A flight simulation method and system based on unmanned aerial vehicle backlighting imaging technology

Abstract

This patent proposes a flight simulation method and system based on UAV-mounted backlighting imaging technology. This technology solves the key scientific issues of target perception and recognition of UAV platforms in backlighting environments, and provides an innovative solution for the cross-study of high dynamic range imaging, target detection, and intelligent flight control. By introducing a backlighting imaging camera and dynamic aperture control technology, combined with multi-point calibration and multi-scale noise reduction methods, it effectively overcomes traditional problems such as insufficient imaging dynamic range, loss of image details, and random noise interference in backlighting environments. At the same time, the image enhancement method based on the generative adversarial network achieves high-fidelity reconstruction of target texture and structural features under complex lighting conditions, avoiding the common artifacts and color drift problems in traditional enhancement algorithms. Furthermore, by combining the enhanced and optimized YOLO detection framework with a high-resolution feature pyramid network, a high-precision detection model for small targets adapted to backlighting scenes was successfully constructed, which significantly improved the robustness and real-time performance of detection while maintaining detection accuracy.

Description

Technical Field

[0001] The present invention belongs to the field of computer vision and unmanned aerial vehicle application technology, and specifically relates to a technology for image enhancement, detection and tracking of targets in backlit or high dynamic lighting scenes. Background Art

[0002] With the development of drone technology, drones are increasingly being used in intelligent surveillance, rescue and search, ecological monitoring, and other fields. However, in complex lighting environments, particularly backlighting, drone target perception still faces significant technical bottlenecks. These conditions often result in uneven illumination of the imaged target, reduced contrast, and loss of detail, severely impacting the accuracy of target detection and tracking.

[0003] Backlighting is a high-dynamic-range lighting scenario in which the background light source (such as the sun) is much stronger than the light reflected by the target. This results in: 1) the target being too dark or completely obscured by shadows, making it difficult for conventional imaging systems to distinguish details between the background and the target; 2) overexposure of highlights, where the background's excessive brightness obscures image details and causes significant information loss; and 3) blurred target outlines, where light scattering or strong edge halation make it difficult to detect the target's edges. Traditional imaging techniques, such as high-dynamic-range imaging, can partially improve the brightness range, but typically require the fusion of multiple image frames, making it difficult to meet the real-time perception requirements of drones.

[0004] Current backlit image processing technologies are mainly divided into the following categories: 1) Brightness enhancement based on global adjustment: enhancing the target area by increasing the overall brightness of the image. However, this method easily causes overexposure of the background or insufficient contrast between the target and the background, making it impossible to accurately separate the target; 2) Local enhancement based on the Retinex model: The Retinex model achieves target enhancement through local contrast adjustment, but it is often accompanied by artifacts (such as chromatic aberration) or loss of texture details in backlit scenes; 3) Image enhancement based on deep learning: Using generative adversarial networks or convolutional neural networks to enhance backlit scene images, although it improves the ability to restore details, the model is usually highly dependent on training data and is difficult to generalize to actual complex scenes. In addition, this type of method has high requirements for hardware computing resources and is difficult to implement in real-time drone applications.

[0005] Under backlight conditions, target detection and tracking technology faces the following challenges: 1) Low-contrast targets are difficult to detect: Due to the large contrast in light intensity, the distinction between the target and the background is reduced, and the accuracy of existing detection algorithms (such as YOLO or SSD) is significantly reduced; 2) Small target detection is unstable: When the drone flies at a high altitude, the resolution of small targets is limited and the target is easily interfered with by background noise; 3) Multiple target occlusion and discontinuous tracking: Under backlight conditions, the target may not be tracked continuously due to occlusion or blurred edges, resulting in loss of tracking trajectory. Summary of the Invention

[0006] The technical problems to be solved by the present invention are:

[0007] In order to solve the problems of target detection and tracking technology under backlight conditions, such as poor robustness and real-time performance of target perception, limited resolution of small targets when the UAV is flying at a high altitude, and multi-target occlusion and tracking discontinuity, the present invention provides a flight simulation method and system based on UAV-mounted backlight imaging technology.

[0008] The technical solution adopted by the present invention to solve the above technical problems is:

[0009] The present invention proposes a flight simulation method and system based on unmanned aerial vehicle (UAV) backlight imaging technology, the method comprising the following steps:

[0010] Step 1: Build a UAV platform, which includes a backlight imaging camera, a stabilized gimbal, a real-time data transmission module, and an image processor. The backlight imaging camera is mounted on the stabilized gimbal, and the backlight imaging camera transmits the image data sensed by the UAV during flight to the image processor via the real-time data transmission module.

