Moving path dynamic planning method and system for image shooting of single zoom wide-angle camera

Abstract

The invention relates to the technical field of image processing and camera control, in particular to a moving path dynamic planning method and system for image shooting of a single zoom wide-angle camera. The method comprises the following steps: receiving an image acquisition instruction, wherein the instruction comprises a target scene type, key area information and a task priority parameter; calling a preset 3D environment map in response to the instruction, calculating an initial moving path of the camera based on a coverage algorithm, and ensuring that all key areas are covered in a maximum resource state; controlling the camera to move along the path, starting a wide-angle mode scanning environment, and collecting video stream data in real time; performing target detection and behavior analysis on the video stream, identifying key target objects (such as teachers and students) and dynamic characteristics thereof, and sorting regions based on a priority rule; and dynamically adjusting a moving path, a zooming parameter and resource allocation according to a sorting result, transitioning from a maximum resource state to a minimum resource state, and reserving high-priority area coverage. According to the invention, dynamic optimization of camera path planning and resource allocation is realized, the coverage efficiency is effectively improved, the energy consumption is reduced, and the robustness of target tracking and the scene adaptive capability are enhanced.

Description

Technical Field

[0001] This invention relates to the technical field of image processing and camera control, and in particular to a method and system for dynamic planning of movement paths for image capture using a single zoom wide-angle camera. Background Technology

[0002] With the rapid development of intelligent monitoring and image acquisition technologies, single zoom wide-angle cameras have been widely used in educational settings for image acquisition and target tracking. However, existing technologies often employ fixed perspectives or preset static paths for camera control, which cannot adapt to dynamic environmental changes, such as teacher movement, student interaction, or the appearance of obstacles in the classroom, resulting in incomplete coverage of key areas or wasted resources.

[0003] Secondly, in complex and ever-changing teaching activities, such as lectures, discussions, and experiments, cameras need to cover both the overall picture and close-ups. However, existing solutions lack intelligent priority adaptation mechanisms: they often operate in the maximum resource mode, resulting in redundancy in computing power, energy consumption, and travel distance; or due to rigid path planning, they cannot respond to changes in task priority in real time, such as when teachers' lectures take precedence over students' regular activities, causing high-value events to be missed.

[0004] Furthermore, the zoom control logic is imperfect, and the triggering of optical zoom and digital zoom lacks intelligent decision-making based on target distance and behavior, affecting image quality; the target loss handling mechanism is weak, making it difficult to quickly resume tracking when the target is briefly obscured or moves out of the field of view. To address these issues, the inventors believe that existing technologies cannot achieve a balance between dynamic coverage and task adaptation, hindering the efficient application of cameras in resource-constrained environments. Therefore, an innovative path dynamic planning method is urgently needed. Summary of the Invention

[0005] To achieve dynamic optimization of camera path planning and resource allocation, effectively improve coverage efficiency, reduce energy consumption, and enhance the robustness of target tracking and scene adaptability, this application provides a dynamic path planning method and system for image capture using a single zoom wide-angle camera.

[0006] The above-mentioned objective of this application is achieved through the following technical solution:

[0007] A dynamic path planning method for image capture using a single zoom wide-angle camera, comprising the following steps:

[0008] Receive an image acquisition instruction, which includes the target scene type, key area information, and task priority parameters;

[0009] In response to the image acquisition command, a preset 3D environment map is invoked, and the initial movement path of the zoom wide-angle camera is calculated based on the coverage algorithm to ensure coverage of all key areas under maximum resource conditions;

[0010] The zoom wide-angle camera is controlled to move along the initial movement path, and the wide-angle mode is activated to scan the environment and collect video stream data in real time.

[0011] The system performs target detection and behavior analysis on real-time acquired video stream data, identifies key target objects and their dynamic characteristics, and sorts the regions based on preset task priority rules.

[0012] Based on the target priority ranking results, the camera's movement path, zoom parameters, and resource allocation are dynamically adjusted, transitioning from the maximum resource state to the minimum resource state, while preserving coverage of high-priority areas.

[0013] By adopting the above technical solution, and receiving image acquisition commands including target scene type, key area information, and task priority parameters, the system can adaptively configure parameters according to specific scenes, thereby improving the targeting and efficiency of shooting. After responding to the command, it calls up the preset 3D environment map and calculates the initial movement path based on the coverage algorithm, extracts the coordinates of key areas and obstacle information, and optimizes the path length by combining the camera's field of view model. This not only ensures that all key areas are covered without blind spots under maximum resource conditions, but also significantly reduces movement energy consumption, providing a stable foundation for subsequent dynamic adjustments. The system controls the camera to move along the initial path and starts wide-angle mode to scan the environment, acquiring video stream data in real time, avoiding the omission problem caused by the fixed viewpoint of traditional single cameras. It provides high-quality input for real-time analysis; it performs target detection and behavior analysis on video stream data to identify key target objects (such as teachers or students) and their dynamic characteristics, and sorts regions based on priority rules. By generating region heatmaps and updating the coverage list in real time, it improves the accuracy of target tracking and scene adaptability, ensuring that high-priority behaviors (such as teacher lectures) receive priority attention. It dynamically adjusts the path, zoom parameters, and resource allocation according to the priority sorting results, smoothly transitioning from the maximum resource state to the minimum resource state. It prioritizes the use of optical zoom to maintain image quality and replans local paths to reduce movement distance. At the same time, it adjusts the frame rate and computing power. This closed-loop optimization mechanism not only effectively avoids occlusion and resource waste, but also significantly improves energy efficiency and image detail capture capabilities.

[0014] In a preferred embodiment, this application can be further configured such that: the calculation of the initial movement path of the zoom wide-angle camera based on the coverage algorithm specifically includes:

[0015] Load a pre-built 3D environment map and extract the coordinate sets of key areas and obstacle boundary information;

[0016] Based on the camera's field of view model and zoom range, calculate the minimum coverage angle and distance constraints for each key area;

[0017] A global path planning algorithm is used to generate an initial movement path that aims to cover all key areas, and the path length is optimized to minimize movement energy consumption.

