at a fixed stride. All slices are then fed into the detector and the detection data is mapped onto the original image for synthesis.

[0004] However, for ultra-wide-width panning remote sensing images, since their spatial resolution decreases significantly with increasing panning angle, simply cropping the image using a sliding window method based on empirically set overlap ratios can lead to two problems: If the overlap ratio is set too large, fixed-stride segmentation will generate too many redundant slices at high panning angles due to low spatial resolution, impacting detection speed. If the overlap ratio is set too small, fixed-stride segmentation will cause complete objects to be segmented into two adjacent slices at low panning angles, especially near the nadir, due to high spatial resolution. This can lead to misidentification, missed detections, and target positioning errors. In this situation, a natural question is whether a segmentation method more suitable for ultra-wide-width panning remote sensing images can be used to improve detection speed while minimizing the degradation of target detection and positioning accuracy. Summary of the Invention

[0005] The purpose of the present invention is to provide a method for rapid detection and positioning of high-value targets based on ultra-wide-width rotary scanning remote sensing images, which is used to realize rapid identification and positioning of high-value targets in remote sensing images, while improving the detection speed while ensuring that the target detection and positioning accuracy is not reduced as much as possible.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The present invention provides a method for quickly detecting and locating high-value targets based on ultra-wide-width rotary scanning remote sensing images, the method comprising the following steps:

[0008] Step S1: Obtaining an ultra-wide swing-scan remote sensing image and the timestamp corresponding to each column of pixels in the image, remote sensing satellite orbit data, and swing-scan camera parameters;

[0009] Step S2: Using the remote sensing satellite orbit data, the parameters of the swing-scan camera, and the ultra-wide swing-scan remote sensing image, the overlap ratio required for the corresponding pixel position is calculated in real time, and the ultra-wide swing-scan remote sensing image is divided into slices of several sizes according to the overlap ratio;

[0010] Step S3: Using slices of several sizes as input to the detector, the detector outputs the target detection frame, and maps the detection frame back to the ultra-wide remote sensing image based on the position of the slice in the original image;

[0011] Step S4: The pixel coordinates of the center of the target detection frame are used as the image position of the target, and the target pixel coordinates are mapped to the WGS84 coordinates to complete the detection and positioning of the high-value target;

[0012] Step S5: Use the test set, known target location information, and nearest neighbor matching to calculate the positioning error to measure the performance of the positioning method.

[0013] Furthermore, in another preferred embodiment, the above step S1 is specifically as follows:

[0014] In a simulation environment, a scene is built where a swing-scan remote sensing camera shoots a target. The ultra-wide swing-scan remote sensing image after detector superposition is output, and the timestamp, remote sensing satellite orbit data, and swing-scan camera parameters corresponding to each column of pixels in the image are also output simultaneously.

[0015] Furthermore, in a preferred embodiment, the above-mentioned parameters of the swing-scan camera include detector resolution, pixel physical size, focal length and angle information.

[0016] Furthermore, there is a preferred embodiment that uses a spatial resolution model of a sweeping remote sensing satellite to adaptively segment the remote sensing image.

[0017] Furthermore, in another preferred embodiment, in the above step S3, a non-maximum suppression algorithm is used to suppress the overlapping targets.

[0018] Furthermore, there is a preferred embodiment that uses a rigorous geometric model of swing scanning imaging to map the target pixel coordinates to WGS84 coordinates.

[0019] Furthermore, in another preferred embodiment, the above step S5 is specifically as follows:

[0020] The collected test set is used to test and compare the inference speed and mAP of the overall algorithm, and the overall performance of the algorithm is measured by using known target location information and nearest neighbor matching to calculate the positioning error.

