An anti-interference tracking method and system based on target infrared imaging characteristics

Abstract

The present application provides an anti-interference tracking method and system based on target infrared imaging features. Among them, a continuous infrared image sequence of a target object at different time points is acquired; spatio-temporal correlation analysis is used to determine the potential motion trajectory of the target object in the infrared image sequence; a dynamic weight map is generated based on the potential motion trajectory, wherein the dynamic weight map adaptively adjusts the importance of each pixel according to the changes of background noise and target features; the dynamic weight map is combined with the infrared image sequence to strengthen the target area and suppress the non-target area, obtaining a strengthened infrared image sequence; a multiple hypothesis tracking strategy is adopted to perform real-time positioning of the target object in the strengthened infrared image sequence, and the dynamic weight map is updated to maintain continuous tracking of the target object. The technical solution provided by the present application can improve the tracking accuracy.

Description

Technical Field

[0001] Embodiments of the present application relate to the field of image processing technology, and in particular, to an anti-interference tracking method and system based on target infrared imaging features. Background Art

[0002] With the development of technology, infrared imaging technology has been widely used in many fields such as security monitoring, military reconnaissance, and driverless due to its ability to provide good visual information even under low light conditions. These application scenarios have put forward higher requirements for the accuracy and stability of target tracking, especially in the presence of various interference factors (such as complex backgrounds, occlusions, weather changes, etc.).

[0003] Many current market solutions rely on traditional image processing algorithms or simple machine learning models to achieve target detection and tracking. Such methods usually use static feature matching or template-based methods for target localization, and combine prediction models such as Kalman filters to estimate the future position of the target. In addition, some systems attempt to directly extract key frames from the original video stream using deep learning frameworks to optimize the tracking process.

[0004] Traditional methods often have difficulty coping with dynamic changes in the background. Once encountering complex environmental conditions (such as strong light direct shooting, rain and snow weather), it is easy to have problems of misjudgment or target loss. Secondly, when there is more noise in the image, many existing algorithms do not perform well and cannot effectively distinguish the target signal from the background noise, resulting in a decrease in tracking accuracy. Summary of the Invention

[0005] Embodiments of the present application provide an anti-interference tracking method and system based on target infrared imaging features to solve the problem of poor tracking accuracy in the prior art.

[0006] In a first aspect, embodiments of the present application provide an anti-interference tracking method based on target infrared imaging features, including:

[0007] Obtain a continuous infrared image sequence of a target object at different time points;

[0008] Use spatio-temporal correlation analysis to determine the potential motion trajectory of the target object in the infrared image sequence;

[0009] Generate a dynamic weight map based on the potential motion trajectory, where the dynamic weight map adaptively adjusts the importance of each pixel according to the changes in background noise and target features;

[0010] Combine the dynamic weight map with the infrared image sequence to strengthen the target area and suppress the non-target area, and obtain an enhanced infrared image sequence;

[0011] Adopt a multi - hypothesis tracking strategy to perform real - time localization of the target object in the enhanced infrared image sequence, and continuously track the target object by updating the dynamic weight map.

[0012] Optionally, the use of spatio - temporal correlation analysis to determine the potential motion trajectory of the target object in the infrared image sequence includes:

[0013] Calculate the inter - frame difference of the continuous infrared image sequence to obtain the change information between adjacent frames;

[0014] Construct an optical flow field based on the change information, where the optical flow field represents the movement of pixel points in the infrared image sequence from the previous frame to the next frame;

[0015] Remove noise and outliers in the optical flow field through filtering techniques to obtain an optical flow estimate;

[0016] According to the optical flow estimate, apply a dynamic clustering algorithm to identify the motion regions related to the target object;

[0017] Establish the correspondence between the motion regions and consecutive frames to form the potential motion trajectory of the target object.

[0018] Optionally, the generation of the dynamic weight map based on the potential motion trajectory includes:

[0019] Extract the regions associated with the target object from the potential motion trajectory as the regions of interest;

[0020] Conduct feature analysis on the regions of interest to identify the key feature points representing the target object;

[0021] According to the positions of the key feature points and the changes of the key feature points over time, calculate the importance coefficient of each pixel point for the target object;

[0022] Combine the current frame's background noise level to assign a noise suppression factor to each pixel point to reflect the degree to which the pixel point is affected by background noise;

[0023] Combine the importance coefficient and the noise suppression factor to generate a dynamic weight map.

[0024] Optionally, the combination of the dynamic weight map and the infrared image sequence to enhance the target region and suppress the non - target region to obtain the enhanced infrared image sequence includes:

[0025] For each pixel point in each frame of the infrared image sequence, apply the weight value in the dynamic weight map corresponding to the position of the pixel point to enhance or weaken the intensity value of the pixel point to form the enhanced infrared image sequence;

[0026] Among them, the process of enhancing or weakening the intensity value of the pixel points includes: for the pixel points within the target area, using a first preset weight value to enhance the intensity value of the pixel points to improve the visibility of the target area; for the pixel points outside the target area, using a second preset weight value to weaken the intensity value of the pixel points to reduce the visibility of the target area.

[0027] Optionally, the multi-hypothesis tracking strategy is adopted to perform real-time positioning of the target object in the enhanced infrared image sequence, and the dynamic weight map is updated to maintain continuous tracking of the target object, including:

[0028] For each frame of the enhanced infrared image sequence, multiple hypotheses about the position and state of the target object are constructed;

[0029] The prediction model is used to predict the position of the target object in the next frame of each hypothesis;

[0030] In the next frame of the enhanced infrared image sequence, the likelihood score corresponding to each hypothesis is calculated according to the predicted position;

[0031] The hypothesis with the highest likelihood score is selected as the current optimal estimate, and a preset number of sub-optimal hypotheses are retained to cope with uncertainties;

[0032] According to the result of the current optimal estimate, the weight distribution in the dynamic weight map is updated so that the weight value is more conducive to highlighting the target object and suppressing background noise to maintain continuous tracking of the target object.

[0033] Optionally, calculating the importance coefficient of each pixel point for the target object includes:

[0034] The importance coefficient of each pixel point for the target object is calculated through the following calculation formula:

[0035]

[0036] Among them, I(x, y, t) represents the importance coefficient of the pixel point at the position (x, y) at time t, N is the number of key feature points, ω i (t) is the adaptive weight factor of the i-th key feature point at time t, x i (t), y i (t) are the horizontal and vertical coordinates of the i-th key feature point at time t respectively, σ i (t) is the spatial scale parameter associated with the i-th key feature point, is a two-dimensional Gaussian function used to measure the distance between the current position (x, y) and the key feature point (x i(t), y i The influence of the distance between (t)) on the importance coefficient is the gradient information of the key feature point i at time t is a non-linear function based on the gradient information of the key feature point Direction parameter θ i and local texture feature ψ i (t) and attention weight A t to adjust the importance coefficient

[0037] Optionally, updating the weight distribution in the dynamic weight map according to the result of the current optimal estimation includes:

[0038] Calculating the weight distribution in the updated dynamic weight map through the following calculation formula:

[0039] W′(x, y, t + 1)

[0040] = W(x, y, t) + α(t)·(β(t)·I(x, y, t) - W(x, y, t)) + γ(t)

[0041] ·(N(x, y, t) - μ N (t)) + λ·ΔW(x, y, t) +

[0042]

[0043] where W'(x, y, t + 1) is the weight value at the position (x, y) in the updated dynamic weight map at time t + 1, W(x, y, t) is the weight value at the current time t, α(t) is the learning rate varying with time, β(t) is the target importance gain coefficient varying with time, I(x, y, t) is defined as above and is the importance coefficient at this position, γ(t) is the noise suppression gain coefficient varying with time, N(x, y, t) is a function reflecting the background noise level at the position (x, y) at time t, μ N (t) is the mean value of the background noise level of the entire image at time t, λ is the weight coefficient of the smoothing term, ΔW(x, y, t) is the result of the Laplacian operator of the weight map at the position (x, y), η is the weight coefficient of the additional adjustment term is a function based on a convolutional neural network (CNN) and an attention mechanism, used to receive the current weight map W(x, y, t), context information C t and hidden state H t , and output a correction term for further optimizing the weight map

[0044] In a second aspect, an anti-interference tracking system based on target infrared imaging features provided by an embodiment of the present application includes:

[0045] An acquisition module, configured to acquire a continuous infrared image sequence of a target object at different time points;

[0046] An analysis and determination module, configured to determine a potential motion trajectory of the target object in the infrared image sequence by using spatio-temporal correlation analysis;

[0047] A generation and adjustment module, configured to generate a dynamic weight map based on the potential motion trajectory, wherein the dynamic weight map adaptively adjusts the importance of each pixel according to changes in background noise and target features;

[0048] A combination module, configured to combine the dynamic weight map with the infrared image sequence to strengthen the target area and suppress the non-target area, so as to obtain a strengthened infrared image sequence;

[0049] A real-time positioning and tracking module, configured to adopt a multiple hypothesis tracking strategy to perform real-time positioning on the target object in the strengthened infrared image sequence, and maintain continuous tracking of the target object by updating the dynamic weight map.

[0050] In a third aspect, an embodiment of the present application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement an anti-interference tracking method and system based on target infrared imaging features as described in any item of the first aspect above.

[0051] In a fourth aspect, an embodiment of the present application provides a computer storage medium, storing a computer program, and when the computer program is executed by a computer, it implements an anti-interference tracking method and system based on target infrared imaging features as described in any item of the first aspect above.

[0052] In an embodiment of the present application, a continuous infrared image sequence of a target object is acquired; a potential motion trajectory of the target object in the infrared image sequence is determined by using spatio-temporal correlation analysis; a dynamic weight map is generated based on the potential motion trajectory, wherein the dynamic weight map adaptively adjusts the importance of each pixel according to changes in background noise and target features; the dynamic weight map is combined with the infrared image sequence to strengthen the target area and suppress the non-target area, so as to obtain a strengthened infrared image sequence; a multiple hypothesis tracking strategy is adopted to perform real-time positioning on the target object in the strengthened infrared image sequence, and continuous tracking of the target object is maintained by updating the dynamic weight map. The technical solution provided by the present application can improve the tracking accuracy.

[0053] These aspects or other aspects of the present application will be more clearly understood in the following description of the embodiments. Description of the Drawings

[0054] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0055] Figure 1 It is a flowchart of an anti-interference tracking method based on target infrared imaging features provided by an embodiment of the present application;

[0056] Figure 2 It is a schematic structural diagram of an anti-interference tracking system based on target infrared imaging features provided by an embodiment of the present application;

[0057] Figure 3 It is a schematic structural diagram of a computing device provided by an embodiment of the present application. Detailed implementation manners

[0058] To enable those skilled in the art to better understand the solutions of the present application, the following will clearly and completely describe the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application.

[0059] In some processes described in the specification and claims of the present application and the above-mentioned drawings, a plurality of operations appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order in which they appear herein or may be executed in parallel. The operation numbers such as 101 and 102 are only used to distinguish different operations, and the numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first" and "second" in this article are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, nor do they limit that "first" and "second" are of different types.

[0060] The following will clearly and completely describe the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0061] Figure 1 An embodiment of the present application provides a flowchart of an anti-interference tracking method based on target infrared imaging features, as Figure 1 shown, the method includes:

[0062] 101. Obtain a continuous infrared image sequence of the target object at different time points;

[0063] In this step, the aim is to collect a series of continuous infrared images of the target area taken at different time points. In this way, the changes of the target over time can be captured, providing basic data for subsequent analysis.

[0064] In the embodiment of the present application, a high-resolution infrared camera is used to continuously photograph the monitoring area, and the frame rate is set to ensure that fast-moving objects can be clearly recorded. For example, for a tracking task of a vehicle moving at night, a rate of 30 frames per second can be set to obtain all infrared images of the vehicle from entering the field of view to leaving the field of view.

[0065] 102. Use spatio-temporal correlation analysis to determine the potential motion trajectory of the target object in the infrared image sequence;

[0066] In this step, by performing correlation analysis in the spatio-temporal domain on the obtained series of infrared images, the position paths that the target may pass through are identified. This method takes into account the relationship between adjacent frames, which helps to improve the prediction accuracy.

[0067] In the embodiment of the present application, the optical flow method is used to calculate the displacement of pixel points between two frames, and then the moving direction and speed of the object in the entire sequence are inferred. Suppose a pedestrian is being tracked, then the walking route can be estimated by comparing the position changes of the pedestrian in several consecutive frames, and a preliminary trajectory model can be constructed accordingly.

[0068] The present application takes into account that in the existing infrared image sequence analysis technology, there are often the following problems in determining the motion trajectory of the target object: First, inaccurate target detection caused by environmental interference (such as temperature changes, background clutter, etc.); Second, it is difficult to distinguish the real moving target when the contrast between the target and the background is insufficient; Third, image blurring caused by camera jitter or the rapid movement of the target itself. These problems may all lead to deviations in the tracking and recognition of the target object, thus affecting subsequent applications, such as security monitoring and obstacle detection in driverless vehicles. To solve the above-mentioned technical problems, the present application proposes a method based on spatio-temporal correlation analysis to more accurately determine the potential motion trajectory of the target object in the infrared image sequence. This method can effectively filter out noise interference and improve the identification ability of real moving targets by comprehensively considering the continuity in the time dimension and the changes in spatial positions.

[0069] The specific optional solution is as follows:

[0070] Optionally, "determining the potential motion trajectory of the target object in the infrared image sequence using spatio-temporal correlation analysis" in 102 includes: calculating the inter-frame difference of the continuous infrared image sequence to obtain the change information between adjacent frames; constructing an optical flow field based on the change information, where the optical flow field represents the movement of pixel points in the infrared image sequence from the previous frame to the next frame; removing noise and outliers in the optical flow field through filtering techniques to obtain an optical flow estimate; identifying the motion regions related to the target object according to the optical flow estimate by applying a dynamic clustering algorithm; and establishing the correspondence between the motion regions and consecutive frames to form the potential motion trajectory of the target object.

[0071] Inter-frame difference calculation: It refers to comparing the pixel values between two consecutive frames to find the differences, so as to discover the changes in the image content.

[0072] Optical flow field: It is a data structure used to describe the displacement of all points in an image sequence from one frame to the next.

[0073] Filtering technique: It is used to reduce the noise components in the signal and make the effective information clearer and more distinguishable.

[0074] Dynamic clustering algorithm: A method of automatically forming categories according to the data characteristics. Here, it refers to classifying pixel regions with similar motion characteristics together.

[0075] Potential motion trajectory: The possible path that the target may pass through predicted based on the above processing results.

[0076] Inter-frame difference calculation means obtaining a difference image by performing subtraction operations on adjacent frames. This step can highlight the changing parts in the scene.

[0077] Constructing the optical flow field is to estimate the velocity vectors of each pixel point using an optical flow algorithm (such as the Lucas-Kanade algorithm), that is, how they move from the current frame to the next frame.

[0078] Filtering and denoising refers to using median filtering or other appropriate filters to remove the mis-matched points generated during the optical flow estimation process.

[0079] Dynamic clustering is to use clustering algorithms such as K-means to gather pixels with similar velocity vectors to form several clusters representing different object motion patterns.

[0080] Establishing the correspondence and forming the trajectory means tracking the development and changes of these clusters over time, and then depicting the complete motion routes of each target object.

[0081] In the embodiments of the present application, assume that there is a video clip of a street taken at night, which contains images of pedestrians walking. First, the frame difference method is used to obtain the difference image between each pair of adjacent frames, and then the optical flow algorithm is applied to estimate the moving direction and distance of each pixel point. Then, some isolated outliers are eliminated through median filtering. After that, the K-means algorithm is used to classify the remaining valid optical flow vectors to find out the clusters belonging to pedestrians. Finally, the position coordinates of the centers of these clusters are linked in chronological order to obtain the exact path of the pedestrians crossing the street.

[0082] By implementing this solution, not only can problems such as high false detection rate and weak anti-interference ability in traditional methods be overcome, but also the accuracy and stability of target tracking can be significantly improved. Especially for complex and changing actual application scenarios, this technical means based on spatio-temporal correlation analysis shows stronger adaptability and robustness.

[0083] 103. Generate a dynamic weight map based on the potential motion trajectory, where the dynamic weight map adaptively adjusts the importance of each pixel according to the changes in background noise and target features;

[0084] In this step, a map reflecting the importance of each region is created based on the known or predicted target motion path. This map automatically adjusts the weight value of each pixel point according to the background noise level and the characteristics of the target itself, so as to highlight the key parts.

[0085] In the embodiments of the present application, a model is trained using a machine learning algorithm to learn to distinguish which are real targets and which are just interference factors. When a new frame is detected, the model will evaluate the probability of each pixel belonging to the target and assign corresponding weights accordingly. For example, when looking for wild animals in a forest environment, the system may assign higher weights to areas showing characteristics of animal heat signals.

[0086] The present application takes into account that in the prior art, target tracking based on potential motion trajectories usually faces the following problems: one is the interference of background noise, which may lead to misjudgment or loss of the target object; the other is the changes in target features (such as partial occlusion, pose changes, etc.), which make it difficult to continuously and stably identify the target. These problems limit the performance and reliability of the target tracking system. To solve these problems, the present application proposes a method for generating a dynamic weight map, which can adaptively adjust the importance of each pixel in the image according to the changes in background noise and target features, thereby improving the accuracy and robustness of target detection and tracking.

[0087] The specific implementation of this alternative solution is as follows:

[0088] Optionally, "generating a dynamic weight map based on the potential motion trajectory" in 103 includes: extracting a region associated with the target object from the potential motion trajectory as the region of interest; performing feature analysis on the region of interest to identify key feature points representing the target object; calculating an importance coefficient for each pixel point according to the positions of the key feature points and the changes of the key feature points over time; combining the background noise level in the current frame to assign a noise suppression factor to each pixel point to reflect the degree to which the pixel point is affected by the background noise; and combining the importance coefficient and the noise suppression factor to generate a dynamic weight map.

[0089] Region of interest: Refers to the part of an image that is considered to contain important information (such as a moving target).

[0090] Key feature point: Refers to a specific position or structure that can be used to uniquely identify a target object.

[0091] Importance coefficient: A value that measures the contribution degree of a pixel to determining the target position.

[0092] Noise suppression factor: A parameter that represents the degree to which a pixel is affected by background noise.

[0093] Dynamic weight map: An image in which each pixel value represents the importance degree of the pixel for the current task (such as target tracking).

[0094] Extracting the region of interest means selecting, from the potential motion trajectory obtained in the previous step, those regions that are most likely to belong to the target object as the focus of further processing.

[0095] Feature analysis and key point recognition are to use feature extraction algorithms such as SIFT, SURF, etc. to find stable and discriminative feature points within the region of interest.

[0096] Calculating the importance coefficient means giving each pixel point a score according to the position of the key feature point and its changes over time, and this score reflects the importance degree of the pixel for tracking the target.

[0097] Assigning the noise suppression factor is to evaluate the noise level in each region of the current frame and assign a suppression factor to each pixel to reduce the impact of noise on the pixel.

[0098] Generating the dynamic weight map is to combine the importance coefficient and the noise suppression factor of each pixel to create a new image, in which different gray levels or colors represent the importance of different pixels.

[0099] In the embodiment of the present application, it is assumed that pedestrians in a video stream are being monitored. First, the potential movement trajectories of the pedestrians are obtained using the aforementioned technology, and the specific area where the pedestrians are located is determined as the region of interest. Then, the SIFT algorithm is applied to identify some significant feature points on the pedestrians, such as the head, shoulders, etc. Next, based on the positions of these feature points and the way they move with the pedestrians, the importance coefficient of each pixel is calculated - pixels closer to the feature points will obtain higher weights. At the same time, considering the relatively high noise level that may exist in night-time shooting, the noise distribution in the entire scene is also estimated, and a noise suppression factor is given to each pixel accordingly. Finally, the importance coefficient is multiplied by the noise suppression factor, and the result constitutes the dynamic weight map. In this weight map, the pixel values of the pedestrian body part are higher, while the pixel values of the background and other irrelevant areas are lower.

[0100] After adopting this method, the system can more accurately distinguish the target area from the non-target area in a complex background, especially maintaining a good tracking effect even in the presence of a large amount of noise. In addition, by dynamically focusing on the target feature points, the attention to the target can be effectively maintained even when the target is occluded or its posture changes, greatly improving the continuity and accuracy during the tracking process. This improvement not only enhances the anti-interference ability of the system but also expands the overall application scope and practicality.

[0101] 104. Combine the dynamic weight map with the infrared image sequence to strengthen the target area and suppress the non-target area, obtaining an enhanced infrared image sequence;

[0102] In this step, the dynamic weight map obtained in the previous step is applied to the original infrared image sequence. Through weighted processing, the area where the target is located becomes more obvious, while reducing the influence of the non-target area.

[0103] In the embodiment of the present application, an image fusion technology is developed, which can intelligently enhance the target contour lines and reduce the background brightness according to the information of the weight map. This is particularly useful in military reconnaissance scenarios and can help operators more easily detect enemy units hidden in complex terrains.

[0104] The present application takes into account that in existing infrared imaging technologies, especially when performing target tracking at night or under low-light conditions, the following problems are often encountered: First, the contrast between the background and the foreground (i.e., the target) is insufficient, resulting in the target being not easily and clearly identified; Second, thermal noise and interference sources in the environment may cause the image quality to deteriorate, further affecting the detection of the target. To solve these problems, the present application proposes a method of combining a dynamic weight map with an infrared image sequence to improve the visibility and recognition accuracy of the target by strengthening the target area and suppressing the non-target area.

[0105] The optional solution is as follows:

[0106] Optionally, in 104, "combining the dynamic weight map with the infrared image sequence to enhance the target area and suppress the non-target area to obtain an enhanced infrared image sequence" includes: for each pixel point in each frame of the infrared image sequence, applying the weight value in the dynamic weight map corresponding to the position of the pixel point to enhance or weaken the intensity value of the pixel point to form an enhanced infrared image sequence; wherein, the process of enhancing or weakening the intensity value of the pixel point includes: for the pixel points in the target area, using a first preset weight value to enhance the intensity value of the pixel point to improve the visibility of the target area; for the pixel points in the non-target area, using a second preset weight value to weaken the intensity value of the pixel point to reduce the visibility of the target area.

[0107] Infrared image sequence: A series of continuously captured infrared photos used to capture the heat distribution in a scene.

[0108] Dynamic weight map: A mapping where each pixel value represents the degree of importance of that position for the current task (such as highlighting the target).

[0109] First preset weight value: A value greater than 1 used to amplify the intensity of pixel points in the target area.

[0110] Second preset weight value: A value less than 1 but greater than 0 used to reduce the intensity of pixel points in the non-target area.

[0111] Combining the dynamic weight map with the infrared image means that for each pixel in each frame of the infrared image, the corresponding weight value is found according to its corresponding position on the dynamic weight map.

[0112] Adjusting the pixel intensity means that for pixels belonging to the target area, the original intensity value is multiplied by a higher first preset weight value to increase the brightness of these pixels.

[0113] For pixels in the non-target area, a lower second preset weight value is applied to reduce their brightness.

[0114] Generating the enhanced infrared image sequence means that after the above processing, the entire image sequence will become more focused on the target object, while the background information becomes less prominent.

[0115] In the embodiments of the present application, it is assumed that in a security monitoring scenario, it is necessary to accurately track a person from a series of infrared images taken at night. First, a dynamic weight map for this person has been obtained according to the technology mentioned above. Next, consider a specific infrared image I, and define the first preset weight value W1 = 1.5 and the second preset weight value W2 = 0.7. For any pixel P in this frame of image, if it is located within the previously determined region of interest (i.e., considered part of the target), then the new intensity value P' = P * W1; otherwise, if P is in a non-interest region, then P' = P * W2. After such processing, the resulting new image not only makes the target more obvious but also effectively weakens the influence of the surrounding environment.

[0116] Let the original pixel intensity be I(x, y), and the corresponding dynamic weight map be W(x, y). If a certain pixel belongs to the target area, then:

[0117] I'(x, y) = I(x, y) × 1.5

[0118] Conversely, if this pixel does not belong to the target area, then:

[0119] I'(x, y) = I(x, y) × 0.7

[0120] Here, I'(x, y) represents the processed pixel intensity value.

[0121] Adopting this scheme can significantly improve the visibility of the target object in a complex background. Especially in the case of strong background interference, it can more effectively highlight the object of concern. In addition, by adjusting the relative intensity of pixels in different regions, the overall visual effect of the image can be optimized, facilitating subsequent manual analysis or automated processing. This method not only enhances the anti-noise ability of the system but also improves the performance of the infrared imaging system in practical application scenarios.

[0122] 105. Adopt a multiple hypothesis tracking strategy to perform real-time positioning of the target object in the enhanced infrared image sequence, and maintain continuous tracking of the target object by updating the dynamic weight map.

[0123] In this step, in the final stage, a multiple hypothesis tracking method is adopted to real-time locate the target in the enhanced image sequence and continuously update the dynamic weight map to ensure effective tracking even when the target behavior undergoes sudden changes.

[0124] In the embodiments of the present application, a tracking framework based on a particle filter is designed, which contains multiple hypothesis branches running in parallel, and each branch represents a possible target state. As new information arrives, the system will re-evaluate the likelihood of each hypothesis and select the most likely one as the current best estimate. If the object being tracked suddenly changes direction or speed, new hypothesis branches are added to adapt to this change and ensure that the tracking process is not interrupted. For example, when monitoring the movement of abnormal packages on the baggage conveyor belt during airport security checks, the system needs to be able to quickly respond to any unexpected changes in behavior patterns.

[0125] The present application takes into account that in existing target tracking systems, especially when dealing with targets in a dynamic environment, there are the following problems: First, the target may be partially occluded or move rapidly, resulting in tracking interruption; second, background noise and interference may affect the accurate prediction of the target position. To solve these problems, the present application proposes a method adopting a multiple hypothesis tracking strategy, by constructing multiple hypotheses about the target position and state, and combining the enhanced infrared image sequence to improve the accuracy of real-time positioning. In addition, by continuously updating the dynamic weight map, it can better adapt to the changes of the target, so as to maintain continuous tracking of the target object.

[0126] The specific optional solution is as follows:

[0127] Optionally, "adopting the multiple hypothesis tracking strategy, performing real-time positioning on the target object in the enhanced infrared image sequence, and maintaining continuous tracking of the target object by updating the dynamic weight map" in 105 includes: for each frame of the enhanced infrared image sequence, constructing multiple hypotheses about the position and state of the target object; using a prediction model to predict the position of the target object in the next frame of each hypothesis; in the next frame of the enhanced infrared image sequence, calculating the likelihood score corresponding to each hypothesis according to the predicted position; selecting the hypothesis with the highest likelihood score as the current optimal estimate, and retaining a preset number of sub-optimal hypotheses to cope with uncertainties; according to the result of the current optimal estimate, updating the weight distribution in the dynamic weight map so that the weight values are more conducive to highlighting the target object and suppressing background noise, in order to maintain continuous tracking of the target object.

[0128] Multiple hypothesis tracking strategy: A tracking method based on multiple prediction models, which can simultaneously consider multiple possible target trajectories to cope with uncertainties.

[0129] Prediction model: A mathematical model used to estimate the position and state of a target at a future moment.

[0130] Likelihood score: A numerical value measuring the matching degree between a hypothesis and actual observed data.

[0131] Optimal Estimation: Among all the hypotheses, the one with the highest likelihood score is considered the current estimate closest to the true situation.

[0132] Sub-optimal Hypotheses: In addition to the optimal estimate, some of the more likely correct hypotheses are retained to handle uncertainties and unexpected situations.

[0133] Constructing multiple hypotheses means generating several different hypotheses about the current position and state of the target for each enhanced infrared image frame.

[0134] Predicting the next frame position means using an appropriate prediction model (such as a Kalman filter) to predict the possible position of the target in the next frame under each hypothesis.

[0135] Calculating the likelihood score means comparing the predicted position with the actually observed data in the next frame image to assign a likelihood score to each hypothesis.

[0136] Selecting the optimal and sub-optimal hypotheses means choosing the hypothesis with the highest score as the current best estimate and retaining a certain number of sub-optimal hypotheses to handle possible occlusions or other uncertainty factors.

[0137] Updating the dynamic weight map means adjusting the dynamic weight map according to the latest best estimate result to make the weight values more conducive to highlighting the target and suppressing background noise.

[0138] In the embodiment of this application, it is assumed that a video stream is being monitored, in which a car is moving. After the previous steps, a series of enhanced infrared images have been obtained. Now, these images are input into a multi-hypothesis tracking system. First, five different hypotheses H1 to H5 are constructed for the current frame, and each hypothesis represents a possible position and speed of the car. Then, the Kalman filter is used to predict the position of the car in the next frame under each hypothesis. When a new frame image arrives, the likelihood score of each hypothesis is calculated by comparing the predicted position with the actually detected position of the car. Suppose hypothesis H1 obtains the highest score of 0.9, while the scores of the other hypotheses are 0.7, 0.5, 0.3, and 0.1 respectively. Therefore, H1 is selected as the current best estimate, and H2 and H3 are retained as alternative hypotheses. Finally, based on the result of H1, the dynamic weight map is updated, further enhancing the pixel intensity in the area where the car is located and reducing the influence of the surrounding environment.

[0139] Let H i represent the i-th hypothesis, and L(H i ) represent the likelihood score of this hypothesis. For each hypothesis, its likelihood score can be calculated by the following formula:

[0140]

[0141] Here, x pred,i is the predicted position under hypothesis H i , x obs is the actually observed target position, T is the transpose of a matrix or vector, and P is the prediction error covariance matrix. This formula reflects that the smaller the deviation between the predicted value and the observed value, the higher the likelihood score.

[0142] By introducing the multiple hypothesis tracking strategy, not only can complex situations such as target occlusion and rapid movement be effectively handled, but also the impact brought by environmental changes can be alleviated to a certain extent. In addition, with the continuous update of the dynamic weight map, the system can focus more on the target area, reduce the interference of background noise, and thus significantly improve the stability and accuracy of target tracking. This method not only enhances the robustness of the system but also improves its performance in various practical application scenarios.

[0143] The formula of this application is used to calculate the importance coefficient of each pixel point for the target object, which is an important step in many computer vision tasks (such as object detection, segmentation, tracking, etc.). By evaluating the importance of each pixel point, the system can more effectively focus on the key areas of the target object, ignore background noise, and thus improve the accuracy of the task.

[0144] The specific optional solution is as follows:

[0145] Optionally, calculating the importance coefficient of each pixel point for the target object includes:

[0146] Calculating the importance coefficient of each pixel point for the target object through the following calculation formula:

[0147]

[0148] where I(x, y, t) represents the importance coefficient of the pixel point at position (x, y) at time t, N is the number of key feature points, ω i (t) is the adaptive weight factor of the i-th key feature point at time t, x i (t), y i (t) are the horizontal and vertical coordinates of the i-th key feature point at time t respectively, σ i (t) is the spatial scale parameter associated with the i-th key feature point, is a two-dimensional Gaussian function used to measure the influence of the distance between the current position (x, y) and the key feature point (x i (t), y i (t)) on the importance coefficient, is the gradient information of the key feature point i at time t, is a non - linear function and is based on the gradient information of key feature points direction parameter θ i , local texture feature ψ i (t) and attention weight A t to adjust the importance coefficient.

[0149] The formula comprehensively considers multiple factors to evaluate the importance of pixel points, including the distance between the pixel point and the key feature point, the adaptive weight of the key feature point, the gradient information of the key feature point, the direction parameter, the local texture feature, and the attention weight. Such a design enables the importance coefficient to comprehensively reflect the characteristics of the target object and helps the system to more accurately locate and identify the target.

[0150] two - dimensional Gaussian function

[0151] Function: Measure the influence of the distance between the current position (x, y) and the key feature point (x i (t), y i (y)) on the importance coefficient.

[0152] Principle: The closer the pixel point is to the key feature point, the higher its importance coefficient; the farther the distance, the lower the importance coefficient.

[0153] adaptive weight factor ω i (t):

[0154] Function: Adjust the contribution of each key feature point to the importance coefficient.

[0155] Principle: Different key feature points have different importance to the target object, and the influence of each key feature point can be flexibly adjusted through the adaptive weight factor.

[0156] gradient information

[0157] Function: Use the gradient information of the key feature point to enhance the calculation of the importance coefficient.

[0158] Principle: The gradient information reflects the edges and contours of the image, and these regions are usually more critical for the recognition of the target object.

[0159] non - linear function

[0160] Function: Comprehensively consider the gradient information, direction parameter, local texture feature, and attention weight to adjust the importance coefficient.

[0161] Principle: Through the non - linear function, more complex feature relationships can be captured to improve the accuracy of the importance coefficient.

[0162] The acquisition of each parameter is as follows:

[0163] N is the number of key feature points, usually obtained through feature detection algorithms (such as SIFT, Harris corner detection, etc.).

[0164] ω i (t) is an adaptive weight factor, which can be set through optimization algorithms (such as gradient descent) or experience.

[0165] x i (t), y i (t) are the horizontal and vertical coordinates of the i-th key feature point at time t, obtained through the feature detection algorithm.

[0166] σ i (t) is the spatial scale parameter, usually set according to the scale information of the key feature points.

[0167] is the gradient information of the key feature point i at time t, obtained through image gradient calculation.

[0168] θ i is the direction parameter, usually obtained through the feature detection algorithm.

[0169] ψ i (t) is the local texture feature, which can be obtained through local texture analysis (such as LBP).

[0170] A t is the attention weight, which can be obtained through the attention mechanism model (such as the self-attention mechanism).

[0171] In the embodiments of the present application, it is assumed that in an object detection task, it is necessary to calculate the importance coefficient of a certain pixel point (x, y) at time t. The specific parameters are as follows:

[0172] N = 3: There are 3 key feature points. ω1(t) = 0.6, ω2(t) = 0.3, ω3(t) = 0.1: Adaptive weight factor.

[0173] x1(t) = 10, y1(t) = 20; x2(t) = 30, y2(t) = 40; x3(t) = 50, y3(t) = 60: Coordinates of the key feature points.

[0174] σ1(t) = 5, σ2(t) = 10, σ3(t) = 15: Spatial scale parameters.

[0175] Gradient information.

[0176] θ1 = π / 4, θ2 = π / 2, θ3 = 3π / 4: Direction parameters.

[0177] ψ1(t) = 0.7, ψ2(t) = 0.6, ψ3(t) = 0.5: Local texture characteristics.

[0178] A t = 0.9: Attention weight.

[0179] (x, y) = (25, 35): Coordinates of the currently calculated pixel point.

[0180] Assume the non - linear function F is defined as:

[0181]

[0182] Substitute into the formula to calculate I(x, y, t):

[0183]

[0184] Calculate each term separately:

[0185] For i = 1:

[0186]

[0187] ω1(t)·0.000123·0.36 ≈ 0.000027

[0188] For i = 2:

[0189]

[0190] ω2(t)·0.7788·0 = 0

[0191] For i = 3:

[0192]

[0193] ω3(t)·0.0625·(-0.0945) ≈ -0.00176

[0194] Finally, add all the terms together:

[0195] I(25, 35, t) = 0.000027 + 0 + (-0.00176) ≈ -0.001733

[0196] The calculation results show that the importance coefficient of the pixel point at position (25, 35) is approximately -0.001733. The negative value may indicate that the position has a relatively low importance for the target object in the current situation, possibly because the position is far from the key feature points, or the influence of factors such as the gradient information, direction parameters, and local texture characteristics of the key feature points is small. This can help the system focus on other more important regions in subsequent processing, improving the efficiency and accuracy of target detection.

[0197] The formula of this application comes from an adaptive weight update mechanism in a dynamic system, which is usually applied to scenarios that require real-time adjustment of weights to optimize performance, such as object detection, tracking, image processing and other fields. This mechanism allows the system to continuously adjust its weight distribution according to changes in the environment and newly obtained data, thereby improving the accuracy and robustness of the system.

[0198] The specific optional solution is as follows:

[0199] Optionally, updating the weight distribution in the dynamic weight map according to the result of the current optimal estimate includes:

[0200] Calculating the weight distribution in the updated dynamic weight map through the following calculation formula:

[0201] W′(x,y,t+1)

[0202] =W(x,y,t)+α(t)·(β(t)·I(x,y,t)-W(x,y,t))+γ(t)

[0203] ·(N(x,y,t)-μ N (t))+λ·ΔW(x,y,t)+

[0204]

[0205] where W'(x,y,t+1) is the weight value at the position (x,y) of the updated dynamic weight map at time t+1, W(x,y,t) is the weight value at the current time t, α(t) is the learning rate that changes with time, β(t) is the target importance gain coefficient that changes with time, I(x,y,t) is the importance coefficient at this position as defined above, γ(t) is the noise suppression gain coefficient that changes with time, N(x,y,t) is a function reflecting the background noise level at the position (x,y) at time t, μ N (t) is the mean value of the background noise level of the entire image at time t, λ is the weight coefficient of the smoothing term, ΔW(x,y,t) is the result of the Laplacian operator at the position (x,y) of the weight map, η is the weight coefficient of the additional adjustment term, is a function based on a convolutional neural network (CNN) and an attention mechanism, used to receive the current weight map W(x,y,t), context information C t and hidden state H t , and output a correction term for further optimizing the weight map.

[0206] The formula aims to construct a dynamic model that can adaptively adjust the weight distribution according to environmental changes. By combining multiple factors (such as target importance, background noise, smoothness, etc.), the model can allocate resources more intelligently, ensuring that key regions receive sufficient attention, while reducing noise interference and maintaining the smoothness of the weight distribution.

[0207] Learning rate (α(t)): A parameter that controls the update speed of the weight value, usually changing over time to adapt to the needs of different stages.

[0208] Smoothing term (λ·ΔW(x,y,t)): The smoothing term of the weight map calculated using the Laplacian operator, used to maintain the spatial consistency of the weight map.

[0209] Additional adjustment term The function output based on the convolutional neural network and attention mechanism is used to further optimize the weight map.

[0210] Target importance gain β(t)·I(x,y,t): Emphasizes the importance of the target region, ensuring that these regions occupy higher weights in the weight map.

[0211] Noise suppression gain γ(t)·(N(x,y,t)-μ N (t)): Reduces the influence of background noise and improves the signal-to-noise ratio.

[0212] The acquisition of each parameter is as follows:

[0213] W(x,y,t) and W'(x,y,t + 1) are obtained through the initialization of the model and the calculation results of the previous time step.

[0214] Parameters such as α(t), β(t), γ(t), λ, η are usually determined through experiments or automatically adjusted using an optimization algorithm (such as gradient descent).

[0215] I(x,y,t) is manually labeled according to the characteristics and positions of the target or automatically recognized through an algorithm.

[0216] N(x,y,t) and μ N (t) are obtained through statistical analysis of the background region.

[0217] ΔW(x,y,t) is calculated by applying the Laplacian operator to the current weight map.

[0218] Calculated through a pre-trained convolutional neural network and attention mechanism model.

[0219] In the embodiments of the present application, it is assumed that a target detection system is being developed, which needs to track a moving target in a video stream. To simplify the calculation, all parameters are set to fixed values, but in actual applications, these parameters should be dynamically adjusted.

[0220] Set the initial conditions:

[0221] W(x,y,t) = 0.5, I(x,y,t) = 1, N(x,y,t) = 0.2, μ N (t) = 0.1, ΔW(x,y,t) = 0.05, C t = [some context information], H t = [some hidden state].

[0222] Fixed parameters: α(t) = 0.1, β(t) = 0.8, γ(t) = 0.5, λ = 0.01, η = 0.1.

[0223] Assume (This usually needs to be calculated through CNN and attention mechanisms).

[0224] Substitute into the formula to calculate W'(x,y,t+1):

[0225] W'(x,y,t+1) = 0.5 + 0.1·(0.8·1 - 0.5) + 0.5·(0.2 - 0.1) + 0.01·0.05 + 0.1·0.05

[0226] W'(x,y,t+1) = 0.5 + 0.03 + 0.005 + 0.0005 + 0.005

[0227] W'(x,y,t+1) ≈ 0.5405

[0228] The calculation results show that the weight at position (x,y) is updated from 0.5 to approximately 0.5405. This means that based on the current observation data and context information, the system considers this position to have a slightly increased importance for the target detection task. This may be because the target appears near this position, or the background noise at this position is lower, resulting in an increase in the system's confidence in this area. In this way, the system can better adapt to environmental changes and improve the accuracy and reliability of target detection.

[0229] Figure 2 For the embodiments of the present application, a structural schematic diagram of an anti-interference tracking system based on the target infrared imaging characteristics is provided, as Figure 2 shown, the device includes:

[0230] An acquisition module 21, configured to acquire a continuous infrared image sequence of a target object at different time points;

[0231] An analysis and determination module 22, configured to determine a potential motion trajectory of a target object in the infrared image sequence by using spatio-temporal correlation analysis;

[0232] A generation and adjustment module 23, configured to generate a dynamic weight map based on the potential motion trajectory, wherein the dynamic weight map adaptively adjusts the importance of each pixel according to changes in background noise and target features;

[0233] A combination module 24, configured to combine the dynamic weight map with the infrared image sequence to strengthen the target area and suppress the non-target area, so as to obtain a strengthened infrared image sequence;

[0234] A real-time positioning and tracking module 25, configured to adopt a multiple hypothesis tracking strategy to perform real-time positioning of the target object in the strengthened infrared image sequence, and maintain continuous tracking of the target object by updating the dynamic weight map.

[0235] Figure 2 The anti-interference tracking system based on target infrared imaging features can execute Figure 1 The anti-interference tracking method based on target infrared imaging features described in the embodiments shown, and its implementation principle and technical effects will not be elaborated. For the anti-interference tracking system based on target infrared imaging features in the above embodiments, the specific manners in which each module and unit perform operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0236] In a possible design, Figure 2 The anti-interference tracking system based on target infrared imaging features described in the embodiments shown can be implemented as a computing device, such as Figure 3 shown, and the computing device may include a storage component 31 and a processing component 32;

[0237] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32.

[0238] The processing component 32 is configured to: obtain a continuous infrared image sequence of a target object at different time points; determine a potential motion trajectory of the target object in the infrared image sequence by using spatio-temporal correlation analysis; generate a dynamic weight map based on the potential motion trajectory, wherein the dynamic weight map adaptively adjusts the importance of each pixel according to changes in background noise and target features; combine the dynamic weight map with the infrared image sequence to strengthen the target area and suppress the non-target area, so as to obtain a strengthened infrared image sequence; adopt a multiple hypothesis tracking strategy to perform real-time positioning of the target object in the strengthened infrared image sequence, and maintain continuous tracking of the target object by updating the dynamic weight map.

[0239] Among them, the processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above-mentioned method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components for executing the above-mentioned method.

[0240] The storage component 31 is configured to store various types of data to support the operation of the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0241] Of course, the computing device may also necessarily include other components, such as input / output interfaces, display components, communication components, etc.

[0242] The input / output interface provides an interface between the processing component and the peripheral interface module, and the above-mentioned peripheral interface module may be an output device, an input device, etc.

[0243] The communication component is configured to facilitate communication between the computing device and other devices in a wired or wireless manner, etc.

[0244] Among them, the computing device may be a physical device or an elastic computing host provided by a cloud computing platform, etc. At this time, the computing device may refer to a cloud server, and the above-mentioned processing component, storage component, etc. may be basic server resources leased or purchased from a cloud computing platform.

[0245] The embodiment of the present application also provides a computer storage medium storing a computer program, and when the computer program is executed by a computer, it can implement the above-mentioned Figure 1 anti-interference tracking method based on target infrared imaging features shown in the above-mentioned embodiment.

[0246] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described systems, devices and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0247] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0248] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0249] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An anti-interference tracking method based on target infrared imaging features, characterized in that: include: Acquire a sequence of continuous infrared images of the target object at different time points; Determining the potential motion trajectory of the target object in the infrared image sequence by using spatiotemporal correlation analysis; Generate a dynamic weight map based on the potential motion trajectory, wherein the dynamic weight map adaptively adjusts the importance of each pixel according to changes in background noise and target features; combining the dynamic weight map with the infrared image sequence to enhance the target area and suppress the non-target area, thereby obtaining an enhanced infrared image sequence; A multi-hypothesis tracking strategy is used to locate the target object in real time in the enhanced infrared image sequence, and the target object is continuously tracked by updating the dynamic weight map; The generating a dynamic weight map based on the potential motion trajectory comprises: Extracting a region associated with the target object from the potential motion trajectory as a region of interest; Performing feature analysis on the region of interest to identify key feature points representing the target object; Calculating the importance coefficient of each pixel point to the target object according to the position of the key feature point and the change of the key feature point over time; In combination with the background noise level in the current frame, a noise suppression factor is assigned to each pixel to reflect the degree to which the pixel is affected by the background noise; combining the importance coefficient with the noise suppression factor to generate a dynamic weight map; The calculating the importance coefficient of each pixel point to the target object includes: The importance coefficient of each pixel point to the target object is calculated by the following calculation formula: ； in, Indicates at time Time, Location The importance coefficient of the pixel at is the number of key feature points, It is Key feature points at time The adaptive weight factor, They are Key feature points at time The horizontal and vertical coordinates of It is with The spatial scale parameter associated with each key feature point, is a two-dimensional Gaussian function used to measure the current position With key feature points The influence of the distance between them on the importance coefficient, It is the key feature point In time The gradient information of It is a nonlinear function based on the gradient information of key feature points , Direction parameters , local texture characteristics and attention weights to adjust the importance factor.

2. The method according to claim 1, characterized in that: The method of determining the potential motion trajectory of the target object in the infrared image sequence by using spatiotemporal correlation analysis includes: Performing inter-frame difference calculation on the continuous infrared image sequence to obtain change information between adjacent frames; constructing an optical flow field based on the change information, wherein the optical flow field represents the movement of pixels in the infrared image sequence from a previous frame to a next frame; Removing noise and outliers in the optical flow field by filtering technology to obtain an optical flow estimate; Based on the optical flow estimation, a dynamic clustering algorithm is applied to identify motion regions associated with the target object; A correspondence between the motion region and the continuous frames is established to form a potential motion trajectory of the target object.

3. The method according to claim 1, characterized in that The step of combining the dynamic weight map with the infrared image sequence to enhance the target area and suppress the non-target area to obtain an enhanced infrared image sequence includes: For each pixel point in each frame of the infrared image sequence, a weight value in a dynamic weight map corresponding to the position of the pixel point is applied to enhance or weaken the intensity value of the pixel point to form an enhanced infrared image sequence; Among them, the process of enhancing or weakening the intensity value of the pixel point includes: for the pixel points in the target area, using a first preset weight value to enhance the intensity value of the pixel point to improve the visibility of the target area; for the pixel points in the non-target area, using a second preset weight value to weaken the intensity value of the pixel point to reduce the visibility of the target area.

4. The method according to claim 1, characterized in that: The method adopts a multi-hypothesis tracking strategy to locate the target object in real time in the enhanced infrared image sequence, and keeps tracking the target object by updating the dynamic weight map, including: For each frame of enhanced infrared image sequence, multiple hypotheses about the position and state of the target object are constructed; Predicting the position of the target object in each hypothesized next frame using a prediction model; In the next frame of enhanced infrared image sequence, the likelihood score corresponding to each hypothesis is calculated according to the predicted position; The hypothesis with the highest likelihood score is selected as the current best estimate, and a preset number of suboptimal hypotheses are retained to cope with uncertainty; According to the result of the current optimal estimation, the weight distribution in the dynamic weight map is updated so that the weight value is more conducive to highlighting the target object and suppressing the background noise, so as to maintain continuous tracking of the target object.

5. The method according to claim 4, characterized in that The updating of the weight distribution in the dynamic weight map according to the result of the current optimal estimation includes: The updated weight distribution in the dynamic weight graph is calculated by the following calculation formula: ； in, is the updated dynamic weight graph at time Position at time The weight value at is the current time The weight value of is the learning rate that varies over time, is the target importance gain coefficient that changes over time, As defined above, is the importance coefficient of the position, is the time-varying noise suppression gain factor, Reflects the location In time is a function of the background noise level, It's in time The mean background noise level of the entire image is is the weight coefficient of the smoothing term, is the weight graph in The Laplacian result on the position is, is the weight coefficient of the additional adjustment term, It is a function based on convolutional neural network (CNN) and attention mechanism to receive the current weight map , context information and hidden state , output a correction term for further optimizing the weight graph.

6. An anti-interference tracking system based on target infrared imaging features, characterized in that: include: An acquisition module is used to acquire a sequence of continuous infrared images of a target object at different time points; An analysis and determination module, used for determining a potential motion trajectory of a target object in the infrared image sequence by using spatiotemporal correlation analysis; A generating and adjusting module is used to generate a dynamic weight map based on the potential motion trajectory, wherein the dynamic weight map adaptively adjusts the importance of each pixel according to changes in background noise and target features; A combining module, used for combining the dynamic weight map with the infrared image sequence to enhance the target area and suppress the non-target area, thereby obtaining an enhanced infrared image sequence; A real-time positioning and tracking module, configured to adopt a multi-hypothesis tracking strategy to locate the target object in real time in the enhanced infrared image sequence, and to keep tracking the target object by updating the dynamic weight map; The generating a dynamic weight map based on the potential motion trajectory comprises: Extracting a region associated with the target object from the potential motion trajectory as a region of interest; Performing feature analysis on the region of interest to identify key feature points representing the target object; Calculating the importance coefficient of each pixel point to the target object according to the position of the key feature point and the change of the key feature point over time; In combination with the background noise level in the current frame, a noise suppression factor is assigned to each pixel to reflect the degree to which the pixel is affected by the background noise; combining the importance coefficient with the noise suppression factor to generate a dynamic weight map; The calculating the importance coefficient of each pixel point to the target object includes: The importance coefficient of each pixel point to the target object is calculated by the following calculation formula: ； in, Indicates at time Time, Location The importance coefficient of the pixel at is the number of key feature points, It is Key feature points at time The adaptive weight factor, They are Key feature points at time The horizontal and vertical coordinates of It is with The spatial scale parameter associated with each key feature point, is a two-dimensional Gaussian function used to measure the current position With key feature points The influence of the distance between them on the importance coefficient, It is the key feature point In time The gradient information of It is a nonlinear function based on the gradient information of key feature points , Direction parameters , local texture characteristics and attention weights to adjust the importance factor.

7. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement an anti-interference tracking method and system based on target infrared imaging characteristics as described in any one of claims 1 to 5.

8. A computer storage medium, characterized in that A computer program is stored, and when the computer program is executed by a computer, an anti-interference tracking method and system based on target infrared imaging characteristics as described in any one of claims 1 to 5 is implemented.

Images