[0018] By adopting the above technical solution, in the process of loading a pre-built 3D environment map and extracting the coordinate set of key areas and obstacle boundary information, high-precision map data is used to ensure the accuracy and integrity of the environment, providing a reliable spatial basis for path planning. This avoids the coverage blind spots or collision risks caused by incomplete data in traditional methods, thereby improving the safety and comprehensiveness of the initial path. Coordinates and boundaries are extracted through geometric processing. Based on the camera's field of view model and zoom range, the minimum coverage angle and distance constraints of each key area are calculated to ensure that the camera achieves maximum coverage with minimal energy consumption, avoiding resource waste or insufficient viewing angle. A global path planning algorithm is used to generate an initial movement path with the goal of covering all key areas, and the path length is optimized to minimize movement energy consumption. Through heuristic search and energy consumption model evaluation, the camera movement distance and motor power consumption are reduced, which not only improves path efficiency but also extends equipment life.

[0019] In a preferred embodiment, this application can be further configured such that: the target detection and behavior analysis of the real-time acquired video stream data specifically includes:

[0020] Based on the video stream data, extract consecutive frame images, detect target objects (including teachers, students, and equipment) based on the consecutive frame images, and output their bounding boxes and category labels;

[0021] Track the movement of the target object, predict its short-term location based on the movement, and record its behavioral characteristics;

[0022] Based on preset task priority rules, the detected target objects are dynamically scored, and higher priority behaviors are assigned higher weights.

[0023] A regional heat map is generated based on the dynamic scoring results, and the coverage priority list of key areas is updated in real time based on the regional heat map.

[0024] By employing the above technical solution, continuous frame images are extracted based on video stream data, and target objects (such as teachers, students, and equipment) are detected based on these continuous frame images. Their bounding boxes and category labels are output, enabling real-time identification of key targets. This ensures the accuracy and efficiency of image processing and avoids the insufficient coverage problem caused by target omission or misidentification in traditional methods, thereby improving the comprehensiveness and reliability of scene perception. Furthermore, by associating targets in continuous frames using a multi-target tracking algorithm, trajectory sequences are generated and future coordinates are predicted, enhancing the system's stable tracking capability for dynamic targets. This reduces the risk of loss due to rapid target movement or brief occlusion, and improves response speed. The system combines high accuracy and adaptive performance with preset task priority rules to dynamically score detected target objects and assign higher weights to high-priority behaviors. By updating scores through a weighted summation formula and a time decay factor, it achieves intelligent resource allocation, ensuring that high-value areas receive priority attention and optimizing overall shooting efficiency and economy. Based on the dynamic scoring results, it generates regional heat maps and updates the coverage priority list of key areas in real time based on the heat maps. By mapping scores to a two-dimensional grid and sorting regions, a dynamic feedback mechanism is formed, enabling the system to quickly adjust paths and resources, improving real-time decision-making capabilities and robustness in complex environments.

[0025] In a preferred embodiment, this application can be further configured such that: dynamically adjusting the camera's movement path, zoom parameters, and resource allocation based on the target priority sorting result specifically includes:

[0026] Based on the target priority ranking results, calculate the required zoom level and resolution parameters for high-priority areas;

[0027] Optical zoom is triggered for capturing details in distant scenes, or digital zoom is used for close-up shots of specific areas, with optical zoom taking precedence over digital zoom to maintain image quality.

[0028] Based on priority changes, local paths are replanned to generate the shortest obstacle avoidance path, reducing the camera's movement distance.

[0029] Dynamically adjust camera frame rate and processing power to free up resources in low-priority areas and optimize energy consumption.

[0030] By adopting the above technical solutions, and by parsing the priority list and optimizing settings based on distance and object size, the system ensures that high-interest areas obtain accurate detail capture parameters, thereby improving image clarity and usability. Optical zoom is triggered for capturing distant details, while digital zoom is used for close-ups, with optical zoom being prioritized to maintain image quality. The optical lens is adjusted preferentially by monitoring target distance and size thresholds, and digital zoom enhancement is only enabled in extreme situations. This layered strategy effectively balances image quality and detail requirements, reduces pixel loss, and ensures adaptability and reliability in both distant and close-up scenes. By integrating real-time obstacle data through local path planning, path length and steering are optimized, significantly reducing mobile energy consumption and equipment wear, while enhancing system response speed and obstacle avoidance capabilities. This ensures stable coverage in highly dynamic environments. Resource management reallocates computing power, improving energy efficiency and extending equipment lifespan. Overall, the system achieves intelligent and economical resource scheduling in complex scenarios, improving overall operational efficiency and sustainability.

[0031] In a preferred embodiment, this application can be further configured such that: the triggered optical zoom is used for capturing distant details, or the digital zoom is used for local close-ups, specifically including:

[0032] Monitor the distance and size of the target object, and when the distance exceeds the threshold and detailed capture is required, prioritize optical zoom;

[0033] If the optical zoom has reached its limit and still cannot meet the detail requirements, then digital zoom is triggered to crop and enhance pixels.

[0034] By adopting the above technical solution, target parameters are monitored in real time through laser rangefinders or image parallax calculations. This ensures rapid response to detail requirements in long-distance scenes, prioritizing optical zoom to adjust the lens focal length. This avoids pixel loss and image blurring issues that may be introduced by digital zoom, thus maintaining high image quality and realistic details. If optical zoom has reached its limit and still cannot meet detail requirements, digital zoom is triggered to perform pixel cropping and enhancement. Pixel cropping is used to locally magnify and apply enhancement to improve clarity, ensuring readability of details under extreme distance or size conditions. This compensates for the shortcomings of optical zoom and can flexibly cope with various shooting scenarios.

[0035] In a preferred embodiment, this application can be further configured such that the motion path dynamic planning method for image capture by the single zoom wide-angle camera also includes:

[0036] Real-time monitoring of the tracking status of key targets; triggering a loss handling protocol when a target loss event is detected.

[0037] Based on historical trajectory and environmental data analysis, the cause of loss can be distinguished as temporary occlusion, target moving out of the field of view, or systematic error.

[0038] If the obstruction is temporary, pause path adjustment, maintain the current zoom parameters, and enable the prediction algorithm to estimate the target's reappearance location;

[0039] If the target continues to be lost, the camera will revert to its last known location, adjust the camera angle, or activate the wide-angle scanning mode to recapture the target.

