Vehicle-mounted camera embedded system and method for intelligent driving at night

Abstract

The invention relates to the technical field of automatic driving, and discloses a vehicle-mounted camera embedded system and method for night intelligent driving, and the system comprises an image collection module, a target detection module, a data verification module, a man-machine interaction module and a feedback module. And a complete closed-loop architecture with risk prediction, credibility verification, man-machine fusion decision making and emergency execution capabilities is constructed. Compared with a driving assistance system which only depends on image recognition or single judgment logic in the prior art, the system has the advantages that the target recognition precision, the system judgment stability and the takeover response timeliness are remarkably improved in the low-illumination and complex traffic environment at night; the technical defects of misjudgment, slow response or improper control at night in the traditional scheme are effectively overcome.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to an on-board camera embedded system and method for nighttime intelligent driving. Background Art

[0002] With the continuous advancement of science and technology, autonomous driving technology, a key application in the field of artificial intelligence, has been widely adopted in various modes of transportation and has become a key component of intelligent transportation systems. The core goal of autonomous driving technology is to achieve perception and understanding of the road environment through methods such as computer vision and sensor fusion, thereby replacing or assisting human driving. Ensuring driving safety, especially in complex driving environments, has become a key research focus.

[0003] Despite significant progress in automotive camera technology in recent years, its performance at night or in low-light environments still has certain limitations. Many current automotive cameras rely primarily on traditional visible light imaging technology, which results in images captured by the cameras in dark or dim environments often being noisy and having poor contrast, making it impossible to clearly identify pedestrians, obstacles, or other potential hazards on the road. During night driving, although some systems use infrared cameras and lidar to enhance night vision, their processing technologies and algorithms have not yet fully solved problems such as blurred images and low target recognition accuracy in low-light environments. In addition, data fusion and real-time decision-making between different sensors still face technical challenges such as data latency and information asymmetry, which affect the system's response speed and accuracy.

[0004] Therefore, we propose an embedded system and method for vehicle-mounted camera for nighttime intelligent driving to solve the above problems. Summary of the Invention

[0005] The purpose of the present invention is to provide an embedded system and method for an on-board camera for nighttime intelligent driving, so as to solve the problem that before the above-mentioned background technology was proposed, many on-board cameras mainly relied on traditional visible light imaging technology, which resulted in the images captured by the camera in dark or dim environments often having high noise and poor contrast, and being unable to clearly identify pedestrians, obstacles or other potential dangers on the road.

[0006] To achieve the above-mentioned object, the present invention provides the following technical solution: an embedded system for a vehicle-mounted camera for nighttime intelligent driving, characterized in that it includes an image acquisition module, a target detection module, a data verification module, a human-computer interaction module, and a feedback module; The image acquisition module is used to collect and pre-process data of the surrounding environment and vehicle conditions, and organize them into a first data group and a second data group; The target detection module is used to calculate the first data group and the second data group to generate a target monitoring reference coefficient MBJ, and analyze the target monitoring reference coefficient MBJ; The data verification module is used to calculate the first data group, the second data group and the target monitoring reference coefficient to generate a data verification coefficient MBY, and analyze the data verification coefficient MBY; The human-computer interaction module is used to calculate the target monitoring reference coefficient MBJ and the data verification coefficient MBY to generate the human-computer interaction coefficient JHX, and analyze the human-computer interaction coefficient JHX; The feedback module is used to execute takeover and alarm instructions.

[0007] Preferably, the image acquisition module includes a data acquisition unit and a data preprocessing unit; The data acquisition unit is used to collect data on the surrounding environment and vehicle conditions, including ambient light intensity, camera exposure, driving speed, obstacle distance, obstacle relative position angle, lane deviation, camera clarity, and road curvature; The data preprocessing unit is used to preprocess and dimensionlessly transform the collected parameters, and reorganize them into a first data group and a second data group; The first data set includes ambient light intensity A, obstacle distance B, obstacle relative position angle C, lane deviation D, and road curvature E; The second data set includes camera exposure F, camera definition G, and driving speed H.

