Method for processing sensor signal of vehicle

Abstract

The invention relates to a method for processing a sensor signal of a vehicle, the method comprising obtaining the sensor signal; calculating a corresponding characteristic value according to the value of the sensor signal in the past preset time period, wherein the characteristic value represents the stability of the current sensor signal; whether the current sensor signal is abnormal or not is determined according to a comparison of the characteristic value with a predetermined characteristic threshold value, and the value of the current sensor signal is replaced by a replacement value in the case of an abnormal sensor signal.

Description

Technical Field

[0001] The invention relates to a method for processing sensor signals of a vehicle. Background Art

[0002] With the development of automobile intelligence, more and more sensors are installed in vehicles to assist or replace drivers in perceiving the surrounding environment and traffic conditions. The signals collected by these sensors, such as image acquisition devices and radars, especially the signals about different objects around the vehicle, are fed to the vehicle's driving assistance system. The vehicle's driving assistance system adjusts the vehicle's driving state according to the signals collected by these sensors, such as adjusting the vehicle's driving speed, changing the vehicle's driving lane, or braking the vehicle, so as to actively avoid accidents or mitigate the consequences of accidents.

[0003] In addition, the lighting equipment on the vehicle can also change the lighting state according to the signals collected by the sensor, thereby realizing the function of adaptive lighting. Adaptive lighting can adaptively adjust the lighting state of the vehicle's headlights or taillights and the projection range of the lights when meeting other vehicles, encountering other traffic participants, or being followed by vehicles, so as to avoid dazzling and causing danger to oncoming and following vehicles and other traffic participants.

[0004] However, since vehicle sensors may misidentify and be interfered by other light sources on the road, the original sensor signals may be unstable and jumpy, which will damage the driving state of the vehicle and cause the vehicle lights to flicker, thus seriously affecting driving safety. Summary of the invention

[0005] The embodiment of the present disclosure provides a method for processing a sensor signal of a vehicle. The method according to the embodiment of the present disclosure can eliminate jumps in the original sensor signal and make the optimized sensor signal more stable. In this way, the adjustment of vehicle functions related to the sensor signal can be made more stable, thereby improving the driving safety of the vehicle and preventing damage to other traffic participants.

[0006] An embodiment of the present disclosure provides a method for processing a sensor signal of a vehicle, the method comprising: obtaining a sensor signal within a predetermined time period; determining a corresponding characteristic value based on the value of the sensor signal, the characteristic value characterizing the stability of the current sensor signal; and determining whether the sensor signal is abnormal based on a comparison of the characteristic value with a predetermined characteristic threshold, and if the sensor signal is abnormal, replacing the value of the sensor signal with an alternative value.

[0007] In an embodiment according to the present disclosure, the feature threshold is determined according to a plurality of historical feature values ​​corresponding to the feature value.

[0008] In an embodiment according to the present disclosure, the feature threshold is determined based on multiple historical feature values ​​corresponding to the feature value, including: determining the feature threshold based on the distribution of the multiple historical feature values ​​so that most of the multiple historical feature values ​​are smaller than the feature threshold.

[0009] In an embodiment according to the present disclosure, the replacement value is a value of a previous sensor signal or a predicted value based on the value of the sensor signal.

[0010] In an embodiment of the present disclosure, when the sensor signal is a distance signal, the predicted value is the sum of the value of the distance signal at the previous moment and the predicted change, and the predicted change is the relative speed of the target object multiplied by the time interval to the previous moment; and when the sensor signal is an angle signal, the predicted value is the sum of the value of the angle signal at the previous moment and the predicted change, and the predicted change is the relative angular speed of the target object multiplied by the time interval to the previous moment.

[0011] In an embodiment according to the present disclosure, an abnormality duration threshold is set; when the duration of the abnormality of the sensor signal is greater than the abnormality duration threshold, the value of the previous sensor signal is used as a substitute value to replace the value of the sensor signal, and when the duration of the abnormality of the sensor signal is less than the abnormality duration threshold, the predicted value is used as a substitute value to replace the value of the sensor signal.

