CN112344979B - Method and device for adjusting detection stability of sensor - Google Patents
Method and device for adjusting detection stability of sensor Download PDFInfo
- Publication number
- CN112344979B CN112344979B CN201910726045.XA CN201910726045A CN112344979B CN 112344979 B CN112344979 B CN 112344979B CN 201910726045 A CN201910726045 A CN 201910726045A CN 112344979 B CN112344979 B CN 112344979B
- Authority
- CN
- China
- Prior art keywords
- sensor
- information entropy
- sub
- target
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D18/00—Testing or calibrating apparatus or arrangements provided for in groups G01D1/00 - G01D15/00
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/40—Means for monitoring or calibrating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/211—Selection of the most significant subset of features
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Remote Sensing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Radar, Positioning & Navigation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The application provides a detection stability adjusting method of a sensor, which comprises the following steps: determining information entropy of the sensor according to data detected by the sensor in a preset time period; and when the information entropy of the sensor is determined not to meet the preset condition, adjusting the sensor parameters related to the detection stability so as to enable the information entropy of the sensor to meet the preset condition. Because the influence of the environmental condition on the performance of the sensor is expressed on the detection data output by the sensor, the information entropy of the sensor is determined according to the data detected by the sensor in a period of time to evaluate the current detection stability, so that the parameter related to the detection stability of the sensor is regulated when the evaluation is unstable, the environmental change can be indirectly sensed without adding any auxiliary sensor, and the sensor parameter is adaptively regulated to overcome the problem of the performance degradation of the sensor caused by the environmental change.
Description
Technical Field
The present disclosure relates to the field of sensors, and in particular, to a method and an apparatus for adjusting detection stability of a sensor.
Background
With the progress of technology, various sensors are increasingly used. In practical application, the performance of the sensor is related to the environment in which the sensor is located, and under different environmental conditions, the detection stability of the sensor is different, for example, the detection stability of the radar sensor under different environmental conditions (such as rainy, wind-blowing and other environmental conditions) is quite different.
The detection stability of the sensor is related to the sensor parameters, and the detection stability of the sensor is optimized by adjusting the sensor parameters under different environmental conditions, so that the influence of the environment on the detection stability of the sensor is overcome, and the detection capability of the sensor is ensured. At present, an auxiliary sensor is added to sense environmental changes, such as a temperature sensor, a humidity sensor and the like, and the sensor is adjusted by utilizing the parameters corresponding to the determined current environmental conditions, so that the detection stability of the sensor is optimal. However, this approach complicates the sensor structure and also increases the sensor cost.
Disclosure of Invention
In view of this, the present application provides a method and apparatus for adjusting the detection stability of a sensor, so as to solve the problems of complex structure and high cost of the sensor caused by adding an auxiliary sensor.
According to a first aspect of embodiments of the present application, there is provided a detection stability adjustment method of a sensor, the method including:
determining the information entropy of the sensor according to the data detected by the sensor in a preset time period;
and when the information entropy of the sensor is determined not to meet the preset condition, adjusting the sensor parameters related to the detection stability so as to enable the information entropy of the sensor to meet the preset condition.
According to a second aspect of embodiments of the present application, there is provided a detection stability adjustment device of a sensor, the device including:
the information entropy determining module is used for determining the information entropy of the sensor according to the data detected by the sensor in a preset time period;
and the parameter adjusting module is used for adjusting the sensor parameters related to the detection stability when the information entropy of the sensor is determined not to meet the preset condition, so that the information entropy of the sensor meets the preset condition.
According to a third aspect of embodiments of the present application, there is provided a sensor comprising a readable storage medium and a processor;
wherein the readable storage medium is for storing machine executable instructions;
the processor is configured to read the machine executable instructions on the readable storage medium and execute the instructions to implement the steps of the method of the first aspect.
By applying the embodiment of the application, the information entropy of the sensor is determined through the data detected by the sensor in the preset time period, and then when the information entropy of the sensor is determined to not meet the preset condition, the parameters related to the detection stability of the sensor are adjusted, so that the information entropy of the radar sensor meets the preset condition.
Based on the above description, since the influence of the environmental condition on the sensor performance is represented on the detection data output by the sensor, the information entropy of the sensor is determined according to the data detected by the sensor in a period of time to evaluate the current detection stability, so that the parameter related to the detection stability of the sensor can be adjusted when the evaluation is unstable, the environmental change can be indirectly sensed without adding any auxiliary sensor, and the sensor parameter can be adaptively adjusted to overcome the problem of the sensor performance degradation caused by the environmental change.