[0008] Preferably, the target detection module includes a target coefficient generation unit and a target coefficient analysis unit; The target coefficient generation unit is used to couple the first data group and the second data group by integrating the ambient light intensity A, obstacle distance B, obstacle relative position angle C, lane deviation D, road curvature E, camera exposure F, camera clarity G, and driving speed H, wherein the ambient light intensity A is calculated independently, the obstacle distance B and the driving speed H are coupled through an exponential function, the obstacle relative position angle C, lane deviation D and road curvature E are coupled, and the exposure F and clarity G are coupled, and the multiple groups of calculations are integrated to ultimately generate the target monitoring reference coefficient MBJ; The specific calculation formula is as follows: ; Where: A is the ambient light intensity, B is the distance to the obstacle, C is the relative position angle of the obstacle, D is the lane deviation, E is the road curvature, F is the camera exposure, G is the camera definition, and H is the driving speed; The target coefficient analysis unit is used to analyze the target monitoring reference coefficient MBJ, so as to generate a first analysis result. According to the first analysis result, it is judged whether there are suspicious obstacles in the area.

[0009] Preferably, the first analysis result is specifically as follows: When MBJ < Y, it means that there are no potential obstacles in the current visible area; When MBJ = Y, it means that there are potential obstacles in the current visible area and secondary analysis and calibration are required; When MBJ > Y, it means that there are visible obstacles in the current visible area and early warning is required.

[0010] Preferably, the data verification module includes a verification coefficient generation unit and a verification coefficient analysis unit; The verification coefficient generation unit is used to couple the first data group, the second data group and the target monitoring reference coefficient MBJ. By coupling the light intensity A, the image clarity G, and the exposure F among the three, and then coupling the obstacle distance B, the relative position angle C of the obstacle, the lane deviation D, the road curvature E, and the camera exposure F, and then integrating and calculating the two sets of coupled data to finally generate the data verification coefficient MBY; The specific calculation formula is as follows: ; In the formula: A is the environmental light intensity, B is the obstacle distance, C is the relative position angle of the obstacle, D is the lane deviation, E is the road curvature, F is the camera exposure, G is the camera clarity, H is the driving speed, and MBJ is the target monitoring reference coefficient MBJ; The verification coefficient analysis unit is used to analyze the data verification coefficient MBY, generate a second analysis result, and judge the rationality of the existence of suspicious objects according to the second analysis result.

[0011] Preferably, the second analysis result is specifically as follows: When MBJ < R, it means that the current data is not in the credible interval and no marking is performed; When MBJ = R, it means that the current data is in the low credible interval, marking is performed and re-analysis is prepared; When MBJ > R, it means that the current data is in the high credible interval and alarm is prepared.

[0012] Preferably, the human-computer interaction module includes a takeover coefficient generation unit and a takeover coefficient analysis unit; The takeover coefficient generation unit is used to couple the target monitoring reference coefficient MBJ and the data verification coefficient MBY, and finally generate the human-computer interaction coefficient JHX; The specific calculation formula is as follows: JHX=a1×MBJ+a2×MBY+a3×(MBJ+MBY); Where: MBJ is the target monitoring reference coefficient, MBY is the data verification coefficient, a1, a2, and a3 are weight values, and the values of a1, a2, and a3 are adjusted by the user; The takeover coefficient analysis unit is used to perform data analysis to generate a third analysis result, and determine whether an alarm and emergency takeover are required based on the third analysis result.

[0013] Preferably, the third analysis result is as follows: When JHX < 0.4, it means that the current operation is stable, the risk is reduced, and the system does not intervene or alarm; When 0.4≤JHX<0.8, it means the current operation risk is increasing and there is a level 1 risk. The system will give a voice prompt alarm and take over after 10 seconds. When JHX ≥ 0.8, it means that the current operation risk is extremely high and there is a second-level risk. The system will immediately take over and send a message to the emergency contact.

[0014] This application also includes an embedded method for a vehicle-mounted camera for nighttime intelligent driving, the specific steps of which are as follows: S1. Collecting and preprocessing data on the surrounding environment and vehicle conditions through an image acquisition module, and arranging the data into a first data group and a second data group; S2. Calculating the first data group and the second data group by a target detection module to generate a target monitoring reference coefficient MBJ, and analyzing the target monitoring reference coefficient MBJ; S3. Calculating the first data group, the second data group, and the target monitoring reference coefficient by a data verification module to generate a data verification coefficient MBY, and analyzing the data verification coefficient MBY; S4. Calculate the target monitoring reference coefficient MBJ and the data verification coefficient MBY through the human-computer interaction module to generate a human-computer interaction coefficient JHX, and analyze the human-computer interaction coefficient JHX; S5. Execute takeover and alarm instructions through the feedback module.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention provides an embedded vehicle camera system for nighttime intelligent driving. Through the organic linkage of multiple modules, it establishes a complete closed-loop architecture capable of risk prediction, credibility verification, human-machine fusion decision-making, and emergency response. Compared to existing driver assistance systems that rely solely on image recognition or single judgment logic, this system significantly improves target recognition accuracy, system judgment stability, and timely response in low-light and complex traffic conditions at night. This effectively overcomes the technical shortcomings of traditional solutions, which are prone to misjudgment, slow response, or improper control at night.