[0021] The method for rapid detection and positioning of high-value targets based on ultra-wide-width rotary sweep remote sensing images described in the present invention can be fully implemented using computer software. Therefore, correspondingly, the present invention also provides a system for rapid detection and positioning of high-value targets based on ultra-wide-width rotary sweep remote sensing images, the system comprising:

[0022] A storage device for obtaining ultra-wide swing-scan remote sensing images and the timestamp corresponding to each column of pixels in the image, remote sensing satellite orbit data, and swing-scan camera parameters;

[0023] A storage device for calculating the overlap ratio required for corresponding pixel positions in real time using remote sensing satellite orbit data, swing-scan camera parameters, and ultra-wide swing-scan remote sensing images, and for dividing the ultra-wide swing-scan remote sensing images into slices of several sizes according to the overlap ratio;

[0024] A device for taking slices of several sizes as input to a detector, outputting a target detection frame, and mapping the detection frame back to a storage device for the ultra-wide remote sensing image based on the position of the slice in the original image;

[0025] A storage device for using the pixel coordinates of the center of the target detection frame as the image position of the target and mapping the target pixel coordinates to WGS84 coordinates to complete the detection and positioning of high-value targets;

[0026] A storage device for measuring the performance of a positioning method using a test set, known target location information, and nearest neighbor matching to calculate positioning errors.

[0027] The present invention also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, any one of the above-mentioned methods for rapid detection and positioning of high-value targets based on ultra-wide-width rotary scanning remote sensing images is executed.

[0028] The present invention also provides a computer device, which includes a memory and a processor, wherein a computer program is stored in the memory. When the processor runs the computer program stored in the memory, the processor executes any one of the above-mentioned methods for rapid detection and positioning of high-value targets based on ultra-wide-width rotary scanning remote sensing images.

[0029] The beneficial effects of the present invention are:

[0030] This paper proposes a method for rapid detection and positioning of high-value targets based on ultra-wide-width rotary-scan remote sensing imagery. This method constructs a dataset of swing-scan remote sensing images and implements a full-link simulation from swing-scan remote sensing images to high-precision latitude and longitude positions of targets. This method can effectively identify and locate high-value targets in ultra-wide-width rotary-scan remote sensing imagery, achieving faster detection and positioning speeds than traditional methods while maintaining accuracy.

[0031] 2. The present invention solves the input problem of ultra-wide remote sensing images in traditional methods, realizes rapid detection and positioning of large images of any size, and ensures that the accuracy is not reduced. In addition, the present invention can be used in conjunction with the most advanced detectors to achieve faster detection speed and detection accuracy.

[0032] The present invention is used to realize rapid recognition and positioning of high-value targets in remote sensing images. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are 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.

[0034] Figure 1This is a flow chart of the overall solution of a method for rapid detection and positioning of high-value targets based on ultra-wide-width rotary scanning remote sensing images according to the present invention;

[0035] Figure 2 It is the characteristic diagram of the rotary sweep remote sensing image of the present invention;

[0036] Figure 3 is a schematic diagram of the rotary sweep remote sensing according to the present invention;

[0037] Figure 4 Schematic diagram of the segmentation algorithm of the present invention;

[0038] Figure 5 The remote sensing satellite orbit data of the present invention;

[0039] Figure 6 This is a diagram showing the relationship between the optical center of the camera and the object point during the swing scanning imaging process described in the present invention;

[0040] Figure 7 It is the vertical track direction ground pixel resolution model of the present invention;

[0041] Figure 8 It is the ground pixel resolution model in the along-track direction of the present invention;

[0042] Figure 9 is an example diagram of the segmentation algorithm described in the present invention;

[0043] Figure 10 It is a strict geometric model of ultra-wide sweep imaging described in the present invention;

[0044] Figure 11 This is the time-mAP comparison diagram of the present invention;

[0045] Figure 12 This is a time-position error comparison diagram according to the present invention. DETAILED DESCRIPTION

[0046] The specific embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The following embodiments will help those skilled in the art further understand the present invention, but are not intended to limit the present invention in any form. It should be noted that those skilled in the art may make various changes and improvements without departing from the scope of the present invention, and these are all within the scope of protection of the present invention.

[0047] Implementation method 1, see Figure 1 This embodiment provides a method for rapid detection and positioning of high-value targets based on ultra-wide sweep remote sensing images, which is used to achieve rapid identification and positioning of high-value targets in remote sensing images. Specifically, the following steps are included: Figure 1 As shown:

[0048] Step 1: Build a scene in a simulation environment where a pendulum-scan remote sensing camera captures a target. Output the ultra-wide-format pendulum-scan remote sensing image after detector stacking. Simultaneously, output the timestamp, remote sensing satellite orbit data, and pendulum-scan camera parameters (including detector resolution, pixel physical size, focal length, and angle information) corresponding to each pixel in the image. The overall system inputs are satellite orbit data, camera parameters, and ultra-wide-format pendulum-scan remote sensing images.

