Intelligent collision detection method and system

Abstract

The invention relates to the technical field of radar detection, in particular to an intelligent collision detection method and system, and the method comprises the following steps: setting an initial emission angle of a radar, monitoring a reflection signal during the movement of an object, recording the return time, calculating a reflection distance according to the light velocity and the time, adjusting the emission angle, optimizing the coverage range, and obtaining angle correction data. According to the method, the position of the object can be more accurately determined by recording the return time of the reflection signal in real time and calculating the reflection distance by using the light velocity and the time difference, and potential collision risks can be more accurately predicted and identified by iteratively optimizing the scanning path, enhancing the adaptability to the dynamic environment and updating the target trajectory information. Intelligent judgment of risk levels and adjustment of emergency response measures are carried out, the response efficiency and accuracy of an early warning system are improved, the function of a collision detection system is enhanced, traffic safety is remarkably improved, and potential accident risks are reduced.

Description

Technical Field

[0001] The present invention relates to the field of radar detection technology, and in particular to an intelligent collision detection method and system. Background Art

[0002] The field of radar detection technology covers the use of radar systems to detect and analyze objects in the environment. It has been developed from the military field and is widely used in civil fields such as aviation, maritime and traffic safety. Radar systems can determine the position, speed and characteristics of objects by emitting electromagnetic waves and receiving reflected waves. In modern applications, radar detection technology has evolved to achieve high-precision distance measurement and speed perception. It is an indispensable part of intelligent systems such as autonomous vehicles and collision warning systems. Radar technology is particularly suitable for external monitoring and warning systems due to its ability to work reliably in all weather conditions.

[0003] Among them, an intelligent collision detection method refers to the use of a radar system to continuously monitor obstacles in front of or around the vehicle, analyze potential collision risks in real time, and automatically take preventive measures such as adjusting the vehicle speed or issuing warnings to avoid or mitigate collisions. Its purpose is to enhance vehicle safety, reduce traffic accidents, and improve the protection level of drivers and passengers, especially at high speeds or in complex traffic environments.

[0004] Although existing radar detection technology has been widely used in military and civilian fields, it has problems with insufficient response speed and accuracy when processing real-time data in highly dynamic and complex environments. Existing technologies cannot effectively adapt to emergencies in rapidly changing traffic environments, especially in multi-target tracking and dynamic path prediction, resulting in delayed response or false alarms in the early warning system. Existing systems lack sufficient flexibility in radar coverage and signal optimization, and cannot adjust emission angles or scanning parameters according to real-time conditions. Technical limitations are particularly evident at high speeds or in severe weather conditions, resulting in reduced system performance and affecting overall safety assurance capabilities. The lack of a highly adaptive collision prevention mechanism is the main shortcoming of existing technologies in improving driving safety. In actual applications, it results in insufficient or inaccurate responses to potential dangers, and is unable to effectively prevent accidents. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an intelligent collision detection method and system.

[0006] In order to achieve the above object, the present invention adopts the following technical solution, an intelligent collision detection method, comprising the following steps: S1: Set the initial transmission angle of the radar, monitor the reflected signal of the moving object and record the return time, calculate the reflection distance according to the speed of light and time, adjust the transmission angle to optimize the coverage range, and obtain the angle correction data; S2: using the angle correction data, converting the radar signal into coordinate data, synchronously updating the radar scanning parameters to match the real-time position change of the object, iteratively optimizing the scanning path, and generating scanning coverage data; S3: Based on the scanning coverage data, analyze the speed vector and direction vector of the object, analyze the position change of the object in combination with the time series, update the target trajectory information in real time, and obtain the movement trajectory of the object; S4: identifying the deviation between the object's motion trajectory and a preset trajectory, classifying and predicting potential collision targets, detecting the probability of collision through difference analysis, and obtaining collision prediction data; S5: using the collision prediction data, analyzing the potential risk of intelligent collision, determining the collision risk level of the detected object through a threshold, and outputting a risk quantification analysis result; S6: Based on the risk quantification analysis results, automatic warning is carried out and emergency measures are designed, including the intensity and response time of the alarm signal, matching the processing requirements of differentiated risk levels, and obtaining warning emergency configuration.

[0007] As a further solution of the present invention, the angle correction data includes peak coverage angles, valley coverage angles and associated angle adjustment values, the scanning coverage data includes a set of coordinate points of the scanning area, the correlation between the coordinate points and the scanning time, and the spatial distribution density of the coordinate points, the target trajectory information includes the position, velocity vector and direction vector of the object in differentiated time, the collision prediction data includes a collision probability score, a category of potential collision objects, a motion trend and a prediction time window, the risk quantification analysis results include probability values ​​associated with risk levels, risk assessment criteria and risk probability calculation results, and the early warning emergency configuration includes the intensity of the alarm signal, the response time and a differentiated emergency measures list.