[0016] 2. This system divides the response range into four levels based on the JHX value, corresponding to the progressive response logic from "no intervention required" to "delayed takeover" and "immediate takeover". This can not only avoid unnecessary system over-intervention, but also quickly ensure driving safety in high-risk situations, and improve the system's scenario adaptability and human-machine coordination. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a system flow chart of the present invention.

[0018] Figure 2 A diagram showing the steps of the method of the present invention.

[0019] In the figure: 1. Image acquisition module; 11. Data acquisition unit; 12. Data preprocessing unit; 2. Target detection module; 21. Target coefficient generation unit; 22. Target coefficient analysis unit; 3. Data verification module; 31. Verification coefficient generation unit; 32. Verification coefficient analysis unit; 4. Human-computer interaction module; 41. Takeover coefficient generation unit; 42. Takeover coefficient analysis unit; 5. Feedback module. DETAILED DESCRIPTION

[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0021] Example 1: Please refer to Figure 1 , a vehicle-mounted camera embedded system for nighttime intelligent driving, comprising an image acquisition module 1, a target detection module 2, a data verification module 3, a human-computer interaction module 4, and a feedback module 5; The image acquisition module 1 is used to collect and pre-process data of the surrounding environment and vehicle conditions, and organize them into a first data group and a second data group; The target detection module 2 is used to calculate the first data group and the second data group to generate a target monitoring reference coefficient MBJ, and analyze the target monitoring reference coefficient MBJ; The data verification module 3 is used to calculate the first data group, the second data group and the target monitoring reference coefficient to generate a data verification coefficient MBY, and analyze the data verification coefficient MBY; The human-computer interaction module 4 is used to calculate the target monitoring reference coefficient MBJ and the data verification coefficient MBY, thereby generating a human-computer interaction coefficient JHX, and analyzing the human-computer interaction coefficient JHX; The feedback module 5 is used to execute takeover and alarm instructions.

[0022] In this embodiment, image acquisition module 1 is used to capture images and data of the vehicle's surroundings and its own operating status, and preprocesses the raw data to improve the efficiency of subsequent identification and analysis. Specifically, this module collects information such as ambient light intensity, obstacle distance, obstacle relative angle, lane deviation, and road curvature, organizing it into a first data set. It also collects information such as camera exposure, clarity, and vehicle speed, organizing it into a second data set. Through grouped and structured processing, image acquisition module 1 effectively improves data manageability and processing speed, enhances image quality and data integrity under complex nighttime lighting conditions, and provides high-quality input for analysis and processing in subsequent modules.

[0023] Target Detection Module 2 is used to perform a fusion analysis of the first and second data sets to identify potential surrounding targets and assess their impact on driving safety. Based on a preset multi-parameter weighted model, this module comprehensively considers key parameters such as obstacle distance, angle, light intensity, and image quality to calculate and generate a target monitoring reference coefficient (MBJ). MBJ is then evaluated and analyzed to preliminarily determine the target's threat level and plausibility. By introducing multi-dimensional fusion judgment logic, Target Detection Module 2 effectively improves the accuracy of nighttime target recognition, particularly maintaining stable detection capabilities in low-light or image-degraded scenarios, thereby enhancing the system's perception robustness in nighttime environments.

[0024] Data Verification Module 3 performs cross-validation analysis on the first and second data sets and the target monitoring reference coefficient MBJ to generate a data verification coefficient MBY, which is then further analyzed. This module establishes a judgment model based on data consistency, completeness, and rationality to identify any deviations, redundancies, or distortions in the camera data, thereby determining the credibility of the target detection results. By introducing a verification mechanism, Data Verification Module 3 effectively filters out misjudgments caused by nighttime image blur, sensor anomalies, or short-term occlusions, improving the reliability of the system's overall judgment and providing solid data support for subsequent decision-making.

[0025] Human-computer interaction module 4 couples the target monitoring reference coefficient MBJ with the data verification coefficient MBY to generate the human-computer interaction coefficient JHX, which is then comprehensively analyzed. JHX measures the balance between the risk level of the current driving environment and the confidence level of the system's judgment. Human-computer interaction module 4 uses a multi-level response strategy to perform a zoned evaluation of JHX to determine whether the driver needs to be prompted to take over, or to issue a warning signal when necessary. By introducing a sensitivity adjustment mechanism and a coupling threshold model, this module enables the system to make reasonable judgments about takeover timing in dynamic nighttime environments, thereby optimizing human-computer collaboration efficiency and avoiding issues such as false triggering and delayed response.

[0026] Feedback Module 5 is used to execute appropriate warning or takeover operations based on the analysis results of the human-machine interaction coefficient JHX. Based on the preset response level, this module issues voice, visual, or tactile alerts to alert the driver to risks, or automatically executes emergency takeover instructions if the driver fails to respond in a timely manner. Feedback Module 5 also supports graded intervention strategies, such as providing early warnings when risks are high but not critical, and directly switching to system takeover mode in critical situations, including vehicle deceleration, braking, or lane maintenance. This module implements a closed-loop mechanism from risk analysis to control execution, enhancing the nighttime autonomous driving system's response capabilities and safety and reliability in emergency situations.

[0027] The present invention provides an embedded system for nighttime intelligent driving using an onboard camera. Through the organic linkage of multiple modules, it constructs a complete closed-loop architecture capable of risk prediction, credibility verification, human-machine fusion decision-making, and emergency response. Compared to existing driver assistance systems that rely solely on image recognition or single judgment logic, this system significantly improves target recognition accuracy, system judgment stability, and timely response in low-light and complex traffic conditions at night. This effectively overcomes the technical shortcomings of traditional solutions, which are prone to misjudgment, slow response, or improper control at night.

[0028] Example 2: Please refer to Figure 1 , the image acquisition module 1 includes a data acquisition unit 11 and a data preprocessing unit 12; The data acquisition unit 11 is used to collect data about the surrounding environment and vehicle conditions, including ambient light intensity, camera exposure, driving speed, obstacle distance, obstacle relative position angle, lane deviation, camera clarity, and road curvature; The data preprocessing unit 12 is used to preprocess and dimensionlessly transform the collected parameters, and reorganize them into a first data group and a second data group; The first data set includes ambient light intensity A, obstacle distance B, obstacle relative position angle C, lane deviation D, and road curvature E; The second data set includes camera exposure F, camera definition G, and driving speed H.

[0029] In this embodiment: the parameters collected by the data acquisition unit 11 not only cover the external environment information, but also integrate the camera's own working status parameters and vehicle operation status information, realizing dual perception of the driving environment and the perception device status, and effectively supplementing the misjudgment problem caused by the lack of equipment self-test information in the traditional system.

[0030] The data preprocessing unit 12 preprocesses the multi-source heterogeneous data, including operations such as denoising, normalization, and dimensionless transformation. It then divides the data into a first data group and a second data group based on their characteristics, enabling subsequent algorithms to perform differentiated processing based on environmental risk factors and image quality / driving status factors, respectively. This structure not only improves data clarity but also provides logically clear and well-defined data input for subsequent target detection and verification analysis modules, avoiding data redundancy and information coupling confusion.

[0031] Example 3: Please refer to Figure 1 , the target detection module 2 includes a target coefficient generation unit 21 and a target coefficient analysis unit 22; The target coefficient generation unit 21 is used to couple the first data group and the second data group by integrating the ambient light intensity A, obstacle distance B, obstacle relative position angle C, lane deviation D, road curvature E, camera exposure F, camera clarity G, and driving speed H. The ambient light intensity A is calculated independently, the obstacle distance B and driving speed H are coupled through an exponential function, the obstacle relative position angle C, lane deviation D and road curvature E are coupled, and the exposure F and clarity G are coupled. The multiple groups of calculations are integrated to ultimately generate the target monitoring reference coefficient MBJ; The specific calculation formula is as follows: ; Where: A is the ambient light intensity, B is the distance to the obstacle, C is the relative position angle of the obstacle, D is the lane deviation, E is the road curvature, F is the camera exposure, G is the camera definition, and H is the driving speed; The target coefficient analysis unit 22 is used to analyze the target monitoring reference coefficient MBJ to generate a first analysis result, and determine whether there is a suspicious obstacle in the area based on the first analysis result.

[0032] In this embodiment: The target detection module 2 includes a target coefficient generation unit 21 and a target coefficient analysis unit 22, which are used to accurately identify potential obstacles and evaluate their risk levels in complex night environments, thereby enhancing the environmental perception ability and response accuracy of the intelligent driving system in low-light scenarios.

