Self-diagnosis and adaptive adjustment control system and method for mobile capture equipment
By using closed-loop diagnosis and adjustment with multi-source data acquisition and adaptive adjustment, the problem of insufficient initiative in handling faults of capture equipment and sensor malfunctions in unattended scenarios is solved, realizing automatic fault detection and correction, and improving the safety and availability of equipment operation.
Patent Information
- Application Number
- CN202611332298.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-08-31
- Publication Date
- 2026-11-17
AI Technical Summary
In unattended scenarios, existing technologies lack proactive diagnostic mechanisms for fault handling of capture devices, making it impossible to guarantee that adjustments are in place. Furthermore, reliance on single-sensor positioning can easily lead to malfunctions of the robotic arm.
The system uses a sensing unit to collect multi-source data, and combines image quality assessment, pose deviation diagnosis, sensor cross-verification, and hardware status monitoring with a decision-making and adjustment unit to generate an adaptive adjustment strategy, forming a closed-loop diagnosis and adjustment. It also uses multi-sensor cross-verification to identify faulty sensors.
It enables automatic fault detection and correction of mobile capture devices in unattended scenarios, avoids malfunctions of the robotic arm, and improves operational safety and availability.
Smart Images

Figure CN123113347A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of unattended operation technology, specifically to a self-diagnosis and adaptive adjustment control system and method for mobile capture devices applied in unattended scenarios. Background Technology
[0002] With the rapid development of digital logistics, unmanned vehicle access management in logistics parks, factories, parking lots and other scenarios is usually achieved by setting up access control gates, capture cameras, human-computer interaction devices and other equipment to realize unmanned vehicle clearance and information collection.
[0003] For the adjustment and troubleshooting of image capture devices, existing technologies mainly include the following types of solutions:
[0004] (1) Set up an identification map or reference identification object in the identification area, control the pan-tilt head to drive the camera to make horizontal and vertical movements, and control the zoom lens to focus on the identification object, so as to solve the problem of difficult camera installation and debugging and long-term focus drift.
[0005] (2) Obtain a reference target image containing the reference license plate, calculate the current tilt angle of the reference license plate, and generate an angle adjustment command to adjust the camera to a horizontal position accordingly;
[0006] (3) Establish a cluster of zoom tracking curves under different object distances, so that the focusing motor moves along the matching curve, and monitor the image clarity in real time during the process. Adaptive climbing search focusing is adopted to solve the problem of blurry image when the pan-tilt camera is inspected.
[0007] Therefore, it can be seen that existing technologies often only adjust one degree of freedom. After adjustment, there is a lack of a closed-loop convergence mechanism for evaluation and readjustment. It is impossible to guarantee whether the adjustment is truly in place. Moreover, most of them are passive adjustments and cannot actively determine whether the equipment has malfunctioned. Equipment malfunctions can only be passively discovered by manual inspection, resulting in a delayed response. Furthermore, unattended scenarios rely heavily on multiple distance sensors for positioning. Existing solutions also lack sensor cross-verification and failure identification mechanisms. Once a sensor malfunctions, it will cause the robotic arm to move erroneously. Summary of the Invention
[0008] In view of the technical defects mentioned in the background art, the purpose of the embodiments of the present invention is to provide a self-diagnosis and adaptive adjustment control system and method for mobile capture devices, which aims to at least solve one of the technical problems in the related art to a certain extent.
[0009] To achieve the above objectives, in a first aspect, the present invention provides a self-diagnosis and adaptive adjustment control system for mobile capture devices, the system comprising:
[0010] A sensing unit is used to collect multi-source data; wherein the multi-source data is collected by a deployed mobile capture device and multiple sensors;
[0011] The diagnostic unit is used to perform fault self-diagnosis and classification on the collected multi-source data to obtain diagnostic results;
[0012] Decision adjustment unit, used for:
[0013] Based on the diagnostic results, an adjustment strategy is generated and the actuator is driven to perform adaptive adjustment.
[0014] After the actuator completes the adjustment, the mobile capture device is triggered to capture again, and the diagnostic unit performs a re-diagnosis to form a closed loop. When the re-evaluation meets the standards, the adjustment parameters and fault characteristics are associated and recorded in the deployed parameter library.
[0015] As a specific implementation of this application, the multi-source data includes current pose parameters, environmental parameters, and captured images; the diagnostic unit includes an image quality assessment module, a pose deviation diagnosis module, a sensor cross-verification module, a hardware status monitoring module, and a fault diagnosis and classification module.