[0012] In an embodiment according to the present disclosure, the characteristic values ​​and the historical characteristic values ​​include: the signal value of the sensor signal, the duration of the peak in the sensor signal, the mean, dispersion, skewness and kurtosis of the values ​​of the sensor signal in a predetermined time period in the past.

[0013] In an embodiment of the present disclosure, the sensor signal is an output signal of a vehicle-mounted camera.

[0014] According to an embodiment of the present disclosure, the method further includes: determining whether the sensor signal is valid; if the sensor signal is valid, determining a corresponding characteristic value based on the value of the sensor signal; if the sensor signal is invalid, comparing the duration of the sensor signal being invalid with an invalid duration threshold to determine whether to output the sensor signal.

[0015] In an embodiment according to the present disclosure, a corresponding characteristic value is determined according to the value of the sensor signal, and whether the sensor signal is abnormal is determined according to a comparison between the characteristic value and a predetermined characteristic threshold, and in the case that the sensor signal is abnormal, the value of the sensor signal is replaced by an alternative value, including: determining a jump duration of the sensor signal according to the sensor signal, and in the case that the jump duration is greater than the jump duration threshold, outputting the previous sensor signal.

[0016] In an embodiment of the present disclosure, whether the sensor signal is abnormal is determined based on a comparison between the characteristic value and a predetermined characteristic threshold value, and when the sensor signal is abnormal, the value of the sensor signal is replaced by a substitute value. It also includes: when the sensor signal is normal, comparing the change amount of the sensor signal with a change amount threshold value, when the change amount of the sensor signal is greater than the change amount threshold value, outputting a predicted value to replace the value of the sensor signal, and when the change amount of the sensor signal is less than the change amount threshold value, outputting the value of the sensor signal.

[0017] In an embodiment according to the present disclosure, the obtained sensor signal includes a first sensor signal and a second sensor signal; when the value of the first sensor signal does not change, the second sensor signal is output; when the value of the first sensor signal changes, the characteristic value of the second sensor signal is compared with a predetermined characteristic threshold to determine whether the current second sensor signal is abnormal, and when the second sensor signal is abnormal, the value of the second sensor signal is replaced by an alternative value.

[0018] In an embodiment according to the present disclosure, the first sensor signal includes different levels, wherein different levels represent different target object types, and the second sensor signal includes: a distance signal, a speed signal, an angle signal and an angular velocity signal of the target objects around the vehicle relative to the vehicle.

[0019] An embodiment of the present disclosure further provides a computer-readable storage medium having computer-readable instructions stored thereon. When the computer-readable instructions are executed by a processor, the processor executes the method for processing sensor signals of a vehicle according to the present disclosure.

[0020] An embodiment of the present disclosure further provides a camera device, which includes a computer-readable storage medium according to the present disclosure.

[0021] An embodiment of the present disclosure also provides a motor vehicle, which includes the camera device according to the present disclosure.

[0022] According to the method, computer-readable storage medium, camera device and motor vehicle of the embodiment of the present disclosure, the jump in the original sensor signal can be eliminated, and the optimized sensor signal can be made more stable. In this way, the adjustment of the vehicle function related to the sensor signal can be made smoother, thereby improving the driving safety of the vehicle and preventing damage to other traffic participants. When the sensor signal is applied to the adaptive lighting of the vehicle, the sensor signal can, for example, include the distance signal, speed signal, angle signal and angular velocity signal of the target object around the vehicle relative to the vehicle. These sensor signals can be used to adjust the low beam, high beam and lighting direction of the vehicle, and can also control the brightness of each lamp body in the LED matrix headlight. Based on the optimized more stable sensor signal, the stability of the adaptive lighting can be achieved, so that the adaptive lighting can adaptively adjust the lighting state of the vehicle headlights or taillights and the projection range of the lights when meeting, encountering other traffic participants and following vehicles, so as to avoid dazzling and causing danger to the opposite and following vehicles and other traffic participants. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some exemplary embodiments of the present disclosure, and a person of ordinary skill in the art can obtain other drawings based on these drawings without creative work.