[0049] Step 2: Using the input satellite orbit data, camera parameters, and ultra-wide-angle scanning remote sensing image, the required overlap ratio for the corresponding pixel position is calculated in real time. The ultra-wide-angle scanning remote sensing image is then divided into several slices of appropriate size (e.g., 800×800 pixels) as the detector input.

[0050] Step 3: Use several slices of the cropped image as input to the detector, output the target detection frame, and map the detection frame back to the ultra-wide remote sensing image based on the position of the slice in the original image. For the problem of repeated detection of overlapping targets, the non-maximum suppression algorithm is used to suppress it.

[0051] Step 4: For the output detection frame information, take the pixel coordinates of the detection frame center as the image position of the target. Use the rigorous geometric model of the swing scanning imaging to map the target pixel coordinates to the WGS84 coordinates to achieve detection and positioning of high-value targets.

[0052] Step 5: Use the collected test set to compare the overall algorithm's inference speed and mAP. Using the known target location information, calculate the positioning error using nearest neighbor matching. This provides a comprehensive performance measurement of the algorithm.

[0053] The high-value target rapid detection and positioning method proposed in this implementation builds a data set of pan-scan remote sensing images, enabling full-link simulation from pan-scan remote sensing images to high-precision target latitude and longitude positions. This method can effectively identify and locate high-value targets in ultra-wide-width pan-scan remote sensing images, achieving faster detection and positioning speeds than traditional methods while maintaining accuracy.

[0054] Implementation method 2, see Figures 2 to 12 This embodiment is described in detail. This embodiment specifically describes the method for rapid detection and positioning of high-value targets based on ultra-wide-width rotary sweep remote sensing images described in the first embodiment.

[0055] Step 1: Build a scene in a simulation environment where a pendulum-scan remote sensing camera captures a target. Output the ultra-wide-format pendulum-scan remote sensing image after detector stacking. Simultaneously, output the timestamp, remote sensing satellite orbit data, and pendulum-scan camera parameters (including detector resolution, pixel physical size, focal length, and angle information) corresponding to each pixel in the image. The overall system inputs are satellite orbit data, camera parameters, and ultra-wide-format pendulum-scan remote sensing images.

[0056] Specifically include:

[0057] Simulation scene construction and data output, such as Figures 2 to 3 As shown in the figure, an ultra-wide sweep remote sensing satellite shooting scene is built in the Spacesim simulation system, and different types of ships and aircraft models are randomly placed in the scene as targets to be detected. The remote sensing satellite is used to shoot the ground scene to generate remote sensing images, and the orbit data of the remote sensing satellite is output, as shown in the figure. Figure 5 shown.

[0058] Step 2: Using the input satellite orbit data, camera parameters, and ultra-wide-angle scanning remote sensing image, the required overlap ratio for the corresponding pixel position is calculated in real time. The ultra-wide-angle scanning remote sensing image is then divided into several slices of appropriate size (e.g., 800×800 pixels) as the detector input.

[0059] Specifically include:

[0060] Ultra-wide sweep remote sensing image segmentation, since remote sensing images cannot be directly input into the detector for target detection, it is necessary to segment large-scale remote sensing images into small slices suitable for input. Figure 4 As shown in FIG, the spatial resolution model of the sweep remote sensing satellite is used to realize the adaptive segmentation of large-scale remote sensing images.

[0061] During the scanning period, the field of view angle corresponding to a single pixel of the area array CMOS camera is:

[0062] (1)

[0063] like Figure 6 As shown, when the camera sweep angle is When the angle between OS and OD Using the law of sine we have:

[0064] (2)

[0065] in, is the radius of the Earth, is the satellite orbit altitude.

[0066] and The distance between them (object distance) is:

[0067] (3)

[0068] From this we can get, such as Figure 7 The ground pixel resolution in the vertical direction is shown:

[0069] (4)

[0070] in, is the camera's vertical field of view, Point The corresponding pixel coordinates in the vertical direction.

[0071] Considering the Figure 8 The ground pixel resolution along the track is shown. The ground pixel resolution along the track is the arc segment. The length of

[0072] (5)

[0073] in, for and The angle of for and Angle.