Drawings
FIG. 1 is a flow chart of an embodiment of a method for adjusting the detection stability of a sensor according to an exemplary embodiment of the present application;
FIG. 2A is a flow chart of an embodiment of another method for adjusting the detection stability of a sensor according to an exemplary embodiment of the present application;
FIG. 2B is a schematic view of a radar detection area according to the embodiment of FIG. 2A;
FIG. 3 is a hardware block diagram of a sensor according to an exemplary embodiment of the present application;
fig. 4 is a block diagram showing an embodiment of a detection stability adjusting device of a sensor according to an exemplary embodiment of the present application.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as detailed in the accompanying claims.
The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, third, etc. may be used herein to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first message may also be referred to as a second message, and similarly, a second message may also be referred to as a first message, without departing from the scope of the present application. The word "if" as used herein may be interpreted as "at … …" or "at … …" or "responsive to a determination", depending on the context.
The performance of each type of sensor is optimized by using different parameters under different environmental conditions. Taking a radar sensor as an example, parameters suitable for a sunny day can optimize performance under sunny day environmental conditions, parameters suitable for a rainy day can optimize performance under rainy day environmental conditions, and if parameters suitable for a sunny day are applied to a rainy day, the performance of the sensor is poor.
At present, a hardware mode is adopted, an auxiliary sensor is added to sense the environment, and the sensor parameters are adjusted according to the sensing result, so that the performance is optimal, but the hardware mode brings the following problems: the sensor has complex structure and high cost.
In order to solve the above problems, the present application proposes a method for adjusting the detection stability of a sensor, which determines the information entropy of the sensor according to the data detected by the sensor in a preset time period, and then adjusts the parameters related to the detection stability of the sensor when the information entropy of the sensor is determined to not meet the preset condition, so that the information entropy of the radar sensor meets the preset condition.
Based on the above description, since the influence of the environmental condition on the sensor performance is represented on the detection data output by the sensor, the information entropy of the sensor is determined according to the data detected by the sensor in a period of time to evaluate the current detection stability, so that the parameter related to the detection stability of the sensor can be adjusted when the evaluation is unstable, the environmental change can be indirectly sensed without adding any auxiliary sensor, and the sensor parameter can be adaptively adjusted to overcome the problem of the sensor performance degradation caused by the environmental change.
Fig. 1 is a flowchart of an embodiment of a method for adjusting the detection stability of a sensor according to an exemplary embodiment of the present application, where the sensor detection stability adjustment is adaptive adjustment of the sensor, so that the performance of the sensor can be optimized in different environments. As shown in fig. 1, the detection stability adjusting method of the sensor comprises the following steps:
step 101: and determining the information entropy of the sensor according to the data detected by the sensor in the preset time period.
The sensor collects original data according to a certain collection frequency, processes the collected original data each time through a built-in detection algorithm to obtain a data frame, and the data frame at least comprises position information of a detected target, so that the data detected by the sensor in a preset time period comprises a plurality of data frames.
Illustratively, the data frame may also include other information, such as object type information.
In the present application, in order to ensure the real-time performance of the sensor information entropy, the preset time period may be a period of time closest to the current system time. The longer the period, the more data frames are detected, the more accurate the information entropy determined by the plurality of data frames, but the evaluation instantaneity of the possible detection stability is comparatively low, so the preset period can be set according to practical experience.
Taking a camera sensor as an example, each time the camera collects an image, processing the image by using a built-in detection algorithm to obtain a data frame containing the position information of the detected target (namely, the position information of the target in the image), assuming that the preset time period is one minute nearest to the current system time, and the frame rate of the camera is usually 25 frames/second, so that 25 data frames can be detected per second, and the camera can detect 1500 data frames in the nearest one minute.
Taking a radar sensor as an example, each time the radar acquires data, processing the data by utilizing a built-in detection algorithm to obtain a data frame containing the position information of a detected target (namely the position information of the target from the radar), and assuming that the preset time period is one minute nearest to the current system time, acquiring 2000 data by the radar within one minute, so that the radar can detect 2000 data frames within the nearest one minute.
It should be noted that, the final target detected by the sensor is usually represented by a target point cloud, so the detected target in each data frame may be the final target represented by the target point cloud, or may be the target point obtained during the processing of the detection algorithm, and the specific form of the detected target is not limited in this application.
Based on the above description, the combination of the hardware acquisition process and the processing process of the built-in processing algorithm of the sensor shows the total detection stability of the sensor. For measurement of detection stability, since the influence of environmental conditions on the performance of the sensor is represented on the detection data output by the sensor, the information entropy determined by using the data detected by the sensor in the last period of time can be very suitable for measuring the current detection stability of the sensor.
How to determine the information entropy of the sensor based on the data detected by the sensor can be found in the following description of the embodiment shown in fig. 2A, which is not described in detail herein.