[0024] Figure 1 A flowchart of a method according to an embodiment of the present disclosure is shown.

[0025] Figure 2 shows a graph of sensor signals and characteristic values ​​according to an embodiment of the present disclosure,

[0026] Figure 3 shows a graph of an optimized sensor signal according to an embodiment of the present disclosure,

[0027] Figure 4 A flowchart showing a method according to another embodiment of the present disclosure is shown, and

[0028] Figure 5 A flow chart of a method according to another embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solution and advantages of the present disclosure more obvious, the exemplary embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments of the present disclosure, and it should be understood that the present disclosure is not limited to the exemplary embodiments described here.

[0030] In this specification and the accompanying drawings, substantially the same or similar method steps and elements are represented by the same or similar reference numerals, and repeated descriptions of these method steps and elements will be omitted. At the same time, in the description of the present disclosure, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance or ranking. In the embodiments of the present disclosure, unless otherwise explicitly stated, "connection" does not mean that it must be "directly connected" or "directly in contact", but only needs to be electrically connected.

[0031] In this specification and the accompanying drawings, elements are described in singular or plural form, depending on the embodiment. However, the singular and plural forms are appropriately selected for the proposed situation only for the convenience of explanation and are not intended to limit the present disclosure thereto. Therefore, the singular form may include the plural form, and the plural form may also include the singular form, unless the context clearly indicates otherwise.

[0032] Figure 1 A flow chart of a method 100 according to an embodiment of the present disclosure is shown. The method 100 includes: obtaining the sensor signal (step S110); calculating a corresponding characteristic value according to the value of the sensor signal in a predetermined time period in the past (step S120), wherein the characteristic value represents the stability of the current sensor signal; determining whether the current sensor signal is abnormal according to a comparison between the characteristic value and a predetermined characteristic threshold value (step S130), and if the sensor signal is not abnormal, outputting the value of the current sensor signal (step S140); and if the sensor signal is abnormal, replacing the value of the current sensor signal with a substitute value (step S150).

[0033] In a motor vehicle, the sensor may be, for example, an image sensor, such as a vehicle-mounted camera, a radar sensor, and a laser sensor. The motor vehicle may adjust the driving state or lighting of the vehicle according to the signals sensed by the sensor. These sensor signals are particularly associated with the target objects around the vehicle, that is, with the traffic participants around the vehicle, such as passenger cars, trucks, motorcycles, bicycles, and pedestrians, so the sensor signals may include, for example, sensor signals associated with the type of target object, the distance signal, speed signal, angle signal, and angular velocity signal of the target object around the vehicle relative to the vehicle, etc. During the driving of the vehicle, the values ​​of these sensor signals, that is, the values ​​of the corresponding parameters, may change. For example, the target objects around the vehicle may change, and when the target object is an oncoming vehicle, the distance, speed, angle, and angular velocity of the oncoming vehicle relative to the vehicle may change, and when the target object is a vehicle traveling in the same direction, these parameters may also change.

[0034] Figure 2The sensor signals according to the embodiments of the present disclosure are exemplarily shown. Figure 2 The sensor signal, i.e., the change in the distance signal, is exemplarily depicted when the vehicle and the target object, such as other vehicles, are traveling in the same direction. When the vehicles are parallel, the distance between the vehicles is small, and when the vehicles are moving away, the distance between the vehicles becomes larger. The sensor signal as a whole reflects this distance change, but due to sensor misidentification or interference from other light sources, there are drastic jumps in the sensor signal. If the position of the target object is displayed, the driving status of the vehicle is adjusted, or the lighting is adjusted based entirely on the original sensor signal, these functions will also fluctuate drastically, thereby affecting the driving experience and even compromising driving safety.