[0016] The image quality assessment module is used to assess the sharpness, exposure and occlusion / dirt of the captured image, and generate and output image quality indicators.
[0017] The pose deviation diagnosis module is used to compare the current pose with the pre-calibrated reference pose, calculate the pose deviation, and determine whether it exceeds the set threshold.
[0018] The sensor cross-verification module is used to perform consistency cross-verification on the readings of multiple distance sensors to identify drifting or malfunctioning sensors.
[0019] The hardware status monitoring module is used to determine whether the hardware is abnormal based on the collected operating data.
[0020] The fault diagnosis and grading module is used to determine the fault type and fault level based on the results of the above modules; wherein, the fault type includes image quality fault, pose fault, sensor fault and hardware fault; the fault level includes self-healing level, adjustable level and alarm level.
[0021] As a specific implementation of this application, the decision adjustment unit includes an adaptive adjustment control module and an actuator; the adaptive adjustment control module generates a corresponding adjustment strategy according to the fault type and level, and outputs control commands; the actuator responds to the control commands to perform adaptive adjustment; the actuator includes a telescopic motor group for adjusting height and forward / backward horizontal distance, a gimbal for adjusting pitch and yaw angles, an electric lens for adjusting zoom / focus / exposure, and a fill light.
[0022] As a specific implementation of this application, when performing cross-validation on the sensors, the difference between each pair of readings of multiple distance sensors is calculated, and sensors whose differences exceed the consistency threshold are marked as suspected abnormal sensors; and Kalman filtering is used to fuse and estimate the readings of multiple sensors, and the filtered residual is used to identify failed or drifting sensors.
[0023] As a preferred implementation of this application, the parameter library supports cross-device sharing to enable the reuse of historical adjustment parameters across multiple devices.
[0024] In a preferred implementation of this application, the decision adjustment unit is further configured to perform pre-adjustment, specifically including:
[0025] Before the capture device enters working mode, it performs pre-adjustment by matching historical adjustment parameters from the parameter library according to the input target vehicle type.
[0026] Secondly, the present invention also provides a method for self-diagnosis and adaptive adjustment control of faults in a mobile capture device, the method comprising:
[0027] Collect multi-source data; wherein the multi-source data is collected through deployed mobile capture devices and multiple sensors;
[0028] The collected multi-source data is subjected to fault self-diagnosis and classification to obtain diagnostic results;
[0029] Based on the diagnostic results, an adjustment strategy is generated and the actuator is driven to perform adaptive adjustment.
[0030] After the actuator completes the adjustment, the mobile capture device is triggered to capture again and perform a re-diagnosis to form a closed loop. When the re-evaluation meets the standards, the adjustment parameters and fault characteristics are associated and recorded in the deployed parameter library.
[0031] As a preferred implementation of this application, the method further includes a pre-adjustment step, specifically including: before the capture device enters the working state, matching historical adjustment parameters from the parameter library according to the input target vehicle type, and performing pre-adjustment.
[0032] As a specific implementation of this application, the multi-source data includes current pose parameters, environmental parameters, and captured images.
[0033] The process of performing fault self-diagnosis and classification on the collected multi-source data specifically includes:
[0034] The system performs sharpness assessment, exposure assessment, and occlusion / dirt detection on captured images, and generates and outputs image quality indicators.
[0035] The current pose is compared with the pre-calibrated reference pose, the pose deviation is calculated, and it is determined whether it exceeds the set threshold.
[0036] Perform consistency cross-validation on readings from multiple distance sensors to identify drifting or malfunctioning sensors;
[0037] Determine if the hardware is malfunctioning based on the collected operational data;
[0038] Based on the results of the above modules, the fault type and fault level are determined; wherein, the fault type includes image quality fault, pose fault, sensor fault and hardware fault; the fault level includes self-healing level, adjustable level and alarm level.
[0039] The technical solution provided by this invention integrates fault self-diagnosis and adaptive adjustment through steps such as data acquisition, fault self-diagnosis and classification, adaptive adjustment and re-evaluation. This enables the mobile capture device to automatically detect and correct faults in unattended scenarios, overcoming the shortcomings of current passive adjustments where the effectiveness of adjustments cannot be guaranteed. Furthermore, by using multi-sensor consistency cross-verification to identify failed / drift sensors, it avoids malfunctions of the robotic arm due to single sensor errors, improving operational safety in unattended scenarios and enhancing the usability of the solution. Attached Figure Description
[0040] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings used in the description of the specific embodiments or the prior art will be briefly introduced below.