[0033] The target coefficient generation unit 21 receives the first data set and the second data set output by the image acquisition module 1, and constructs a target monitoring reference coefficient MBJ based on the multi-dimensional parameter coupling mechanism. Specifically, the unit integrates and processes eight key parameters such as the environmental light intensity A, the obstacle distance B, the relative position angle C of the obstacle, the lane deviation D, the road curvature E, the camera exposure F, the camera clarity G, and the vehicle driving speed H. Among them, the environmental light intensity A is processed as an independent factor to reflect the impact of changes in external lighting at night on the overall monitoring accuracy; the obstacle distance B and the driving speed H are coupled and calculated through an exponential function to reflect the non-linear change of the approaching speed of the obstacle at different vehicle speeds on the driving risk; the relative position angle C of the obstacle, the lane deviation D, and the road curvature E are multiplied and coupled to reflect the potential risk level under the combined influence of the vehicle path deviation trend and the road curve change; the exposure F and the clarity G jointly evaluate the imaging quality of the camera to quantify the system's perception accuracy of the image content.

[0034] Through the coupling formula, the target coefficient generation unit 21 realizes the fusion modeling of multiple environmental variables and device parameters, and the generated target monitoring reference coefficient MBJ can comprehensively reflect the potential obstacle risk level in the current monitoring area.

[0035] The target coefficient analysis unit 22 is used to analyze and process the generated MBJ, compare it with the set risk threshold or historical data trend, generate a first analysis result, and accordingly judge whether there are suspicious obstacles or abnormal conditions in the current monitoring area. This analysis process can effectively assist the system in realizing efficient and accurate obstacle recognition and warning determination under complex conditions such as insufficient night lighting, image degradation, or vehicle deviation from the track.

[0036] Embodiment Four: Please refer to Figure 1 , the first analysis result is specifically as follows: When MBJ < Y, it means that there are no potential obstacles in the current visible area; When MBJ = Y, it means that there are potential obstacles in the current visible area and secondary analysis and calibration are required; When MBJ > Y, it means that there are visible obstacles in the current visible area and warnings are required.

[0037] In this embodiment: By introducing an intermediate judgment state, the system can perform secondary analysis and calibration on image information with potential uncertainty, avoiding misidentification or missed identification due to image noise or environmental interference, thereby improving the system's perception of faint, low-contrast obstacles.

[0038] Compared with the traditional binary judgment method, this solution provides a three-level judgment mechanism, allowing the system to adopt a tiered response strategy based on different risk levels, including continued observation, secondary analysis, or immediate warning, thus more closely matching the complex and changing visual environment in real driving scenarios.

[0039] By conducting in-depth analysis triggered on demand in the presence of potential obstacles, the system can effectively avoid high-intensity processing of all image data, saving computing resources and improving the overall operating efficiency and energy consumption performance of the system. It is especially suitable for embedded intelligent driving terminals or resource-constrained edge devices.

[0040] The MBJ coefficient, an indicator that integrates image features and risk parameters, can more sensitively reflect image quality and abnormal changes in low-light environments. Combined with a multi-level threshold judgment mechanism, it enables early identification of nighttime obstacles and a reasonable, graded response, significantly enhancing nighttime driving safety.

[0041] Example 5: Please refer to Figure 1 , the data verification module 3 includes a verification coefficient generation unit 31 and a verification coefficient analysis unit 32; The verification coefficient generation unit 31 is used to couple the first data set, the second data set, and the target monitoring reference coefficient MBJ by coupling the light intensity A, image clarity G, and exposure F. It then couples the obstacle distance B, obstacle relative position angle C, lane deviation D, road curvature E, and camera exposure F. The two sets of coupled data are then integrated and calculated to ultimately generate the data verification coefficient MBY. The specific calculation formula is as follows: ; Where: A is the ambient light intensity, B is the obstacle distance, C is the obstacle relative position angle, D is the lane deviation, E is the road curvature, F is the camera exposure, G is the camera definition, H is the driving speed, and MBJ is the target monitoring reference coefficient MBJ; The verification coefficient analysis unit 32 is used to analyze the data verification coefficient MBY, generate a second analysis result, and judge the rationality of the existence of the suspicious object based on the second analysis result.

[0042] In this embodiment: By coupling the light intensity A, image clarity G, and camera exposure F, the effectiveness of the current image quality under actual optical conditions can be dynamically reflected, avoiding misjudgment caused by overexposure, underexposure, or image blurring, thereby improving the judgment stability of the system under complex lighting conditions.

[0043] Jointly modeling the obstacle distance B, relative angle C, lane departure D, road curvature E, driving speed H, etc. with MBJ to generate the verification coefficient MBY can more comprehensively reflect the actual threat level of obstacles under the current driving state, significantly improve the context understanding ability of obstacle recognition, and reduce the false alarm rate and missed alarm rate.