[0011] Step 2: Secure the backlight imaging camera to a stabilized gimbal, ensuring its field of view is consistent with the drone's flight direction and capable of real-time adjustment.

[0012] Step 3: Use a multi-point calibration method to accurately calibrate the internal and external parameters of the backlight imaging camera (backlight imaging equipment) to ensure that lens distortion and geometric errors are eliminated;

[0013] Step 4: The backlight imaging camera is equipped with a dynamic aperture control mechanism to achieve automatic exposure adjustment under drastic changes in lighting conditions and optimize the imaging quality of the target area;

[0014] Step 5: Introduce a multi-scale noise reduction algorithm based on wavelet transform to suppress random noise interference caused by high dynamic range under backlight conditions;

[0015] Step 6: Build a lightweight generative adversarial network model, input the backlit image, and reconstruct the target texture and structural features through multi-layer feature extraction, avoiding artifacts or color drift problems caused by traditional methods;

[0016] Step 7: Based on the enhanced and optimized YOLO detection framework and combined with prior backlit scene data, a real-time target detection model is constructed to extract bounding boxes and classification probabilities of multiple target categories. A high-resolution feature pyramid network is used for small target areas to ensure the accuracy and robustness of target detection. Multi-feature fusion methods are used to further extract target key points and their spatial geometric characteristics, providing a standardized high-dimensional data description.

[0017] Step 8: Superimpose the UAV flight status parameters and light distribution parameters in real time to complete the flight simulation demonstration of the UAV-mounted backlight imaging technology.

[0018] Furthermore, the specific process of step one includes:

[0019] Equipped with a backlight imaging camera, a three-axis mechanically stabilized gimbal and a high-bandwidth real-time data transmission module, it forms a complete drone perception and transmission system framework.

[0020] Furthermore, the specific process of step 2 includes:

[0021] The gimbal uses high-precision servo control technology to ensure that the camera's boresight is stable and can be precisely adjusted under complex flight conditions.

[0022] Furthermore, the specific process of step three includes:

[0023] A multi-point calibration method is used to precisely calibrate the backlighting camera's intrinsic parameters (focal length, principal point position, and distortion coefficient) and extrinsic parameters (camera attitude and position). This calibration process then eliminates errors such as lens distortion, geometric offset, and optical axis misalignment, ensuring the geometric accuracy of the captured image.

[0024] Furthermore, the specific process of step 4 includes:

[0025] The deployment of a dynamic aperture control module based on adaptive light perception can quickly respond to lighting changes in backlit environments. This implements a coordinated adjustment mechanism for aperture, shutter speed, and ISO parameters to ensure optimal imaging quality in both bright and dark areas of the target area.

[0026] Furthermore, the specific process of step five includes:

[0027] A multi-scale noise reduction algorithm based on wavelet transform is introduced to perform noise suppression on backlit imaging data. During the noise reduction process, the high-frequency and low-frequency components of the image are separated to eliminate random noise interference while retaining the detailed features of the target area.

[0028] Furthermore, the specific process of step six includes:

[0029] A lightweight generative adversarial network model is designed. It takes raw image data under backlighting conditions and uses multi-layer feature extraction and illumination compensation to reconstruct the target's texture details and structural features. It then optimizes the generative network using adversarial and perceptual losses, avoiding artifacts and color drift that plague traditional algorithms in backlighting enhancement.

[0030] Furthermore, the specific process of the flight simulation demonstration of the UAV-mounted backlight imaging technology in step eight includes:

[0031] During flight, the drone's onboard backlight imaging camera collects environmental image data, including information about the target object, background scene, and lighting distribution. This data is optimized using dynamic aperture and backlight-aware imaging technology to ensure clear images even under highly variable lighting conditions. In backlight scenarios, the drone's flight status parameters are overlaid onto the image, dynamically displaying the flight status. Intuitive overlay annotations (such as bounding boxes, classification labels, and key points) are then used to analyze target perception capabilities in backlight conditions.