[0040] By adopting the above technical solution, the tracking status of key targets is monitored in real time, and a loss handling protocol is triggered when a target loss event is detected, ensuring the reliability of continuous monitoring of key targets. Based on historical trajectory and environmental data analysis, the cause of loss is diagnosed, distinguishing between temporary occlusion, target moving out of the field of view, or system error. If it is temporary occlusion, path adjustment is paused and the current zoom parameters are maintained. At the same time, a prediction algorithm is used to estimate the target reappearance position. This measure avoids energy waste and equipment wear caused by frequent camera adjustments by pausing unnecessary actions and predicting based on historical data, thus optimizing resource utilization. If the target continues to be lost, the last known position is traced back, the camera angle is adjusted, or a wide-angle scanning mode is activated to recapture the target. By expanding the detection range through coordinate tracing and full-scene scanning, the target is quickly recovered, enhancing robustness and integrity in complex environments.

[0041] In a preferred embodiment, this application can be further configured such that the motion path dynamic planning method for image capture by the single zoom wide-angle camera also includes:

[0042] Define a scenario template library, including templates for lectures, discussions, experiments, and exams, with each template associated with different priority rules and resource presets;

[0043] When a scene switching signal is triggered, the corresponding template is invoked to reset the maximum resource coverage path of the camera. During scene operation, the template parameters are dynamically optimized based on real-time feedback.

[0044] By adopting the above technical solution, a scene template library is defined, enabling the system to pre-configure optimized parameters for different teaching or monitoring scenarios. For example, in the teaching template, the teacher area has high priority and resources are preset to high frame rate; in the discussion template, weights are allocated equally; in the experiment template, the equipment area is covered with emphasis; and in the examination template, cheating detection is given prominence. This ensures that the system can quickly adapt to specific environmental requirements during initialization. When a scene switching signal is triggered, the corresponding template is called to reset the maximum resource coverage path of the camera. By detecting scene changes in real time, such as switching from teaching mode to examination mode, the priority rules and resource presets of the new template are immediately applied, allowing the camera to recalculate the coverage path with maximum resource status. This ensures optimal initial coverage without blind spots, improves the camera's response speed and the smoothness of scene transitions, and reduces the risk of shooting interruption or quality degradation caused by sudden scene changes.

[0045] In a preferred example, this application can be further configured as follows:

[0046] Secondly, the above-mentioned inventive objective of this application is achieved through the following technical solutions:

[0047] A dynamic path planning method system for image capture using a single zoom wide-angle camera, comprising:

[0048] The instruction receiving module is used to receive image acquisition instructions, which include target scene type, key area information and task priority parameters.

[0049] The path planning module is used to respond to the image acquisition command, call the preset 3D environment map, and calculate the initial movement path of the zoom wide-angle camera based on the coverage algorithm to ensure that all key areas are covered under maximum resource conditions.

[0050] The camera control module is used to control the zoom wide-angle camera to move along the initial movement path and start the wide-angle mode to scan the environment and collect video stream data in real time.

[0051] The target object recognition module is used to perform target detection and behavior analysis on real-time acquired video stream data, identify key target objects and their dynamic characteristics, and sort the regions based on preset task priority rules.

[0052] The data analysis module is used to dynamically adjust the camera's movement path, zoom parameters, and resource allocation based on the target priority ranking results, transitioning from the maximum resource state to the minimum resource state while preserving coverage of high-priority areas.

[0053] By adopting the above technical solution,

[0054] Thirdly, the above-mentioned objectives of this application are achieved through the following technical solutions:

[0055] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the above-described dynamic path planning method for image capture by a single zoom wide-angle camera.

[0056] Fourthly, the above-mentioned objectives of this application are achieved through the following technical solutions:

[0057] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described dynamic path planning method for image capture by a single zoom wide-angle camera.

[0058] In summary, this application includes at least one of the following beneficial technical effects:

[0059] 1. By receiving image acquisition commands, including target scene type, key area information, and task priority parameters, the system can adaptively configure parameters according to specific scenes, thereby improving the targeting and efficiency of shooting. After responding to the command, it calls the preset 3D environment map and calculates the initial movement path based on the coverage algorithm, extracts the coordinates of key areas and obstacle information, and optimizes the path length by combining the camera's field of view model. This not only ensures that all key areas are covered without blind spots under maximum resource conditions, but also significantly reduces movement energy consumption, providing a stable foundation for subsequent dynamic adjustments. The system controls the camera to move along the initial path and starts wide-angle mode to scan the environment, acquiring video stream data in real time. This avoids the omission problem caused by the fixed viewpoint of traditional single cameras and provides a basis for real-time analysis. The system provides high-quality input; it performs target detection and behavior analysis on video stream data to identify key target objects (such as teachers or students) and their dynamic features, and sorts regions based on priority rules. By generating region heatmaps and updating the coverage list in real time, it improves the accuracy of target tracking and scene adaptability, ensuring that high-priority behaviors (such as teacher lectures) receive priority attention. Based on the priority sorting results, it dynamically adjusts the path, zoom parameters, and resource allocation, smoothly transitioning from the maximum resource state to the minimum resource state. It prioritizes the use of optical zoom to maintain image quality and replans local paths to reduce movement distance. At the same time, it adjusts the frame rate and computing power. This closed-loop optimization mechanism not only effectively avoids occlusion and resource waste, but also significantly improves energy efficiency and image detail capture capabilities.

[0060] 2. Based on video stream data, continuous frame images are extracted, and target objects (such as teachers, students, and equipment) are detected according to the continuous frame images. Their bounding boxes and category labels are output, and key targets are identified in real time, ensuring the accuracy and efficiency of image processing. This avoids the problem of insufficient coverage caused by target omission or misidentification in traditional methods, thereby improving the comprehensiveness and reliability of scene perception. By associating targets in continuous frames through multi-target tracking algorithms, trajectory sequences are generated and future coordinates are predicted, enhancing the system's stable tracking capability for dynamic targets. This reduces the risk of loss due to rapid target movement or brief occlusion, and improves response speed and adaptive performance. Combined with preset task priority rules, the detected target objects are dynamically scored, and higher priority behaviors are given higher weights. The scores are updated through weighted summation formulas and time decay factors, realizing intelligent resource allocation. This ensures that high-value areas receive priority attention, optimizing overall shooting efficiency and economy. A regional heat map is generated based on the dynamic scoring results, and the coverage priority list of key areas is updated in real time based on the heat map. By mapping the scores to a two-dimensional grid and sorting the regions, a dynamic feedback mechanism is formed, enabling the system to quickly adjust paths and resources, improving real-time decision-making ability and robustness in complex environments.