Step 102: and when the information entropy of the sensor is determined not to meet the preset condition, adjusting the sensor parameters related to the detection stability so as to enable the information entropy of the sensor to meet the preset condition.
In an embodiment, for a process of determining that the information entropy of the sensor does not meet the preset condition, the information entropy of the sensor is too large, which indicates that the sensor is too weak in detection stability and too strong in detection capability, and the information entropy of the sensor is too small, which indicates that the sensor is too strong in detection stability and too weak in detection capability, so that the information entropy of the sensor is too large or too small, which indicates that the sensor parameters are not suitable for the current environmental condition, so that the sensor parameters can be judged by comparing the information entropy with the preset threshold range.
The implementation process can be as follows: if the information entropy of the sensor is not in the preset threshold range, determining that the information entropy of the sensor does not meet the preset condition.
The preset threshold range is used for representing an information entropy range with good detection stability, and can be set according to actual experience. If the information entropy is in a preset threshold range, the sensor detects that the stability is optimal, the sensor parameters are suitable for the current environmental condition, and if the information entropy is not in the preset threshold range, the sensor parameters are unsuitable for the current environmental condition.
In an embodiment, for a process of adjusting a sensor parameter related to the detected stability, if the information entropy of the sensor is greater than a preset threshold range, adjusting the sensor parameter related to the detected stability according to a first preset policy so that the information entropy of the sensor is within the preset threshold range; and if the information entropy of the sensor is smaller than the preset threshold range, adjusting the sensor parameters related to the detection stability according to a second preset strategy so that the information entropy of the sensor is adjusted in the direction of weakening the detection stability within the preset threshold range.
Any sensor has an ideal sensitive range, in which the sensor detects the optimal stability, when the sensor is not in the sensitive range, if the sensor is too sensitive, the sensor detects the target result without the target, the detection stability is too weak, and if the sensor is too slow, the sensor cannot detect the target, the detection stability is too strong, therefore, the preset threshold range is used for representing the evaluation parameter range with better detection stability, and can be set according to practical experience. In the sensor parameter adjusting process, if the information entropy is larger than a preset threshold range, the sensor is excessively sensitive, the detection capability is excessively strong, and the detection stability is excessively weak, adjustment is required according to a first preset strategy, so that the sensor parameter is adjusted in the direction for enhancing the detection stability, the information entropy of the sensor can be in the preset threshold range, if the evaluation parameter is smaller than the preset threshold range, the sensor is excessively dull, the detection capability is excessively weak, and the detection stability is excessively strong, adjustment is required according to a second preset strategy, so that the sensor parameter is adjusted in the direction for weakening the detection stability, and the information entropy of the sensor can be in the preset threshold range.
In this application, the sensor parameters include at least two types of hardware parameters and built-in algorithm parameters, and each type of parameters includes a plurality of different parameters.
For example, a first parameter set and a second parameter set may be included for a hardware parameter type, and a third parameter set and a fourth parameter set may be included for a built-in algorithm parameter type.
The first preset strategy may be to reduce the parameters in the first parameter set, increase the parameters in the second parameter set, reduce the parameters in the third parameter set, and increase the parameters in the fourth parameter set, so as to enhance the detection stability of the sensor; the second preset strategy may be to increase the parameters in the first parameter set, decrease the parameters in the second parameter set, increase the parameters in the third parameter set, and decrease the parameters in the fourth parameter set to decrease the detection stability of the sensor.
It should be noted that, during each adjustment, all parameters of the sensor may be adjusted, or some parameters may be adjusted, and the number of parameters to be adjusted each time is not limited in this application.
For example, the sensor parameters may be adjusted in a fixed step size, and different parameters may be adjusted in different fixed step sizes, and the fixed step size corresponding to each type of parameter may be set according to practical experience.
Taking a camera sensor as an example, the camera sensor may have sensitivity for a first parameter set included in a hardware parameter type in the camera, may have exposure time for a second parameter set, may have confidence of a deep learning algorithm for a third parameter set included in a built-in algorithm parameter type, and may have a euclidean distance ratio threshold of a SIFT algorithm for a fourth parameter set. When the sensor information entropy is larger than a preset threshold range, the sensitivity in the first parameter set can be reduced by a fixed step length, the exposure time in the second parameter set can be increased by a fixed step length, the confidence in the third parameter set is increased by a fixed step length, the Euclidean distance ratio threshold in the fourth parameter set is reduced by a fixed step length, so that the detection capability is weakened, the detection stability is enhanced, the detection stability is enabled to be insensitive, and when the sensor information entropy is smaller than the preset threshold range, the sensitivity in the first parameter set can be increased by a fixed step length, the exposure time in the second parameter set can be reduced by a fixed step length, the confidence in the third parameter set is reduced by a fixed step length, and the Euclidean distance ratio threshold in the fourth parameter set is increased by a fixed step length, so that the detection capability is enhanced, the detection stability is weakened, and the detection stability is enabled to be sensitive.
