An infrared target detection method and system based on deep learning

Abstract

The present application provides a method and system for infrared target detection based on deep learning, which relates to the field of deep learning and infrared image technology. The method includes: obtaining an original infrared image and environmental data corresponding to the original infrared image; annotating target objects appearing in the original infrared image to obtain target annotation information; training a deep learning model for target detection based on the original infrared image, environmental data, and target annotation information to obtain a target detection model; and inputting the preprocessed infrared image to be identified and the corresponding environmental data into the target detection model to obtain infrared target detection results. Implementing this method can help the target detection model learn the characteristic patterns of infrared detection targets in different environments, take into account the impact of environmental data on infrared detection, improve the accuracy and efficiency of infrared target detection, and be more suitable for efficient infrared target recognition in complex environments.

Description

Technical Field

[0001] The present application relates to the fields of deep learning and infrared image technology, and in particular to a method and system for infrared target detection based on deep learning. Background Art

[0002] With advances in computer vision technology, particularly driven by deep learning algorithms, object detection using infrared images has made significant progress. Due to their unique imaging properties, infrared images can play an important role at night or in environments with obstructed vision. Therefore, they are widely used in military reconnaissance, environmental monitoring, and traffic safety.

[0003] Traditional infrared target detection technologies rely primarily on manually designed feature extraction and rule matching to identify targets in images. These methods typically include edge detection, shape matching, and motion detection to identify and track target objects.

[0004] However, traditional infrared detection methods perform poorly when dealing with environmental changes, such as changes in lighting and weather conditions. In particular, in complex environmental conditions such as fog, haze, rain, snow, or extreme lighting conditions, traditional feature extraction techniques struggle to accurately capture target features, significantly reducing target detection accuracy. Summary of the Invention

[0005] The present application provides an infrared target detection method and system based on deep learning, which are used to improve the target detection accuracy in infrared images.

[0006] In a first aspect, the present application provides an infrared target detection method based on deep learning, which is applied to an infrared target detection system. The method includes:

[0007] Acquire an original infrared image and environmental data corresponding to the original infrared image, the environmental data including geographic location coordinates, temperature and humidity, and features of markers in the image, the marker features including the location and category of the markers;

[0008] Marking the target object appearing in the original infrared image to obtain target marking information;

[0009] Training a deep learning model for target detection based on the original infrared image, the environmental data, and the target annotation information to obtain a target detection model;

[0010] The preprocessed infrared image to be identified and the environmental data corresponding to the infrared image are input into the target detection model to obtain the infrared target detection result. The preprocessing includes image enhancement, color optimization and texture optimization.

[0011] Through the above-described embodiment, the infrared target detection system uses raw infrared images labeled with target objects and their corresponding environmental data to train a target detection model, and then uses the trained model to perform target detection on preprocessed infrared images. This method helps the target detection model learn the characteristic patterns of infrared targets in different environments, considers the impact of environmental data on infrared detection, improves the accuracy and efficiency of infrared target detection, and is more suitable for efficient infrared target recognition in complex environments.

[0012] In some embodiments, the step of obtaining the original infrared image and the environmental data corresponding to the original infrared image specifically includes:

[0013] Obtaining the original infrared image, geographic location coordinates, and temperature and humidity sent by an infrared detection device equipped with a positioning system, a temperature sensor, and a humidity sensor;

[0014] The original infrared image is recognized based on an image recognition model to obtain the features of the markers in the original infrared image.

[0015] Through the above embodiments, the infrared target detection system extracts features from the original infrared image through the image recognition model, thereby improving the efficiency of extracting marker features.

[0016] In some embodiments, before the step of identifying the original infrared image based on the image recognition model to obtain the landmark features in the original infrared image, the method further includes:

[0017] Annotate the original infrared image sample to determine the location and category of the marker in the original infrared image sample;

[0018] The convolutional neural network model is trained using the labeled original infrared image samples to obtain an image recognition model, which is used to identify the landmark features in the original infrared image.