[0044] Calculating the verification coefficient MBY through a formula-based modeling method to achieve the mathematical integration of environmental parameters and motion states, enabling the system to have the ability to dynamically adjust the recognition weight and providing more reliable basic data support for subsequent early warning decisions.

[0045] The verification coefficient analysis unit 32 generates a second analysis and judgment based on the analysis result of MBY as a means of verifying and correcting the initial judgment result of MBJ, which helps to filter out the boundary fuzzy areas or low-confidence targets in the initial judgment, thereby further improving the recognition credibility and risk discrimination ability of the system for suspicious obstacles.

[0046] The above technical solutions can be applied to autonomous driving systems in urban roads, highway scenarios, night driving, and complex weather conditions, which helps to build a perception and judgment framework with strong environmental perception, intelligent decision-making, and safety redundancy capabilities.

[0047] Embodiment Six: Please refer to Figure 1 , and the specific second analysis results are as follows: When MBJ < R, it means that the current data is not within the credible interval and is not marked; When MBJ = R, it means that the current data is within the low credible interval, is marked and ready for re-analysis; When MBJ > R, it means that the current data is within the high credible interval and is ready for alarm.

[0048] In this embodiment: By setting the "low credible interval", "high credible interval", and "uncredible interval", the system can perform sub-division processing on the data quality of the analysis results, avoiding directly using abnormally fluctuating or boundary fuzzy data for decision-making, thereby reducing the false alarm and false trigger rates.

[0049] When MBJ falls within the low credible interval, the system not only marks the data but also prepares to enter the re-analysis process, indicating that the system has a self-verification and information compensation mechanism, which is beneficial to delaying decision-making to obtain more context support when the information is incomplete or of poor quality.

[0050] When MBJ>R, that is, the data is in a high-confidence range, the system can directly trigger the alarm preparation process to achieve a rapid response to high-confidence obstacles or risk conditions, effectively shorten the delay from identification to response, and improve the real-time and security of the system.

[0051] The second analysis result is based on the MBJ after the first analysis and data verification, realizing unified closed-loop processing at the data level and the perception level, ensuring that the alarm or intervention process is entered only after sufficient verification, thereby improving the judgment logic integrity and safety robustness of the entire system.

[0052] This mechanism supports dynamic adjustment of processing paths based on data credibility, effectively preventing situations such as "over-alertness" or "slow response", and providing autonomous driving or assisted driving systems with risk identification and response solutions that are more human-like in terms of cognitive logic.

[0053] Example 7: Please refer to Figure 1 , the human-computer interaction module 4 includes a takeover coefficient generation unit 41 and a takeover coefficient analysis unit 42; The takeover coefficient generation unit 41 is used to couple the target monitoring reference coefficient MBJ and the data verification coefficient MBY to finally generate the human-computer interaction coefficient JHX; The specific calculation formula is as follows: JHX=a1×MBJ+a2×MBY+a3×(MBJ+MBY); Where: MBJ is the target monitoring reference coefficient, MBY is the data verification coefficient, a1, a2, and a3 are weight values, and the values of a1, a2, and a3 are adjusted by the user; The takeover coefficient analysis unit 42 is used to perform data analysis, generate a third analysis result, and determine whether an alarm and emergency takeover are required based on the third analysis result.

[0054] The third analysis results are as follows: When JHX < 0.4, it means that the current operation is stable, the risk is reduced, and the system does not intervene or alarm; When 0.4≤JHX<0.8, it means the current operation risk is increasing and there is a level 1 risk. The system will give a voice prompt alarm and take over after 10 seconds. When JHX ≥ 0.8, it means that the current operation risk is extremely high and there is a second-level risk. The system will immediately take over and send a message to the emergency contact.

[0055] In this embodiment: by weighted coupling of the target monitoring reference coefficient MBJ and the data verification coefficient MBY, a unified human-computer interaction coefficient JHX is formed, which can comprehensively reflect multi-dimensional factors such as environmental risk, image quality, obstacle characteristics and data credibility, effectively quantify the risk level of the current driving status, and provide an efficient and accurate judgment basis for takeover decisions.

[0056] A weight parameter is introduced into the formula for generating the takeover coefficient, allowing users to flexibly adjust it according to actual driving needs or system scenarios, enhancing the controllability and scenario migration capabilities of the algorithm model, and facilitating adaptive optimization under different vehicle models, driving styles or operating preferences.