[0035] By using the method 100 disclosed herein, on the one hand, it is possible to determine in the sensor signal whether an abnormality occurs in the current sensor signal, i.e., whether a jump occurs; on the other hand, in the event that an abnormality occurs in the current sensor signal, it can be replaced by a substitute value so that the sensor signal is within a reasonable range, thereby ensuring the stability of various functions of the vehicle. Figure 2 The characteristic value curve of the sensor signal is also exemplarily depicted, wherein each characteristic value is obtained according to the value of the sensor signal in a predetermined time period in the past, and the predetermined time period can be, for example, in the range of 1 ms to 100 ms. According to an embodiment of the present disclosure, the characteristic value includes the signal value of the sensor signal in the predetermined time period in the past, the mean value of the sensor signal, the degree of dispersion, such as the standard deviation and variance, skewness and kurtosis, etc.

[0036] The mean μ of the sensor signal is:

[0037]

[0038] Among them, X i represents the value of the sensor signal within a predetermined time period, 1≤i≤n. The mean μ reflects the overall size of the value of the sensor signal within the predetermined time period.

[0039] The degree of dispersion can be expressed, for example, as variance or standard deviation. For example, the standard deviation σ of the value of the sensor signal is:

[0040]

[0041] Among them, X i represents the value of the sensor signal within a predetermined time period, 1≤i≤n, μ is the mean value of the sensor signal. The standard deviation σ reflects the degree of dispersion of the sensor signal value within a predetermined time period, that is, the degree of deviation from the mean μ. Based on the standard deviation σ of the sensor signal value, the variance σ of the sensor signal value can also be determined. 2 .

[0042] The skewness S of the value of the sensor signal is:

[0043]

[0044] Among them, X i represents the value of the sensor signal within a predetermined time period, 1≤i≤n, μ is the mean value of the sensor signal. σ is the standard deviation of the value of the sensor signal. The skewness S reflects the asymmetry of the probability distribution of the value of the sensor signal within the predetermined time period. When the skewness is 0, the value of the sensor signal conforms to the normal distribution, and the values ​​of the sensor signal are evenly distributed on both sides of the mean μ. When the skewness S is greater than 0, the probability distribution of the value of the sensor signal is shifted to the right, and when the skewness S is less than 0, the probability distribution of the value of the sensor signal is shifted to the left.

[0045] The kurtosis K of the value of the sensor signal is:

[0046]

[0047] Among them, X i represents the value of the sensor signal within a predetermined time period, 1≤i≤n, μ is the mean value of the sensor signal. σ is the standard deviation of the sensor signal. Kurtosis reflects the outlier degree of the sensor signal value. When the kurtosis is equal to 3, the distribution of the sensor signal value conforms to the standard normal distribution. If the kurtosis is greater than 3, it means that the extreme values ​​in the sensor signal value, that is, the values ​​far away from the mean, are increasing.

[0048] Figure 2 The characteristic value curve shown in is, by way of example, the standard deviation σ of the sensor signal. Figure 2 It can be seen that when the sensor signal jumps, the characteristic value at the corresponding moment, that is, the standard deviation, increases dramatically, and is much larger than other standard deviations when no jump occurs. Therefore, it is possible to determine whether the sensor signal at the current moment is abnormal, that is, whether a jump occurs, based on the comparison of the characteristic value with the predetermined characteristic threshold. According to an embodiment of the present disclosure, in the case of an abnormal sensor signal, the value of the sensor signal at the current moment can be replaced by a substitute value. According to an embodiment of the present disclosure, the substitute value may be the value of a previous sensor signal, such as the value of a previous sensor signal or the value of a sensor signal at a previous moment. According to an embodiment of the present disclosure, the substitute value may also be a value predicted based on the value of a past sensor signal. For example, based on two sensor signals at past moments, the trend of the sensor signal growth or decline, such as the slope, is determined, and thereby the amount of change in the value of the sensor signal from the past moment to the current moment is determined, and thereby the value of the sensor signal at the current moment is calculated.

