Obstacle recognition method and device, electronic equipment and storage medium
By calculating the autocorrelation coefficient of the aftershock value of the ultrasonic sensor, the problem of difficulty in identifying obstacles in the detection blind zone was solved, and accurate obstacle identification was achieved in both static and dynamic states, thus improving the detection reliability of the ultrasonic sensor.
Patent Information
- Application Number
- CN202410599643.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-14
- Publication Date
- 2025-11-21
AI Technical Summary
Existing ultrasonic sensors cannot effectively identify obstacles in the detection blind zone, especially when the probe and the obstacle are stationary. The echo signal and aftershock signal are mixed together and cannot be distinguished, resulting in the failure to identify obstacles in the blind zone.
By calculating the autocorrelation coefficient of the aftershock values of the ultrasonic sensor, and using the historical average and moving average of the aftershock values, combined with the autocorrelation coefficient threshold, it is determined whether there are obstacles in the detection blind zone, adapting to the static or moving state of the probe and the obstacle.
This technology enables accurate identification of obstacles within the detection blind zone, whether the probe and the obstacle are stationary or in motion, thus improving the detection reliability and applicability of ultrasonic sensors.
Smart Images
Figure CN120993427A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of environmental perception technology, specifically to an obstacle recognition method and device, electronic equipment, and storage medium. Background Technology
[0002] Most ultrasonic sensors currently use transceiver probes, combining the functions of sending and receiving ultrasonic waves. While emitting ultrasonic signals, they also receive echo signals. The probe includes a piezoelectric crystal. Due to the inherent mechanical inertia of the piezoelectric crystal, it will continue to decay and oscillate for a period of time, known as aftershock. If the probe receives an echo signal reflected from an obstacle during this aftershock period, the echo signal will be mixed with the aftershock signal (the vibration signal generated by the aftershock) and cannot be distinguished. This creates a detection blind zone, making it impossible to effectively identify obstacles within the ultrasonic detection blind zone.
[0003] Current methods generally rely on predicting or calculating the relative motion between the probe and the obstacle to determine whether there is an obstacle in the detection blind zone. However, if an obstacle is already in the detection blind zone when the ultrasonic detection is started, and both the probe and the obstacle are stationary, this method cannot effectively identify whether there is an obstacle in the detection blind zone. Summary of the Invention
[0004] The purpose of this application is to provide an obstacle recognition method and device, electronic device, and computer-readable storage medium for effectively recognizing obstacles in detection blind zones.
[0005] To achieve the above objectives, embodiments of this application provide an obstacle recognition method, the method comprising:
[0006] Obtain the aftershock value of the ultrasonic sensor during the current detection period and the aftershock value during historical detection periods;
[0007] The average aftershock value for the entire operating cycle and the moving average aftershock value for the most recent m operating cycles are calculated based on the aftershock value of the current detection cycle and the aftershock value of the historical detection cycles; wherein, the entire operating cycle is the operating time of the ultrasonic sensor after it is powered on, and m is a preset value.
[0008] The autocorrelation coefficient between the aftershock value of the current detection period and the aftershock value of the entire operation period is calculated based on the aftershock value of the current detection period, the average aftershock value, and the moving average aftershock value.
[0009] The autocorrelation coefficient is compared with a preset autocorrelation coefficient threshold, and the presence of an obstacle in the detection blind zone is determined based on the comparison result.
[0010] Embodiments of this application also provide an obstacle recognition device, the device comprising:
[0011] The aftershock acquisition module is used to acquire the aftershock value of the ultrasonic sensor during the current detection period and the aftershock value during the historical detection periods.
[0012] The aftershock calculation module is used to calculate the average aftershock value for the entire operating cycle and the moving average aftershock value for the most recent m operating cycles based on the aftershock value of the current detection cycle and the aftershock value of the historical detection cycles; wherein, the entire operating cycle is the operating time of the ultrasonic sensor after it is powered on, and m is a preset value;
[0013] The autocorrelation calculation module is used to calculate the autocorrelation coefficient between the aftershock value of the current detection period and the aftershock value of the entire operation period based on the aftershock value of the current detection period, the average aftershock value, and the moving average aftershock value.
[0014] The obstacle recognition module is used to compare the autocorrelation coefficient with a preset autocorrelation coefficient threshold, and determine whether there is an obstacle in the detection blind zone based on the comparison result.
[0015] Embodiments of this application also provide an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the obstacle recognition method as described above.
[0016] Embodiments of this application also provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the obstacle recognition method described above.