[0008] As a further solution of the present invention, the steps of setting the initial transmission angle of the radar, monitoring the reflected signal of the moving object and recording the return time, calculating the reflection distance according to the speed of light and time, adjusting the transmission angle to optimize the coverage range, and obtaining the angle correction data are specifically as follows: S101: Set the initial transmission angle of the radar, start the radar monitoring and capture the reflected signal of the object, and record the return time of the reflected signal, use the speed of light and the time difference to calculate the reflected distance, and generate the initialization distance data; S102: Based on the initialized distance data, adjusting the transmission angle of the radar, testing the signal coverage under the differentiated configuration by adjusting the angle, re-recording the adjusted reflection signal and return time, and obtaining the adjusted distance data; S103: using the adjusted distance data, iteratively optimizing the radar's emission angle, checking the radar's coverage, cyclically recording and calculating the reflection distance, and obtaining angle correction data.

[0009] As a further solution of the present invention, the angle correction data is used to convert the radar signal into coordinate data, the radar scanning parameters are synchronously updated to match the real-time position change of the object, the scanning path is iteratively optimized, and the steps of generating the scanning coverage data are specifically as follows: S201: using the angle correction data, converting the signal received by the radar into coordinate data, calculating the position of the object by analyzing the angle and distance of each reflected signal, and generating position coordinate data; S202: Using the position coordinate data, synchronously updating the scanning parameters of the radar to match the real-time position change of the object, including adjusting the scanning frequency and angle, and acquiring real-time scanning data; S203: Based on the real-time scanning data, iteratively optimize the scanning path of the radar, and optimize the area covered by the path and the scanning efficiency by adjusting the starting point and the end point of the scanning to obtain scanning coverage data.

[0010] As a further solution of the present invention, based on the scanning coverage data, analyzing the speed vector and direction vector of the object, combining the time series to analyze the position change of the object, updating the target trajectory information in real time, and obtaining the object motion trajectory are specifically as follows: S301: Analyze each coordinate point data of the object based on the scan coverage data, calculate the speed vector and direction vector of each scan of the object, calculate the speed through the position and time difference between two consecutive points, and generate initialization data of speed and direction; S302: using the initialization data of speed and direction, combined with a time series analysis method, tracking and analyzing the position change of the object, updating the real-time motion state of the object by comparing the position data of consecutive time points, and obtaining dynamic trajectory update data; S303: Use the dynamic trajectory to update data, track and analyze the motion trajectory of the object, capture the motion trend and position change in real time, detect the collision probability of the object in motion, check the continuity and consistency of tracking, and obtain the motion trajectory of the object.

[0011] As a further solution of the present invention, the steps of identifying the deviation between the object's motion trajectory and the preset trajectory, classifying and predicting potential collision targets, detecting the probability of collision through difference analysis, and obtaining collision prediction data are specifically as follows: S401: comparing the object motion trajectory data with a preset trajectory, using a Euclidean distance algorithm to measure distance difference and angle difference, performing intelligent collision detection on the object, and generating trajectory deviation data; S402: Using the trajectory deviation data, classify the objects as potential collision targets, predict the collision risk according to the deviation value and direction, set a collision risk threshold, classify the objects according to the risk level, and obtain collision risk classification data; S403: Based on the collision risk classification data, the collision probability of multiple types of targets is iteratively detected through difference analysis, and the time and location of the collision are calculated to obtain collision prediction data.

[0012] As a further solution of the present invention, the formula of the Euclidean distance algorithm is as follows: in, is the adjusted deviation Euclidean distance, is the dimension, The actual trajectory point is dimensional coordinates, are the coordinates of the preset trajectory points, is the error correction factor for each dimension, is the weight coefficient of the dimension, is the environmental impact factor, is the adjustment factor.

[0013] As a further solution of the present invention, the steps of using the collision prediction data to analyze the potential risk of intelligent collision, determining the collision risk level of the detected object by a threshold value, and outputting the risk quantification analysis result are specifically as follows: S501: using the collision prediction data, analyzing the collision risks of multiple types of objects, including the evaluation of speed, direction and closing rate, and generating initialization risk analysis data by evaluating the risk weights of differentiated data points; S502: using the initialized risk analysis data, determining through a set risk level threshold, classifying the collision risk level of the object, identifying the risk classification, and obtaining the graded risk data; S503: Based on the graded risk data, quantify the value of the collision risk level of the object, analyze the probability value associated with the risk level, and obtain the risk quantification analysis result by real-time monitoring the movement of the object.

[0014] As a further solution of the present invention, based on the risk quantification analysis results, automatic warning is performed, emergency measures are designed, including the intensity and response time of the alarm signal, and the processing requirements of the differentiated risk levels are matched. The steps of obtaining the warning emergency configuration are specifically as follows: S601: using the risk quantification analysis result, starting automatic warning, adjusting the intensity of the alarm signal according to the differentiated risk level, including the signal frequency and sound intensity, verifying that the alertness of the alarm matches the risk level, and generating alarm configuration data; S602: Use the alarm configuration data to design response time parameters, check that the time span from alarm activation to response is synchronized with the risk level, respond to risk events first, and obtain response time setting data; S603: Based on the response time setting data, combined with the alarm signal strength and response time of the object collision, emergency measures for differentiated risk levels are formulated, including evacuation guidelines and safety measures guidance, to obtain early warning emergency configuration.