[0049] Figure 3FIG. 1 shows a graph of optimized sensor signals according to an embodiment of the present disclosure. After replacing the unstable sensor signal value, i.e., the abnormal or jumpy sensor signal value, with the substitute value, a curve is formed. Figure 3 The optimized sensor signal curve is shown in . Figure 3 It can be seen that there are no drastic jumps in the optimized sensor curve, and the value of the sensor signal remains stable as a whole. Therefore, by adjusting the various functions of the vehicle based on the optimized sensor signal in the vehicle, the function adjustment of the vehicle can be smoother, so that the driver can have a better driving experience, and it also contributes to the safety of other traffic participants. In particular, when the original sensor signal is used to control the vehicle lights, the original sensor signal is prone to jumps and instabilities because the sensor may be interfered by other lights or because of poor light conditions at night. The optimized sensor signal according to the present disclosure avoids such jumps and instabilities, thereby avoiding the flickering of vehicle lights and preventing glare to other traffic participants.

[0050] In an embodiment according to the present disclosure, the feature threshold may be determined based on a plurality of historical feature values ​​corresponding to the feature value. For example, as much historical data of the feature value as possible may be obtained, and based on these historical feature values, it may be determined which historical feature values ​​are abnormal, for example, which historical feature values ​​are far from other historical feature values. Subsequently, the feature threshold may be determined based on the determined abnormal historical feature values, for example, when it is greater than the feature threshold, all or most abnormal historical feature values ​​may be covered.

[0051] In an embodiment of the present disclosure, the feature threshold is determined based on multiple historical feature values ​​corresponding to the feature value, which may include: determining the feature threshold based on the distribution of the multiple historical feature values, so that most of the multiple historical feature values ​​are smaller than the feature threshold, that is, the number of the multiple historical feature values ​​greater than the feature threshold is smaller than, preferably significantly smaller than, the number of the multiple historical feature values ​​less than the feature threshold.

[0052] In an embodiment according to the present disclosure, for example, after obtaining as much historical data of feature values ​​as possible, these historical feature values ​​are sorted, for example, from small to large, and then the feature threshold is determined so that most of the historical feature values ​​are less than the feature threshold. According to the feature threshold, it can be determined that the reappearance of a feature value less than the feature threshold is a high-probability event, while the reappearance of a feature value greater than the feature threshold is a low-probability event. Preferably, for example, a larger feature threshold can be selected so that 50% to 100% of the values ​​in the historical feature values ​​are less than the feature threshold.

[0053] In an embodiment according to the present disclosure, for example, after obtaining the historical data of the characteristic value, the probability distribution of these historical characteristic values ​​can also be determined first, and the characteristic threshold value can be determined according to the probability distribution of the historical characteristic values, so that the reappearance of a characteristic value less than the characteristic threshold value is a high probability event, and the reappearance of a characteristic value greater than the characteristic threshold value is a low probability event. For example, the probability distribution of the historical characteristic values ​​conforms to the normal distribution. In the case of a normal distribution, the characteristic threshold value can be determined, for example, based on the mean μ and standard deviation σ of the characteristic value. For example, the characteristic threshold value can be specified as μ+kσ, and k>0, and the characteristic value greater than the characteristic threshold value is considered to be an abnormal low probability event, and the sensor signal abnormality at the corresponding moment is determined thereby. In an embodiment according to the present disclosure, the characteristic threshold value is, for example, determined as the sum of the mean of the normal distribution and 2 times the standard value, that is, μ+2σ. In this case, the probability of being greater than the characteristic threshold value is 2.28%.

[0054] Figure 4 A flow chart of a method 400 according to another embodiment of the present disclosure is shown. In the method 400, a first sensor signal is first obtained (step S410). According to an embodiment of the present disclosure, the first sensor signal includes different levels, wherein the different levels represent different target object types. For a vehicle, valid target object types may include, for example, traffic participants such as passenger cars, trucks, motorcycles, bicycles, and pedestrians. Then, in step S420, it is determined whether the value of the first sensor signal is valid. In the case where the value of the first sensor signal is invalid, for example, the level of the current first sensor signal does not represent any target object type, in step S430, the invalid duration is compared with the invalid duration threshold, for example, it is determined whether the invalid duration is greater than the invalid duration threshold, and the invalid duration threshold may be set to 300ms, for example. In the case where the invalid duration is greater than the invalid duration threshold, the previous first sensor signal is output in step S431. The first sensor signal represents the previous target object. In this case, it is assumed that the valid target object actually still exists, and the reason why the current target object is determined to be invalid is due to the misidentification or misjudgment of the sensor. By outputting the previous target object, the various functions of the vehicle can be kept in the previous state. When the invalid duration is less than the invalid duration threshold, it is determined in step S432 that the first sensor signal is not output, for example, a level signal of 0 is output. In this case, it is assumed that the identified target object is indeed an invalid target object.

[0055] In the case where the value of the first sensor signal is valid, for example, the level of the current first sensor signal represents one of the target object types, it is determined in step S440 whether the first sensor signal has jumped. In the case where the first sensor signal has not jumped, the current first sensor signal is output in step S441, that is, it is determined that the target object has not changed. If the first sensor signal jumps, the jump duration is compared with the jump duration threshold in step S450, for example, it is determined whether the jump duration is greater than the jump duration threshold, and the jump duration can be 150ms, for example. In the case where the jump duration is greater than the jump duration threshold, the current first sensor signal that has been jumped is output. In this case, it is assumed that the target object has changed. In the case where the jump duration is less than the jump duration threshold, the previous first sensor signal is output in step S451. In this case, it is assumed that the target object has not changed, and therefore the previous target object is output. According to the method 400 shown in this embodiment, the first sensor signal can be optimized, and the optimized first sensor signal is finally formed.

[0056] Figure 5 A flowchart of a method 500 according to another embodiment of the present disclosure is shown. Figure 4 In the method 400 shown, the optimized first sensor signal can be determined, and it can be determined whether the target object has changed. Therefore, in method 500, in step S510, it is first determined whether the first sensor signal has changed, that is, whether the target object has changed. In the case where the value of the first sensor signal has not changed, it is determined that the target object has not changed, and the second sensor signal can be directly output in step S511. In an embodiment according to the present disclosure, the second sensor signal may, for example, include: a distance signal, a speed signal, an angle signal, an angular velocity signal, etc. of the target objects around the vehicle relative to the vehicle.

[0057] In the case where the value of the first sensor signal changes, that is, in the case where the target object changes, the characteristic value of the second sensor signal is compared with a predetermined characteristic threshold in step S520 to determine whether the current sensor signal is abnormal. In an embodiment according to the present disclosure, comparing the characteristic value of the second sensor signal with the predetermined characteristic threshold may include: comparing the confidence of the second sensor signal with the confidence threshold, and comparing the characteristic value of the second sensor signal with the predetermined characteristic threshold. Since the signal output by the sensor may not directly represent the value of the parameter, but rather represent the probability of the value of the parameter, it is necessary to determine whether the current sensor signal is credible, that is, whether its confidence is large enough before calculating the characteristic value.

[0058] According to the comparison result of the characteristic value of the second sensor signal with the predetermined characteristic threshold value, for example, when the characteristic value of the second sensor signal is less than the predetermined characteristic threshold value, it is assumed that the current second sensor signal is not abnormal. In the case that the current second sensor signal is not abnormal, the variation of the second sensor signal is compared with the variation threshold value in step S540. In the case that the variation of the second sensor signal is greater than the variation threshold value, it is assumed that the variation of the second sensor signal is too large and unreliable, and therefore the second sensor signal is replaced by the predicted value. For example, when the sensor signal is a distance signal, the predicted variation of the distance signal can be determined according to the value of the distance signal at the last moment and the speed of the target object relative to the vehicle. The predicted current distance signal is therefore the value of the distance signal at the last moment plus the relative speed multiplied by the time interval, wherein when the distance between the target object and the vehicle becomes smaller, for example, when the target object is traveling in the opposite direction or when the target object is traveling in the same direction and approaches the vehicle, the relative speed is negative, however, when the distance between the target object and the vehicle becomes larger, for example, when the target object is traveling in the same direction and away from the vehicle, the relative speed is positive. In contrast, when the change amount of the second sensor signal is smaller than the change amount threshold value, it is assumed that the change amount of the second sensor signal is plausible, and therefore the current value of the second sensor signal can be directly output.

[0059] In step 520, according to the comparison result of the characteristic value of the second sensor signal and the predetermined characteristic threshold value, for example, when the characteristic value of the second sensor signal is greater than the predetermined characteristic threshold value, it is assumed that the current sensor signal is abnormal. In this case, the duration of the abnormality of the second sensor signal is determined in step S530, and the abnormal duration is compared with the abnormal duration threshold value. For example, in the case where the abnormal duration is less than the abnormal duration threshold value, it is assumed that the abnormal duration of the second sensor signal is not long, and therefore the value of the second sensor signal within the abnormal duration can be predicted. Therefore, the value of the current second sensor signal can be replaced by outputting the predicted value according to the method described in detail above. However, in the case where the abnormal duration is greater than the abnormal duration threshold value, since the abnormal duration of the second sensor signal is too long, the predicted value may have a large deviation. In order to avoid this situation, the value of the previous second sensor signal, for example, the value of the second sensor signal at the previous moment, can be directly output to replace the value of the current second sensor signal.

[0060] In addition, the present disclosure also proposes a computer-readable storage medium having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by a processor, the processor executes the above-mentioned Figures 1 to 5 For a detailed description of the computer-readable storage medium, see Figures 1 to 5 , which will not be described here for the sake of brevity.

[0061] In addition, the present disclosure also proposes a camera device, which includes the above computer-readable storage medium. For a detailed description of the camera device, please refer to Figures 1 to 5 , which will not be described here for the sake of brevity.

[0062] In addition, the present disclosure also provides a motor vehicle, which includes a camera device according to the present disclosure. For a detailed description of the motor vehicle, please refer to Figures 1 to 5 , which will not be described here for the sake of brevity.

[0063] According to the method, computer-readable storage medium, camera device and motor vehicle of the embodiment of the present disclosure, the jump in the original sensor signal can be eliminated, and the optimized sensor signal can be made more stable. In this way, the adjustment of the vehicle function related to the sensor signal can be made smoother, thereby improving the driving safety of the vehicle and preventing damage to other traffic participants. When the sensor signal is applied to the adaptive lighting of the vehicle, the sensor signal can, for example, include the distance signal, speed signal, angle signal and angular velocity signal of the target object around the vehicle relative to the vehicle. These sensor signals can be used to adjust the low beam, high beam and lighting direction of the vehicle, and can also control the brightness of each lamp body in the LED matrix headlight. Based on the optimized more stable sensor signal, the stability of the adaptive lighting can be achieved, so that the adaptive lighting can adaptively adjust the lighting state of the vehicle headlights or taillights and the projection range of the lights when meeting, encountering other traffic participants and following vehicles, so as to avoid dazzling and causing danger to the opposite and following vehicles and other traffic participants.

[0064] The block diagrams of the circuits, units, devices, apparatuses, equipment, and systems involved in the present disclosure are only illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these circuits, units, devices, apparatuses, equipment, and systems may be connected, arranged, and configured in any manner as long as the desired purpose can be achieved. The circuits, units, devices, and apparatuses involved in the present disclosure may be implemented in any suitable manner, such as by using a dedicated integrated circuit, a field programmable gate array (FPGA), etc., or may be implemented by using a general processing unit in combination with a program.

[0065] Those skilled in the art should understand that the above-mentioned specific embodiments are merely examples and not limitations, and various modifications, combinations, partial combinations and replacements may be made to the embodiments of the present disclosure according to design requirements and other factors. As long as they are within the scope of the attached claims or their equivalents, they belong to the scope of rights to be protected by the present disclosure.

Claims

1. A method for processing a sensor signal of a vehicle, comprising: Obtaining sensor signals within a predetermined time period, Determine a corresponding characteristic value according to the value of the sensor signal, wherein the characteristic value characterizes the stability of the current sensor signal, and Whether the sensor signal is abnormal is determined based on a comparison of the characteristic value with a predetermined characteristic threshold value, and if the sensor signal is abnormal, the value of the sensor signal is replaced by a substitute value.