Taking a radar sensor as an example, for a first parameter set included in a hardware parameter type in the radar, there may be a amplification factor of an amplifier and a filtering bandwidth of a filter, a second parameter set may be a attenuation factor of an attenuator, and for a third parameter set included in a built-in algorithm parameter type, there may be a minimum clustering point number and a CFAR threshold (Constant False-Alarm Rate) in a clustering algorithm (such as a k-means algorithm, a mean-shift algorithm, etc.). When the information entropy of the sensor is larger than a preset threshold range, the amplification factor of the amplifier in the first parameter set and the filtering bandwidth of the filter can be reduced by a fixed step length, the attenuation factor of the attenuator in the second parameter set is increased by the fixed step length, the clustering point number in the third parameter set and the CFAR threshold value are both increased by the fixed step length so as to weaken the detection capability and enhance the detection stability, so that the sensor becomes insensitive.
In the embodiment of the application, the information entropy of the sensor is determined according to the data detected by the sensor in the preset time period, and then when the information entropy of the sensor is determined to not meet the preset condition, the sensor parameters related to the detection stability are adjusted so that the information entropy of the sensor meets the preset condition.
Based on the above description, since the influence of the environmental condition on the performance of the sensor is represented on the detection data output by the sensor, the current detection stability of the sensor can be evaluated according to the data detected by the sensor, so that the parameter related to the detection stability of the sensor can be adjusted when the evaluation is unstable, the environmental change can be indirectly sensed without adding any auxiliary sensor, and the sensor parameter can be adaptively adjusted to overcome the problem of reduced performance of the sensor caused by the environmental change.
Fig. 2A is a flowchart of an embodiment of another method for adjusting the detection stability of a sensor according to an exemplary embodiment of the present application, based on the embodiment shown in fig. 1, the present embodiment is exemplified by how to determine the information entropy of the sensor according to the data detected by the sensor in a preset period of time, and the sensor is taken as a radar sensor, and the detected data includes N data frames, as shown in fig. 2A, where the method for adjusting the detection stability of a sensor further includes:
step 201: the detection area of the radar sensor is divided into M sub-areas.
The detection area can be divided according to the size of the preset subareas, all subareas obtained through division are relatively independent, the number M of subareas obtained through division is related to the size of the detection area and the size of the preset subareas, and under the condition that the size of the preset subareas is fixed, the larger the detection area is, the larger M is.
Different types of sensors can be divided by adopting preset subareas with different shapes, and the subarea division is introduced by taking radar as an example:
since it detects the position of the target in the real coordinate system, the detection area of the radar is a sector area composed of the detection distance and the detection angle range, and the sector area can be divided by adopting a sector ring sub-area.
The dividing process may be to determine a detection area of the radar according to a detection distance and a detection angle range of the radar, and divide the detection area into M fan ring sub-areas according to a preset fan ring sub-area size.
Wherein the sector ring sub-area size includes a sector ring radius and a sector ring angle.
As shown in fig. 2B, for a schematic diagram of the detection area division of the radar, the maximum detection distance of the radar in the vertical direction is 120 meters, the detection angle range in the horizontal direction is plus or minus 75 degrees, and if the sector ring sub-area is set to be 20 meters in radius and 15 degrees, then m= (120/20) = (75+75)/15 ] =60 can be obtained.
The above-described division of the detection area of the radar is merely an exemplary illustration, and the present application is not limited to a specific division of the detection area of other sensors.
Step 202: and aiming at each sub-area, obtaining N target numbers from the target numbers of the detected targets of which the statistical position information belongs to the sub-area in each data frame, and determining the information entropy of the sub-area according to the N target numbers.
In an embodiment, for the process of determining the information entropy of the sub-region according to the N target numbers obtained by statistics, a target number with a different value may be selected from the N target numbers, and for each selected target number, the probability that the target number appears in the N target numbers is determined, and then the information entropy of the sub-region is determined according to the probability that each selected target number appears in the N target numbers.
Wherein, the probability formula of the occurrence of a certain selected target number in the N target numbers is as follows: (equation 1)
p i ＝t i /N
Wherein p is i Representing the probability of occurrence of the ith selected target number, t i Representing the number of times the i-th selected target number appears in the N target numbers.
The information entropy formula for determining the subregion may be: (equation 2)
Wherein H is j Information entropy indicating the jth sub-region, and n indicating the total number of target numbers having different values from each other.