[0074] Approximately to the vertical track direction, the sine theorem can be used to obtain and for:

[0075] (6)

[0076] The ground pixel resolution can be obtained:

[0077] (7)

[0078] in, is the camera's vertical field of view, Point The corresponding pixel coordinates in the vertical track direction.

[0079] For example, Figure 9 As shown:

[0080] Given a raw ultra-wide-width panning remote sensing image, the absolute overlap size is first set based on prior information about the identified object (for example, the approximate size determined based on the object's type). Next, starting from the upper left corner of the original ultra-wide-width panning remote sensing image (i.e., pixel coordinate (0,0)), an initial 800x800 pixel patch is extracted along the track (pixel rows) and vertically (pixel columns). The ground resolution corresponding to the edge pixels is then calculated based on the panning camera's spatial resolution model. The image overlap ratio is then calculated based on a preset overlap value, achieving adaptive image segmentation at varying resolutions.

[0081] Step 3: Use several slices of the cropped image as input to the detector, output the target detection frame, and map it back to the ultra-wide remote sensing image based on the position of the slice in the original image. For the problem of repeated detection of overlapping targets, the non-maximum suppression algorithm is used to suppress it.

[0082] Specifically include:

[0083] For target detection, the image data output from step 1 above is used to create a target detection dataset. This implementation uses a simulated environment to capture targets using a panning remote sensing camera. The orbital altitude is 450 km, the orbital eccentricity is zero, and the vertical panning angle range is 0° to 65°. To enhance the dataset's coverage, different camera pixel sizes and focal lengths are set for different panning angle ranges to simulate image capture conditions at different orbital altitudes. The initial dataset consists of 1,803 images covering 22 object categories, including two main categories: aircraft and ships. Aircraft includes four subcategories, such as B52 and B737, and ships include 16 subcategories, such as Acasta and Aigle. The image size is 800 × 800 pixels. To improve the model's rotation invariance, the dataset is scaled, rotated, and subjected to perspective transformations. The final dataset contains 28,848 images and 27,725 instances.

[0084] The detection model for this method was implemented using the YOLOv5 framework. The training set and validation set ratio was 7:3, the initial learning rate was set to 0.01, and SGD was used as the optimizer for model training. The training process used a bit rate of 8 for 300 epochs. The detection confidence level was 0.10, and the IoU threshold was 0.50. After detection, the detection bounding boxes generated by all patches were re-projected onto the original large image. In the overlapping regions of adjacent images, the non-maximum suppression algorithm (NMS) was used to suppress the results with a threshold of 0.1.

[0085] Step 4: For the output detection frame information, take the pixel coordinates of the detection frame center as the image position of the target. Use the rigorous geometric model of the swing scanning imaging to map the target pixel coordinates to the WGS84 coordinates to achieve detection and positioning of high-value targets.

[0086] Specifically include:

[0087] Target position calculation, after using the detector to obtain the pixel coordinates of the target in the image, it is necessary to map the pixel coordinates back to WGS84 coordinates to obtain the longitude and latitude information of the target.

[0088] Considering the Figure 10 The strict geometric imaging model of the sweep remote sensing satellite shown is:

[0089] (8)

[0090] Generally, the imaging model is a series of transformation processes from the pixel coordinate system to the WGS84 coordinate system. For array scanning satellites, a rotation matrix is ​​introduced. , used to describe the geometric relationship between the equivalent area array CMOS and the camera. Rewritten as:

[0091] (9)

[0092] in, The coordinates of the ground point corresponding to the image point in the WGS84 coordinate system; The WGS84 coordinates of the array scanning satellite when it is in orbit; Represents the rotation matrix from the J2000 coordinate system to the WGS84 coordinate system; Represents the rotation matrix from the satellite orbit coordinate system to the J2000 coordinate system; Represents the rotation matrix from the satellite body coordinate system to the satellite orbit coordinate system; Represents the rotation matrix from the camera coordinate system to the satellite body coordinate system; Represents the rotation matrix from the equivalent array CMOS coordinate system to the camera coordinate system.

[0093] After establishing the correspondence between each pixel in the image and the coordinates of the ground object point, the remote sensing image can be used to locate the ground target. Assuming that the elevation H of the ground target to be located is known, it can be assumed that the target is located on the following ellipsoid:

[0094] (10)

[0095] Where a is the major axis of the Earth and b is the minor axis.