[0019] Through the above embodiments, the infrared target detection system can construct an image recognition model based on the original infrared images acquired historically before obtaining the landmark features of the original infrared images, which is used to perform landmark features on the original images in the training data set when subsequently constructing the target detection model, thereby improving the efficiency of constructing the training data set.

[0020] In some embodiments, the step of training a deep learning model for target detection based on the original infrared image, the environmental data, and the target annotation information to obtain a target detection model specifically includes:

[0021] Constructing a training data set based on the original infrared image, the environmental data, and the target annotation information, wherein the training data set includes a training set, a test set, and a validation set;

[0022] The deep learning model is trained using the training data set to obtain a target detection model, which is used to identify the target object in the original infrared image based on the input original infrared image and environmental data.

[0023] Through the above embodiments, the infrared target detection system constructs a training data set including original infrared images and their corresponding environmental data, which is used to help the target detection model learn the characteristic patterns of infrared detection targets in different environments, thereby improving the adaptability and accuracy of the target detection model in target detection of original infrared images in different environments.

[0024] In some embodiments, the step of training a deep learning model using the training dataset to obtain a target detection model specifically includes:

[0025] Divide the collection time of the environmental data into multiple time periods;

[0026] Dividing the training data set according to the multiple time periods to obtain multiple sub-training data sets;

[0027] The multiple sub-training data sets are used to train the deep learning model respectively to obtain the target detection model corresponding to each time period.

[0028] Through the above embodiment, the infrared target detection system divides the training dataset into multiple sub-training datasets for different time periods and performs model training. This allows different target detection models to adapt to the characteristic patterns of infrared targets in different time environments (such as winter and summer), making the target detection models more targeted.

[0029] In some embodiments, after the step of training the deep learning model using the multiple sub-training data sets to obtain the object detection model corresponding to each time period, the method further includes:

[0030] Determining the acquisition time corresponding to the infrared image to be identified, where the acquisition time of the infrared image and the environmental data corresponding to the infrared image are the same;

[0031] The infrared image to be identified is identified using a target detection model that matches the acquisition time to obtain an infrared target detection result.

[0032] Through the above embodiments, the infrared target detection system can more accurately process environmental factors related to specific times, such as different conditions at night and during the day, by selecting a model that matches the image acquisition time for infrared detection, thereby further improving the accuracy of detection.

[0033] In some embodiments, after the step of inputting the pre-processed infrared image to be identified and the environmental data corresponding to the infrared image into the target detection model to obtain the infrared target detection result, the method further includes:

[0034] The infrared images with recognition errors are annotated and the incremental training set is expanded by combining the environmental data corresponding to the infrared images;

[0035] After detecting that the incremental training set exceeds a preset capacity threshold, the target detection model is incrementally trained using the incremental training set.

[0036] Through the above embodiments, the infrared target detection system marks the images with recognition errors and uses these data to perform incremental training of the model, continuously optimizes and adjusts the model, thereby improving the real-time performance of the target detection model and the accuracy of infrared detection.

[0037] In a second aspect, the present application provides an infrared target detection system, the infrared target detection system comprising: one or more processors and a memory;

[0038] The memory is coupled to the one or more processors, and the memory is used to store computer program code, which includes computer instructions. The one or more processors call the computer instructions so that the infrared target detection system can implement an infrared target detection method based on deep learning provided in the above embodiment, which will not be repeated here.

[0039] In a third aspect, the present application provides a computer-readable storage medium comprising instructions. When the instructions are executed on an infrared target detection system, the infrared target detection system can implement an infrared target detection method based on deep learning provided in the above embodiment, which will not be described in detail here.

[0040] Fourthly, the present application provides a computer program product. When the computer program product runs on an infrared target detection system, the infrared target detection system can implement an infrared target detection method based on deep learning provided in the above embodiment, which will not be repeated here.

[0041] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0042] 1. Using original infrared images labeled with target objects and their corresponding environmental data to train the target detection model not only allows the model to learn the visual features of the target in the infrared image, but also takes into account the impact of environmental factors such as temperature and time on the infrared features, thereby improving the model's adaptability and accuracy in complex environments, thereby improving the accuracy of infrared target detection.