[0061] 3. Real-time monitoring of the tracking status of key targets and triggering a loss handling protocol when a target loss event is detected to ensure the reliability of continuous monitoring of key targets. Based on historical trajectory and environmental data analysis, the cause of loss is diagnosed and the root cause of loss is distinguished as temporary occlusion, target moving out of the field of view, or system error. If it is temporary occlusion, the path adjustment is paused and the current zoom parameters are maintained. At the same time, the prediction algorithm is used to estimate the target reappearance position. This measure avoids the energy waste and equipment wear caused by frequent camera adjustments by pausing unnecessary actions and predicting based on historical data, thus optimizing resource utilization. If the target continues to be lost, the last known position is traced back, the camera angle is adjusted or the wide-angle scanning mode is started to recapture the target. The detection range is expanded by coordinate tracing and full-scene scanning to ensure that the target is quickly recovered, enhancing the robustness and integrity in complex environments.

[0062] 4. Defining a scene template library enables the system to pre-configure optimized parameters for different teaching or monitoring scenarios. For example, in the teaching template, the teacher area has high priority and resources are preset to high frame rate; in the discussion template, weights are allocated equally; in the experiment template, the equipment area is highlighted; and in the exam template, cheating detection is emphasized. This ensures that the system can quickly adapt to specific environmental requirements during initialization. When a scene switching signal is triggered, the corresponding template is called to reset the camera's maximum resource coverage path. By detecting scene changes in real time, such as switching from teaching mode to exam mode, the priority rules and resource presets of the new template are immediately applied, allowing the camera to recalculate the coverage path with maximum resource status. This ensures optimal initial coverage without blind spots, improves camera response speed and the smoothness of scene transitions, and reduces the risk of shooting interruption or quality degradation caused by sudden scene changes. Attached Figure Description

[0063] Figure 1 This is a flowchart of a dynamic path planning method for image capture by a single zoom wide-angle camera in one embodiment of this application;

[0064] Figure 2 This is a flowchart illustrating the implementation of step S20 in the dynamic planning method for moving paths in image capture using a single zoom wide-angle camera, as described in one embodiment of this application.

[0065] Figure 3 This is a flowchart illustrating the implementation of step S40 in the dynamic planning method for moving paths in image capture using a single zoom wide-angle camera, as described in one embodiment of this application.

[0066] Figure 4 This is a flowchart illustrating the implementation of step S50 in the dynamic planning method for moving paths in image capture using a single zoom wide-angle camera, as described in one embodiment of this application.

[0067] Figure 5This is another implementation flowchart of step S52 in the dynamic planning method for moving path of image capture by a single zoom wide-angle camera in one embodiment of this application;

[0068] Figure 6 This is a flowchart illustrating the implementation of the target loss handling step in the dynamic planning method for moving paths in image capture by a single zoom wide-angle camera according to an embodiment of this application.

[0069] Figure 7 This is a flowchart illustrating the implementation of the multi-scene switching steps in the dynamic planning method for moving paths in image capture by a single zoom wide-angle camera according to an embodiment of this application.

[0070] Figure 8 This is a principle block diagram of a dynamic path planning method system for image capture by a single zoom wide-angle camera in one embodiment of this application;

[0071] Figure 9 This is a schematic diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0072] The present application will be further described in detail below with reference to the accompanying drawings.

[0073] In one embodiment, such as Figure 1 As shown, this application discloses a dynamic path planning method for image capture using a single zoom wide-angle camera, specifically including the following steps:

[0074] S10: Receive image acquisition command, which includes target scene type, key area information and task priority parameters.

[0075] In this embodiment, the target scene type refers to the type of environment that the camera needs to capture, such as a classroom, conference room, or laboratory; the key area information refers to the set of coordinates of the physical areas that need to be covered in the scene; and the task priority parameter refers to the importance weight of different areas for data collection, which is used for resource allocation.

[0076] Specifically, image acquisition commands are usually triggered by users or upper-level systems. The target scene type (such as a teaching scene or an experimental scene) defines the overall environmental characteristics, and the key area information specifies the physical areas that need to be covered first (such as the coordinates of the podium and experimental platform). The task priority parameter is used to quantify the attention given to different areas. For example, the priority of the teacher area is 0.9, and the priority of the student area is 0.5. By parsing the command, pre-configured templates, such as teaching templates in the scene template library, are loaded to ensure that subsequent path planning meets the scene requirements.

[0077] S20: In response to the image acquisition command, call the preset 3D environment map, and calculate the initial movement path of the zoom wide-angle camera based on the coverage algorithm to ensure coverage of all key areas under maximum resource conditions.

[0078] In this embodiment, the 3D environment map refers to a pre-built 3D model of the scene, which includes obstacles and key area coordinates; the coverage algorithm is a path optimization algorithm designed to cover all target points with the shortest path; the maximum resource state refers to the full-function mode of the camera initialization, including wide-angle scanning and high frame rate.

[0079] Specifically, by loading a pre-built 3D environment map, which is generated using SLAM technology in the form of a point cloud or a mesh map, the coordinate sets of key areas and obstacle boundary information are extracted. Based on the coverage algorithm and combined with the camera's field of view model (120° in wide-angle mode, with a zoom range from 5mm to 100mm), the minimum coverage angle and distance constraints of each key area are calculated to ensure that the camera scans the entire scene in wide-angle mode in the initial stage, laying the foundation for subsequent dynamic adjustments.

[0080] S30: Control the zoom wide-angle camera to move along the initial moving path and start the wide-angle mode to scan the environment and collect video stream data in real time.

[0081] In this embodiment, wide-angle mode refers to the maximum field of view of the camera, used for global scanning; video stream data refers to a continuous sequence of frames acquired in real time.

[0082] Specifically, the camera control module drives the camera motor to move along the initial path, and at the same time activates the wide-angle mode (field of view set to 120°) to scan the environment to capture a panoramic video stream. The real-time video stream data is then transmitted to the processing unit. The wide-angle mode prioritizes the use of optical lens groups to achieve distortion correction, avoids image distortion, and provides high-quality input for subsequent target detection.

[0083] S40: Performs target detection and behavior analysis on real-time acquired video stream data, identifies key target objects and their dynamic characteristics, and sorts the regions based on preset task priority rules.

[0084] In this embodiment, object detection refers to identifying specific objects (such as human bodies) in a video; behavior analysis refers to tracking the movement patterns of objects; dynamic features include position, speed, and posture; and task priority rules are based on scene-based scoring criteria.

[0085] Specifically, based on video stream data, continuous frame images are extracted, and target detection algorithms are used to identify key target objects, including teachers, students, and equipment. Their bounding boxes (represented by pixel coordinates) and category labels are output. Multi-target tracking algorithms (such as Kalman filtering or SORT algorithm) are used to track the movement of target objects, predicting short-term positions, such as coordinates within the next 5 seconds, and recording behavioral characteristics, such as movement speed and posture. Combined with preset task priority rules, such as a weight of 0.8 for teacher explanations and 0.3 for student interactions, the detected target objects are dynamically scored, generating regional heatmaps. Based on these heatmaps, the coverage priority list of key areas is updated in real time, providing a basis for path adjustment.

[0086] S50: Based on the target priority ranking results, dynamically adjust the camera's movement path, zoom parameters, and resource allocation, transitioning from the maximum resource state to the minimum resource state, while preserving coverage of high-priority areas.

[0087] In this embodiment, zoom parameters include optical zoom magnification and digital zoom level; resource allocation involves frame rate and computing power allocation; minimum resource state refers to the optimized low-power mode.

[0088] Specifically, based on the target priority ranking results, the required zoom level and resolution parameters for high-priority areas are calculated. For example, for distant teacher areas, optical zoom to 50mm and resolution to 4K are required. Based on the priority changes, local paths are replanned (using RRT* or artificial potential field algorithms to generate the shortest obstacle avoidance path), reducing camera movement distance (e.g., the optimized path is shortened by 20%). Simultaneously, the camera frame rate is dynamically adjusted (from 30fps to 15fps for low-priority areas) and processing power is increased (resources are released through CPU / GPU load balancing) to optimize energy consumption.

[0089] In this embodiment, by receiving image acquisition instructions, including target scene type, key area information, and task priority parameters, the system can adaptively configure parameters according to the specific scene, thereby improving the targeting and efficiency of shooting. After responding to the instructions, a preset 3D environment map is invoked, and an initial movement path is calculated based on a coverage algorithm. Key area coordinates and obstacle information are extracted, and the path length is optimized by combining the camera's field of view model. This not only ensures that all key areas are covered without blind spots under maximum resource conditions, but also significantly reduces movement energy consumption, providing a stable foundation for subsequent dynamic adjustments. The camera is controlled to move along the initial path and start wide-angle mode to scan the environment, acquiring video stream data in real time. This avoids the omission problem caused by the fixed viewpoint of traditional single cameras, and provides... Real-time analytics provides high-quality input; target detection and behavior analysis are performed on video stream data to identify key target objects (such as teachers or students) and their dynamic characteristics. Regions are sorted based on priority rules, and the coverage list is updated in real time by generating region heatmaps, which improves the accuracy of target tracking and scene adaptability, ensuring that high-priority behaviors (such as teacher lectures) receive priority attention. The path, zoom parameters, and resource allocation are dynamically adjusted according to the priority sorting results, smoothly transitioning from the maximum resource state to the minimum resource state. Optical zoom is used first to maintain image quality, and local paths are replanned to reduce movement distance. At the same time, frame rate and computing power are adjusted. This closed-loop optimization mechanism not only effectively avoids occlusion and resource waste, but also significantly improves energy efficiency and image detail capture capabilities.

[0090] In one embodiment, such as Figure 2 As shown, in step S20, the initial movement path of the zoom wide-angle camera is calculated based on the coverage algorithm, which specifically includes:

[0091] S21: Load the pre-built 3D environment map and extract the coordinate set of key areas and obstacle boundary information.

[0092] In this embodiment, the key area coordinate set refers to the spatial coordinate array of the points to be covered; obstacle boundary information refers to the geometric outline of fixed obstacles in the scene.

[0093] Specifically, map data is loaded from a pre-built 3D environment map database, which is usually stored in CAD or point cloud format. The database calls local or cloud storage services through API interfaces and uses geometry processing libraries, such as OpenCV or PCL, to extract the coordinate sets of key areas. For example, boundary detection algorithms are used to identify the vertex coordinates of areas such as the podium and student seating areas. At the same time, semantic segmentation technology is used to obtain obstacle boundary information (such as the geometric contours of tables, chairs, and walls).

[0094] S22: Calculate the minimum coverage angle and distance constraints for each key area based on the camera's field of view model and zoom range.

[0095] In this embodiment, the field of view model refers to the optical characteristics of the camera, such as a 120° field of view in wide-angle mode; zoom range refers to the scaling capability of optical and digital zoom; and minimum coverage angle refers to the minimum angle of view that ensures the area is visible.

[0096] Specifically, the camera's hardware parameter library is accessed to obtain the field of view model (e.g., a 120° field of view in wide-angle mode) and zoom range (e.g., optical zoom magnification 1-10x). Based on these parameters, triangulation and geometric calculation tools are used to calculate the minimum coverage angle (the minimum field of view required to ensure the area is fully visible) and distance constraints (e.g., the optimal acquisition distance is 3-5 meters) for each key area (e.g., the podium area). The calculation process considers the camera's physical limitations, such as resolution attenuation at maximum zoom, and the feasibility of the constraints is verified through a simulation module.

[0097] S23: Employ a global path planning algorithm to generate an initial movement path aimed at covering all key areas, and optimize the path length to minimize movement energy consumption.

[0098] In this embodiment, the global path planning algorithm refers to a method for solving path optimization across the entire scene, such as Dijkstra's algorithm; mobile energy consumption refers to the energy consumption of the camera motor drive.

[0099] Specifically, a global path planning algorithm is employed, using the coordinates of key areas as target points to generate an initial path traversing all areas. The algorithm incorporates obstacle boundary information for collision detection to avoid path conflicts. During the path optimization phase, heuristic search (such as a genetic algorithm) is used to minimize the path length, and an energy consumption model (considering camera movement speed, acceleration, and motor power consumption) is integrated to evaluate movement energy consumption. The optimized path undergoes smoothing processing (such as B-spline curves) to reduce sharp turns. The final output is a coordinate sequence, stored in a path buffer for real-time access by the camera control module.

[0100] In one embodiment, such as Figure 3 As shown, in step S40, target detection and behavior analysis are performed on the real-time acquired video stream data, specifically including:

[0101] S41: Extract consecutive frame images based on the video stream data, detect target objects, including teachers, students and equipment, based on the consecutive frame images, and output their bounding boxes and category labels.

[0102] In this embodiment, continuous frame images refer to the time sequence frames of a video; bounding boxes refer to the rectangular bounding boxes of target objects; and category labels are object classification identifiers.

[0103] Specifically, consecutive frame images are extracted from the video stream buffer in time windows (e.g., 10 frames per second), and preprocessing tools are used for format normalization and noise reduction. Then, each frame image is analyzed to identify target objects (e.g., teachers, students, experimental equipment), and the bounding box (rectangular coordinates) and category label (e.g., "teacher" or "student") of each object are output.

[0104] S42: Track the movement of the target object, predict the short-term location of the target object based on the movement track, and record its behavioral characteristics.

[0105] In this embodiment, motion trace refers to the target's historical trajectory points; short-term position prediction refers to the position estimate for the next few seconds; behavioral characteristics include action types, such as raising a hand.

[0106] Specifically, the multi-target tracking algorithm (SORT algorithm) is used to associate target bounding boxes in consecutive frames to generate motion traces (trajectory point sequences). Linear regression is performed based on the trace data to estimate the short-term position of the target, such as the coordinates within the next 5 seconds. At the same time, behavioral characteristics, such as movement speed and attitude, are recorded and stored as time series data.

[0107] S43: Combine the preset task priority rules to dynamically score the detected target objects and assign higher weights to high-priority behaviors.

[0108] In this embodiment, dynamic scoring refers to priority scores based on real-time behavior; weight is the multiplication factor in the scoring.

[0109] Specifically, the system calls upon a task priority rule base, such as the academic affairs rule base, and assigns an initial weight to the behavior of each target object based on the scenario type, such as the teaching mode. For example, the weight of a teacher's lecturing behavior is 0.9. Based on real-time behavioral characteristics, such as raising a hand, the system calculates a score and updates the score using a weighted summation formula combined with a time decay factor. High-priority behaviors, such as a teacher moving to the podium, automatically receive a higher weight, and the score is adjusted through a threshold trigger mechanism. The scoring results are fed back to the decision-making system in real time.

[0110] S44: Generate regional heat maps based on dynamic scoring results, and update the coverage priority list of key areas in real time based on the regional heat maps.

[0111] In this embodiment, the regional heat map refers to a two-dimensional distribution map of attention in the scene; the coverage priority list is a queue of regional collection order.

[0112] Specifically, the dynamic scoring results are mapped onto a two-dimensional grid of the scene to generate a regional heat map, in which high-scoring areas are displayed as "hot spots". Based on the heat map, key areas are sorted in descending order of score to generate a coverage priority list. The list is refreshed in real time, and path planning is notified through a message queue to achieve dynamic adjustment of path planning.

[0113] In one embodiment, such as Figure 4 As shown, in step S50, the camera's movement path, zoom parameters, and resource allocation are dynamically adjusted based on the target priority ranking result. Specifically, this includes:

[0114] S51: Calculate the zoom level and resolution parameters required for high-priority areas based on the target priority ranking results.

[0115] In this embodiment, zoom level refers to the degree of scaling; resolution parameter refers to the image detail precision.

[0116] Specifically, the priority list is parsed to identify high-priority areas, and the required zoom level and resolution parameters are calculated based on the area distance and object size. The calculation process uses a camera parameter model and combines ambient light sensor data to optimize settings. For example, for small targets at a distance, a higher zoom level and higher resolution are calculated to ensure detail capture.

[0117] S52: Trigger optical zoom for capturing details in distant scenes, or digital zoom for close-ups of specific areas, with optical zoom taking priority over digital zoom to maintain image quality.

[0118] In this embodiment, optical zoom is achieved through physical adjustment of the lens; digital zoom is achieved by cropping and enlarging pixels.

[0119] Specifically, the system first monitors the target distance and size. When the distance exceeds the threshold and detail capture is required, optical zoom is triggered first. The focal length is adjusted by controlling the zoom lens motor. If the optical zoom has reached its limit and still does not meet the requirements, it automatically switches to digital zoom for pixel cropping and enhancement.

[0120] S53: Based on priority changes, replan local paths, generate the shortest obstacle avoidance path, and reduce the camera's movement distance.

[0121] In this embodiment, local path planning refers to dynamic segment optimization; obstacle avoidance shortest path takes into account real-time obstacles.

[0122] Specifically, when the priority list is updated, a local path planning algorithm, such as the RRT algorithm, is invoked. Starting from the current camera position and ending at the high-priority area, a new local path is generated. The algorithm integrates real-time obstacle data, performs obstacle avoidance checks, and optimizes the path length. After the path is smoothed, the control module executes movement commands to reduce unnecessary turns and stops, thereby minimizing movement distance and energy consumption.

[0123] S54: Dynamically adjusts camera frame rate and processing power to release resources in low-priority areas and optimize energy consumption.

[0124] Specifically, resources are dynamically allocated based on a priority list. For example, the frame rate in low-priority areas is reduced, and computing power is reallocated to high-priority tasks through resource management.

[0125] In one embodiment, such as Figure 5 As shown, in step S52, which triggers optical zoom for capturing distant details or digital zoom for close-up shots, the specific steps include:

[0126] S521: Monitors the distance and size of the target object. When the distance exceeds the threshold and detail capture is required, optical zoom is enabled first.

[0127] In this embodiment, the distance threshold is a preset value that triggers zoom.

[0128] Specifically, the system continuously monitors the distance and size of the target object, calculates the distance using a laser rangefinder or image parallax, determines the size of the target object based on the pixel area of ​​the bounding box, and prioritizes optical zoom when the distance exceeds a preset threshold and it is determined that detail capture is required, i.e., when the target behavior score is high. This includes sending control signals to the zoom motor, adjusting the focal length to the calculated value, and verifying the zoom effect through feedback loops to ensure rapid response.

[0129] S522: If the optical zoom has reached its limit and still cannot meet the detail requirements, then digital zoom is triggered to perform pixel cropping and enhancement.

[0130] In this embodiment, pixel cropping is region enlargement; enhancement refers to sharpening processing.

[0131] Specifically, when the optical zoom reaches its hardware limit (such as the maximum zoom magnification), digital zoom is automatically triggered to crop the image area by pixels (enlarging it with the target as the center), and then enhancement algorithms (such as sharpening or super-resolution networks) are applied to improve the clarity of details.

[0132] In one embodiment, such as Figure 6 As shown, the dynamic programming method for motion paths in image capture by a single zoom wide-angle camera also includes a target loss handling step:

[0133] S60: Monitors the tracking status of critical targets in real time, and triggers the loss handling protocol when a target loss event is detected.

[0134] Specifically, the visibility of key targets is monitored in real time by the tracking module. When no target is detected in consecutive frames, a loss handling protocol is triggered. The protocol includes pausing the current path adjustment, saving the last known state of the target, and initiating diagnostics.

[0135] S70: Analyzes the cause of loss based on historical trajectory and environmental data, distinguishing between temporary occlusion, target moving out of the field of view, or system error.

[0136] Specifically, historical trajectory data and environmental data are analyzed, and classification algorithms are used to distinguish the causes of loss: temporary occlusion (such as the target being temporarily occluded by an object), the target moving out of the field of view (such as the trajectory showing the target moving out of the boundary), or systematic errors (such as detection model failure).

[0137] S80: If the obstruction is temporary, pause path adjustment, maintain the current zoom parameters, and enable the prediction algorithm to estimate the target's reappearance location.

[0138] Specifically, if the loss is due to temporary occlusion, the system pauses the path adjustment module, maintains the current zoom parameters, and enables a prediction algorithm (such as a particle filter) to estimate the target's reappearance position based on historical trajectories (such as predicting the position in the next 3 seconds).

[0139] S90: If the target continues to be lost, the camera will revert to its last known location, adjust the camera angle, or activate the wide-angle scanning mode to recapture the target.

[0140] Specifically, if the target is continuously lost (e.g., for more than 10 seconds), the system will trace back to the last known location coordinates, adjust the camera view (e.g., rotate to that position) or start a wide-angle scanning mode (full-scene scanning). The re-capture process includes expanding the detection range and increasing the frame rate until the target is recovered, and the tracking status will be updated through a confirmation mechanism.

[0141] In one embodiment, such as Figure 7 As shown, the dynamic path planning method for image capture by a single zoom wide-angle camera also includes a multi-scene mode switching step:

[0142] S101: Define a scenario template library, including templates for lectures, discussions, experiments, and exams. Each template is associated with different priority rules and resource presets.

[0143] Specifically, a predefined scenario template library is provided, including teaching templates, discussion templates, experiment templates, and exam templates. The priority rule for teaching templates is that the teacher area has a high weight, the priority rule for discussion templates is that they have equal weight, the priority rule for implementation templates is that the equipment area has a high weight, and the priority rule for exam templates is that cheating detection has a high weight. Each template is associated with preset resources, such as frame rate and zoom default values, and users can customize and update them through the management interface.

[0144] S102: When the scene switching signal is triggered, the corresponding template is called to reset the maximum resource coverage path of the camera. During scene operation, the template parameters are dynamically optimized based on real-time feedback.

[0145] Specifically, when a scene switching signal is triggered, such as a scheduling system command or user input, the corresponding template is invoked, the camera is reset to its maximum resource state (e.g., full frame rate, wide-angle mode), and the coverage path is recalculated. During scene operation, real-time feedback data (e.g., changes in target behavior) is used to dynamically optimize template parameters (e.g., adjusting weights through machine learning) to ensure adaptive performance.

[0146] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0147] In one embodiment, a dynamic path planning method system for image capture using a single zoom wide-angle camera is provided. This dynamic path planning method system for image capture using a single zoom wide-angle camera corresponds one-to-one with the dynamic path planning method for image capture using a single zoom wide-angle camera described in the above embodiments. For example... Figure 8 As shown, the system for dynamic path planning in image capture using a single zoom wide-angle camera includes a command receiving module, a path planning module, a camera control module, a target object recognition module, and a data analysis module. Detailed descriptions of each functional module are as follows:

[0148] The instruction receiving module is used to receive image acquisition instructions, which include target scene type, key area information and task priority parameters.

[0149] The path planning module is used to respond to the image acquisition command, call the preset 3D environment map, and calculate the initial movement path of the zoom wide-angle camera based on the coverage algorithm to ensure that all key areas are covered under maximum resource conditions.

[0150] The camera control module is used to control the zoom wide-angle camera to move along the initial movement path and start the wide-angle mode to scan the environment and collect video stream data in real time.

[0151] The target object recognition module is used to perform target detection and behavior analysis on real-time acquired video stream data, identify key target objects and their dynamic characteristics, and sort the regions based on preset task priority rules.

[0152] The data analysis module is used to dynamically adjust the camera's movement path, zoom parameters, and resource allocation based on the target priority ranking results, transitioning from the maximum resource state to the minimum resource state while preserving coverage of high-priority areas.

[0153] Specific limitations regarding the dynamic path planning method system for image capture using a single zoom wide-angle camera can be found in the above-described limitations, and will not be repeated here. Each module in the aforementioned dynamic path planning method system for image capture using a single zoom wide-angle camera can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in an electronic device, or stored in the memory of the electronic device in software form, so that the processor can call and execute the corresponding operations of each module.

[0154] In one embodiment, an electronic device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 9 As shown, this electronic device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores data. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements a dynamic path planning method for image capture using a single zoom wide-angle camera.

[0155] In one embodiment, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps:

[0156] Receive an image acquisition instruction, which includes the target scene type, key area information, and task priority parameters;

[0157] In response to the image acquisition command, a preset 3D environment map is invoked, and the initial movement path of the zoom wide-angle camera is calculated based on the coverage algorithm to ensure coverage of all key areas under maximum resource conditions;

[0158] The zoom wide-angle camera is controlled to move along the initial movement path, and the wide-angle mode is activated to scan the environment and collect video stream data in real time.

[0159] The system performs target detection and behavior analysis on real-time acquired video stream data, identifies key target objects and their dynamic characteristics, and sorts the regions based on preset task priority rules.

[0160] Based on the target priority ranking results, the camera's movement path, zoom parameters, and resource allocation are dynamically adjusted, transitioning from the maximum resource state to the minimum resource state, while preserving coverage of high-priority areas.