[0015] An intelligent collision detection system, the intelligent collision detection system is used to execute the above-mentioned intelligent collision detection method, the system comprises: The angle adjustment module adjusts the transmission angle based on the radar initialization settings, captures the reflected signal, and records the return time. It uses the speed of light and the time difference to calculate the reflection distance, adjusts the transmission angle to optimize the radar coverage, and generates angle correction data. The data conversion module converts the radar signal into coordinate data according to the angle correction data, updates the radar scanning parameters to match the real-time position of the object, iteratively optimizes the scanning path, and generates scanning coverage data; The trajectory analysis module calculates the velocity vector and direction vector of the object through the scanning coverage data, identifies the position change of the object in combination with the time series, updates the trajectory of the target, and obtains the motion trajectory of the object; The deviation calculation module uses the object motion trajectory to compare the object trajectory with the preset trajectory, calculates the deviation of the distance and angle difference, and performs object classification and collision probability prediction to generate collision prediction data; The emergency response module analyzes the risk of intelligent collision based on the collision prediction data, and uses the risk threshold to analyze the collision risk level of the object, adjusts the intensity and response time of the alarm signal according to the risk level, and obtains the early warning emergency configuration.

[0016] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, the radar's emission angle is set and adjusted to optimize the coverage range, thereby improving the accuracy and reaction speed of radar detection. By recording the return time of the reflected signal in real time and calculating the reflection distance using the speed of light and the time difference, the position of the object can be determined more accurately. By iteratively optimizing the scanning path, the adaptability to dynamic environments is enhanced. In combination with the updated target trajectory information of time series analysis, potential collision risks can be predicted and identified more accurately, which is particularly critical in dynamic traffic environments. Through differential analysis technology, intelligent judgment of risk levels and adjustment of emergency response measures are performed. Measures can be automatically adjusted according to real-time data to improve the response efficiency and accuracy of the early warning system. The overall processing logic not only enhances the function of the collision detection system, but also significantly improves traffic safety and reduces potential accident risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of the workflow of the present invention; Figure 2 This is a detailed flow chart of S1 of the present invention; Figure 3 This is a detailed flow chart of S2 of the present invention; Figure 4 This is a detailed flow chart of S3 of the present invention; Figure 5 This is a detailed flow chart of S4 of the present invention; Figure 6 This is a detailed flow chart of S5 of the present invention; Figure 7 This is a detailed flow chart of S6 of the present invention; Figure 8 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0019] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0020] See also Figure 1 The present invention provides a technical solution, an intelligent collision detection method, comprising the following steps: S1: Set the initial transmission angle of the radar, monitor the reflected signal of the moving object and record the return time, calculate the reflection distance according to the speed of light and time, adjust the transmission angle to optimize the coverage range, and obtain the angle correction data; S2: Use angle correction data to convert radar signals into coordinate data, synchronously update radar scanning parameters to match the real-time position changes of objects, iteratively optimize the scanning path, and generate scanning coverage data; S3: Based on the scanning coverage data, analyze the speed vector and direction vector of the object, analyze the position change of the object in combination with the time series, update the target trajectory information in real time, check the continuity and consistency of tracking, and obtain the movement trajectory of the object; S4: Identify the deviation between the object's motion trajectory and the preset trajectory, classify and predict potential collision targets, detect the probability of collision through difference analysis, set the collision risk threshold, and classify objects according to risk level to obtain collision prediction data; S5: Use collision prediction data to analyze the potential risks of intelligent collisions, determine the collision risk level of the detected object through thresholds, monitor the movement of objects in real time, identify risk classifications, and output risk quantification analysis results; S6: Based on the results of risk quantification analysis, automatic warning is carried out and emergency measures are designed, including the intensity and response time of the alarm signal, matching the processing requirements of differentiated risk levels, and obtaining warning emergency configuration.

[0021] The angle correction data includes the peak coverage angle, the valley coverage angle and the associated angle adjustment values. The scanning coverage data includes the coordinate point set of the scanning area, the correlation between the coordinate points and the scanning time, and the spatial distribution density of the coordinate points. The target trajectory information includes the position, velocity vector and direction vector of the object in differentiated time. The collision prediction data includes the collision probability score, the category of potential collision objects, the motion trend and the prediction time window. The risk quantification analysis results include the probability value associated with the risk level, the risk assessment criteria and the risk probability calculation results. The early warning emergency configuration includes the intensity of the alarm signal, the response time and the differentiated emergency measures list.