[0041] Figure 1 This is a block diagram illustrating the principle of a mobile capture device fault self-diagnosis and adaptive adjustment control system provided in an embodiment of the present invention.
[0042] Figure 2 This is a flowchart of a mobile capture device fault self-diagnosis and adaptive adjustment control method provided in an embodiment of the present invention. Detailed Implementation
[0043] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0044] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.
[0045] It should be noted that, unless otherwise stated, the technical terms used in this embodiment have the common meaning as understood in the relevant technical field.
[0046] Please refer to Figure 1 This invention provides a self-diagnosis and adaptive adjustment control system for mobile capture devices, the system comprising:
[0047] A sensing unit is used to collect multi-source data; wherein the multi-source data is collected by a deployed mobile capture device and multiple sensors;
[0048] The diagnostic unit is used to perform fault self-diagnosis and classification on the collected multi-source data to obtain diagnostic results;
[0049] Decision adjustment unit, used for:
[0050] Based on the diagnostic results, an adjustment strategy is generated and the actuator is driven to perform adaptive adjustment.
[0051] After the actuator completes the adjustment, the mobile capture device is triggered to capture again, and the diagnostic unit performs a re-diagnosis to form a closed loop. When the re-evaluation meets the standards, the adjustment parameters and fault characteristics are associated and recorded in the deployed parameter library.
[0052] In another embodiment, based on the above scheme, the system also deploys an output unit for alarm and reporting.
[0053] The mobile capture device integrates a camera and an electric lens, and is installed at the end of a robotic arm (including a first telescopic motor in the vertical direction and a second telescopic motor in the horizontal direction). It moves with the robotic arm and is used for mobile capture.
[0054] The multiple sensors include a pose sensor, a distance sensor array, and an environmental sensor, specifically:
[0055] Pose sensor: including at least one of gyroscope, accelerometer and motor encoder, used to detect the current pose (height, horizontal distance, pitch angle, yaw angle, etc.) of the mobile capture device.
[0056] Distance sensor array: includes multiple distance sensors distributed above, below, to the left and right of the road, used to detect the spatial position of the target vehicle;
[0057] Environmental sensors: including at least one of light intensity sensors and temperature and humidity sensors, used to detect ambient light intensity and temperature and humidity.
[0058] Furthermore, the multi-source data includes current pose parameters, environmental parameters, and captured images; the diagnostic unit includes an image quality assessment module, a pose deviation diagnosis module, a sensor cross-validation module, a hardware status monitoring module, and a fault diagnosis and classification module.
[0059] The image quality assessment module is used to perform sharpness assessment, exposure assessment, and occlusion / dirt detection on the captured image, and generate and output image quality indicators, such as sharpness evaluation value, exposure evaluation value, and occlusion / dirt confidence level.
[0060] The pose deviation diagnosis module is used to compare the current pose with the pre-calibrated reference pose, calculate the pose deviation, and determine whether it exceeds the set threshold.
[0061] The sensor cross-verification module is used to perform consistency cross-verification on the readings of multiple distance sensors to identify drifting or malfunctioning sensors.
[0062] The hardware status monitoring module is used to determine whether the hardware is abnormal based on the collected operating data (device heartbeat, power supply voltage, motor current, temperature, etc.).
[0063] The fault diagnosis and grading module is used to determine the fault type and fault level based on the results of the above modules; wherein, the fault type includes image quality fault, pose fault, sensor fault and hardware fault; the fault level includes self-healing level, adjustable level and alarm level.
[0064] Specifically, if the image quality, pose, sensor, and hardware are all normal, it indicates no fault and the process ends.
[0065] If there are only deviations that can be automatically corrected (such as slight pose shift, slight defocus, underexposure, and insufficient lighting), it is classified as adjustable.
[0066] If the sensor consistency is abnormal but there is redundancy that can be replaced, it is classified as self-healing level, the failed sensor is shielded and the redundant data is used;
[0067] If there is a hardware failure (motor jamming, abnormal power supply) or if the circuit still cannot converge after adjustment, it will be set to alarm level and an alarm will be triggered.