In an alternative embodiment, in order to reduce the amount of calculation of the information entropy, the number of targets detected by the sub-region may be classified in advance.
For example, in a certain application scenario, the maximum number of objects that can be detected in a sub-area is 20, and if the interval between the classification levels is 5, the classification may be divided into five or more levels of 0 to 4, 5 to 9, 10 to 14, 15 to 19, and 20.
Based on this, for the process of determining the information entropy of the sub-region according to the N target numbers obtained by statistics, the number of target numbers belonging to the level may be counted as the number of occurrences of the level in the N target numbers for each level, the occurrence probability of the level may be determined according to the number of occurrences of the level in the N target numbers, and finally the information entropy of the sub-region may be determined according to the occurrence probability of each level.
Wherein, if the information entropy of the subareas is determined by a hierarchical manner, the above formula (1) is the probability of occurrence of the ith level, t in formula (1) i Representing the number of times the ith level appears in the N target numbers. N in the above formula (2) represents the total number of ranks.
Step 203: and determining the information entropy of the radar sensor according to the information entropy of each sub-area.
In an embodiment, since the sub-regions are independent from each other, each sub-region is considered to be an independent event, the sum of the information entropies of the sub-regions can be determined as the information entropy of the radar sensor, and the information entropy expression formula is (formula 3):
wherein H is j Information entropy indicating the jth sub-region, and M indicating the total number of sub-regions.
According to the formula (1), the formula (2) and the formula (3), the minimum value of the information entropy is 0, which indicates that the sensor has no target detection all the time, and the maximum value is M x logn.
In general, the information entropy represents the disorder degree of the system, the information entropy is too large to represent the disorder degree of the system and the sensor detects the stability to be weak, the information entropy is too small to represent the disorder degree of the system and the sensor detects the stability to be strong. Based on this, the present embodiment utilizes the information entropy to measure the detection stability of the sensor system to realize the evaluation of the detection stability.
Step 204: and if the information entropy of the radar sensor is larger than a preset threshold range, adjusting sensor parameters related to the detection stability according to a first preset strategy so that the information entropy of the radar sensor is in the preset threshold range.
Step 205: and if the information entropy of the radar sensor is smaller than the preset threshold range, adjusting sensor parameters related to the detection stability according to a second preset strategy so that the information entropy of the radar sensor is in the preset threshold range.
For the above-mentioned processes of step 204 and step 205, the minimum value of the information entropy derived from the above-mentioned derivation is 0, which indicates that the detection stability of the sensor is too strong, and the maximum value is M log n, which indicates that the detection stability of the sensor is too weak, so that the preset threshold range is a range greater than 0 and less than M log n.
In an embodiment, since the parameters of the sensor may be adjusted in regions, when the information entropy of the sensor is within a preset threshold range, a sub-region affecting the detection stability of the sensor may be further extracted, and parameters belonging to the sub-region may be adjusted to optimize the detection stability of the sensor.
The implementation process can be as follows: and under the condition that the information entropy of the sensor meets the preset condition, for each sub-area, if the ratio of the information entropy of the sub-area to the information entropy of the sensor is larger than a preset threshold value, adjusting the sensor parameters which belong to the sub-area and are related to the detection stability or not processing the data which belong to the sub-area.
The preset threshold may be set according to practical experience, for example, 0.8. If the ratio of the information entropy of the subarea to the information entropy of the sensor is larger than a preset threshold, the detection capability of the subarea is too strong, the detection stability is too weak, the subarea is a main influencing factor of the detection stability of the sensor, and parameters belonging to the subarea need to be adjusted in the direction of enhancing the detection stability or shielding treatment is carried out on the subarea.
For example, for the amplification factor of an amplifier, the filtering bandwidth of a filter, the attenuation factor of an attenuator, the number of clustering points, a CFAR threshold value and the like in the radar, if the ratio of the information entropy of a certain subarea to the information entropy of a sensor is greater than a preset threshold value, the amplification factor and the filtering bandwidth of the subarea can be reduced by a fixed step length, the attenuation factor of the attenuator is increased by the fixed step length, and the number of clustering points and the CFAR threshold value of the subarea are increased by the fixed step length, so that the detection stability is enhanced, the detection capability is weakened, and the detection capability is made insensitive.
It should be noted that, the information entropy of the camera sensor may also be determined by dividing the detection area of the camera into a plurality of sub-areas, and the detection area of the camera may be an image area because the camera detects the pixel position of the target in the image and belongs to the target detection performed on the pixel level. Since the image area is rectangular, the image area can be divided by rectangular subareas.
Thus, the flow of the embodiment shown in fig. 2A is completed, and the embodiment determines the information entropy of the sensor by dividing the subareas, and adjusts the parameters of the sensor by the determination result of the information entropy.