[0022] See also Figure 2 , set the initial transmission angle of the radar, monitor the reflected signal of the moving object and record the return time, calculate the reflection distance according to the speed of light and time, adjust the transmission angle to optimize the coverage range, and obtain the angle correction data in the following steps: S101: Set the initial transmission angle of the radar, start the radar monitoring and capture the reflected signal of the object, and record the return time of the reflected signal, use the speed of light and the time difference to calculate the reflected distance, and generate the execution process of the initialization distance data as follows; Set the initial launch angle of the radar and start the radar system to monitor and capture the reflected signal of the object. By accurately recording the time point when the reflected signal returns and using the speed of light constant, the difference between the return time and the launch time is used to calculate the reflection distance of the signal, providing direct evidence of the initial efficiency and accuracy of the radar monitoring system, which is crucial for subsequent adjustments and optimizations. The initialization distance data is generated using the formula: in, Indicates the reflection distance of the object, is the speed of light, is the round trip time of the reflected signal.

[0023] S102: Based on the initialized distance data, the transmission angle of the radar is adjusted, the signal coverage under the differentiated configuration is tested by adjusting the angle, and the adjusted reflection signal and return time are re-recorded to obtain the adjusted distance data. The execution process is as follows; Based on the initialization distance data, the radar transmission angle adjustment test is carried out. By changing the radar transmission angle, the signal coverage under different configurations is tested, and the adjusted reflection signal and return time are re-recorded. The adjustment aims to explore the optimal radar configuration to achieve the widest coverage and the most accurate reflection data capture. After each adjustment, the system will generate new distance data, which is used to evaluate the effectiveness of the angle adjustment and obtain the adjusted distance data. The formula used is: in, Indicates the adjusted reflection distance, is the speed of light, is the adjusted return time of the reflected signal.

[0024] S103: Using the adjusted distance data, iteratively optimizing the radar's transmission angle, checking the radar's coverage, cyclically recording and calculating the reflection distance, and obtaining the angle correction data, the execution process is as follows; Using the adjusted distance data, the radar's emission angle is iteratively optimized. During the process, the system continuously detects and records changes in the radar coverage and cyclically calculates the reflection distance. The radar configuration can be fine-tuned to ensure that the radar can achieve the best performance standards under different operating conditions and environmental settings, and the angle correction data is obtained. The formula used is: in, Represents the optimized reflection distance, is the speed of light, is the optimized reflected signal return time.

[0025] See also Figure 3 , using angle correction data, converting radar signals into coordinate data, synchronously updating radar scanning parameters to match the real-time position changes of objects, iteratively optimizing the scanning path, and generating scanning coverage data in the following steps: S201: Using the angle correction data, convert the signal received by the radar into coordinate data, and calculate the position of the object by analyzing the angle and distance of each reflected signal. The execution process of generating the position coordinate data is as follows; Using angle correction data, the signal received by the radar is converted into coordinate data. The radar system resolves the angle and distance data of each reflected signal into specific position coordinates. By accurately calculating the angle deviation and distance change of the signal, the system can determine the exact position of the object in space, which is crucial for subsequent monitoring and tracking. The position coordinate data is generated using the formula: and in, and Represents the position coordinates of the object in the plane coordinate system, is the distance from the radar to the object, is the angle of the object relative to the radar.

[0026] S202: Using the position coordinate data, synchronously updating the scanning parameters of the radar to match the real-time position change of the object, including adjusting the scanning frequency and angle, the execution process of obtaining the real-time scanning data is as follows; Use the position coordinate data to synchronously update the radar's scanning parameters, including adjusting the radar's scanning frequency and angle according to the real-time position changes of the object. Through dynamic adjustment, the radar can track the target object more accurately and ensure the continuity and accuracy of signal coverage. Each update of the scanning parameters is based on the latest position data to ensure the timeliness and effectiveness of the radar system response and obtain real-time scanning data. The formula used is: and in, is the updated scanning frequency, is the time interval between consecutive scans, is the adjusted scanning angle, is the scanning angle before adjustment, is the angle adjustment value.

[0027] S203: Based on the real-time scanning data, the scanning path of the radar is iteratively optimized, and the area covered by the path and the scanning efficiency are optimized by adjusting the starting point and the end point of the scanning. The execution process of obtaining the scanning coverage data is as follows; Based on real-time scanning data, the radar scanning path is iteratively optimized. By adjusting the starting and ending points of the scan, the system can optimize the coverage area and the overall efficiency of the scan. This ensures that the radar system can monitor a large area more efficiently, while reducing blind spots and repeated scanning areas, improving the overall efficiency and accuracy of the scan, and obtaining the scan coverage data. The formula used is: in, Indicates the coverage area of ​​the scan. and are the starting angle and ending angle of the scanning path, is at an angle The scanning distance below.