[0032] According to another aspect of the present invention, a flight simulation system (software) based on UAV-mounted backlight imaging technology is proposed, comprising:

[0033] A backlight imaging camera system is used to acquire environmental image data under backlight conditions; its configured dynamic aperture control mechanism optimizes the imaging quality of the target area through automatic exposure adjustment; the high-quality environmental image data acquired under backlight conditions is input into the data processing and image enhancement system in the image processor; corresponding to steps 1, 3, and 4, it is used to implement the functions of steps 1, 3, and 4;

[0034] The stabilization control system is used to ensure the stability of the imaging device during flight, the field of view adjustment capability, and the quality of image acquisition; the servo system of the stabilized gimbal is used to accurately control the motion state of the mechanical device, especially the precise operation of position, speed, and acceleration; corresponding to step 2, it is used to realize the function of step 2;

[0035] The image processor is used to read high-quality environmental image data under backlight conditions and provide basic processing for target perception and recognition. It is equipped with a data processing and image enhancement system and a target detection and feature extraction system.

[0036] A data processing and image enhancement system, which includes a wavelet transform multi-scale noise reduction algorithm, a lightweight generative adversarial network, and a multi-scale image enhancement algorithm, is used to reduce noise, enhance, and reconstruct target features of raw image data under backlight conditions, thereby improving perception and recognition performance; corresponding to step five, and is used to implement the functions of step five;

[0037] The target detection and feature extraction system uses the YOLO target detection framework to detect multiple target categories in backlit scenes in real time, extract key features, and generate standardized descriptions to provide input for flight decision-making. This corresponds to steps six and seven and implements their functions.

[0038] The beneficial technical effects of the present invention are:

[0039] The present invention effectively solves the key scientific issues of target perception and recognition of UAV platforms in backlit environments, and provides an innovative solution for the cross-study of high dynamic range imaging, target detection and intelligent flight control. By introducing backlit imaging cameras and dynamic aperture control technology, combined with multi-point calibration and multi-scale noise reduction methods, it effectively overcomes traditional problems such as insufficient imaging dynamic range, loss of image details and random noise interference in backlit environments. At the same time, the image enhancement method based on the generative adversarial network achieves high-fidelity reconstruction of target texture and structural features under complex lighting conditions, avoiding the common artifacts and color drift problems in traditional enhancement algorithms. Furthermore, by combining the enhanced and optimized YOLOv8 detection framework with a high-resolution feature pyramid network, a high-precision detection model for small targets adapted to backlit scenes was successfully constructed, which significantly improved the robustness and real-time performance of the detection while maintaining the detection accuracy.

[0040] The advantages of this invention are reflected in many aspects: First, this technology breaks through the dependence of traditional target detection methods on standard lighting conditions, and achieves significant improvement in imaging and detection performance, especially in complex scenes such as backlighting; second, through the deep collaboration between the UAV flight control system and the backlighting perception module, it solves the problems of data real-time and stability under high dynamic lighting changes; finally, through the three-dimensional flight simulation display platform, the UAV backlighting perception data and flight status parameters are integrated in real-time dynamic visualization for the first time, which not only verifies the effectiveness of the perception and detection algorithms, but also provides a new research tool for UAV mission planning and performance optimization in complex scenes.

[0041] This invention is a comprehensive solution combining illumination modeling, image enhancement, and target detection. Taking into account the dynamics and hardware limitations of drones, it significantly improves the robustness and real-time performance of target perception in backlit conditions, providing new technical support for drone applications in complex environments. The patented technology can ensure clear backlit target perception while reducing the complexity of drone imaging systems. This technology can support drone applications in a wider range of scenarios and improve drone autonomous perception systems.

[0042] The present invention is suitable for image enhancement, detection and tracking of targets in backlit or high dynamic lighting scenes, and is used in fields such as intelligent monitoring, emergency rescue, disaster monitoring and full-angle autonomous perception and navigation of unmanned aerial vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The present invention can be further understood by referring to the description provided below in conjunction with the accompanying drawings. These drawings, together with the detailed description that follows, constitute an integral part of this specification. They not only intuitively demonstrate the technical framework and implementation process of the present invention, but also further illustrate the core principles and technical advantages of the present invention through specific preferred embodiments. Through these drawings and description, one can clearly understand how the present invention achieves high-quality imaging, precise target perception and recognition, and dynamic flight simulation in backlit environments, as well as the overall technical solution and its practical application effects.

[0044] Figure 1 This is a flow chart of a flight simulation method based on UAV-mounted backlighting imaging technology according to an embodiment of the present invention.

[0045] Figure 2 Schematic diagram of a UAV platform equipped with a backlight imaging system according to an embodiment of the present invention.

[0046] Figure 3 1 is a schematic diagram of the principle of multi-point calibration of a backlight camera mounted on a drone in an embodiment of the present invention.