[0096] In summary:

[0097] (11)

[0098] The two solutions of the equation represent the intersection of the vector corresponding to the image pixel coordinates and the earth ellipsoid. Substituting the smaller root into the above formula (11) can obtain the coordinates of the object point D in the WGS-84 coordinate system.

[0099] The center of the detection frame is taken as the target position, the height is preset to 0.5km, and the position calculation module is input to obtain the longitude and latitude corresponding to each point.

[0100] Step 5: Use the collected test set to compare the overall algorithm's inference speed and mAP. Using the known target location information, calculate the positioning error using nearest neighbor matching. This provides a comprehensive performance measurement of the algorithm.

[0101] Specifically:

[0102] Figure 11 The figure shows a comparison of the inference speed and mAP of the overall algorithm. It can be seen from the figure that compared with the traditional algorithm, the AICM method proposed in this embodiment not only achieves a higher inference speed, but also has a certain improvement in mAP. Specifically, the inference speed is improved by 7.39%, and the mAP is improved by 7.54%.

[0103] Figure 12 The figure shows a time-position error comparison diagram. It can be seen from the figure that compared with the traditional algorithm, the AICM method proposed in this embodiment not only achieves a higher inference speed, but also has a certain improvement in positioning accuracy. Specifically, in the case of small sweep angles ([0, 25]), the positioning accuracy is improved by 4.13%.

[0104] Implementation method 3: Any of the above methods for rapid detection and positioning of high-value targets based on ultra-wide-width rotary sweep remote sensing images can be implemented entirely using computer software. Therefore, correspondingly, this implementation method provides a system for rapid detection and positioning of high-value targets based on ultra-wide-width rotary sweep remote sensing images, the system comprising:

[0105] A storage device for obtaining ultra-wide swing-scan remote sensing images and the timestamp corresponding to each column of pixels in the image, remote sensing satellite orbit data, and swing-scan camera parameters;

[0106] A storage device for calculating the overlap ratio required for corresponding pixel positions in real time using remote sensing satellite orbit data, swing-scan camera parameters, and ultra-wide swing-scan remote sensing images, and for dividing the ultra-wide swing-scan remote sensing images into slices of several sizes according to the overlap ratio;

[0107] A device for taking slices of several sizes as input to a detector, outputting a target detection frame, and mapping the detection frame back to a storage device for the ultra-wide remote sensing image based on the position of the slice in the original image;

[0108] A storage device for using the pixel coordinates of the center of the target detection frame as the image position of the target and mapping the target pixel coordinates to WGS84 coordinates to complete the detection and positioning of high-value targets;

[0109] A storage device for measuring the performance of a positioning method using a test set, known target location information, and nearest neighbor matching to calculate positioning errors.

[0110] Implementation method 4. This implementation method provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it executes a method for rapid detection and positioning of high-value targets based on ultra-wide-width rotary scanning remote sensing images as described in any one of the above implementation methods.

[0111] Implementation method five: This implementation method provides a computer device, which includes a memory and a processor, wherein a computer program is stored in the memory. When the processor runs the computer program stored in the memory, the processor executes a method for rapid detection and positioning of high-value targets based on ultra-wide-width rotary scanning remote sensing images as described in any one of the above implementation methods.

[0112] A computer device is provided in this embodiment. The hardware device of this part is a general model and is not shown in the form of a diagram. The system includes a processor and a memory, wherein the processor and the memory can be connected via a bus or other means. The memory is a non-transitory computer-readable storage medium that can be used to store non-transitory software programs, non-transitory computer executable programs and modules, and corresponding program instructions / modules. The processor executes various functional applications and data processing of the processor by running the non-transitory software programs, instructions and modules stored in the memory, so as to realize the method and steps for rapid detection and positioning of high-value targets based on ultra-wide-width rotary scanning remote sensing images in the above-mentioned method embodiment.

[0113] In the description of this specification, the reference terms "one embodiment," "some embodiments," "example," "specific example," or "some examples" mean that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0114] The foregoing description is merely an embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that the present invention is susceptible to various modifications and variations. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention shall be included within the scope of the claims.