[0028] See also Figure 4 , based on the scan coverage data, analyze the speed vector and direction vector of the object, combine the time series to analyze the position change of the object, update the target trajectory information in real time, and obtain the object's motion trajectory in the following steps: S301: Based on the scan coverage data, analyze each coordinate point data of the object, calculate the speed vector and direction vector of each scan of the object, calculate the speed through the position and time difference between two consecutive points, and generate the execution flow of the initialization data of speed and direction as follows; Based on the scan coverage data, the data of each object coordinate point is extracted, and the speed vector and direction vector of the object in each scan are calculated. By analyzing the position difference and time difference between two consecutive coordinate points, the system can accurately calculate the speed of the object. The calculation not only provides the speed of the object's movement, but also reveals the direction of movement, providing basic data for further dynamic tracking, ensuring the accuracy of the data and the real-time monitoring, and generating the initialization data of speed and direction. The formula used is: in, represents the velocity vector, is the position vector difference between two consecutive points, It's the time difference.

[0029] S302: Using the initialization data of speed and direction, combined with the time series analysis method, tracking and analyzing the position change of the object, updating the real-time motion state of the object by comparing the position data of consecutive time points, and obtaining the dynamic trajectory update data. The execution process is as follows; Using the initialization data of speed and direction, the time series analysis method is used to continue tracking and analyzing the position changes of the object. The core is to use continuous position data points to update and verify the real-time motion state of the object. By comparing the position of the object at different time points, the system can update the object's motion trajectory and state in real time, ensure the real-time and accuracy of the monitoring data, and obtain dynamic trajectory update data. The formula used is: in, is the new position vector, is the position vector at the previous time point, is the velocity vector, It's the time difference.

[0030] S303: Use dynamic trajectory to update data, track and analyze the motion trajectory of the object, capture the motion trend and position change in real time, detect the collision probability of the object in motion, check the coherence and consistency of tracking, and obtain the execution process of the object's motion trajectory as follows; Using dynamic trajectory update data, tracking and analyzing the movement trajectory of objects, the system continuously captures the movement trend and position changes of objects, and records the path of each movement in real time. Through continuous monitoring, the system can detect collisions that occur during the movement of objects, and verify the coherence and consistency of tracking data. It is crucial to ensure the accuracy of the monitoring system and prevent potential safety issues. The object's movement trajectory is obtained using the formula: in, is the collision probability, and are the velocity vectors of the two moving objects, is the minimum distance between two moving objects.

[0031] See also Figure 5 , identify the deviation between the object's motion trajectory and the preset trajectory, classify and predict potential collision targets, detect the probability of collision through difference analysis, and obtain the collision prediction data in the following steps: S401: Compare the object motion trajectory data with the preset trajectory, use the Euclidean distance algorithm to measure the distance difference and angle difference, perform object intelligent collision detection, and generate trajectory deviation data. The execution process is as follows; The object's motion trajectory data is compared with the preset trajectory. The Euclidean distance algorithm is used to measure the distance and angle difference between the actual trajectory and the preset trajectory. This is to achieve intelligent collision detection and ensure that the monitoring system can detect potential collision risks in a timely manner and respond. It can accurately capture trajectory deviations, which is crucial for further risk assessment and prevention and control, and generate trajectory deviation data.

[0032] The formula for the Euclidean distance algorithm is as follows: in, is the adjusted deviation Euclidean distance, is the dimension, The actual trajectory point is dimensional coordinates, are the coordinates of the preset trajectory points, is the error correction factor for each dimension, is the weight coefficient of the dimension, is the environmental impact factor, is the adjustment factor.

[0033] The execution flow is as follows: Set the weight of each dimension , reflects the contribution of each dimension to the total deviation, and calculates the coordinate difference of each dimension , plus the error correction factor , factors are obtained through experimental data to adjust the systematic error, accumulate the square of the adjusted difference, and multiply by their respective weights, and add the environmental impact factor , factors are obtained through real-time environmental monitoring equipment, such as meteorological sensor data, and adjusted by coefficients Determine the degree of impact on the total distance, determined experimentally to ensure the applicability and accuracy of the calculation results.

[0034] S402: Using the trajectory deviation data, classify the objects as potential collision targets, predict the collision risk according to the deviation value and direction, set the collision risk threshold, and classify the objects according to the risk level. The execution process of obtaining the collision risk classification data is as follows; Using trajectory deviation data, objects are classified as potential collision targets. By analyzing the deviation value and direction, the system can predict the collision risk between objects and set the corresponding collision risk threshold. According to the threshold, objects are divided into different risk levels for more detailed monitoring and preventive measures. To ensure that the monitoring system can adjust the response strategy according to the actual risk, improve safety, and obtain collision risk classification data, the formula used is: in, Indicates the collision risk level, is the speed of the object, is the angular difference between the object's moving direction and the preset collision direction. is the distance between objects.

[0035] S403: Based on the collision risk classification data, the collision probability of multiple types of targets is iteratively detected through difference analysis, and the time and location of the collision are calculated to obtain the collision prediction data. The execution process is as follows; Based on the collision risk classification data, the collision probability of multiple types of targets is iteratively detected through the difference analysis method. In addition, the system also calculates the time and place of potential collision, which is crucial for formulating countermeasures and safety warning systems. This process not only increases the prediction ability of the monitoring system, but also improves the efficiency and effectiveness of responding to emergencies, and obtains collision prediction data, using the formula: in, is the estimated time of collision, is the speed of the object, is the angular difference between the object's direction of motion and the direction of collision, is the distance between the predicted collision point and the current position.