[0043] 2. The training dataset is divided into multiple sub-training datasets for different time periods, and dedicated model training is performed on the dataset for each time period. This enables the model to more accurately adapt to environmental influences brought about by different seasons or day and night changes, such as changes in temperature and lighting conditions. This not only improves the model's generalization ability, but also ensures that the most appropriate model can be selected according to the specific time during actual deployment, thereby improving the accuracy of infrared detection.

[0044] 3. Label the images with recognition errors and use this data for incremental training of the model, continuously optimize and adjust the model, and improve the real-time performance of the target detection model and the accuracy of infrared detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is a flowchart of an infrared target detection method based on deep learning in an embodiment of the present application;

[0046] Figure 2 This is another flowchart of an infrared target detection method based on deep learning in an embodiment of the present application;

[0047] Figure 3 Schematic diagram of the principle of target detection of an infrared target detection system for an infrared image to be identified in an embodiment of the present application;

[0048] Figure 4 It is a schematic diagram of the physical device structure of the infrared target detection system in the embodiment of the present application. DETAILED DESCRIPTION

[0049] The terms used in the following examples of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification and appended claims of this application, the singular expressions "a," "an," "said," "above," "the," and "this" are intended to include plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in this application refers to any or all possible combinations comprising one or more of the listed items.

[0050] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of the technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of this application, unless otherwise specified, "plurality" means two or more.

[0051] For ease of understanding, the following describes the process of the method provided by this implementation. Figure 1, which is a flow chart of an infrared target detection method based on deep learning in an embodiment of the present application.

[0052] S101: Acquire an original infrared image and environmental data corresponding to the original infrared image.

[0053] The infrared target detection system first acquires data for training and testing the target detection model. This data includes raw infrared images and the environmental data corresponding to each raw infrared image. Raw infrared images are thermal images directly captured by infrared cameras without any preprocessing. Infrared cameras capture the thermal radiation emitted by objects, allowing for clear images even in harsh environments or at night. These images are known as raw infrared images.

[0054] The environmental data corresponding to the original infrared image contains information about various external factors at the time of image acquisition. This environmental data includes the geographic coordinates of the shooting location (such as longitude and latitude), the temperature and humidity at the time, and the location and type of landmarks.

[0055] For example, in one specific embodiment, an infrared target detection system is deployed on a forest fire monitoring drone, which collects original infrared images of the ground through an onboard infrared camera. At the same time, the drone is also equipped with a GPS positioning system that can record the coordinates of the shooting location of each image. The fuselage is also equipped with a temperature and humidity sensor to collect environmental temperature and humidity data in real time. For each original infrared image collected, the system matches it with the synchronously recorded GPS coordinates, temperature and humidity data, and uses them together as training data. In addition, the system can also automatically mark easily recognizable objects in the infrared image, such as roads, houses, etc., as visually significant landmarks through image recognition algorithms. The categories and coordinates of these landmarks will also be added to the environmental information of the image.

[0056] It's understandable that geographic coordinates help the model learn about regional differences in background characteristics; temperature and humidity data can reflect the impact of meteorological conditions on the target's appearance and infrared characteristics; and landmark information provides spatial reference and scale information for the target. Combining environmental data with raw infrared imagery provides richer semantic information for the training dataset of the target prediction model, thereby improving the robustness of target detection.

[0057] S102: Mark the target object appearing in the original infrared image to obtain target marking information.

[0058] After acquiring the raw infrared image and its surrounding data, the infrared target detection system needs to annotate the target of interest within the raw infrared image. For example, if the target is an animal, the animal's species and location within the raw infrared image must be annotated. This can be done manually or with the aid of annotation tools, though this is not a specific approach.

[0059] S103: Training a deep learning model for target detection based on the original infrared image, environmental data, and target annotation information to obtain a target detection model.