Claims

1. A method for rapid detection and positioning of high-value targets based on ultra-wide sweep remote sensing images, characterized in that: The method is: S1: Obtain ultra-wide swing-scan remote sensing images and the timestamp corresponding to each column of pixels in the image, remote sensing satellite orbit data, and swing-scan camera parameters; S2: Using remote sensing satellite orbit data, pendulum camera parameters, and ultra-wide-width pendulum remote sensing images, the required overlap ratio for corresponding pixel positions is calculated in real time. The ultra-wide-width pendulum remote sensing images are then divided into slices of several sizes based on the overlap ratio. S3: Take slices of several sizes as input to the detector, output the target detection box, and map the detection box back to the ultra-wide remote sensing image based on the position of the slice in the original image; S4: The pixel coordinates of the center of the target detection frame are used as the image position of the target, and the target pixel coordinates are mapped to WGS84 coordinates to complete the detection and positioning of high-value targets; S5: The performance of the positioning method is measured using the test set, known target location information, and nearest neighbor matching to calculate the positioning error.

2. The method for rapid detection and positioning of high-value targets based on ultra-wide-width rotary sweep remote sensing images according to claim 1 is characterized in that: S1 is specifically: In a simulation environment, a scene is built where a swing-scan remote sensing camera shoots a target. The ultra-wide swing-scan remote sensing image after detector superposition is output, and the timestamp, remote sensing satellite orbit data, and swing-scan camera parameters corresponding to each column of pixels in the image are also output simultaneously.

3. The method for rapid detection and positioning of high-value targets based on ultra-wide-width rotary sweep remote sensing images according to claim 2 is characterized in that: The parameters of the swing scan camera include detector resolution, pixel physical size, focal length, and angle information.

4. The method for rapid detection and positioning of high-value targets based on ultra-wide-width rotary sweep remote sensing images according to claim 1 is characterized in that: The spatial resolution model of the sweeping remote sensing satellite is used to adaptively segment the remote sensing images.

5. The method for rapid detection and positioning of high-value targets based on ultra-wide sweep remote sensing images according to claim 1 is characterized in that: In S3, the non-maximum suppression algorithm is used to suppress overlapping targets.

6. The method for rapid detection and positioning of high-value targets based on ultra-wide sweep remote sensing images according to claim 1, characterized in that: The target pixel coordinates are mapped to WGS84 coordinates using a rigorous geometric model of pendulum scanning imaging.

7. The method for rapid detection and positioning of high-value targets based on ultra-wide sweep remote sensing images according to claim 1, characterized in that: S5 is specifically: The collected test set is used to test and compare the inference speed and mAP of the overall algorithm, and the overall performance of the algorithm is measured by using known target location information and nearest neighbor matching to calculate the positioning error.

8. A high-value target rapid detection and positioning system based on ultra-wide sweep remote sensing images, characterized in that: The system includes: A storage device for obtaining ultra-wide swing-scan remote sensing images and the timestamp corresponding to each column of pixels in the image, remote sensing satellite orbit data, and swing-scan camera parameters; A storage device for calculating the overlap ratio required for corresponding pixel positions in real time using remote sensing satellite orbit data, swing-scan camera parameters, and ultra-wide swing-scan remote sensing images, and for dividing the ultra-wide swing-scan remote sensing images into slices of several sizes according to the overlap ratio; A device for taking slices of several sizes as input to a detector, outputting a target detection frame, and mapping the detection frame back to a storage device for the ultra-wide remote sensing image based on the position of the slice in the original image; A storage device for using the pixel coordinates of the center of the target detection frame as the image position of the target and mapping the target pixel coordinates to WGS84 coordinates to complete the detection and positioning of high-value targets; A storage device for measuring the performance of a positioning method using a test set, known target location information, and nearest neighbor matching to calculate positioning errors.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, executes a method for rapid detection and positioning of high-value targets based on ultra-wide-width rotary scanning remote sensing images as described in any one of claims 1 to 7.

10. A computer device, characterized in that: The device includes a memory and a processor, wherein a computer program is stored in the memory. When the processor runs the computer program stored in the memory, the processor executes a method for rapid detection and positioning of high-value targets based on ultra-wide-width rotary scanning remote sensing images as described in any one of claims 1 to 7.

Images