[0036] See also Figure 6 , using collision prediction data, analyzing the potential risk of intelligent collision, determining the collision risk level of the detected object through the threshold, and outputting the risk quantitative analysis results are as follows: S501: Using collision prediction data, analyzing the collision risk of multiple types of objects, including the evaluation of speed, direction and closing rate, and generating the initialization risk analysis data by evaluating the risk weights of differentiated data points. The execution process is as follows; Using collision prediction data, the collision risk of various objects is analyzed, including a comprehensive assessment of speed, direction and closing rate. Each data point is assigned a weight based on the risk potential, which is calculated based on the predicted collision probability and the motion parameters of the object. Determining the potential risk level of each object is the basis for further risk management and mitigation measures, and generating initial risk analysis data using the formula: in, represents the collision risk weight, represents the speed of the object, Represents the distance between objects. Represents the angle between the object's moving direction and the collision direction.

[0037] S502: Using the initialized risk analysis data, determining through the set risk level threshold, classifying the collision risk level of the object, identifying the risk classification, and obtaining the graded risk data, the execution process is as follows; Using the initial risk analysis data, the system classifies the collision risk level of objects through the set risk level threshold. The classification process involves the evaluation of the risk weight of each object, and the risk level is divided into low, medium and high levels according to the preset threshold. High-risk objects can be clearly identified to provide decision support for further safety measures. The goal is to ensure that all risks are appropriately labeled and classified to optimize the allocation of resources and emergency response. To obtain graded risk data, the formula used is: in, Indicates the risk level, represents the risk weight of a single object, Represents the total number of objects evaluated.

[0038] S503: Based on the graded risk data, quantify the value of the collision risk level of the object, analyze the probability value associated with the risk level, and obtain the risk quantification analysis result by real-time monitoring the movement of the object. The execution process is as follows; Based on the hierarchical risk data, the risk level is numerically quantified. By associating the probability value of each risk level, the real-time movement of the object is monitored to update the risk assessment in real time. Through accurate risk quantification analysis, the movement trend and risk change of each object are monitored to ensure timely response to potential collision threats and obtain the risk quantification analysis results. The formula used is: in, represents the quantitative risk value, is the risk level, is the probability value associated with the risk level, is the risk level number of the classification.

[0039] See also Figure 7 Based on the results of risk quantification analysis, automatic warning is carried out and emergency measures are designed, including the intensity and response time of the alarm signal, matching the processing requirements of differentiated risk levels, and obtaining the specific steps of early warning emergency configuration: S601: Using the risk quantification analysis results, start the automatic warning, adjust the intensity of the alarm signal according to the differentiated risk level, including the signal frequency and sound intensity, verify that the alertness of the alarm matches the risk level, and generate the execution process of the alarm configuration data as follows; Using the results of risk quantification analysis, the automatic early warning system is activated. The alarm signal strength and frequency of the early warning system are adjusted according to the differentiated risk level to ensure that the alertness of the alarm matches the risk level. By dynamically adjusting the alarm parameters, more intense and frequent alarms are ensured in cases of higher risk. This not only includes the setting of the alarm itself, but also involves ensuring the synchronization and coordination of all systems for further safety operations and early warnings, and generating alarm configuration data. The formula used is: in, Represents the alarm configuration value, Indicates the alarm frequency, is the risk level, is the sound intensity.

[0040] S602: Use the alarm configuration data to design response time parameters, check that the time span from alarm activation to response is synchronized with the risk level, and respond to risk events first. The execution process of obtaining response time setting data is as follows; Using the alarm configuration data, design response time parameters. The parameters are used to ensure that the time span from alarm activation to response is synchronized with the risk level, and high-risk events are responded to first. Through the precise design and adjustment of the response time settings, potential threats can be responded to quickly and effectively, improving overall security. It is not only required to be able to achieve precise time control in technology, but also to be able to respond quickly in actual operations to meet the needs of different risk levels. To obtain the response time setting data, the formula used is: in, Indicates the response time, is the risk level, Indicates the delay factor for alarm activation.

[0041] S603: Based on the response time setting data, combined with the alarm signal strength and response time of the object collision, emergency measures for differentiated risk levels are formulated, including evacuation guidelines and safety measures guidance, and the execution process of the early warning emergency configuration is obtained as follows; Based on the response time setting data, combined with the alarm signal strength and response time of object collision, emergency measures for differentiated risk levels are formulated, including detailed evacuation guidelines and safety measures guidance, aiming to provide appropriate response strategies for different risk levels. By analyzing the response time and the effectiveness of the alarm signal in real time, the system can adjust and optimize the emergency response plan to ensure that the safety of people and property can be protected to the maximum extent when a collision risk occurs, and obtain the early warning emergency configuration, using the formula: in, Indicates the early warning efficiency, is the effectiveness of emergency measures, is the response time, is the signal strength.