[0017] This application provides an obstacle identification method and device, electronic device, and computer-readable storage medium. After the ultrasonic sensor starts detection, it accumulates and calculates the average value of aftershocks for the entire operating cycle and the moving average value of aftershocks for the most recent m detection cycles based on the received aftershock values in each detection cycle. It then calculates the autocorrelation coefficient between the aftershock value of the current detection cycle and the aftershock value of the entire operating cycle based on the aftershock value of the current detection cycle, the average value of aftershocks, and the moving average value of aftershocks. This autocorrelation coefficient is compared with an autocorrelation coefficient threshold, which is the autocorrelation coefficient calculated when there are no obstacles in the detection blind zone. Based on the comparison result, it is determined whether there are obstacles in the detection blind zone. Regardless of whether the probe and the obstacle are stationary, the autocorrelation coefficient can be calculated and compared normally to identify whether there are obstacles in the detection blind zone. Attached Figure Description
[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the accompanying drawings required in the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0019] Figure 1 This is a flowchart of an obstacle recognition method in one embodiment of this application.
[0020] Figure 2 This is a frame structure diagram of an obstacle recognition device according to another embodiment of this application. Detailed Implementation
[0021] The detailed description of the accompanying drawings is intended to illustrate some present embodiments of this application and is not intended to represent only the forms in which this application can be implemented. It should be understood that the same or equivalent functionality may be achieved by different embodiments intended to be included within the scope of this application.
[0022] One embodiment of this application provides an obstacle recognition method, including but not limited to obstacle recognition using ultrasonic sensors, such as those on vehicles. (See also...) Figure 1 The method includes the following steps:
[0023] Step S10: Obtain the aftershock value of the current detection cycle and the aftershock value of the historical detection cycle of the ultrasonic sensor.
[0024] Specifically, the detection cycle of an ultrasonic sensor refers to the time required for the ultrasonic sensor to complete one complete detection process. This process typically includes sending an ultrasonic pulse, waiting and receiving the echo signal, and processing the signal. In each detection cycle, the ultrasonic sensor emits an ultrasonic pulse, generating an aftershock signal. In practical applications, the detection cycle of an ultrasonic sensor needs to be set according to the specific application scenario and requirements to balance detection speed, accuracy, and resource usage. For example, in automotive reversing radar, the detection cycle may need to be very short to quickly respond to obstacles approaching from behind the vehicle, while in industrial detection or ranging applications, the detection cycle may be longer because the real-time requirements may not be as high. After the ultrasonic sensor is powered on, it collects the aftershock signal in each detection cycle and calculates the amplitude of the aftershock signal, i.e., the aftershock value. Specifically, the aftershock signal is the vibration signal generated by the piezoelectric crystal due to the mechanical inertia of the piezoelectric crystal after the ultrasonic sensor emits an ultrasonic pulse. The amplitude of the aftershock signal refers to the maximum value of the voltage or current during the vibration process, reflecting the intensity of the piezoelectric crystal's vibration.
[0025] Step S20: Calculate the average aftershock value of the entire operating cycle and the moving average aftershock value of the most recent m operating cycles based on the aftershock value of the current detection cycle and the aftershock value of the historical detection cycles; wherein, the entire operating cycle is the operating time of the ultrasonic sensor after it is powered on, and m is a preset value.
[0026] Specifically, the average aftershock value for the entire operating cycle refers to the average of the aftershock values in all detection cycles from the moment the ultrasonic sensor is powered on until now. The entire operating cycle refers to the time period from when the sensor starts working until now, and all aftershock values within this time period are used to calculate the average value.
[0027] The moving average of aftershocks over the most recent m detection cycles refers to the average of the aftershock values over the most recent m detection cycles. m is a preset value, indicating that the average value is calculated by considering the data from the most recent m detection cycles. The moving average can reflect the trend of aftershock values over a recent period of time. In this embodiment, m is not limited to being set to 5.
[0028] By calculating the average aftershock value over the entire operating cycle and the moving average of aftershock values over the most recent m detection cycles, the long-term and short-term characteristics of the aftershock signal can be obtained. This is crucial for analyzing changes in the aftershock signal and determining whether there are obstacles in the detection blind zone. These average values will be used in subsequent steps to calculate the autocorrelation coefficient to help identify obstacles in the detection blind zone.
[0029] Step S30: Calculate the autocorrelation coefficient between the aftershock value of the current detection period and the aftershock value of the entire operation period based on the aftershock value of the current detection period, the average aftershock value, and the moving average aftershock value.
[0030] Specifically, in this embodiment, the autocorrelation coefficient is used to analyze the similarity between the aftershock value of the current detection period and the aftershock value of the entire operating period. The value of the autocorrelation coefficient ranges from -1 to 1. An autocorrelation coefficient value close to 1 indicates that the aftershock value of the current detection period is very similar to the aftershock value of the entire operating period, that is, the aftershock signal has strong self-similarity. An autocorrelation coefficient value close to 0 indicates that there is no obvious correlation between the two. An autocorrelation coefficient value close to -1 indicates that there are completely opposite trends between the two.
[0031] Step S40: Compare the autocorrelation coefficient with a preset autocorrelation coefficient threshold, and determine whether there is an obstacle in the detection blind zone based on the comparison result;
[0032] Specifically, in ultrasonic detection, the transmitter emits ultrasonic pulses. When these pulses encounter interfaces within materials (such as defects, boundaries between different materials, etc.), they are reflected, forming echo signals. These echo signals are captured by the receiver and converted into electrical signals for subsequent analysis and interpretation. The autocorrelation coefficient threshold is the autocorrelation coefficient calculated when there are no obstacles in the detection blind zone, serving as a reference standard. When obstacles exist in the detection blind zone and their echo signals partially overlap with aftershock signals, there should be a significant difference between the calculated autocorrelation coefficient and the autocorrelation coefficient threshold. Therefore, in this case, the presence of obstacles in the detection blind zone can be quickly determined by calculating the autocorrelation coefficient.
[0033] It should be noted that the method in this embodiment can not only handle situations where both the probe and the obstacle are stationary, but also adapt to situations where the probe or the obstacle is in motion. By continuously calculating and comparing the autocorrelation coefficient, the ultrasonic sensor can effectively identify whether there is an obstacle in the detection blind zone, thereby improving the reliability and applicability of the ultrasonic sensor detection.
[0034] In some embodiments, step S20 further includes:
[0035] If the number of historical detection cycles is less than m, then the preset aftershock benchmark value is used as the aftershock average value and the aftershock moving average value to calculate the autocorrelation coefficient between the aftershock value of the current detection cycle and the aftershock value of the entire operation cycle.
[0036] Specifically, when the ultrasonic sensor first starts working, there may not be enough historical data to calculate an accurate average aftershock value and aftershock moving average value, because a certain number of detection cycles are needed to obtain a stable average value. In this case, if there is not enough historical detection cycle data (i.e., the number of cycles is less than the preset value m), then a preset aftershock reference value will be used instead of the actual average aftershock value and aftershock moving average value.
[0037] It should be noted that this preset aftershock baseline value is a pre-defined standard value representing the expected aftershock level under normal conditions. Using the aftershock baseline value as a substitute allows for the calculation of autocorrelation coefficients even in the early operational phase, even if the collected detection period data is insufficient. As the detection period increases and sufficient historical data is accumulated, the use of the aftershock baseline value can be discontinued, and the actual calculated average and moving average of aftershocks can be used to calculate the autocorrelation coefficient. This design minimizes identification errors that may be caused by insufficient data in the early operational phase, improving the stability and reliability of ultrasonic detection in the early stages.
[0038] In some embodiments, the autocorrelation coefficient can be calculated in the following manner:
[0039] (a) Calculate the autocovariance between the aftershock value and the average aftershock movement value during the current detection period;
[0040] (b) Calculate the variance between the aftershock value and the average aftershock value for the current detection period;
[0041] (c) Divide the autocovariance by the variance to obtain the autocorrelation coefficient.
[0042] Specifically, autocovariance measures the degree to which two random variables (aftershock values and the moving average of aftershocks in the current detection period) change together. If the two variables change in the same direction, the autocovariance will be larger; if they change in opposite directions, the autocovariance will be smaller. Variance is a statistic that measures the degree of dispersion of data. In this embodiment, variance is specifically used to measure the degree of difference between the aftershock values in the current detection period and their average values.
[0043] In some embodiments, the autocorrelation coefficient can also be calculated in the following manner:
[0044] Calculate the first difference between the aftershock value of the current detection period and the moving average of the aftershocks, and calculate the second difference between the aftershock value of the current detection period and the moving average of the aftershocks. Finally, divide the first difference by the second difference to obtain the autocorrelation coefficient.
[0045] In one specific embodiment, step S30, which determines whether there is an obstacle in the detection blind zone based on the comparison result, includes:
[0046] If the difference between the autocorrelation coefficient and the autocorrelation coefficient threshold is not within the preset threshold range, it is determined that there is an obstacle in the detection blind zone; if the difference between the autocorrelation coefficient and the autocorrelation coefficient threshold is within the preset threshold range, it is further determined whether there is a complete overlap between the aftershock signal and the echo signal. If so, it is determined that there is an obstacle in the detection blind zone; if not, it is determined that there is no obstacle in the detection blind zone.
[0047] Specifically, the autocorrelation coefficient obtained in calculation step S20 is compared with a pre-set autocorrelation coefficient threshold, which is the autocorrelation coefficient calculated when there are no obstacles in the detection blind zone, and is used as a reference value under normal circumstances.
[0048] When there are obstacles in the detection blind zone, there are two situations. The first is that the aftershock signal and the echo signal partially overlap. In this case, the acquired aftershock value will be larger than the aftershock value when there are no obstacles in the detection blind zone. Therefore, if the difference between the calculated autocorrelation coefficient and the autocorrelation coefficient threshold exceeds the preset threshold range, it indicates that the aftershock value of the current detection cycle is significantly different from the aftershock value under normal conditions. Therefore, it can be determined that there are obstacles in the detection blind zone. This is because the presence of obstacles changes the characteristics of the aftershock signal, leading to an increase in the difference between the autocorrelation coefficient and the autocorrelation coefficient threshold.
[0049] The second scenario is where the aftershock signal and the echo signal completely overlap. In this case, the acquired aftershock value will not change compared to the aftershock value when there are no obstacles in the detection blind zone. Therefore, if the difference between the calculated autocorrelation coefficient and the autocorrelation coefficient threshold is within the preset threshold range, it indicates that the aftershock value of the current detection cycle is similar to the aftershock value under normal circumstances, without obvious abnormalities. This may be due to the absence of obstacles in the detection blind zone or the complete overlap between the aftershock signal and the echo signal. In this case, the following operations are performed: for example, further identify whether there is a complete overlap between the aftershock signal and the echo signal. If not, determine that there are no obstacles in the detection blind zone; if so, determine that there are obstacles in the detection blind zone. Alternatively, a prompt message can be played via voice, indicating that there may be obstacles in the detection blind zone, and asking the user to wait for a preset time, which is the time when the aftershock occurs. After the aftershock disappears, the detection blind zone caused by the aftershock will also disappear, at which point it can be detected normally whether there are obstacles in the previous detection blind zone.
[0050] It should be noted that the preset threshold range depends on the specific application and performance requirements of the ultrasonic sensor. This range should be based on a thorough understanding of the characteristics of the aftershock signal under normal operating conditions and an awareness of signal changes caused by potential obstacles. The specific value of the preset threshold range may need to be determined through extensive testing and data analysis. For example, the threshold range can be set as a few percentages plus or minus the autocorrelation coefficient threshold, or determined based on statistical confidence intervals. In some cases, machine learning algorithms may also be needed to analyze and optimize this range to adapt to different working environments and conditions.
[0051] It should be noted that there are many ways to identify whether aftershock signals and echo signals completely overlap.
[0052] For example, in one specific embodiment, step S30 includes:
[0053] The first echo distance and the first echo amplitude are calculated based on the first echo signal, and it is determined whether the first condition and the second condition are met. If either condition is not met, it is determined that there is no obstacle in the detection blind zone. If both the first condition and the second condition are met, the driving capability of the ultrasonic sensor is further reduced, and it is determined whether the aftershock value after reducing the driving capability is greater than the preset weak driving aftershock threshold. If it is, it is determined that there is an obstacle in the detection blind zone before the driving capability was reduced. If not, it is determined that there is no obstacle in the detection blind zone before the driving capability was reduced. Alternatively, signal filtering technology is used to filter the received aftershock signal, and the presence of an obstacle in the detection blind zone is determined based on the filtering result. Wherein, the first condition is that the first echo distance value is greater than d and less than 2×d, where d is a preset blind zone distance; the second condition is that the first echo amplitude is less than a preset amplitude; the first echo signal is the first echo signal that does not overlap with the aftershock signal received by the ultrasonic sensor in the current detection cycle, and the first echo signal comes from the first reflection interface encountered by the ultrasonic pulse outside the detection blind zone. It may be the first echo signal received by the ultrasonic sensor in the current detection cycle, or it may be the nth echo signal received by the ultrasonic sensor in the current detection cycle, where n is greater than or equal to 2.
[0054] Specifically, if the difference between the autocorrelation coefficient and the autocorrelation coefficient threshold is within the preset threshold range, it indicates that the aftershock autocorrelation coefficient is normal. This suggests that the aftershock signal may not be affected by obstacles (i.e., there are no echo signals from obstacles), or the influence of obstacles is insufficient to change the statistical characteristics of the aftershock signal (i.e., the aftershock signal may completely overlap with the echo signal from the obstacle, but the echo signal from the obstacle is very small). In this case, further analysis is needed to determine whether the first and second conditions are met. If either condition is not met, it is determined that there are no obstacles in the detection blind zone. If both conditions are met, it suggests that there may be obstacles in the detection blind zone, and there is a possibility that the aftershock signal and the echo signal in the blind zone may completely overlap, but further confirmation is needed.
[0055] The reason for the first condition, which is whether the first echo distance value is greater than 1 times the blind zone distance and less than 2 times the blind zone distance, is that when the echo signal completely overlaps with the aftershock signal, the actual single echo distance should be less than the blind zone distance. When the distance is close enough, the nth echo distance is n times the single echo distance (2≤n≤4, n=2 in common cases). Therefore, the first echo distance value calculated at this time is actually the distance of the nth echo that does not overlap with the aftershock range (i.e., the predetermined blind zone distance). After the ultrasonic wave is reflected n times, the echo amplitude will be reduced, which is less than the amplitude obtained at the same distance under normal circumstances. Therefore, the first echo amplitude should be less than the preset amplitude at this time.
[0056] Therefore, if any one of the conditions is not met, it means that the first echo signal is the first echo signal received by the ultrasonic sensor in the current detection cycle, and it can be determined that there is no obstacle in the detection blind zone. If both the first and second conditions are met, it means that the first echo signal is the nth echo signal received by the ultrasonic sensor in the current detection cycle (2≤n≤4, n=2 is common). The actual first echo signal completely overlaps with the aftershock signal. At this time, the driving capability test method of the ultrasonic sensor is further reduced by adjusting the working parameters of the ultrasonic sensor to reduce the driving capability of the ultrasonic sensor to emit waves, including but not limited to reducing the number of waves emitted and reducing the driving current. Then it is determined whether the aftershock value after reducing the driving capability is greater than the preset weak driving aftershock threshold.
[0057] When the driving capability decreases, the intensity of the aftershock signal will also decrease accordingly, which may reduce the range of the detection blind zone. By comparing the aftershock value after reducing the driving capability with the pre-calibrated weak driving aftershock threshold, the following judgments can be made:
[0058] If the aftershock value after reducing the drive capability is greater than the pre-calibrated weak drive aftershock threshold, this indicates that the aftershock signal is still strong even at a lower drive level. This may be because the echo signal reflected by the obstacle partially overlaps with the aftershock signal; that is, without reducing the drive capability, the aftershock signal may completely overlap with the first echo signal of the obstacle. Therefore, it can be determined that an obstacle exists in the detection blind zone of the normal operating parameters (i.e., without reducing the drive capability), and the ultrasonic sensor should be adjusted back to the normal operating parameters.
[0059] If the aftershock value after reducing the driving capability is not greater than the pre-calibrated weak driving aftershock threshold, this indicates that the aftershock signal is weak and there may be no obstacle overlapping with the aftershock signal. Therefore, it can be determined that there are no obstacles within the normal parameter blind zone, and the ultrasonic sensor can be adjusted back to its normal operating parameters.
[0060] The key to this method is to adjust the intensity of the aftershock signal by changing the driving capability, thereby creating conditions to distinguish the aftershock signal from the echo signal reflected by the obstacle. If the aftershock signal is still very strong under weak driving conditions, it may be due to the presence of the obstacle. This method can effectively improve the ability of ultrasonic detection to identify obstacles in the detection blind zone.
[0061] Specifically, using signal filtering technology to filter the received aftershock signal, and determining whether there are obstacles in the detection blind zone based on the filtering results, refers to:
[0062] Aftershock signals are vibration signals generated by the mechanical inertia of the piezoelectric crystal after the ultrasonic probe emits a pulse. These signals are typically short-lived and have a high frequency component because they are caused by the rapid changes in the emitted pulse. Echo signals, on the other hand, are ultrasonic signals reflected from obstacles. These signals are affected by factors such as the shape, size, material, and distance of the obstacle. The frequency of the echo signal is usually the same as the frequency of the emitted ultrasonic pulse because it is a reflection of the original pulse. Ideally, the frequency of the echo signal will not change. Therefore, the aftershock signals received during the aftershock generation period can be filtered based on the frequency of the emitted ultrasonic pulse, removing signals with the same frequency as the ultrasonic pulse. Comparing the signals before and after filtering reveals a significant error; if a large error exists, it indicates that an echo signal has been filtered out, meaning an obstacle exists in the detection blind zone. Conversely, if no error exists, it indicates that no echo signal has been filtered out, meaning no obstacle exists in the detection blind zone.
[0063] This specific embodiment provides a more comprehensive obstacle detection method by combining autocorrelation coefficient analysis and echo signal analysis, as well as testing changes in aftershock values or signal filtering methods by reducing driving capability, thereby improving the accuracy and reliability of detection.
[0064] For example, in another specific embodiment, step S30 includes:
[0065] Reduce the driving capability of the ultrasonic sensor and determine whether the aftershock value after reducing the driving capability is greater than the preset weak driving aftershock threshold. If it is, it is determined that there is an obstacle in the detection blind zone before the driving capability was reduced. If not, it is determined that there is no obstacle in the detection blind zone before the driving capability was reduced.
[0066] Specifically, this embodiment proposes a test method for reducing the driving capability of an ultrasonic sensor. The driving capability of the ultrasonic sensor to emit waves is reduced by adjusting the operating parameters of the ultrasonic sensor, including but not limited to reducing the number of waves emitted and reducing the driving current. Then, it is determined whether the aftershock value after reducing the driving capability is greater than a preset weak driving aftershock threshold.
[0067] When the driving capability decreases, the intensity of the aftershock signal will also decrease accordingly, which may reduce the range of the detection blind zone. By comparing the aftershock value after reducing the driving capability with the pre-calibrated weak driving aftershock threshold, the following judgments can be made:
[0068] If the aftershock value after reducing the drive capability is greater than the pre-calibrated weak drive aftershock threshold, this indicates that the aftershock signal is still strong even at a lower drive level. This may be because the echo signal reflected by the obstacle partially overlaps with the aftershock signal; that is, without reducing the drive capability, the aftershock signal may completely overlap with the first echo signal of the obstacle. Therefore, it can be determined that an obstacle exists in the detection blind zone of the normal operating parameters (i.e., without reducing the drive capability), and the ultrasonic sensor should be adjusted back to the normal operating parameters.
[0069] If the aftershock value after reducing the driving capability is not greater than the pre-calibrated weak driving aftershock threshold, this indicates that the aftershock signal is weak and there may be no obstacle overlapping with the aftershock signal. Therefore, it can be determined that there are no obstacles within the normal parameter blind zone, and the ultrasonic sensor can be adjusted back to its normal operating parameters.
[0070] The key to this method is to adjust the intensity of the aftershock signal by changing the driving capability, thereby creating conditions to distinguish the aftershock signal from the echo signal reflected by the obstacle. If the aftershock signal is still very strong under weak driving conditions, it may be due to the presence of the obstacle. This method can effectively improve the ability of ultrasonic detection to identify obstacles in the detection blind zone.
[0071] In some embodiments, the method further includes:
[0072] Step S50: When it is determined that there are no obstacles in the detection blind zone based on the comparison result, if the current vehicle speed is greater than the preset vehicle speed threshold, or if no echo signal is received within the preset time, the calculated autocorrelation coefficient is stored as the preset autocorrelation coefficient threshold, and the calculated average aftershock value is stored as the preset aftershock reference value.
[0073] Specifically, in certain situations, when the comparison results indicate that there are no obstacles within the detection blind zone, a specific condition is used to determine whether it is a specific scenario. If it is a specific scenario, the internal reference values used for comparison are updated. These conditions include:
[0074] (1) The current vehicle speed is greater than the preset vehicle speed threshold;
[0075] In some applications, such as vehicle assistance systems, vehicle speed can affect the performance of ultrasonic detection. When the vehicle speed exceeds a preset threshold, the surrounding environment can be considered to have changed, and it is assumed that there are no obstacles nearby, or that the influence of obstacles on the vehicle is negligible. Therefore, the currently calculated autocorrelation coefficient and the average aftershock value are updated and stored as the new autocorrelation coefficient threshold and aftershock baseline values.
[0076] (2) No echo signal was received within the preset time;
[0077] No echo signal received means there are no obstacles in the detection area, or the obstacles are too far away for the echo signal to be detected. In this case, the currently calculated average aftershock value and autocorrelation coefficient can be considered to reflect the absence of obstacles. Therefore, the currently calculated autocorrelation coefficient and average aftershock value can be stored as new autocorrelation coefficient thresholds and aftershock baseline values.