[0161] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0162] Receive an image acquisition instruction, which includes the target scene type, key area information, and task priority parameters;

[0163] In response to the image acquisition command, a preset 3D environment map is invoked, and the initial movement path of the zoom wide-angle camera is calculated based on the coverage algorithm to ensure coverage of all key areas under maximum resource conditions;

[0164] The zoom wide-angle camera is controlled to move along the initial movement path, and the wide-angle mode is activated to scan the environment and collect video stream data in real time.

[0165] The system performs target detection and behavior analysis on real-time acquired video stream data, identifies key target objects and their dynamic characteristics, and sorts the regions based on preset task priority rules.

[0166] Based on the target priority ranking results, the camera's movement path, zoom parameters, and resource allocation are dynamically adjusted, transitioning from the maximum resource state to the minimum resource state, while preserving coverage of high-priority areas.

[0167] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0168] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0169] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A dynamic path planning method for image capture using a single zoom wide-angle camera, characterized in that, The dynamic path planning method for image capture by a single zoom wide-angle camera includes the following steps: Receive an image acquisition instruction, which includes the target scene type, key area information, and task priority parameters; In response to the image acquisition command, a preset 3D environment map is invoked, and the initial movement path of the zoom wide-angle camera is calculated based on the coverage algorithm to ensure coverage of all key areas under maximum resource conditions; The zoom wide-angle camera is controlled to move along the initial movement path, and the wide-angle mode is activated to scan the environment and collect video stream data in real time. The system performs target detection and behavior analysis on real-time acquired video stream data, identifies key target objects and their dynamic characteristics, and sorts the regions based on preset task priority rules. Based on the target priority ranking results, the camera's movement path, zoom parameters, and resource allocation are dynamically adjusted, transitioning from the maximum resource state to the minimum resource state, while preserving coverage of high-priority areas.

2. The method for dynamic path planning for image capture using a single zoom wide-angle camera according to claim 1, characterized in that, The calculation of the initial movement path of the zoom wide-angle camera based on the coverage algorithm specifically includes: Load a pre-built 3D environment map and extract the coordinate sets of key areas and obstacle boundary information; Based on the camera's field of view model and zoom range, calculate the minimum coverage angle and distance constraints for each key area; A global path planning algorithm is used to generate an initial movement path that aims to cover all key areas, and the path length is optimized to minimize movement energy consumption.

3. The method for dynamic path planning for image capture using a single zoom wide-angle camera according to claim 1, characterized in that, The aforementioned target detection and behavior analysis of real-time acquired video stream data specifically includes: Based on the video stream data, extract consecutive frame images, detect target objects (including teachers, students, and equipment) based on the consecutive frame images, and output their bounding boxes and category labels; Track the movement of the target object, predict its short-term location based on the movement, and record its behavioral characteristics; Based on preset task priority rules, the detected target objects are dynamically scored, and higher priority behaviors are assigned higher weights. A regional heat map is generated based on the dynamic scoring results, and the coverage priority list of key areas is updated in real time based on the regional heat map.

4. The method for dynamic path planning for image capture using a single zoom wide-angle camera according to claim 1, characterized in that, The step of dynamically adjusting the camera's movement path, zoom parameters, and resource allocation based on the target priority ranking results specifically includes: Based on the target priority ranking results, calculate the required zoom level and resolution parameters for high-priority areas; Optical zoom is triggered for capturing details in distant scenes, or digital zoom is used for close-up shots of specific areas, with optical zoom taking precedence over digital zoom to maintain image quality. Based on priority changes, local paths are replanned to generate the shortest obstacle avoidance path, reducing the camera's movement distance. Dynamically adjust camera frame rate and processing power to free up resources in low-priority areas and optimize energy consumption.

5. The method for dynamic path planning for image capture using a single zoom wide-angle camera according to claim 4, characterized in that, The triggering of optical zoom for capturing distant details, or digital zoom for close-up shots, specifically includes: Monitor the distance and size of the target object, and when the distance exceeds the threshold and detailed capture is required, prioritize optical zoom; If the optical zoom has reached its limit and still cannot meet the detail requirements, then digital zoom is triggered to crop and enhance pixels.

6. The method for dynamic path planning of image capture using a single zoom wide-angle camera according to claim 1, characterized in that, The dynamic path planning method for image capture by a single zoom wide-angle camera also includes: Real-time monitoring of the tracking status of key targets; triggering a loss handling protocol when a target loss event is detected. Based on historical trajectory and environmental data analysis, the cause of loss can be distinguished as temporary occlusion, target moving out of the field of view, or systematic error. If the obstruction is temporary, pause path adjustment, maintain the current zoom parameters, and enable the prediction algorithm to estimate the target's reappearance location; If the target continues to be lost, the camera will revert to its last known location, adjust the camera angle, or activate the wide-angle scanning mode to recapture the target.

7. The method for dynamic path planning of image capture using a single zoom wide-angle camera according to claim 1, characterized in that, The dynamic path planning method for image capture by a single zoom wide-angle camera also includes: Define a scenario template library, including templates for lectures, discussions, experiments, and exams, with each template associated with different priority rules and resource presets; When a scene switching signal is triggered, the corresponding template is invoked to reset the maximum resource coverage path of the camera. During scene operation, the template parameters are dynamically optimized based on real-time feedback.

8. A dynamic path planning method system for image capture using a single zoom wide-angle camera, characterized in that, The motion path dynamic planning method system for image capture by a single zoom wide-angle camera includes: The instruction receiving module is used to receive image acquisition instructions, which include target scene type, key area information and task priority parameters. The path planning module is used to respond to the image acquisition command, call the preset 3D environment map, and calculate the initial movement path of the zoom wide-angle camera based on the coverage algorithm to ensure that all key areas are covered under maximum resource conditions. The camera control module is used to control the zoom wide-angle camera to move along the initial movement path and start the wide-angle mode to scan the environment and collect video stream data in real time. The target object recognition module is used to perform target detection and behavior analysis on real-time acquired video stream data, identify key target objects and their dynamic characteristics, and sort the regions based on preset task priority rules. The data analysis module is used to dynamically adjust the camera's movement path, zoom parameters, and resource allocation based on the target priority ranking results, transitioning from the maximum resource state to the minimum resource state while preserving coverage of high-priority areas.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the motion path dynamic planning method for image capture by a single zoom wide-angle camera as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the dynamic planning method for image capture by a single zoom wide-angle camera as described in any one of claims 1 to 7.

Images