[0042] See also Figure 8 , an intelligent collision detection system, the intelligent collision detection system is used to execute the above intelligent collision detection method, the system comprises: The angle adjustment module adjusts the transmission angle based on the radar initialization settings, captures the reflected signal, and records the return time. It uses the speed of light and the time difference to calculate the reflection distance, adjusts the transmission angle to optimize the radar coverage, and generates angle correction data. The data conversion module converts the radar signal into coordinate data based on the angle correction data, updates the radar scanning parameters to match the real-time position of the object, iteratively optimizes the scanning path, and generates scanning coverage data; The trajectory analysis module calculates the velocity vector and direction vector of the object by scanning the coverage data, identifies the position change of the object in combination with the time series, updates the trajectory of the target, and obtains the motion trajectory of the object; The deviation calculation module uses the object's motion trajectory to compare the object's trajectory with the preset trajectory, calculates the deviation of the distance and angle difference, and performs object classification and collision probability prediction to generate collision prediction data; The emergency response module analyzes the risk of intelligent collision based on collision prediction data, and uses risk thresholds to analyze the collision risk level of objects. It adjusts the intensity and response time of the alarm signal according to the risk level to obtain the early warning emergency configuration.

[0043] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. An intelligent collision detection method, characterized in that: The following steps are involved: Set the initial transmission angle of the radar, monitor the reflected signal of the moving object and record the return time, calculate the reflection distance according to the speed of light and time, adjust the transmission angle to optimize the coverage range, and obtain the angle correction data; The angle correction data is used to convert the radar signal into coordinate data, and the radar scanning parameters are synchronously updated to match the real-time position change of the object, and the scanning path is iteratively optimized to generate scanning coverage data; Based on the scanning coverage data, the velocity vector and direction vector of the object are analyzed, the position change of the object is analyzed in combination with the time series, the target trajectory information is updated in real time, and the motion trajectory of the object is obtained; Identify the deviation between the object's motion trajectory and the preset trajectory, classify and predict potential collision targets, detect the probability of collision through difference analysis, and obtain collision prediction data; Using the collision prediction data, analyzing the potential risk of intelligent collision, determining the collision risk level of the detected object through a threshold, and outputting a risk quantification analysis result; Based on the risk quantification analysis results, automatic warning is carried out and emergency measures are designed, including the intensity and response time of the alarm signal, to match the processing requirements of differentiated risk levels and obtain warning emergency configuration.

2. The intelligent collision detection method according to claim 1, characterized in that: The angle correction data includes the peak coverage angle, the valley coverage angle and the associated angle adjustment value; the scanning coverage data includes the coordinate point set of the scanning area, the correlation between the coordinate points and the scanning time and the spatial distribution density of the coordinate points; the target trajectory information includes the position, velocity vector and direction vector of the object in differentiated time; the collision prediction data includes the collision probability score, the category of potential collision objects, the motion trend and the prediction time window; the risk quantification analysis result includes the probability value associated with the risk level, the risk assessment standard and the risk probability calculation result; the early warning emergency configuration includes the intensity of the alarm signal, the response time and the differentiated emergency measures list.

3. The intelligent collision detection method according to claim 1, characterized in that: The steps to set the initial transmission angle of the radar, monitor the reflected signal of the moving object and record the return time, calculate the reflection distance according to the speed of light and time, adjust the transmission angle to optimize the coverage range, and obtain the angle correction data are as follows: Set the initial launch angle of the radar, start radar monitoring and capture the reflected signal of the object, record the return time of the reflected signal, use the speed of light and time difference to calculate the reflected distance, and generate the initialization distance data; Based on the initialization distance data, adjusting the transmission angle of the radar, testing the signal coverage under the differentiated configuration by adjusting the angle, re-recording the adjusted reflection signal and return time, and obtaining the adjusted distance data; The adjusted distance data is used to iteratively optimize the emission angle of the radar, check the coverage of the radar, and cyclically record and calculate the reflection distance to obtain angle correction data.

4. The intelligent collision detection method according to claim 1, characterized in that: The steps of using the angle correction data to convert the radar signal into coordinate data, synchronously updating the radar scanning parameters to match the real-time position change of the object, iteratively optimizing the scanning path, and generating the scanning coverage data are as follows: The angle correction data is used to convert the signal received by the radar into coordinate data, and the position of the object is calculated by analyzing the angle and distance of each reflected signal to generate position coordinate data; Using the position coordinate data, synchronously updating the scanning parameters of the radar to match the real-time position changes of the object, including adjusting the scanning frequency and angle, and obtaining real-time scanning data; Based on the real-time scanning data, the scanning path of the radar is iteratively optimized, and the area covered by the path and the scanning efficiency are optimized by adjusting the starting point and the end point of the scanning to obtain the scanning coverage data.