[0068] In this embodiment, the decision adjustment unit includes an adaptive adjustment control module and an actuator; the adaptive adjustment control module generates a corresponding adjustment strategy based on the fault type and level, and outputs control commands; the actuator responds to the control commands to perform adaptive adjustment; the actuator includes a telescopic motor assembly for adjusting altitude and horizontal distance, a gimbal for adjusting pitch and yaw angles, a motorized lens for adjusting zoom / focus / exposure, and a fill light.
[0069] Regulation strategies include:
[0070] If there is a height deviation, the first telescopic motor will be driven to adjust the height.
[0071] If there is a deviation in the horizontal distance between the front and rear, the second telescopic motor will be driven to adjust the horizontal distance.
[0072] If there is a pitch / yaw deviation, the gimbal will be driven to adjust the pitch / yaw angle.
[0073] If the image is not sharp enough or out of focus, the motorized lens will be driven to focus, and the zoom will be adjusted if necessary.
[0074] If the exposure is insufficient or excessive, adjust the exposure, gain, and aperture, and also adjust the brightness of the fill light accordingly.
[0075] If there is obstruction or dirt, first try changing the gimbal's angle to avoid the obstruction; if it is determined that the lens is dirty and cannot be self-cleaned, then escalate to an alarm.
[0076] In application, the output unit includes an alarm module and a communication module. The alarm module is used to issue an alarm when an alarm-level fault or over-limit occurs.
[0077] The communication module is used to upload diagnostic results, adjustment records, and snapshot data to the enterprise server / backend for remote monitoring and retrieval.
[0078] It should be noted that after the adaptive adjustment control module completes the adjustment by driving the actuator, it triggers the mobile capture device to recapture the image, and the diagnostic layer re-evaluates the image quality, forming a closed loop of diagnosis-adjustment-reassessment. If the reassessment meets the standards, the adjustment parameters and fault characteristics are associated and recorded in the parameter library for subsequent predictive pre-adjustment. If the reassessment does not meet the standards and the number of iterations does not exceed the limit, iterative adjustment is performed. If the limit is exceeded, the alarm module is triggered to issue an alarm and report to the background.
[0079] Furthermore, when evaluating the sharpness of the image, at least one of the Tenengrad gradient operator, Laplacian operator, energy gradient function, Brenner function, or SMD gray-level variance function is used to calculate the gradient energy value of the captured image as a sharpness evaluation value.
[0080] When performing exposure evaluation on the image, the brightness histogram of the captured image is statistically analyzed, and the proportion of overexposed pixels and the proportion of underexposed pixels are calculated respectively. When the proportion of overexposed pixels or the proportion of underexposed pixels exceeds a preset threshold, the exposure is determined to be abnormal.
[0081] When performing occlusion / dirt detection on the image, inter-frame difference and edge degradation detection are performed on multiple consecutive captured images; or the captured image is input into a lightweight convolutional neural network for dirt classification, thereby outputting occlusion / dirt confidence scores.
[0082] When performing cross-validation on the sensors, the difference between each pair of readings from multiple distance sensors is calculated, and sensors whose differences exceed the consistency threshold are marked as suspected abnormal sensors. Kalman filtering is then used to fuse and estimate the readings from multiple sensors, and the filtered residuals are used to identify failed or drifting sensors.
[0083] Fault classification is based on diagnostic confidence and preset thresholds: when the diagnostic confidence is higher than the first threshold and there is redundant data that can be substituted, it is judged as self-healing level; when there is a deviation that can be automatically corrected, it is judged as adjustable level; when there is a hardware fault or it still cannot converge after adjustment, it is judged as alarm level.
[0084] Furthermore, the parameter library supports cross-device sharing to enable the reuse of historical adjustment parameters across multiple devices.
[0085] In another embodiment, based on the above technical solution, the decision adjustment unit is further configured to perform pre-adjustment, specifically including:
[0086] Before the capture device enters the working state, it matches historical adjustment parameters from the parameter library according to the input target vehicle type (e.g., vehicle type, vehicle height, etc.) and performs pre-adjustment; thereby realizing predictive pre-adjustment for new tasks by accumulating fault characteristics and mapping adjustment parameters, shortening the adjustment time, and further improving customs clearance efficiency.