[0047] Figure 4 This is a flowchart of image processing and target detection and recognition in an embodiment of the present invention. DETAILED DESCRIPTION

[0048] like Figure 1-4 As shown, the present invention relates to a flight simulation method and system based on UAV-mounted backlight imaging technology. This method focuses on solving the technical challenges of target perception and recognition in backlighting scenarios, and achieves high-quality flight simulation through the synergy of multiple technologies. The following describes the implementation method in detail, covering four aspects: system construction, image processing, target detection and recognition, and flight simulation.

[0049] The present invention first designs a hardware platform of a backlight imaging system, which includes a backlight imaging camera, a dynamic aperture module, a stabilized gimbal, a real-time data transmission module and a drone body.

[0050] Step 1: Build a UAV platform equipped with a backlight imaging system;

[0051] The backlight imaging camera is mounted on a three-axis stabilized gimbal. The gimbal coordinates with the drone's flight control system to ensure the camera's field of view remains consistent with the target area. The overall structure of the drone platform has been optimized to reduce wind resistance and enhance flight stability.

[0052] Step 2: Fix the backlight imaging camera on the gimbal;

[0053] The control of the stabilized gimbal uses a three-dimensional rotation matrix, which is calculated as follows:

[0054] R=R z (ψ)R y (θ)R x (φ) (1)

[0055] Among them, R z (ψ),R y (θ),R x (φ) represents the rotation matrix around the x, y, and z axes respectively. The gimbal adjusts the camera's viewing angle in real time through feedback closed-loop control. The formula is:

[0056] e angle =θ desired -θ current (2)

[0057] The controller is based on the angle error e angle Output the corresponding driving signal.

[0058] Step 4: Configure a dynamic aperture control mechanism to achieve automatic exposure adjustment under drastic changes in lighting conditions and optimize the imaging quality of the target area;

[0059] The dynamic aperture module adjusts the aperture size in real time according to the ambient light conditions and adopts an exposure value optimization strategy. The aperture adjustment formula is:

[0060]

[0061] Where A is the aperture diameter, ΔL is the illumination difference, k is the adjustment coefficient, and t is the exposure time. By dynamically combining aperture adjustment and exposure time, the system can accurately image the target area even in strong backlight.

[0062] Step 5: Introduce a multi-scale noise reduction algorithm based on wavelet transform to suppress random noise interference caused by high dynamic range under backlight conditions;

[0063] Backlight imaging cameras are generated by encoding and decoding a mask of a target against a bright background. The quality of an optical system's imaging depends on the phase distribution of the exit pupil, so aberrations in the optical system will cause phase changes in the exit pupil. In physical optics, a generalized pupil function is often used to represent the phase distribution of the pupil. Taking into account the system's defocus τ, the specific expression for the exit pupil function can be given:

[0064] P(x,y,τ)=p(x,y)exp{i[f(x,y)+τ(x 2 +y 2 )]} (4)

[0065]

[0066] Among them, i 2= -1, τ represents the phase distribution of the defocus aberration on the pupil, D is the diameter of the system pupil, and f(x, y) represents the phase mask function of the optical system when a phase plate is inserted into the defocused state.

[0067] After knowing the exit pupil function of the system, we can give the point spread function used to characterize the imaging characteristics of the system in the spatial domain:

[0068] h(x′,y′,τ)=κ{F[P(x,y,τ)]F * [P(x,y,τ)]} (6)

[0069] Where F represents Fourier transform, κ is the normalization constant, and * represents conjugation.

[0070] After obtaining the point spread function of the optical imaging, performing Fourier transform on it can obtain the optical transfer function that characterizes the spatial frequency transfer characteristics of the system:

[0071] H(u,v,τ)=F[h(x′,y′,τ)] (7)

[0072] The backlight imaging camera is able to calculate the optical transfer function in advance through the phase plate surface type, and the physical system can perform a Fourier transform on the point spread function of the point light source imaging acquisition system to obtain the optical transfer function of the system.

[0073] Wiener filtering is also known as minimum mean square error filtering. This method treats the image and noise as random processes, with the ultimate goal of obtaining a statistical error function: The minimum estimate of Where f is the unprocessed original image information, Is the minimum estimate of the original image, and E is the expected difference between the original image and the minimum estimate. The expression formula is:

[0074]

[0075] Among them, |H(u,v) 2 =H * (u,v)H(u,v),H * (u,v) represents the complex conjugate of H(u,v), S n (u,v)=|N(u,v) 2 represents the noise power spectrum of image processing; S f (u,v)=|F(u,v) 2 Represents the power spectrum of the original image.