5. The intelligent collision detection method according to claim 1, characterized in that: Based on the scanning coverage data, the speed vector and direction vector of the object are analyzed, the position change of the object is analyzed in combination with the time series, and the target trajectory information is updated in real time. The steps of obtaining the object motion trajectory are specifically as follows: Based on the scan coverage data, each coordinate point data of the object is analyzed, the speed vector and the direction vector of each scan of the object are calculated, the speed is calculated by the position and time difference between two consecutive points, and the initialization data of the speed and direction are generated; Using the initialization data of speed and direction, combined with a time series analysis method, the position change of the object is tracked and analyzed, and the real-time motion state of the object is updated by comparing the position data of consecutive time points to obtain dynamic trajectory update data; The dynamic trajectory is used to update data, track and analyze the motion trajectory of the object, capture the motion trend and position change in real time, detect the collision probability of the object in motion, check the continuity and consistency of tracking, and obtain the motion trajectory of the object.

6. The intelligent collision detection method according to claim 1, characterized in that: The steps of identifying the deviation between the object's motion trajectory and the preset trajectory, classifying and predicting potential collision targets, detecting the probability of collision through difference analysis, and obtaining collision prediction data are as follows: The object motion trajectory data is compared with the preset trajectory, and the distance difference and angle difference are measured by using the Euclidean distance algorithm to perform intelligent collision detection of the object and generate trajectory deviation data; Using the trajectory deviation data, classifying objects as potential collision targets, predicting collision risks according to deviation values ​​and directions, setting collision risk thresholds, and classifying objects according to risk levels to obtain collision risk classification data; Based on the collision risk classification data, the collision probability of multiple types of targets is iteratively detected through difference analysis, and the time and place of the collision are calculated to obtain collision prediction data.

7. The intelligent collision detection method according to claim 6, characterized in that: The formula of the Euclidean distance algorithm is as follows: in, is the adjusted deviation Euclidean distance, is the dimension, The actual trajectory point is dimensional coordinates, are the coordinates of the preset trajectory points, is the error correction factor for each dimension, is the weight coefficient of the dimension, is the environmental impact factor, is the adjustment factor.

8. The intelligent collision detection method according to claim 1, characterized in that: The steps of using the collision prediction data to analyze the potential risk of intelligent collision, determining the collision risk level of the detected object by a threshold, and outputting the risk quantification analysis result are specifically as follows: Using the collision prediction data, analyzing the collision risks of multiple types of objects, including the assessment of speed, direction, and closing rate, and generating initialization risk analysis data by assessing the risk weights of differentiated data points; Using the initialized risk analysis data, determining through a set risk level threshold, classifying the collision risk level of the object, identifying the risk classification, and obtaining the graded risk data; Based on the graded risk data, the numerical value of the collision risk level of the object is quantified, the probability value associated with the risk level is analyzed, and the risk quantification analysis result is obtained by real-time monitoring of the movement of the object.

9. The intelligent collision detection method according to claim 1, characterized in that: Based on the risk quantification analysis results, automatic warning is carried out, and emergency measures are designed, including the intensity and response time of the alarm signal, to match the processing requirements of the differentiated risk levels. The specific steps for obtaining the warning emergency configuration are as follows: Using the risk quantification analysis results, start automatic warning, adjust the intensity of the alarm signal according to the differentiated risk level, including signal frequency and sound intensity, verify that the alertness of the alarm matches the risk level, and generate alarm configuration data; Using the alarm configuration data, design response time parameters, check that the time span from alarm activation to response is synchronized with the risk level, prioritize risk events for response, and obtain response time setting data; Based on the response time setting data, combined with the alarm signal strength and response time of the object collision, emergency measures for differentiated risk levels are formulated, including evacuation guidelines and safety measures guidance, to obtain an early warning emergency configuration.

10. An intelligent collision detection system, characterized in that: According to the intelligent collision detection method according to any one of claims 1 to 9, the system comprises: The angle adjustment module adjusts the transmission angle based on the radar initialization settings, captures the reflected signal, and records the return time. It uses the speed of light and the time difference to calculate the reflection distance, adjusts the transmission angle to optimize the radar coverage, and generates angle correction data. The data conversion module converts the radar signal into coordinate data according to the angle correction data, updates the radar scanning parameters to match the real-time position of the object, iteratively optimizes the scanning path, and generates scanning coverage data; The trajectory analysis module calculates the velocity vector and direction vector of the object through the scanning coverage data, identifies the position change of the object in combination with the time series, updates the trajectory of the target, and obtains the motion trajectory of the object; The deviation calculation module uses the object motion trajectory to compare the object trajectory with the preset trajectory, calculates the deviation of the distance and angle difference, and performs object classification and collision probability prediction to generate collision prediction data; The emergency response module analyzes the risk of intelligent collision based on the collision prediction data, and uses the risk threshold to analyze the collision risk level of the object, adjusts the intensity and response time of the alarm signal according to the risk level, and obtains the early warning emergency configuration.

Images