[0078] Based on this, this embodiment can automatically adjust its reference value according to the current environmental conditions to improve the accuracy and adaptability of detection. Step S50 helps to maintain optimal performance under different operating conditions and can adapt to environmental changes, thereby improving the robustness and reliability of ultrasonic detection.
[0079] Corresponding to the obstacle recognition method described in the above embodiments, another embodiment of this application also provides an obstacle recognition device, see below. Figure 2 The apparatus includes multiple modules for performing the methods of the above embodiments, the multiple modules including:
[0080] Aftershock acquisition module 1 is used to acquire the aftershock value of the ultrasonic sensor during the current detection period and the aftershock value during the historical detection period;
[0081] The aftershock calculation module 2 is used to calculate the average aftershock value of the entire operating cycle and the moving average aftershock value of the most recent m operating cycles based on the aftershock value of the current detection cycle and the aftershock value of the historical detection cycles; wherein, the entire operating cycle is the operating time of the ultrasonic sensor after it is powered on, and m is a preset value.
[0082] Autocorrelation calculation module 3 is used to calculate the autocorrelation coefficient between the aftershock value of the current detection period and the aftershock value of the entire operation period based on the aftershock value of the current detection period, the average aftershock value, and the moving average aftershock value; and
[0083] The obstacle recognition module 4 is used to compare the autocorrelation coefficient with a preset autocorrelation coefficient threshold, and determine whether there is an obstacle in the detection blind zone based on the comparison result.
[0084] In some embodiments, the aftershock calculation module 2 is used to calculate the autocorrelation coefficient between the aftershock value of the current detection cycle and the aftershock value of the entire operating cycle if the number of cycles of the historical detection cycle is less than m, by using a preset aftershock benchmark value as the aftershock average value and the aftershock moving average value.
[0085] In one specific embodiment, the obstacle recognition module 4 is specifically used for:
[0086] If the difference between the autocorrelation coefficient and the autocorrelation coefficient threshold is not within the preset threshold range, it is determined that there is an obstacle in the detection blind zone; if the difference between the autocorrelation coefficient and the autocorrelation coefficient threshold is within the preset threshold range, it is determined that there is no obstacle in the detection blind zone.
[0087] In another specific embodiment, the obstacle recognition module 4 is specifically used for:
[0088] If the difference between the autocorrelation coefficient and the autocorrelation coefficient threshold is not within the preset threshold range, it is determined that there is an obstacle in the detection blind zone;
[0089] If the difference between the autocorrelation coefficient and the autocorrelation coefficient threshold is within the preset threshold range, then the first echo distance value and the first echo amplitude value are calculated based on the first echo signal, and it is determined whether the first condition and the second condition are met.
[0090] If any one of the conditions is not met, it is determined that there is no obstacle in the detection blind zone; wherein, the first condition is that the first echo distance value is greater than d and less than 2×d, where d is a preset blind zone distance; the second condition is that the first echo amplitude is less than a preset amplitude.
[0091] If both the first and second conditions are met, the driving capability of the ultrasonic sensor is reduced, and it is determined whether the aftershock value after reducing the driving capability is greater than the preset weak driving aftershock threshold. If so, it is determined that there is an obstacle in the detection blind zone before the driving capability was reduced; otherwise, it is determined that there is no obstacle in the detection blind zone before the driving capability was reduced.
[0092] In another specific embodiment, the obstacle recognition module 4 is specifically used for:
[0093] Reduce the driving capability of the ultrasonic sensor and determine whether the aftershock value after reducing the driving capability is greater than the preset weak driving aftershock threshold. If it is, it is determined that there is an obstacle in the detection blind zone before the driving capability was reduced. If not, it is determined that there is no obstacle in the detection blind zone before the driving capability was reduced.
[0094] In some embodiments, the apparatus further includes:
[0095] The parameter update module is used to store the calculated autocorrelation coefficient as the preset autocorrelation coefficient threshold and the calculated average aftershock value as the preset aftershock reference value when it is determined that there is no obstacle in the detection blind zone based on the comparison result, if the current vehicle speed is greater than the preset vehicle speed threshold or no echo signal is received within a preset time.
[0096] The obstacle recognition device described above is merely illustrative. The modules described as separate components may or may not be physically separate. The components of a module may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of the obstacle recognition device solution in the embodiments, depending on actual needs.
[0097] It should be noted that the obstacle recognition device in the above embodiments corresponds to the obstacle recognition method in the above embodiments. Therefore, the parts of the obstacle recognition device in the above embodiments that are not described in detail can be obtained by referring to the content of the obstacle recognition method in the above embodiments, and will not be repeated here.