[0087] The above solution integrates fault self-diagnosis and adaptive adjustment through steps such as data collection, fault self-diagnosis and classification, adaptive adjustment and re-evaluation. This enables the mobile capture device to automatically detect and correct faults in unattended scenarios, overcoming the shortcomings of current passive adjustments where the effectiveness of adjustments cannot be guaranteed. Furthermore, by using multi-sensor consistency cross-verification to identify failed / drift sensors, it avoids malfunctions of the robotic arm due to single sensor errors, improving operational safety in unattended scenarios and enhancing the usability of the solution.
[0088] Reference Figure 2 Based on the same inventive concept, embodiments of the present invention also provide a method for self-diagnosis and adaptive adjustment control of mobile capture devices, the method comprising:
[0089] S101, Collect multi-source data; wherein, the multi-source data is collected by a deployed mobile capture device and multiple sensors;
[0090] S102, perform fault self-diagnosis and classification on the collected multi-source data to obtain diagnostic results;
[0091] S103, Generate an adjustment strategy based on the diagnostic results and drive the actuator to perform adaptive adjustment;
[0092] S104 After the actuator completes the adjustment, the mobile capture device is triggered to capture again and perform a re-diagnosis to form a closed loop. When the re-evaluation meets the standard, the adjustment parameters and fault characteristics are associated and recorded in the deployed parameter library.
[0093] If no fault is found during self-diagnosis, the diagnosis ends; if a fault is found, the fault type and fault level are determined as the diagnosis result.
[0094] The multi-source data includes current pose parameters, environmental parameters, and captured images.
[0095] The process of performing fault self-diagnosis and classification on the collected multi-source data specifically includes:
[0096] The system performs sharpness assessment, exposure assessment, and occlusion / dirt detection on captured images, and generates and outputs image quality indicators.
[0097] The current pose is compared with the pre-calibrated reference pose, the pose deviation is calculated, and it is determined whether it exceeds the set threshold.
[0098] Perform consistency cross-validation on readings from multiple distance sensors to identify drifting or malfunctioning sensors;
[0099] Determine if the hardware is malfunctioning based on the collected operational data;
[0100] Based on the results of the above modules, the fault type and fault level are determined; wherein, the fault type includes image quality fault, pose fault, sensor fault and hardware fault; the fault level includes self-healing level, adjustable level and alarm level.
[0101] In another embodiment, the method further includes a pre-adjustment step, specifically including: before the capture device enters the working state, matching historical adjustment parameters from the parameter library according to the input target vehicle type, and performing pre-adjustment.
[0102] It should be noted that for a more specific application description of the method embodiments, please refer to the aforementioned system embodiments section, which will not be repeated here.
[0103] The above solution integrates fault self-diagnosis and adaptive adjustment through steps such as data collection, fault self-diagnosis and classification, adaptive adjustment and re-evaluation. This enables the mobile capture device to automatically detect and correct faults in unattended scenarios, overcoming the shortcomings of current passive adjustments where the effectiveness of adjustments cannot be guaranteed. Furthermore, by using multi-sensor consistency cross-verification to identify failed / drift sensors, it avoids malfunctions of the robotic arm due to single sensor errors, improving operational safety in unattended scenarios and enhancing the usability of the solution.
[0104] In the embodiments provided in this application, it should be understood that the disclosed methods and systems can also be implemented in other ways. The system embodiments described above are merely illustrative. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the figures. For example, two consecutive blocks may actually be executed substantially in parallel, or they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified functions or actions, or using a combination of dedicated hardware and computer instructions.
[0105] Furthermore, the functional modules in the various embodiments of this invention can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part. The integrated modules can be implemented in hardware or as software functional modules. When in use, each module will only collect and store user information with the user's full authorization and in compliance with relevant laws and regulations, protecting the security and privacy of user data and strictly prohibiting unauthorized access; data processing will be conducted within the scope stipulated by law and will not exceed the purpose and scope authorized by the user; at the same time, users have the rights to access, correct, delete, restrict, and refuse processing of their personal data; and must strictly comply with applicable laws and regulations and conduct compliance reviews.
[0106] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention can have various modifications and variations. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.
[0107] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.
Claims
1. A self-diagnostic and adaptive adjustment control system for mobile capture devices, characterized in that, The system includes: A sensing unit is used to collect multi-source data; wherein the multi-source data is collected by a deployed mobile capture device and multiple sensors; The diagnostic unit is used to perform fault self-diagnosis and classification on the collected multi-source data to obtain diagnostic results; Decision adjustment unit, used for: Based on the diagnostic results, an adjustment strategy is generated and the actuator is driven to perform adaptive adjustment. After the actuator completes the adjustment, the mobile capture device is triggered to capture again, and the diagnostic unit performs a re-diagnosis to form a closed loop. When the re-evaluation meets the standards, the adjustment parameters and fault characteristics are associated and recorded in the deployed parameter library.
2. The system as described in claim 1, characterized in that, The multi-source data includes current pose parameters, environmental parameters, and captured images; the diagnostic unit includes an image quality assessment module, a pose deviation diagnosis module, a sensor cross-validation module, a hardware status monitoring module, and a fault diagnosis and classification module. The image quality assessment module is used to assess the sharpness, exposure and occlusion / dirt of the captured image, and generate and output image quality indicators. The pose deviation diagnosis module is used to compare the current pose with the pre-calibrated reference pose, calculate the pose deviation, and determine whether it exceeds the set threshold. The sensor cross-verification module is used to perform consistency cross-verification on the readings of multiple distance sensors to identify drifting or malfunctioning sensors. The hardware status monitoring module is used to determine whether the hardware is abnormal based on the collected operating data. The fault diagnosis and grading module is used to determine the fault type and fault level based on the results of the above modules; wherein, the fault type includes image quality fault, pose fault, sensor fault and hardware fault; the fault level includes self-healing level, adjustable level and alarm level.
3. The system as described in claim 2, characterized in that, The decision adjustment unit includes an adaptive adjustment control module and an actuator; the adaptive adjustment control module generates a corresponding adjustment strategy based on the fault type and level, and outputs control commands; the actuator responds to the control commands to perform adaptive adjustment; the actuator includes a telescopic motor assembly for adjusting altitude and horizontal distance, a gimbal for adjusting pitch and yaw angles, a motorized lens for adjusting zoom / focus / exposure, and a fill light.
4. The system as described in claim 2, characterized in that, When performing cross-validation on the sensors, the difference between each pair of readings from multiple distance sensors is calculated, and sensors whose differences exceed the consistency threshold are marked as suspected abnormal sensors. Kalman filtering is then used to fuse and estimate the readings from multiple sensors, and the filtered residuals are used to identify failed or drifting sensors.
5. The system as described in any one of claims 1 to 4, characterized in that, The parameter library supports cross-device sharing, enabling the reuse of historical adjustment parameters across multiple devices.
6. The system as described in claim 5, characterized in that, The decision adjustment unit is also used for pre-adjustment, specifically including: Before the capture device enters the working state, it matches historical adjustment parameters from the parameter library according to the input target vehicle type and performs pre-adjustment.
7. A method for self-diagnosis and adaptive adjustment control of faults in a mobile capture device, characterized in that, The method includes: Collect multi-source data; wherein the multi-source data is collected through deployed mobile capture devices and multiple sensors; The collected multi-source data is subjected to fault self-diagnosis and classification to obtain diagnostic results; Based on the diagnostic results, an adjustment strategy is generated and the actuator is driven to perform adaptive adjustment. After the actuator completes the adjustment, the mobile capture device is triggered to capture again and perform a re-diagnosis to form a closed loop. When the re-evaluation meets the standards, the adjustment parameters and fault characteristics are associated and recorded in the deployed parameter library.
8. The method as described in claim 7, characterized in that, The method also includes a pre-adjustment step, which specifically includes: before the capture device enters the working state, matching historical adjustment parameters from the parameter library according to the input target vehicle type and performing pre-adjustment.
9. The method as described in claim 7, characterized in that, The multi-source data includes current pose parameters, environmental parameters, and captured images. The process of performing fault self-diagnosis and classification on the collected multi-source data specifically includes: The system performs sharpness assessment, exposure assessment, and occlusion / dirt detection on captured images, and generates and outputs image quality indicators. The current pose is compared with the pre-calibrated reference pose, the pose deviation is calculated, and it is determined whether it exceeds the set threshold. Perform consistency cross-validation on readings from multiple distance sensors to identify drifting or malfunctioning sensors; Determine if the hardware is malfunctioning based on the collected operational data; Based on the results of the above modules, the fault type and fault level are determined; wherein, the fault type includes image quality fault, pose fault, sensor fault and hardware fault; the fault level includes self-healing level, adjustable level and alarm level.