[0076] Under normal conditions, the distribution of most signals and noises cannot produce accurate results, so Equation (8) can be simplified to:

[0077]

[0078] There will inevitably be some random noise in the image perceived by the backlight imaging camera. In order to suppress the random noise in the high dynamic range image, multi-scale wavelet transform is used for noise reduction. The input image I(x,y) is decomposed into low-frequency component L and high-frequency component H. i , the specific formula is:

[0079]

[0080] Noise reduction is accomplished using the soft thresholding method, using the formula:

[0081]

[0082] Among them, H i ′ is the high-frequency component after noise reduction, and λ is the noise threshold, which is automatically estimated through noise statistics.

[0083] Step 6: Design a lightweight generative adversarial network model that takes a backlit image as input and extracts multiple layers of features to reconstruct the target's texture and structural features, avoiding artifacts or color drift caused by traditional methods.

[0084] Step 7: Based on the enhanced and optimized YOLOv8 detection framework and combined with prior backlighting scene data, a real-time object detection model is built to extract bounding boxes and classification probabilities of multiple categories of objects;

[0085] The target detection system uses the enhanced and optimized YOLOv8 framework. Input backlit image I input The detection network extracts multi-scale features and outputs the bounding box and category probability of the target through the fully connected layer. The loss function L of the bounding box is box for:

[0086]

[0087] in, is the predicted bounding box, is the true bounding box. The classification loss uses the cross entropy function, and the formula is:

[0088]

[0089] The complete detection loss is:

[0090] L total =L box +L cls (14)

[0091] On the basis of detecting the target, key point information is further extracted. The key point is determined by the response function R:

[0092]

[0093] Among them, Ω(k i ) is the pixel area around the keypoint, and F(p) is the eigenvalue. Multi-eigenvalue fusion is performed through a feature pyramid network, combining high-resolution features with low-resolution global features to generate the final target description.

[0094] Verification of the technical effect of the present invention:

[0095] This paper proposes a deep learning-based method for recognizing dim targets in backlit environments. By combining image preprocessing, deep convolutional neural networks (CNNs), and data enhancement techniques, it effectively addresses issues such as complex backgrounds, weak target contrast, and blurred target features in backlit environments. The following are specific implementation examples of this invention, demonstrating its effectiveness in real-world scenarios.

[0096] Case 1: Pedestrian Detection in Autonomous Driving

[0097] Pedestrian detection is a crucial task in autonomous driving systems. This is especially true in backlit environments, such as early morning or dusk, where the strong sunlight from the front can overexpose the background, blurring pedestrians' outlines or even rendering them completely unrecognizable. Traditional feature-based pedestrian detection methods struggle in these situations.

[0098] Implementation process:

[0099] Dataset Preparation: First, we used a backlight camera to generate a large number of images in backlighting environments. This dataset includes autonomous driving datasets for various backlighting scenarios. Data augmentation was performed on the dataset. This augmentation method simulated direct sunlight of varying intensities and angles, as well as varying lighting conditions under various weather conditions.

[0100] Image preprocessing and enhancement: Adaptive contrast enhancement is then performed on the original image to improve local contrast and ensure pedestrian visibility in backlit conditions. Secondly, background highlights are removed to preserve pedestrian details. Noise and shadows are also effectively removed.

[0101] Deep learning model training and detection: The YOLOv5 model is used for object detection. This model uses multiple convolutional layers to extract features of pedestrians in backlit backgrounds and combines feature fusion techniques to enhance the representation of features in low-contrast areas.

[0102] Test results: During the test, the system was able to accurately detect pedestrians in different backlighting environments, especially in low contrast and high light intensity conditions, with recognition accuracy improved by about 15% compared to traditional methods.

[0103] This implementation case demonstrates that deep learning-based object detection methods, particularly through the combination of backlight camera perception imaging, image preprocessing, and deep convolutional neural networks, can effectively improve the accuracy and robustness of pedestrian recognition in backlit environments. Application of this method in autonomous driving systems can significantly reduce the false recognition rate caused by backlighting and improve the reliability of pedestrian detection.

[0104] Case 2: Vehicle Identification in Security Monitoring

[0105] In the security surveillance field, especially road traffic monitoring, vehicle identification in backlit conditions is a long-standing challenge. Especially when the camera's orientation is misaligned with the angle of sunlight, the details of the vehicle can be completely lost due to the strong light, affecting the normal operation of the monitoring system.

[0106] Implementation process:

[0107] Dataset preparation: We collected road traffic backlight perception video data under various backlight conditions. The dataset includes various weather conditions, light intensities, and time periods to ensure the diversity of training data.