[0098] Furthermore, if the obstacle recognition device of the above embodiments is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium.
[0099] Another embodiment of this application provides an electronic device including a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the obstacle recognition method described in the above embodiments.
[0100] The electronic device may also include a bus connecting different components, including memory and processor. The memory may include a computer-readable medium in the form of volatile memory, such as random access memory (RAM) and / or cache memory. The memory may also include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this application. The electronic device may also communicate with one or more external devices (e.g., keyboard, pointing device, display, etc.), and with one or more devices that enable a user to interact with the electronic device, and / or with any device (e.g., a network interface card) that enables the electronic device to communicate with one or more other computing devices, such communication may be performed via an input / output (I / O) interface, and the electronic device may also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via a network adapter.
[0101] Another embodiment of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the obstacle recognition method as described in the above embodiments.
[0102] Specifically, the computer-readable storage medium may include any entity or recording medium capable of carrying the computer program instructions, such as a USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media.
[0103] The various embodiments of this application have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical applications, or technological improvements to the embodiments in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.
Claims
1. An obstacle recognition method, characterized in that, The method includes: Obtain the aftershock value of the ultrasonic sensor during the current detection period and the aftershock value during historical detection periods; The average aftershock value for the entire operating cycle and the moving average aftershock value for the most recent m operating cycles are calculated based on the aftershock value of the current detection cycle and the aftershock value of the historical detection cycles; wherein, the entire operating cycle is the operating time of the ultrasonic sensor after it is powered on, and m is a preset value. The autocorrelation coefficient between the aftershock value of the current detection period and the aftershock value of the entire operation period is calculated based on the aftershock value of the current detection period, the average aftershock value, and the moving average aftershock value. The autocorrelation coefficient is compared with a preset autocorrelation coefficient threshold, and the presence of an obstacle in the detection blind zone is determined based on the comparison result.
2. The method according to claim 1, characterized in that, The method further includes: If the number of historical detection cycles is less than m, then the preset aftershock baseline value will be used as the average aftershock value and the moving average aftershock value.
3. The method according to claim 1, characterized in that, The autocorrelation coefficient is calculated in the following way: Calculate the autocovariance between the aftershock value and the average aftershock movement value during the current detection period; Calculate the variance between the aftershock value and the average aftershock value during the current detection period; The autocorrelation coefficient is obtained by dividing the autocovariance by the variance.
4. The method according to claim 1, characterized in that, The step of determining whether there is an obstacle in the detection blind zone based on the comparison result includes: If the difference between the autocorrelation coefficient and the autocorrelation coefficient threshold is not within the preset threshold range, it is determined that there is an obstacle in the detection blind zone; if the difference between the autocorrelation coefficient and the autocorrelation coefficient threshold is within the preset threshold range, it is further identified whether there is a complete overlap between the aftershock signal and the echo signal. If so, it is determined that there is an obstacle in the detection blind zone; if not, it is determined that there is no obstacle in the detection blind zone.
5. The method according to claim 4, characterized in that, The further identification of whether aftershock signals and echo signals completely overlap includes: The first echo distance value and the first echo amplitude are obtained based on the first echo signal, and it is determined whether the first condition and the second condition are met. If any one of the conditions is not met, it is determined that there is no obstacle in the detection blind zone; Wherein, the first condition is that the first echo distance value is greater than d and less than 2×d, where d is a preset blind zone distance; the second condition is that the first echo amplitude is less than a preset amplitude; the first echo signal is the first echo signal that does not overlap with the aftershock signal in the current detection period.
6. The method according to claim 4, characterized in that, The further identification of whether aftershock signals and echo signals completely overlap includes: Reduce the driving capability of the ultrasonic sensor and determine whether the aftershock value after reducing the driving capability is greater than the preset weak driving aftershock threshold. If it is, it is determined that there is an obstacle in the detection blind zone before the driving capability was reduced. If not, it is determined that there is no obstacle in the detection blind zone before the driving capability was reduced.
7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: When it is determined that there are no obstacles in the detection blind zone based on the comparison results, if the current vehicle speed is greater than the preset vehicle speed threshold, or if no echo signal is received within the preset time, the calculated autocorrelation coefficient is stored as the preset autocorrelation coefficient threshold, and the calculated average aftershock value is stored as the preset aftershock reference value.
8. An obstacle recognition device, characterized in that, The apparatus includes a module for performing the obstacle recognition method according to any one of claims 1 to 7.
9. An electronic device comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the obstacle recognition method as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the obstacle recognition method as described in any one of claims 1 to 7.