FIG. 3 is a hardware block diagram of a sensor according to an exemplary embodiment of the present application, the sensor comprising: a communication interface 301, a processor 302, a machine-readable storage medium 303, and a bus 304; wherein the communication interface 301, the processor 302 and the machine-readable storage medium 303 perform communication with each other via a bus 304. The processor 302 may perform the method of sensor stability detection described above by reading and executing machine-executable instructions in the machine-readable storage medium 303 corresponding to the control logic of the method of sensor stability detection, the details of which are not further described herein with reference to the above embodiments.
The machine-readable storage medium 303 referred to in this application may be any electronic, magnetic, optical, or other physical storage device that may contain or store information, such as executable instructions, data, or the like. For example, a machine-readable storage medium may be: volatile memory, nonvolatile memory, or similar storage medium. In particular, the machine-readable storage medium 303 may be RAM (Radom Access Memory, random access memory), flash memory, a storage drive (e.g., hard drive), any type of storage disk (e.g., optical disk, DVD, etc.), or a similar storage medium, or a combination thereof.
Fig. 4 is a structural diagram of an embodiment of a detection stability adjusting device of a sensor according to an exemplary embodiment of the present application, and as shown in fig. 4, the detection stability adjusting device of the sensor includes:
an information entropy determining module 410, configured to determine an information entropy of the sensor according to data detected by the sensor in a preset time period;
and the parameter adjusting module 420 is configured to adjust the sensor parameter related to the detected stability when it is determined that the information entropy of the sensor does not meet the preset condition, so that the information entropy of the sensor meets the preset condition.
In an alternative implementation manner, the data comprises N data frames, each data frame comprises position information of a detected target, and the sensor is a radar sensor;
the information entropy determining module 410 is specifically configured to divide a detection area of the radar sensor into M sub-areas; for each sub-region, N target numbers are obtained from the target numbers of the detected targets of which the statistical position information belongs to the sub-region in each data frame, and the information entropy of the sub-region is determined according to the N target numbers; and determining the information entropy of the radar sensor according to the information entropy of each sub-area.
In an optional implementation manner, the information entropy determining module 410 is specifically configured to select, in determining the information entropy of the sub-region according to the N target numbers, a target number with a different value from the N target numbers; determining the probability of the target number in the N target numbers aiming at each selected target number; and determining the information entropy of the subarea according to the probability of each selected target number in the N target numbers.
In an alternative implementation, the apparatus further comprises (not shown in fig. 4):
the subarea adjusting module is used for comparing the ratio of the information entropy of each subarea to the information entropy of the radar sensor with a preset threshold value for each subarea when the information entropy of the sensor meets a preset condition; and if the ratio is greater than a preset threshold value, adjusting the sensor parameters which belong to the subarea and are related to the detection stability or not processing the data which belong to the subarea.
In an optional implementation manner, the parameter adjustment module 420 is specifically configured to, in determining that the information entropy of the sensor does not meet the preset condition, determine that the information entropy of the sensor does not meet the preset condition if the information entropy of the sensor is not within the preset threshold range;
the parameter adjustment module 420 is further specifically configured to, in a process of adjusting the sensor parameter related to the detected stability, adjust the sensor parameter related to the detected stability according to a first preset policy if the information entropy of the sensor is greater than a preset threshold range, so that the information entropy of the sensor is within the preset threshold range; and if the information entropy of the sensor is smaller than the preset threshold range, adjusting the sensor parameters related to the detection stability according to a second preset strategy so that the information entropy of the sensor is in the preset threshold range.
In an alternative implementation, the sensor parameters include at least two types of hardware parameters and built-in algorithm parameters.
The implementation process of the functions and roles of each unit in the above device is specifically shown in the implementation process of the corresponding steps in the above method, and will not be described herein again.
For the device embodiments, reference is made to the description of the method embodiments for the relevant points, since they essentially correspond to the method embodiments. The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purposes of the present application. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
The foregoing description of the preferred embodiments of the present invention is not intended to limit the invention to the precise form disclosed, and any modifications, equivalents, improvements and alternatives falling within the spirit and principles of the present invention are intended to be included within the scope of the present invention.