[0060] The infrared target detection system generates a training dataset (including training, test, and validation sets) based on the acquired raw infrared images, environmental parameter data, and target annotation information. It then constructs a deep learning model (such as Faster R-CNN and YOLO). The training dataset is then fed into the deep learning model for training. Through iterative optimization, the model automatically learns the key feature representations for detecting targets in the training dataset. After multiple rounds of iterative training, when the model's performance on the validation set reaches a preset threshold, the model training is considered complete, resulting in the final infrared target detection model. This infrared target detection model automatically identifies each target instance of interest in the infrared image based on the input infrared image and corresponding environmental data, and provides its location coordinates and category label.

[0061] For example, in a forest fire monitoring scenario, an infrared target detection system can use the YOLO v5 model to build an infrared fire detection algorithm. The acquired raw infrared images, environmental parameters, and fire point annotation information from multiple scenes and time scales are divided proportionally into training, validation, and test sets. After preprocessing with scale normalization and data augmentation, the raw infrared images are input into the YOLO v5 network along with environmental parameter features. Through multiple rounds of iterative optimization on the training set, the model gradually learns the infrared imaging characteristics of fire targets and establishes robust fire discrimination capabilities in different environments. The training process monitors model performance in real time using the validation set, ultimately resulting in a target detection model that can efficiently and accurately detect fire points in infrared images.

[0062] Furthermore, during actual deployment, the infrared target detection system can select detection models of varying performance levels based on specific mission requirements, balancing detection accuracy and real-time performance to meet the demands of various scenarios. Furthermore, the infrared target detection system can continuously acquire new measured data and regularly iterate and optimize the model, continuously improving its detection performance and environmental adaptability to ensure reliable and effective detection results.

[0063] S104: Input the pre-processed infrared image to be identified and the environmental data corresponding to the infrared image into the target detection model to obtain an infrared target detection result.

[0064] Once the infrared target detection system completes the training of the detection model, it can use the model to perform real-time detection and recognition on newly collected infrared image data.

[0065] Specifically, when the infrared target detection system acquires a new infrared image to be detected, it first preprocesses the image, including image enhancement, color optimization, and texture optimization. Simultaneously, the system obtains environmental parameter data corresponding to the infrared image, such as the geographic coordinates of the shooting location and the current temperature and humidity, and encodes it into a feature vector.

[0066] Next, the system inputs the preprocessed infrared image and the corresponding environmental parameter features into the trained target detection model. The detection model automatically analyzes and identifies the input infrared image, using the learned target feature patterns to locate each target of interest within the infrared image and assign its corresponding category label and confidence score. Based on a pre-set confidence threshold, the system automatically selects detection results with confidence scores above the threshold as the final target recognition result. The target detection model typically outputs a bounding box and category label. Each detection result includes the target's category information and location coordinates, allowing for visual annotation and display directly on the original image.

[0067] In the above embodiment, the infrared target detection system uses raw infrared images labeled with target objects and their corresponding environmental data to train a target detection model, and then uses the trained model to perform target detection on preprocessed infrared images. This method helps the target detection model learn the characteristic patterns of infrared targets in different environments, considers the impact of environmental data on infrared detection, improves the accuracy and efficiency of infrared target detection, and is more suitable for efficient infrared target recognition in complex environments.

[0068] The following is a more detailed description of the process of the method provided by this implementation. Figure 2 , is another flow chart of an infrared target detection method based on deep learning in an embodiment of the present application.

[0069] S201: Label the original infrared image sample to determine the position and category of the marker in the original infrared image sample.

[0070] The infrared target detection system annotates a batch of raw infrared image samples. Landmarks are prominent, easily identifiable objects or areas in the image, such as buildings, roads, and plants. The specific number of landmarks can be determined based on actual needs. These landmarks provide important spatial reference information for subsequent target detection.

[0071] Specifically, the annotation process can be done manually or with the help of some semi-automated image annotation tools. The annotation content mainly includes two aspects: the location and category of the landmark. The location information can be given in the form of a bounding box, which marks the approximate range of the landmark in the image.

[0072] S202: Use the labeled original infrared image samples to train a convolutional neural network model to obtain an image recognition model.

[0073] The infrared target detection system uses the original infrared image samples marked in step S201 to train an image recognition model for identifying the marker information in the original infrared image.

[0074] Specifically, the annotated original infrared images are divided into a training set and a validation set. The infrared target detection system uses the training set images to train the CNN model. This involves using a backpropagation algorithm to adjust the model's internal parameters so that it can correctly extract and identify the features of various landmarks from the infrared images. During the training process, the validation set data is not used in the backpropagation process and is only used to evaluate model performance, allowing for timely termination of training and preventing overfitting. The trained CNN model (i.e., image recognition model) can detect and locate different categories of landmarks from any input infrared image.

[0075] In the above embodiment, the infrared target detection system can construct an image recognition model based on the original infrared images acquired historically before obtaining the landmark features of the original infrared images, which is used to perform landmark features on the original images in the training data set when subsequently constructing the target detection model, thereby improving the efficiency of constructing the training data set.

[0076] S203: Obtain the original infrared image, geographic location coordinates, and temperature and humidity sent by the infrared detection device.

[0077] Specifically, the original infrared image can be acquired in real time through an infrared camera. The infrared camera can capture the thermal radiation emitted by the object and convert it into a digital image signal for transmission to the processing unit. At the same time, the detection equipment also needs to support positioning and environmental sensing functions. Among them, the positioning function can be implemented through a positioning system such as GPS to record the shooting location of the image. The environmental sensing function can be implemented through a temperature and humidity sensor to record the ambient temperature and humidity at the time of shooting. The infrared detection device will then send the collected original image and the corresponding position, temperature and humidity data to the infrared target detection system, which becomes the input data of the target detection model.

[0078] S204: Identify the original infrared image based on the image recognition model to obtain the landmark features in the original infrared image.

[0079] Specifically, when the infrared target detection system receives a new frame of original infrared image, it first inputs it into the image recognition model, and outputs the location and category information of different markers in the original infrared image.

[0080] In the above embodiment, the infrared target detection system extracts features from the original infrared image through the image recognition model, thereby improving the efficiency of extracting landmark features.

[0081] S205: Construct a training data set based on the original infrared image, environmental data, and target annotation information.

[0082] The infrared target detection system combines raw infrared images, environmental parameters, and manually annotated target information to construct a training dataset. The raw infrared images are acquired in real time by infrared cameras. Environmental parameters, such as the geographic location, temperature, and humidity at the time of capture, correspond one-to-one with the raw infrared images. Target annotation information is manually added to indicate the location and category of the target of interest in each raw infrared image.

[0083] In the above embodiment, the infrared target detection system constructs a training data set including the original infrared image and its corresponding environmental data to help the target detection model learn the characteristic patterns of infrared detection targets in different environments, thereby improving the adaptability and accuracy of the target detection model in performing target detection on the original infrared image in different environments.

[0084] S206: Divide the environmental data collection time into multiple time periods.

[0085] Specifically, the infrared target detection system can select an appropriate time granularity for division based on the application scenario, such as dividing it into four time periods: spring, summer, autumn, and winter; or dividing it into two time periods: daytime and nighttime, etc., without limitation here.

[0086] S207 : Divide the training data set according to multiple time periods to obtain multiple sub-training data sets.

[0087] After completing the time period division according to step S206, the infrared target detection system divides the existing training data set accordingly according to the time period corresponding to the acquisition timestamp of each training sample (including the original infrared image and environmental parameters), thereby obtaining a sub-training data set corresponding to each time period.

[0088] After constructing multiple sub-training datasets, the infrared target detection system further divides each sub-training dataset into a training set, a validation set, and a test set. The training set is used for model training, the validation set is used to evaluate model performance and adjust parameters during training, and the test set is used to evaluate the final performance indicators of the trained model. A typical split ratio of 7:2:1 or 8:1:1 is sufficient, but this is not a specific requirement.

[0089] S208. Use multiple sub-training data sets to train the deep learning model respectively to obtain the target detection model corresponding to each time period.

[0090] The process of using the sub-training data set for the deep learning model is basically the same as step S103 and will not be repeated here.

[0091] In the above embodiment, the infrared target detection system divides the training dataset into multiple sub-training datasets for different time periods and performs model training. This allows different target detection models to adapt to the characteristic patterns of infrared targets detected in different time environments (e.g., winter and summer), making the target detection models more targeted.

[0092] S209: Determine the acquisition time corresponding to the infrared image to be identified.

[0093] Because each infrared image is timestamped when it is captured, the infrared target detection system can directly read the timestamp and store it along with the environmental parameter data as metadata for the image. When the infrared image to be identified needs to be detected, the infrared target detection system simply queries its acquisition timestamp to determine which pre-defined time period it belongs to.

[0094] S210 , using a target detection model that matches the acquisition time to identify the infrared image to be identified, to obtain an infrared target detection result.

[0095] After step S208, the infrared target detection system already has multiple target detection models for different time periods. During actual infrared target detection, the infrared target detection system matches the target detection model for the corresponding time period based on the timestamp added to each original infrared image when it was captured. The specific detection process has been described in step S104 and will not be repeated here.

[0096] In the above embodiment, the infrared target detection system can more accurately process environmental factors related to specific times, such as different conditions at night and during the day, by selecting a model that matches the image acquisition time for infrared detection, thereby further improving the accuracy of detection.

[0097] Furthermore, when using a trained target detection model to detect new infrared images, the infrared target detection system inevitably encounters some recognition errors. To address this, the infrared target detection system monitors the target detection model's output in real time. When a detection result differs from expectations or the confidence level is too low, it is considered a recognition error. At this point, the infrared target detection system automatically initiates the labeling process, relabeling the incorrectly detected targets in the image through artificial intelligence algorithms or manual review. These relabeled erroneous samples are automatically added to a separate incremental training set. When the sample size of the incremental training set reaches a certain level, exceeding a preset capacity threshold, the system uses the newly collected samples to fine-tune or locally optimize the model to adapt it to the new data distribution, thereby improving the real-time performance and infrared detection accuracy of the target detection model.

[0098] The following is a schematic diagram of the principle of the infrared target detection system in the embodiment of the present application performing target detection on the infrared image to be identified. Figure 3 shown.

[0099] In the embodiment of the present application, the infrared target detection system performs target detection on the infrared image to be identified in two main processes. One is the process of constructing a target detection model, and the other is the process of performing target detection on the infrared image to be identified based on the constructed target detection model. Among them, the target detection model construction process is to construct a training data set based on the original infrared image and environmental data collected by the infrared detection equipment, as well as the target annotation information of the original infrared image. The training data set is used to train the deep learning model, and the deep learning model whose performance index reaches the preset threshold is screened and evaluated as the target detection model. When performing infrared target detection, the infrared image to be identified and the corresponding collected environmental data are input into the target detection model, and the infrared target detection result, that is, the category information and position coordinate information of the target, is output.

[0100] The infrared target detection system of the embodiment of the present invention is applied to electronic equipment. Figure 4A schematic diagram of the architecture of an electronic device suitable for implementing an embodiment of the present invention is shown.

[0101] It should be noted that Figure 4 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0102] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be accomplished by instructions (computer programs) or by controlling related hardware through instructions (computer programs), and the instructions can be stored in a computer-readable storage medium and loaded and executed by a processor. The electronic device of this embodiment includes a storage medium and a processor, wherein the storage medium stores a plurality of instructions, which can be loaded by the processor to execute any step of the method provided in the embodiment of the present invention.

[0103] Specifically, the storage medium and the processor are electrically connected directly or indirectly to achieve data transmission or interaction. For example, these elements can be electrically connected to each other via one or more signal lines. The storage medium stores computer-executable instructions for implementing the data access control method, including at least one software function module that can be stored in the storage medium in the form of software or firmware. The processor executes various functional applications and data processing by running the software programs and modules stored in the storage medium. The storage medium can be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc. The storage medium is used to store programs, and the processor executes the programs after receiving the execution instructions.

[0104] Furthermore, the software programs and modules in the above-mentioned storage medium may also include an operating system, which may include various software components and / or drivers for managing system tasks (such as memory management, storage device control, power management, etc.), and may communicate with various hardware or software components to provide an operating environment for other software components. The processor may be an integrated circuit chip having signal processing capabilities. The above-mentioned processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc., which may implement or execute the various methods, steps, and logic flow diagrams disclosed in this embodiment. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0105] Since the instructions stored in the storage medium can execute the steps of any method provided in the embodiments of the present invention, the beneficial effects of any method provided in the embodiments of the present invention can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0106] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A deep learning-based infrared target detection method, applied to an infrared target detection system, characterized in that: The method comprises: Obtaining an original infrared image, geographic location coordinates, and temperature and humidity sent by an infrared detection device equipped with a positioning system, a temperature sensor, and a humidity sensor; Annotating the original infrared image samples to determine the location and category of the markers in the original infrared image samples; using the annotated original infrared image samples to train a convolutional neural network model to obtain an image recognition model, wherein the image recognition model is used to identify the features of the markers in the original infrared image; Recognizing the original infrared image based on an image recognition model to obtain marker features in the original infrared image, wherein the marker features include a position and a category of the marker; Marking the target object appearing in the original infrared image to obtain target marking information; Training a deep learning model for target detection based on the original infrared image, environmental data, and target annotation information to obtain a target detection model, wherein the environmental data includes geographic location coordinates, temperature and humidity, and landmark features in the original infrared image; The preprocessed infrared image to be identified and the environmental data corresponding to the infrared image are input into the target detection model to obtain the infrared target detection result, and the preprocessing includes image enhancement, color optimization and texture optimization.

2. The method according to claim 1, characterized in that The step of training a deep learning model for target detection based on the original infrared image, the environmental data, and the target annotation information to obtain a target detection model specifically includes: Constructing a training data set based on the original infrared image, the environmental data, and the target annotation information, wherein the training data set includes a training set, a test set, and a validation set; The deep learning model is trained using the training data set to obtain a target detection model, which is used to identify the target object in the original infrared image based on the input original infrared image and environmental data.

3. The method according to claim 2, characterized in that The step of using the training data set to train the deep learning model to obtain the target detection model specifically includes: Dividing the collection time of the environmental data into multiple time periods; Dividing the training data set according to the multiple time periods to obtain multiple sub-training data sets; The deep learning model is trained respectively using the multiple sub-training data sets to obtain a target detection model corresponding to each time period.

4. The method according to claim 3, characterized in that After the step of using the multiple sub-training data sets to train the deep learning model respectively to obtain the target detection model corresponding to each time period, the method further includes: Determining a collection time corresponding to the infrared image to be identified, where the collection time of the infrared image and the environmental data corresponding to the infrared image are the same; The infrared image to be identified is identified using a target detection model that matches the acquisition time to obtain an infrared target detection result.

5. The method according to claim 1, wherein After the step of inputting the pre-processed infrared image to be identified and the environmental data corresponding to the infrared image into the target detection model to obtain the infrared target detection result, the method further includes: Annotate infrared images with recognition errors and expand the incremental training set by combining the environmental data corresponding to the infrared images; After detecting that the incremental training set exceeds a preset capacity threshold, the object detection model is incrementally trained using the incremental training set.

6. An infrared target detection system, characterized in that: The infrared target detection system includes: one or more processors and memory; The memory is coupled to the one or more processors, and is used to store computer program code, where the computer program code includes computer instructions. The one or more processors call the computer instructions to enable the infrared target detection system to execute the method according to any one of claims 1 to 5.

7. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on an infrared target detection system, the infrared target detection system is caused to execute the method according to any one of claims 1 to 5.

8. A computer program product, characterized in that When the computer program product is run on an infrared target detection system, the infrared target detection system is enabled to perform the method according to any one of claims 1 to 5.

Images