[0057] This system divides the response range into three levels based on the JHX value, corresponding to the progressive response logic from "no intervention required" to "delayed takeover" and "immediate takeover". This can not only avoid unnecessary system over-intervention, but also quickly ensure driving safety in high-risk situations, and improve the system's scenario adaptability and human-machine coordination.

[0058] When the system identifies a level 2 risk, it will alert the driver to the risk through voice and complete takeover preparations within the set delay; when a level 3 risk is identified, the system will immediately initiate automatic takeover and proactively send an alarm message to the preset emergency contact, helping to build a complete closed-loop safety mechanism of pre-warning, in-process intervention and post-notification.

[0059] Due to the limited perception capabilities in nighttime environments, risk response requirements are higher. The present invention uses a fine-grained hierarchical judgment mechanism of the takeover coefficient to achieve rapid identification and response to sudden obstacles, image distortion and system abnormalities at night, significantly improving the stability and safety of the nighttime intelligent driving system.

[0060] This application also includes an embedded method for a vehicle-mounted camera for nighttime intelligent driving, the specific steps of which are as follows: Step 1: The image acquisition module 1 collects and pre-processes data on the surrounding environment and vehicle conditions, and organizes the data into a first data set and a second data set; Step 2: Calculate the first data set and the second data set by the target detection module 2 to generate a target monitoring reference coefficient MBJ, and analyze the target monitoring reference coefficient MBJ; Step 3: Calculate the first data group, the second data group, and the target monitoring reference coefficient through the data verification module 3 to generate a data verification coefficient MBY, and analyze the data verification coefficient MBY; Step 4: Calculate the target monitoring reference coefficient MBJ and the data verification coefficient MBY through the human-computer interaction module 4 to generate the human-computer interaction coefficient JHX, and analyze the human-computer interaction coefficient JHX; Step 5: Execute takeover and alarm instructions through the feedback module 5.

[0061] The contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0062] Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A vehicle-mounted camera embedded system for nighttime intelligent driving, characterized by: It includes an image acquisition module (1), a target detection module (2), a data verification module (3), a human-computer interaction module (4) and a feedback module (5); The image acquisition module (1) is used to collect and pre-process data on the surrounding environment and vehicle conditions, and organize them into a first data group and a second data group; The target detection module (2) is used to calculate the first data group and the second data group to generate a target monitoring reference coefficient MBJ, and analyze the target monitoring reference coefficient MBJ; The data verification module (3) is used to calculate the first data group, the second data group and the target monitoring reference coefficient, thereby generating a data verification coefficient MBY, and analyzing the data verification coefficient MBY; The human-computer interaction module (4) is used to calculate the target monitoring reference coefficient MBJ and the data verification coefficient MBY, thereby generating a human-computer interaction coefficient JHX, and analyzing the human-computer interaction coefficient JHX; The feedback module (5) is used to execute takeover and alarm instructions.

2. The vehicle-mounted camera embedded system for nighttime intelligent driving according to claim 1, characterized in that: The image acquisition module (1) includes a data acquisition unit (11) and a data preprocessing unit (12); The data acquisition unit (11) is used to collect data on the surrounding environment and vehicle conditions, including ambient light intensity, camera exposure, driving speed, obstacle distance, obstacle relative position angle, lane deviation, camera clarity, and road curvature; The data preprocessing unit (12) is used to preprocess and dimensionlessly transform the collected parameters, and reorganize them into a first data group and a second data group; The first data set includes ambient light intensity A, obstacle distance B, obstacle relative position angle C, lane deviation D, and road curvature E; The second data set includes camera exposure F, camera definition G, and driving speed H.

3. The vehicle-mounted camera embedded system for nighttime intelligent driving according to claim 2, characterized in that: The target detection module (2) includes a target coefficient generation unit (21) and a target coefficient analysis unit (22); The target coefficient generating unit (21) is used to couple the first data group and the second data group by integrating the ambient light intensity A, the obstacle distance B, the obstacle relative position angle C, the lane deviation D, the road curvature E, the camera exposure F, the camera clarity G and the driving speed H, wherein the ambient light intensity A is calculated independently, the obstacle distance B and the driving speed H are coupled through an exponential function, the obstacle relative position angle C, the lane deviation D and the road curvature E are coupled, the exposure F and the clarity G are coupled, and the multiple groups of calculations are integrated to finally generate the target monitoring reference coefficient MBJ; The specific calculation formula is as follows: ； Where: A is the ambient light intensity, B is the distance to the obstacle, C is the relative position angle of the obstacle, D is the lane deviation, E is the road curvature, F is the camera exposure, G is the camera definition, and H is the driving speed; The target coefficient analysis unit (22) is used to analyze the target monitoring reference coefficient MBJ, thereby generating a first analysis result, and judging whether there is a suspicious obstacle in the area based on the first analysis result.

4. The vehicle-mounted camera embedded system for nighttime intelligent driving according to claim 3, characterized in that: The first analysis results are as follows: When MBJ < Y, it means that there are no potential obstacles in the current visible area; When MBJ = Y, it means that there are potential obstacles in the current visible area and secondary analysis and calibration are required; When MBJ > Y, it means that there are visible obstacles in the current visible area and warnings need to be issued.

5. The vehicle-mounted camera embedded system for nighttime intelligent driving according to claim 4, characterized in that: The data verification module (3) includes a verification coefficient generation unit (31) and a verification coefficient analysis unit (32); The verification coefficient generation unit (31) is used to couple the first data group, the second data group, and the target monitoring reference coefficient MBJ. By coupling the light intensity A, the image clarity G, and the exposure F, and then coupling the obstacle distance B, the relative position angle C of the obstacle, the lane deviation D, the road curvature E, and the camera exposure F, and then integrating and calculating the two groups of coupled data to finally generate the data verification coefficient MBY; The specific calculation formula is as follows: ； In the formula: A is the ambient light intensity, B is the obstacle distance, C is the relative position angle of the obstacle, D is the lane deviation, E is the road curvature, F is the camera exposure, G is the camera clarity, H is the driving speed, and MBJ is the target monitoring reference coefficient MBJ; The verification coefficient analysis unit (32) is used to analyze the data verification coefficient MBY, generate a second analysis result, and judge the rationality of the existence of suspicious objects according to the second analysis result.

6. The vehicle-mounted camera embedded system for nighttime intelligent driving according to claim 5, characterized in that: The specific second analysis result is as follows: When MBJ < R, it means that the current data is not within the credible interval and no marking is performed; When MBJ = R, it means that the current data is in the low credible interval, marking is performed and re-analysis is prepared; When MBJ > R, it means that the current data is in the high credible interval and alarm preparation is performed.

7. The vehicle-mounted camera embedded system for nighttime intelligent driving according to claim 6, characterized in that: The human-computer interaction module (4) includes a takeover coefficient generation unit (41) and a takeover coefficient analysis unit (42); The takeover coefficient generation unit (41) is used to couple the target monitoring reference coefficient MBJ and the data verification coefficient MBY, and finally generate the human-computer interaction coefficient JHX; The specific calculation formula is as follows: JHX = a1 × MBJ + a2 × MBY + a3 × (MBJ + MBY); In the formula: MBJ is the target monitoring reference coefficient, MBY is the data verification coefficient, a1, a2, and a3 are weight values, and the values of a1, a2, and a3 are adjusted and set by the user; The takeover coefficient analysis unit (42) is used to perform data analysis, generate a third analysis result, and judge whether alarm and emergency takeover are required according to the third analysis result.

8. The vehicle-mounted camera embedded system for nighttime intelligent driving according to claim 7, characterized in that: The specific third analysis result is as follows: When JHX < 0.4, it means that the current operation is stable, the risk is reduced, and the system does not intervene or alarm; When 0.4 ≤ JHX < 0.8, it means that the current operation risk is increased, there is a first-level risk, the system issues a voice prompt alarm, and takes over after 10 seconds; When JHX ≥ 0.8, it means that the current operation risk is extremely high, there is a second-level risk, the system immediately executes takeover and sends information to the emergency contact.

9. A vehicle-mounted camera embedded method for nighttime intelligent driving, characterized by: The specific steps are as follows: S1, collecting and preprocessing data on the surrounding environment and vehicle conditions through the image acquisition module (1), and arranging them into a first data group and a second data group; S2, calculating the first data group and the second data group by the target detection module (2), thereby generating a target monitoring reference coefficient MBJ, and analyzing the target monitoring reference coefficient MBJ; S3, calculating the first data group, the second data group and the target monitoring reference coefficient by the data verification module (3), thereby generating a data verification coefficient MBY, and analyzing the data verification coefficient MBY; S4, calculating the target monitoring reference coefficient MBJ and the data verification coefficient MBY through the human-computer interaction module (4), thereby generating the human-computer interaction coefficient JHX, and analyzing the human-computer interaction coefficient JHX; S5. Execute takeover and alarm instructions through the feedback module (5).

Images