Claims (8)
1. A method for adjusting detection stability of a sensor, the method comprising:
determining the information entropy of the sensor according to the data detected by the sensor in a preset time period, wherein the information entropy comprises the following steps: determining the information entropy of the sensor according to the detected target number in a plurality of data frames detected by the sensor in a preset time period; the information entropy is inversely related to the detection stability of the target number of the sensor; the sensor includes a radar sensor;
the data comprises N data frames, and each data frame comprises position information of a detected target;
when the sensor is a radar sensor, determining the information entropy of the sensor according to the data detected by the sensor in a preset time period, including: dividing a detection area of the radar sensor into M sub-areas; for each sub-region, N target numbers are obtained from the target numbers of the detected targets of which the statistical position information belongs to the sub-region in each data frame, and the information entropy of the sub-region is determined according to the N target numbers; determining the information entropy of the radar sensor according to the information entropy of each sub-area;
and when the information entropy of the sensor is determined not to meet the preset condition, adjusting the sensor parameters related to the target number detection stability so as to enable the information entropy of the sensor to meet the preset condition.
2. The method of claim 1, wherein determining the information entropy of the sub-region based on the N target numbers comprises:
selecting target numbers with different values from the N target numbers;
determining the probability of the target number in the N target numbers aiming at each selected target number;
and determining the information entropy of the subarea according to the probability of each selected target number in the N target numbers.
3. The method of claim 1, wherein if the information entropy of the sensor satisfies a preset condition, the method further comprises:
comparing the ratio of the information entropy of each sub-region to the information entropy of the radar sensor with a preset threshold value for each sub-region;
and if the ratio is greater than a preset threshold value, adjusting the sensor parameters which belong to the subarea and are related to the detection stability or not processing the data which belong to the subarea.
4. The method of claim 1, wherein determining that the information entropy of the sensor does not satisfy a preset condition comprises:
if the information entropy of the sensor is not in the preset threshold range, determining that the information entropy of the sensor does not meet the preset condition;
adjusting a sensor parameter associated with a detected stability, comprising:
if the information entropy of the sensor is larger than a preset threshold range, adjusting sensor parameters related to detection stability according to a first preset strategy so that the information entropy of the sensor is in the preset threshold range;
and if the information entropy of the sensor is smaller than the preset threshold range, adjusting the sensor parameters related to the detection stability according to a second preset strategy so that the information entropy of the sensor is in the preset threshold range.
5. The method of any of claims 1-4, wherein the sensor parameters include at least two types of hardware parameters and built-in algorithm parameters.
6. A detection stability adjustment device for a sensor, the device comprising:
the information entropy determining module is configured to determine, according to data detected by the sensor in a preset time period, information entropy of the sensor, and includes: determining the information entropy of the sensor according to the detected target number in a plurality of data frames detected by the sensor in a preset time period; the information entropy is inversely related to the detection stability of the target number of the sensor; the sensor includes a radar sensor;
the data comprises N data frames, each data frame comprises position information of a detected target, and the sensor is a radar sensor;
the information entropy determining module is specifically configured to divide a detection area of the radar sensor into M sub-areas; for each sub-region, N target numbers are obtained from the target numbers of the detected targets of which the statistical position information belongs to the sub-region in each data frame, and the information entropy of the sub-region is determined according to the N target numbers; determining the information entropy of the radar sensor according to the information entropy of each sub-area;
and the parameter adjusting module is used for adjusting the sensor parameters related to the target number detection stability when the information entropy of the sensor is determined not to meet the preset condition, so that the information entropy of the sensor meets the preset condition.
7. The apparatus according to claim 6, wherein the information entropy determining module is specifically configured to select, in determining the information entropy of the sub-region according to the N target numbers, a target number having a different value from the N target numbers; determining the probability of the target number in the N target numbers aiming at each selected target number; and determining the information entropy of the subarea according to the probability of each selected target number in the N target numbers.