2. The method according to claim 1, wherein: The feature threshold is determined according to a plurality of historical feature values ​​corresponding to the feature value.

3. The method according to claim 2, wherein: The characteristic threshold is determined according to a plurality of historical characteristic values ​​corresponding to the characteristic value, including: The feature threshold is determined according to the distribution of the plurality of historical feature values, so that most of the plurality of historical feature values ​​are smaller than the feature threshold.

4. The method according to claim 1, wherein: The substitute value is a previous value of the sensor signal or a predicted value based on the value of the sensor signal.

5. The method according to claim 4, wherein: In the case where the sensor signal is a distance signal, the predicted value is the sum of the value of the distance signal at the last moment and the predicted change, and the predicted change is the relative speed of the target object multiplied by the time interval to the last moment, and When the sensor signal is an angle signal, the predicted value is the sum of the angle signal value at the previous moment and the predicted change, and the predicted change is the relative angular velocity of the target object multiplied by the time interval to the previous moment.

6. The method according to claim 4, wherein: Set the abnormal persistence threshold. In a case where the duration of the abnormality of the sensor signal is greater than the abnormality duration threshold, the value of the previous sensor signal is used as a substitute value to replace the value of the sensor signal, and In a case where the duration of the abnormality of the sensor signal is shorter than the abnormality duration threshold, the predicted value replaces the value of the sensor signal as a substitute value.

7. The method according to claim 1, wherein: The characteristic values ​​and the historical characteristic values ​​include: the signal value of the sensor signal, the duration of a peak in the sensor signal, and the mean, dispersion, skewness, and kurtosis of the values ​​of the sensor signal in a predetermined period of time in the past.

8. The method according to claim 1, wherein: The sensor signal is an output signal of the vehicle-mounted camera.

9. The method according to claim 1, further comprising: determining whether the sensor signal is valid, In the case where the sensor signal is valid, determining a corresponding characteristic value according to the value of the sensor signal, In the case that the sensor signal is invalid, the duration of the invalidity of the sensor signal is compared with an invalidity duration threshold to determine whether to output the sensor signal.

10. The method according to claim 1, wherein: Determining a corresponding characteristic value according to the value of the sensor signal, and determining whether the sensor signal is abnormal according to a comparison between the characteristic value and a predetermined characteristic threshold, and replacing the value of the sensor signal by a substitute value when the sensor signal is abnormal, including: A transition duration of the sensor signal is determined according to the sensor signal, and when the transition duration is greater than the transition duration threshold, a previous sensor signal is output.

11. The method according to claim 1, wherein: Determining whether the sensor signal is abnormal according to a comparison between the characteristic value and a predetermined characteristic threshold, and replacing the value of the sensor signal with a substitute value when the sensor signal is abnormal, further comprising: When the sensor signal is normal, the change in the sensor signal is compared with a change threshold. When the change in the sensor signal is greater than the change threshold, a predicted value is output to replace the value of the sensor signal. When the change in the sensor signal is less than the change threshold, the value of the sensor signal is output.

12. The method according to claim 1, wherein: The obtained sensor signal includes a first sensor signal and a second sensor signal, When the value of the first sensor signal does not change, outputting the second sensor signal, When the value of the first sensor signal changes, the characteristic value of the second sensor signal is compared with a predetermined characteristic threshold to determine whether the current second sensor signal is abnormal, and when the second sensor signal is abnormal, the value of the second sensor signal is replaced by a substitute value.

13. The method according to claim 12, wherein: The first sensor signal includes different levels, wherein different levels represent different target object types. And the second sensor signal includes: a distance signal, a speed signal, an angle signal and an angular velocity signal of the target objects around the vehicle relative to the vehicle.

14. A computer-readable storage medium having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 13.

15. A camera device comprising the computer-readable storage medium according to claim 14.

16. A motor vehicle comprising a camera device according to claim 15.

Images