[0108] Image preprocessing and enhancement: Adaptive contrast enhancement and local histogram equalization methods are used to optimize the brightness and contrast of vehicle images under backlight, especially in strong sunlight, enhancing the vehicle's outline and texture.

[0109] Deep learning model training and detection: The Faster R-CNN model is used for vehicle detection. During the training process, images with backlit backgrounds and different lighting conditions are added to enable the network to learn the characteristics of vehicles in backlit environments.

[0110] Results: In real monitoring scenarios, the vehicle detection system's accuracy in backlight conditions increased by more than 20%, especially in low-contrast and small-target conditions, the system can still maintain a high accuracy rate.

[0111] This implementation demonstrates the ability of the present invention to accurately identify vehicles in backlit environments using a deep learning model. By combining image enhancement with deep learning, the system can effectively identify low-contrast, blurred targets in backlit environments, thereby improving the stability and accuracy of the security monitoring system.

[0112] Case 3: Drone Target Identification

[0113] When drones conduct aerial inspections or monitoring, they often encounter backlighting conditions. Especially when photographing distant targets, due to changes in the sun's position, the target object's outline is blurred or overexposed, resulting in target recognition failure.

[0114] Implementation process:

[0115] Dataset Preparation: We selected a dataset of aerial images captured by a drone-mounted backlight camera, which includes objects under various backlighting conditions. The dataset contains images from different time periods and environments.

[0116] Image preprocessing and enhancement: Backlight enhancement is performed on the image, using adaptive brightness adjustment and shadow removal techniques to improve the visibility of the target area. Image detail restoration methods are used in low-contrast areas to make the target appear clearer in the image.

[0117] Deep learning model training and detection: An improved YOLOv4 model is used for target detection, especially in backlit scenes with poor image quality. The model enhances the recognition ability of target areas through multi-layer feature extraction and context information fusion.

[0118] Results: During the aerial inspection process, the system successfully identified multiple low-contrast targets, especially under backlight conditions, and the system's recognition accuracy increased by 17%.

[0119] This implementation demonstrates the effectiveness of a deep learning-based target detection method for drone backlit photography. By optimizing backlit environments, this method improves target visibility and enhances detection accuracy, significantly enhancing target recognition capabilities during drone missions.

Claims

1. A flight simulation method based on unmanned aerial vehicle backlighting imaging technology, characterized in that: The following steps are involved: Step 1: Build a UAV platform, which includes a backlight imaging camera, a stabilized gimbal, a real-time data transmission module, and an image processor. The backlight imaging camera is mounted on the stabilized gimbal, and the backlight imaging camera transmits the image data sensed by the UAV during flight to the image processor via the real-time data transmission module. Step 2: Secure the backlight imaging camera to a stabilized gimbal, ensuring its field of view is consistent with the drone's flight direction and capable of real-time adjustment. Step 3: Use the multi-point calibration method to accurately calibrate the internal and external parameters of the backlight imaging camera to ensure that lens distortion and geometric errors are eliminated; Step 4: The backlight imaging camera is equipped with a dynamic aperture control mechanism to achieve automatic exposure adjustment under drastic changes in lighting conditions and optimize the imaging quality of the target area; Step 5: Introduce a multi-scale noise reduction algorithm based on wavelet transform to suppress random noise interference caused by high dynamic range under backlight conditions; Step 6: Build a lightweight generative adversarial network model, input the backlit image, and reconstruct the target texture and structural features through multi-layer feature extraction, avoiding artifacts or color drift problems caused by traditional methods; Step 7: Based on the enhanced and optimized YOLO detection framework and combined with prior backlit scene data, a real-time target detection model is constructed to extract bounding boxes and classification probabilities of multiple target categories. A high-resolution feature pyramid network is used for small target areas to ensure the accuracy and robustness of target detection. Multi-feature fusion methods are used to further extract target key points and their spatial geometric characteristics, providing a standardized high-dimensional data description. Step 8: Superimpose the UAV flight status parameters and light distribution parameters in real time to complete the flight simulation demonstration of the UAV-mounted backlight imaging technology.

2. The flight simulation method based on the UAV-mounted backlight imaging technology according to claim 1, characterized in that: In step one, the stabilized gimbal adopts a three-axis mechanical stabilized gimbal, and the real-time data transmission module is a high-bandwidth real-time data transmission module. The backlight imaging camera, the three-axis mechanical stabilized gimbal and the high-bandwidth real-time data transmission module form a complete UAV perception and transmission system framework.

3. The flight simulation method based on the UAV-mounted backlighting imaging technology according to claim 1 or 2, characterized in that: In step two, the stabilized gimbal uses high-precision servo control technology, utilizing the servo system to achieve precise control of the motion state of the mechanical equipment, especially precise operation in terms of position, speed, and acceleration, to ensure that the camera's line of sight is stable and can be precisely adjusted under complex flight conditions.

4. The flight simulation method based on the UAV-mounted backlight imaging technology according to claim 3, characterized in that: Step three is as follows: A multi-point calibration method is used to accurately calibrate the intrinsic and extrinsic parameters of the backlighting camera. The calibration process then eliminates errors such as lens distortion, geometric offset, and optical axis inconsistency to ensure the geometric accuracy of the acquired image. The intrinsic parameters include focal length, principal point position, and distortion coefficient; the extrinsic parameters include camera attitude and position.

5. The flight simulation method based on the UAV-mounted backlight imaging technology according to claim 4, characterized in that: Step 4 is as follows: The deployment of a dynamic aperture control module based on adaptive light perception can quickly respond to lighting changes in backlit environments to achieve a linked adjustment mechanism for aperture, shutter speed, and ISO parameters, ensuring optimal imaging quality in both bright and dark areas of the target area.

6. The flight simulation method based on the UAV-mounted backlight imaging technology according to claim 5, characterized in that: Step 5 is as follows: A multi-scale noise reduction algorithm based on wavelet transform is introduced to perform noise suppression on backlit imaging data. During the noise reduction process, the high-frequency and low-frequency components of the image are separated to eliminate random noise interference while retaining the detailed features of the target area.

7. The flight simulation method based on the UAV-mounted backlight imaging technology according to claim 6, characterized in that: Step six is ​​as follows: A lightweight generative adversarial network model is designed. The original image data under backlighting conditions is input, and the texture details and structural features of the target are reconstructed through multi-layer feature extraction and illumination compensation. The adversarial loss and perceptual loss are then used to optimize the generative network to avoid the artifacts and color drift problems of traditional algorithms in backlight enhancement.

8. The flight simulation method based on the UAV-mounted backlight imaging technology according to claim 7, characterized in that: The specific process of the flight simulation demonstration of the UAV-mounted backlighting imaging technology in Step 8 includes: The backlight imaging camera carried by the drone collects environmental image data during flight, including target objects, background scenes and lighting distribution information. The collected data needs to be optimized by dynamic aperture and backlight perception imaging technology to ensure clear imaging under conditions of drastic changes in light. In backlight scenes, the drone's flight status parameters are superimposed on the picture to dynamically present the flight status. Then, intuitive superimposed annotations are used to help analyze the target perception ability under backlight conditions. The superimposed annotations include bounding boxes, classification labels and key points.

9. The flight simulation method based on the UAV-mounted backlighting imaging technology according to claim 1, 2, 4, 5, 6, 7 or 8, wherein the specific process is as follows: Step 1: Build a UAV platform equipped with a backlight imaging system; The backlight imaging camera is mounted on a three-axis stabilized gimbal. The gimbal is linked with the UAV flight control system to achieve attitude adjustment, ensuring that the backlight imaging camera's field of view is consistent with the target area. Step 2: Fix the backlight imaging camera on the gimbal; The stabilization gimbal is controlled using a three-dimensional rotation matrix, which is calculated as follows: R=R z (ψ)R y (i)R x (f) (1) in, R z (ψ),R y (θ),R x (φ) represents the rotation matrix around the x, y, and z axes respectively; The gimbal adjusts the camera's viewing angle in real time through feedback closed-loop control. The formula is: e angle =θ desired -θ current (2) The controller is based on the angle error e angle Output corresponding driving signal; Step 4: Configure a dynamic aperture control mechanism to achieve automatic exposure adjustment under drastic changes in lighting conditions and optimize the imaging quality of the target area; The dynamic aperture module adjusts the aperture size in real time according to the ambient light conditions and adopts an exposure value optimization strategy. The aperture adjustment formula is: Where A is the aperture diameter, ΔL is the illumination difference, k is the adjustment coefficient, and t is the exposure time. By dynamically combining aperture adjustment and exposure time, the system can accurately image the target area even in strong backlight. Step 5: Introduce a multi-scale noise reduction algorithm based on wavelet transform to suppress random noise interference caused by high dynamic range under backlight conditions; The backlight imaging camera is generated by encoding and restoring the target mask against a strong background. Taking into account the system defocus τ, the specific expression of the exit pupil function is given: P(x,y,τ)=p(x,y)exp{i[f(x,y)+τ(x 2 +y 2 )]} (4) Among them, i 2 = -1, τ represents the phase distribution of the defocus aberration on the pupil, D is the diameter of the system pupil, and f(x, y) represents the phase mask function of the optical system when a phase plate is inserted in the defocus condition; After knowing the exit pupil function of the system, the point spread function used to characterize the imaging characteristics of the system in the spatial domain is given: h(x′,y′,τ)=κ{F[P(x,y,τ)]F * [P(x,y,τ)]} (6) Where F represents Fourier transform, κ is the normalization constant, and * represents conjugation; After obtaining the point spread function of the optical imaging, performing Fourier transform on it can obtain the optical transfer function that characterizes the spatial frequency transfer characteristics of the system: H(u,v,τ)=F[h(x′,y′,τ)] (7) The backlight imaging camera is able to calculate the optical transfer function in advance through the phase plate profile, and the physical system can perform a Fourier transform on the point spread function of the point light source imaging acquisition system to obtain the optical transfer function of the system; Wiener filtering is called minimum mean square error filtering. This method regards the image and noise as random processes, and the ultimate goal is to obtain a statistical error function: The minimum estimate of Where f is the unprocessed original image information, is the minimum estimate of the original image, and E is the expectation of the difference between the original image and the minimum estimate, which is expressed as: Among them, |H(u,v) 2 =H * (u,v)H(u,v),H * (u,v) represents the complex conjugate of H(u,v), S n (u,v)=|N(u,v) 2 represents the noise power spectrum of image processing; S f (u,v)=|F(u,v) 2 Represents the power spectrum of the original image; Formula (8) can be simplified to: In order to suppress random noise in high dynamic range images, multi-scale wavelet transform is used for noise reduction; the input image I(x, y) is decomposed into low-frequency component L and high-frequency component H i , the specific formula is: Noise reduction is accomplished using the soft thresholding method, using the formula: Among them, H i ′ is the high-frequency component after noise reduction, λ is the noise threshold, which is automatically estimated through noise statistics; Step 6: Design a lightweight generative adversarial network model that takes a backlit image as input and extracts multiple layers of features to reconstruct the target's texture and structural features, avoiding artifacts or color drift caused by traditional methods. Step 7: Based on the enhanced and optimized YOLOv8 detection framework and combined with prior backlighting scene data, a real-time object detection model is built to extract bounding boxes and classification probabilities of multiple categories of objects; The target detection system uses the enhanced and optimized YOLOv8 framework and inputs the backlit image I input The detection network extracts multi-scale features and outputs the bounding box and category probability of the target through the fully connected layer. The loss function of the bounding box is L box for: in, is the predicted bounding box, is the true bounding box, and the classification loss uses the cross entropy function, the formula is: The complete detection loss is: L total =L box +L cls (14) On the basis of detecting the target, key point information is extracted, and the key point is determined by the response function R: Among them, Ω(k i ) is the pixel area around the key point, and F(p) is the eigenvalue; multiple eigenvalues ​​are fused through the feature pyramid network to integrate high-resolution features and low-resolution global features to generate the final target description.

10. A flight simulation system based on UAV-mounted backlight imaging technology, characterized by: The system has a program module corresponding to the steps of any one of claims 1 to 9 above, and when running, executes the steps of the flight simulation method based on the unmanned aerial vehicle backlighting imaging technology, which includes: The backlight imaging camera system is used to acquire environmental image data under backlight conditions. Its configured dynamic aperture control mechanism optimizes the imaging quality of the target area through automatic exposure adjustment. The high-quality environmental image data acquired under backlight conditions is input into the data processing and image enhancement system of the image processor. The stabilization control system is used to ensure the stability of the imaging equipment during flight, the ability to adjust the field of view angle, and the quality of image acquisition. The servo system that controls the stabilized gimbal accurately controls the motion state of the mechanical equipment, especially the precise operation in terms of position, speed, and acceleration. The image processor is used to read high-quality environmental image data under backlight conditions and provide basic processing for target perception and recognition. It is equipped with a data processing and image enhancement system and a target detection and feature extraction system. A data processing and image enhancement system, which includes a wavelet transform multi-scale noise reduction algorithm, a lightweight generative adversarial network, and a multi-scale image enhancement algorithm. This system is used to reduce noise, enhance, and reconstruct target features from raw image data under backlighting conditions, improving perception and recognition performance. The target detection and feature extraction system uses the YOLO target detection framework to detect multi-category targets in backlit scenes in real time, extract key features and generate standardized descriptions to provide input for flight decisions.

Images