8. A sensor, the sensor comprising a readable storage medium and a processor;
wherein the readable storage medium is for storing machine executable instructions;
the processor being configured to read the machine executable instructions on the readable storage medium and execute the instructions to implement the steps of the method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910726045.XA CN112344979B (en) | 2019-08-07 | 2019-08-07 | Method and device for adjusting detection stability of sensor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910726045.XA CN112344979B (en) | 2019-08-07 | 2019-08-07 | Method and device for adjusting detection stability of sensor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112344979A CN112344979A (en) | 2021-02-09 |
| CN112344979B true CN112344979B (en) | 2023-06-30 |
Family
ID=74366693
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910726045.XA Active CN112344979B (en) | 2019-08-07 | 2019-08-07 | Method and device for adjusting detection stability of sensor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112344979B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113011712B (en) * | 2021-02-25 | 2024-01-19 | 长安大学 | Driver driving stability assessment method based on Euclidean distance and information entropy |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014013180A (en) * | 2012-07-04 | 2014-01-23 | Mitsubishi Electric Corp | Radar processor |
| JP2014016190A (en) * | 2012-07-06 | 2014-01-30 | Mitsubishi Electric Corp | Radar device |
| CN107728124A (en) * | 2017-09-08 | 2018-02-23 | 中国电子科技集团公司信息科学研究院 | A kind of more radar dynamic regulating methods and device based on comentropy |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5668778A (en) * | 1996-07-09 | 1997-09-16 | The United States Of America As Represented By The Secretary Of The Navy | Method for detecting acoustic signals from an underwater source |
| CN102116658A (en) * | 2010-10-19 | 2011-07-06 | 中国矿业大学(北京) | Method for detecting bin level based on image entropy |
| GB201116961D0 (en) * | 2011-09-30 | 2011-11-16 | Bae Systems Plc | Fast calibration for lidars |
| CN103237173A (en) * | 2013-04-28 | 2013-08-07 | 中国空间技术研究院 | Adaptive quick focusing device and method for optical camera |
| CN103417176B (en) * | 2013-08-01 | 2015-02-18 | 深圳先进技术研究院 | Capsule endoscope and automatic focusing method thereof |
| CN104766073A (en) * | 2015-04-28 | 2015-07-08 | 天津理工大学 | Self-adaptive hand back vein image collecting system |
| US9972067B2 (en) * | 2016-10-11 | 2018-05-15 | The Boeing Company | System and method for upsampling of sparse point cloud for 3D registration |
| CN107707917B (en) * | 2017-08-09 | 2019-10-29 | 南京邮电大学 | A kind of video adaptive sample rate setting method based on comentropy |
| CN107742113B (en) * | 2017-11-08 | 2019-11-19 | 电子科技大学 | One kind being based on the posterior SAR image complex target detection method of destination number |
| CN108834252B (en) * | 2018-04-28 | 2020-04-21 | 东华大学 | Self-adaptive light source illumination system and method for fine 3D reconstruction of cultural relics |
| CN108680552A (en) * | 2018-07-13 | 2018-10-19 | 山东省科学院海洋仪器仪表研究所 | Marine optics dissolved oxygen sensor nominal data blending algorithm based on comentropy |
| RU184465U9 (en) * | 2018-07-18 | 2018-12-06 | Акционерное общество "Федеральный научно-производственный центр "Нижегородский научно-исследовательский институт радиотехники" | False target selection device |
-
2019
- 2019-08-07 CN CN201910726045.XA patent/CN112344979B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014013180A (en) * | 2012-07-04 | 2014-01-23 | Mitsubishi Electric Corp | Radar processor |
| JP2014016190A (en) * | 2012-07-06 | 2014-01-30 | Mitsubishi Electric Corp | Radar device |
| CN107728124A (en) * | 2017-09-08 | 2018-02-23 | 中国电子科技集团公司信息科学研究院 | A kind of more radar dynamic regulating methods and device based on comentropy |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112344979A (en) | 2021-02-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10636129B2 (en) | Wind motion threshold image analysis system | |
| CN109035299B (en) | Target tracking method and device, computer equipment and storage medium | |
| CN114092820B (en) | Target detection method and moving target tracking method applying same | |
| JP6891972B2 (en) | River risk assessment device, river risk assessment method, and program | |
| EP3618422B1 (en) | Method and apparatus for calculating brightness value of region of interest | |
| CN106971401B (en) | Multi-target tracking device and method | |
| CN105631418A (en) | People counting method and device | |
| US20220026277A1 (en) | Method, apparatus and system for passive infrared sensor framework | |
| CN108986097A (en) | A kind of camera lens hazes condition detection method, computer installation and readable storage medium storing program for executing | |
| KR20210027778A (en) | Apparatus and method for analyzing abnormal behavior through object detection and tracking | |
| CN112508803B (en) | Denoising method and device for three-dimensional point cloud data and storage medium | |
| CN112344979B (en) | Method and device for adjusting detection stability of sensor | |
| CN103456009A (en) | Method, device and monitoring system for target detection | |
| CN110969200A (en) | Image target detection model training method and device based on consistency negative sample | |
| US6614917B1 (en) | Dynamic process for identifying objects in multi-dimensional data | |
| CN110542482B (en) | Blind pixel detection method and device and electronic equipment | |
| CN107844734A (en) | Monitoring objective determines method and device, video frequency monitoring method and device | |
| CN116243273A (en) | Photon counting laser radar data filtering method and device | |
| CN115453563A (en) | Three-dimensional space dynamic object identification method, system and storage medium | |
| CN116049158A (en) | Soil information acquisition method based on multi-sensor data fusion algorithm | |
| CN113784119B (en) | Focusing detection method and device and electronic equipment | |
| JP2020160901A (en) | Object tracking device and object tracking method | |
| KR101232185B1 (en) | Device and method for monitoring water level | |
| CN113705672A (en) | Threshold value selection method, system and device for image target detection and storage medium | |
| CN111126106B (en) | Lane line identification method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |