Perception multi-target performance statistical method and device and storage medium

Abstract

The invention provides a perception multi-target performance statistical method and device and a storage medium, and the method comprises the steps: carrying out the perception estimation of a perception signal, and determining a perception two-dimensional diagram; performing perception multi-target identification on the perception two-dimensional graph to obtain a plurality of perception estimation targets; and performing performance statistics on the plurality of perception estimation targets, and determining a perception multi-target performance statistics result. According to the sensing multi-target performance statistical method and device and the storage medium provided by the invention, firstly, the sensing estimation is performed on the sensing signal, the sensing two-dimensional diagram is determined, then the sensing multi-target identification is performed on the sensing two-dimensional diagram, the plurality of sensing estimation targets are obtained, and finally the performance statistics is performed on the plurality of sensing estimation targets. Therefore, the actual scene requirement of sensing multiple targets is met.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a method, device and storage medium for perceiving multi-objective performance statistics. Background Art

[0002] The synaesthesia integrated system is oriented to B5G and 6G. The perception function of the synaesthesia integrated system can effectively perceive the surrounding environment and the state of objects, and further assist communication to improve the overall performance of the system. The main perception parameters include distance, speed, angle, etc., among which the angle includes the vertical angle of arrival (Zenith of Arrival, ZOA) and the horizontal angle of arrival (Azimuth of Arrival, AOA).

[0003] For the synaesthesia integrated system, currently only single-target performance statistics can be achieved. Even if there are multiple targets in the environment, the target with the best performance is usually selected for performance statistics, which does not meet the performance statistics requirements of perceiving multiple targets. After perceiving multiple targets, it is necessary to design a corresponding multi-target performance statistics method to verify the reliability of the system design or perception algorithm. Summary of the invention

[0004] The embodiments of the present application provide a method, device and storage medium for perceiving multi-objective performance statistics, so as to solve the technical problem that the related art cannot meet the demand for statistics on multi-objective performance.

[0005] In a first aspect, an embodiment of the present application provides a method for perceiving multi-objective performance statistics, including:

[0006] Performing perception estimation on the perception signal to determine a perception two-dimensional map;

[0007] Performing perceptual multi-target recognition on the perceptual two-dimensional image to obtain multiple perceptual estimation targets;

[0008] The performance statistics of multiple perception estimation targets are performed to determine the perception multi-target performance statistics results.

[0009] In some embodiments, performing performance statistics on multiple perception estimation targets and determining a perception multi-target performance statistics result includes:

[0010] After multiple multi-target matching and difference threshold judgment, the final remaining difference set is obtained;

[0011] The perceptual multi-objective performance statistics are determined based on the final remaining difference set.

[0012] In some embodiments, performing multi-target matching and performing difference threshold determination includes:

[0013] Generate a perception estimation multi-target matrix, and determine a difference matrix between the perception estimation multi-target matrix and the perception true multi-target matrix;

[0014] Matching the perceived estimated multi-targets and the perceived real multi-targets based on the difference matrix to determine a second perceived estimated multi-target vector, a second perceived real multi-target vector, and a difference vector;

[0015] Based on a preset difference threshold, the differences in the matched difference vector that are greater than the difference threshold are removed, the perceived estimated targets corresponding to the differences in the second perceived estimated multi-target vector, and the perceived real targets corresponding to the differences in the second perceived real multi-target vector.

[0016] In some embodiments, generating a perceptual estimation multi-objective matrix includes:

[0017] Determining a first perceptual estimation multi-target vector based on the perceptual estimation result;

[0018] The first perceptual estimation multi-target vector is repeated M rows to generate a perceptual estimation multi-target matrix; wherein M represents the number of perceived real multi-targets.

[0019] In some embodiments, performing multi-target matching and performing difference threshold determination further includes:

[0020] The preset first perceived true multi-target vector is transposed and repeated N columns to generate a perceived true multi-target matrix; wherein N represents the number of perceived estimated multi-targets.

[0021] In some embodiments, determining the perceptual multi-objective performance statistics based on the final remaining difference set includes:

[0022] Based on the final remaining difference set, determine the number of targets L that exist and are successfully estimated D , the number of targets detected but without true value L FA and the number of targets L that exist but are not detected MD ;

[0023] Based on the L D , the L FA and the L MD Determine the perceptual multi-objective performance statistics.

[0024] In some embodiments, the perceived multi-objective performance statistics include one or more of the following:

[0025] Perceptual accuracy;

[0026] Detection success rate;

[0027] False alarm rate;

[0028] Missed detection rate.

[0029] In some embodiments, the method further comprises:

[0030] A perceptual estimation algorithm used for perceptual estimation is adjusted based on perceptual multi-objective performance statistics.

[0031] In some embodiments, the method further comprises:

[0032] The time-frequency resources and / or coding sequences used to transmit the perception signal are adjusted based on the perception multi-objective performance statistics.

[0033] In some embodiments, the method further comprises:

[0034] The threshold of the perceptual recognition algorithm used for perceptual multi-target recognition is adjusted based on the perceptual multi-target performance statistical results.

[0035] In a second aspect, an embodiment of the present application provides an electronic device, including a memory, a transceiver, and a processor;

[0036] A memory for storing a computer program; a transceiver for transmitting and receiving data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations:

[0037] Performing perception estimation on the perception signal to determine a perception two-dimensional map;

[0038] Performing perceptual multi-target recognition on the perceptual two-dimensional image to obtain multiple perceptual estimation targets;

[0039] The performance statistics of multiple perception estimation targets are performed to determine the perception multi-target performance statistics results.

[0040] In some embodiments, performing performance statistics on multiple perception estimation targets and determining a perception multi-target performance statistics result includes:

[0041] After multiple multi-target matching and difference threshold judgment, the final remaining difference set is obtained;

[0042] The perceptual multi-objective performance statistics are determined based on the final remaining difference set.

[0043] In some embodiments, performing multi-target matching and performing difference threshold determination includes:

[0044] Generate a perception estimation multi-target matrix, and determine a difference matrix between the perception estimation multi-target matrix and the perception true multi-target matrix;

[0045] Matching the perceived estimated multi-targets and the perceived real multi-targets based on the difference matrix to determine a second perceived estimated multi-target vector, a second perceived real multi-target vector, and a difference vector;

[0046] Based on a preset difference threshold, the differences in the matched difference vector that are greater than the difference threshold are removed, the perceived estimated targets corresponding to the differences in the second perceived estimated multi-target vector, and the perceived real targets corresponding to the differences in the second perceived real multi-target vector.

[0047] In some embodiments, generating a perceptual estimation multi-objective matrix includes:

[0048] Determining a first perceptual estimation multi-target vector based on the perceptual estimation result;

[0049] The first perceptual estimation multi-target vector is repeated M rows to generate a perceptual estimation multi-target matrix; wherein M represents the number of perceived real multi-targets.

[0050] In some embodiments, performing multi-target matching and performing difference threshold determination further includes:

[0051] The preset first perceived true multi-target vector is transposed and repeated N columns to generate a perceived true multi-target matrix; wherein N represents the number of perceived estimated multi-targets.

[0052] In some embodiments, determining the perceptual multi-objective performance statistics based on the final remaining difference set includes:

[0053] Based on the final remaining difference set, determine the number of targets L that exist and are successfully estimated D , the number of targets detected but without true value L FA and the number of targets L that exist but are not detected MD ;

[0054] Based on the L D , the L FA and the L MD Determine the perceptual multi-objective performance statistics.

[0055] In some embodiments, the perceived multi-objective performance statistics include one or more of the following:

[0056] Perceptual accuracy;

[0057] Detection success rate;

[0058] False alarm rate;

[0059] Missed detection rate.

[0060] In some embodiments, the processor is further configured to read the computer program in the memory and perform the following operations:

[0061] A perceptual estimation algorithm used for perceptual estimation is adjusted based on perceptual multi-objective performance statistics.

[0062] In some embodiments, the processor is further configured to read the computer program in the memory and perform the following operations:

[0063] The time-frequency resources and / or coding sequences used to transmit the perception signal are adjusted based on the perception multi-objective performance statistics.

[0064] In some embodiments, the processor is further configured to read the computer program in the memory and perform the following operations:

[0065] The threshold of the perceptual recognition algorithm used for perceptual multi-target recognition is adjusted based on the perceptual multi-target performance statistical results.

[0066] In a third aspect, an embodiment of the present application provides a device for perceiving multi-objective performance statistics, including:

[0067] A perception estimation module, used for performing perception estimation on the perception signal and determining a perception two-dimensional map;

[0068] A perception recognition module, used for performing perception multi-target recognition on the perception two-dimensional image to obtain multiple perception estimation targets;

[0069] The performance statistics module is used to perform performance statistics on multiple perception estimation targets and determine the perception multi-target performance statistics results.

[0070] In some embodiments, the performance statistics module includes a matching submodule and a determining submodule;

[0071] The matching submodule is used to obtain the final remaining difference set after performing multiple target matching and performing difference threshold judgment for multiple times;

[0072] The determination submodule is used to determine the perceptual multi-objective performance statistics based on the final remaining difference set.

[0073] In some embodiments, the matching submodule includes a first generating unit, a matching unit, and a removing unit;

[0074] The first generating unit is used to generate a perception estimation multi-target matrix and determine a difference matrix between the perception estimation multi-target matrix and the perception true multi-target matrix;

[0075] The matching unit is used to match the perception estimation multi-target and the perception real multi-target based on the difference matrix, and determine the second perception estimation multi-target vector, the second perception real multi-target vector and the difference vector;

[0076] The removal unit is used to remove the differences in the matched difference vector that are greater than the difference threshold based on a preset difference threshold, the perceived estimated targets corresponding to the differences in the second perceived estimated multi-target vector, and the perceived real targets corresponding to the differences in the second perceived real multi-target vector.

[0077] In some embodiments, the first generating unit includes a determining subunit and a generating subunit;

[0078] The determining subunit is used to determine a first perceptual estimation multi-target vector based on the perceptual estimation result;

[0079] The generating subunit is used to repeat the first perceptual estimation multi-target vector by M rows to generate a perceptual estimation multi-target matrix; wherein M represents the number of perceived real multi-targets.

[0080] In some embodiments, the matching submodule further includes a second generation unit;

[0081] The second generating unit is used to transpose the preset first perceived real multi-target vector, and then repeat N columns to generate a perceived real multi-target matrix; wherein N represents the number of perceived estimated multi-targets.

[0082] In some embodiments, the determination submodule includes a first determination unit and a second determination unit;

[0083] The first determination unit is used to determine the number of targets L that exist and are successfully estimated based on the final remaining difference set. D , the number of targets detected but without true value L FA and the number of targets L that exist but are not detected MD ;

[0084] The second determining unit is configured to determine the D , the L FA and the L MD Determine the perceptual multi-objective performance statistics.

[0085] In some embodiments, the perceived multi-objective performance statistics include one or more of the following:

[0086] Perceptual accuracy;

[0087] Detection success rate;

[0088] False alarm rate;

[0089] Missed detection rate.

[0090] In some embodiments, the apparatus further comprises a first adjustment module;

[0091] The first adjustment module is used to adjust the perception estimation algorithm used for perception estimation based on the perception multi-objective performance statistical results.

[0092] In some embodiments, the apparatus further comprises a second adjustment module;

[0093] The second adjustment module is used to adjust the time-frequency resources and / or coding sequences used to transmit the perception signal based on the perception multi-objective performance statistics result.

[0094] In some embodiments, the apparatus further comprises a third adjustment module;

[0095] The third adjustment module is used to adjust the threshold of the perception recognition algorithm used for perceptual multi-target recognition based on the perception multi-target performance statistics.

[0096] In a fourth aspect, an embodiment of the present application further provides a non-transitory readable storage medium, wherein the non-transitory readable storage medium stores a computer program, and the computer program is used to enable a processor to execute the perceptual multi-objective performance statistics method described in the first aspect above.

[0097] In a fifth aspect, an embodiment of the present application further provides a processor-readable storage medium, wherein the processor-readable storage medium stores a computer program, and the computer program is used to enable the processor to execute the perceptual multi-objective performance statistics method described in the first aspect above.

[0098] In a sixth aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is used to enable a computer to execute the perceptual multi-objective performance statistics method described in the first aspect above.

[0099] In a seventh aspect, an embodiment of the present application further provides a communication device, in which a computer program is stored, and the computer program is used to enable the communication device to execute the perceptual multi-objective performance statistics method described in the first aspect above.

[0100] In an eighth aspect, an embodiment of the present application further provides a chip product, wherein a computer program is stored in the chip product, and the computer program is used to enable the chip product to execute the perceptual multi-objective performance statistics method described in the first aspect above.

[0101] The perceptual multi-target performance statistics method, device and storage medium provided in the present application first perform perceptual estimation on the perceptual signal to determine a perceptual two-dimensional map, then perform perceptual multi-target identification on the perceptual two-dimensional map to obtain multiple perceptual estimation targets, and finally perform performance statistics on the multiple perceptual estimation targets to determine the perceptual multi-target performance statistics results, thereby meeting the actual scenario requirements of perceptual multi-targets. BRIEF DESCRIPTION OF THE DRAWINGS

[0102] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the following is a brief introduction to the drawings required for use in the embodiments or the related technical descriptions. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0103] Figure 1 It is a flowchart of a method for statistically analyzing multi-objective performance of perception provided by an embodiment of the present application;

[0104] Figure 2 It is a schematic diagram of the logic flow of perceiving multi-objective performance statistics provided by an embodiment of the present application;

[0105] Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application;

[0106] Figure 4 It is a structural diagram of a device for perceiving multi-objective performance statistics provided in an embodiment of the present application. DETAILED DESCRIPTION

[0107] The synaesthesia integrated system is oriented to B5G and 6G. The perception function of the synaesthesia integrated system can effectively perceive the surrounding environment and the state of objects, and further assist communication to improve the overall performance of the system. The main perception parameters include distance, speed, angle, etc., among which the angle includes the vertical angle of arrival (Zenith of Arrival, ZOA) and the horizontal angle of arrival (Azimuth of Arrival, AOA).

[0108] After the perception signal reaches the perception receiver through the channel, it first needs to be processed by the perception estimation algorithm of the perception receiver to obtain a perception two-dimensional map. Then the multi-target recognition processing of the perception receiver is carried out. After the processing of the perception multi-target recognition algorithm, the perception estimation target finally obtained by the perception receiver can perfectly coincide with the perception real target. However, although the perception estimation value and the perception real value are ordered and matched one by one from the perception two-dimensional map, they are actually disordered. The perception estimation value and the real value obtained after the perception multi-target recognition algorithm are not matched well, so further work is needed to perform multi-target matching.

[0109] In addition, since synaesthesia is aimed at high frequency bands, the higher the frequency band, the shorter the wavelength, and the more obvious the reflection and scattering of the signal in the environment, so in practice, multiple targets are often perceived. Due to the complexity of the multi-target situation, currently, the single target with the strongest perceived received signal is generally taken as the object of subsequent performance statistics. This statistical method does not meet the actual needs of multiple targets, and the final statistical performance is often better than the performance of multi-target statistics, that is, the performance is falsely high.

[0110] Based on the above technical problems, the embodiments of the present application propose a method, device and storage medium for perceptual multi-target performance statistics. First, perceptual estimation is performed on the perceptual signal to determine a perceptual two-dimensional map. Then, perceptual multi-target identification is performed on the perceptual two-dimensional map to obtain multiple perceptual estimation targets. Finally, performance statistics are performed on the multiple perceptual estimation targets to determine the perceptual multi-target performance statistics results, which meet the actual scenario requirements of perceptual multi-targets.

[0111] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0112] Figure 1 is a flow chart of a method for perceiving multi-objective performance statistics provided in an embodiment of the present application, such as Figure 1 As shown, the embodiment of the present application provides a method for perceiving multi-objective performance statistics, and the execution subject may be a perceiving receiver, such as a mobile phone, a base station, etc. The method includes:

[0113] Step 101: perform perceptual estimation on the perceptual signal to determine a perceptual two-dimensional map.

[0114] Specifically, Figure 2 is a schematic diagram of the logic flow of perceiving multi-objective performance statistics provided by the embodiment of the present application, such as Figure 2 As shown, the sensing transmitter first performs sensing configuration, including configuring time-frequency resources, coding sequences, etc. used for sensing.

[0115] After the perception configuration of the perception transmitter is completed, the perception transmitter sends a perception signal.

[0116] The perception signal reaches the perception receiver after passing through the synaesthesia channel, and the perception receiver receives the perception signal.

[0117] The synaesthesia channel includes AA mode and AB mode. AA mode means that the sensing transmitter and the sensing receiver are on the same side, and AB mode means that the sensing transmitter and the sensing receiver are on different sides.

[0118] The perception receiver uses the perception estimation algorithm to determine the perception two-dimensional map. The perception two-dimensional map can show preliminary results. The number of multi-targets estimated in the preliminary results is greater than the actual multi-targets. Some of the multi-targets estimated in the preliminary results are not accurate and need to be processed further.

[0119] The perception estimation algorithm may be a periodogram method, or a multiple signal classification (MUSIC) algorithm. The MUSIC algorithm may be used for perception ranging, speed measurement, angle measurement, and the like.

[0120] Step 102: Perform perceptual multi-target recognition on the perceptual two-dimensional image to obtain multiple perceptual estimation targets.

[0121] Specifically, in an embodiment of the present application, the perception receiver obtains multiple perception estimation targets from the perception two-dimensional map after processing using a perception multi-target recognition algorithm.

[0122] After being processed by the perceptual multi-target recognition algorithm, the number of multiple perceptual estimated targets obtained is equal to the number of perceived real multi-targets.

[0123] For example, after being processed by the perceptual estimation algorithm, the obtained perceptual two-dimensional map contains 10 perceptual estimation targets, while the perceptual real targets are only 5. After being processed by the perceptual multi-target recognition algorithm, 5 perceptual estimation targets are obtained from the 10 perceptual estimation targets.

[0124] Step 103: Perform performance statistics on multiple perception estimation targets to determine the perception multi-target performance statistics results.

[0125] Specifically, in an embodiment of the present application, the perception receiver uses a perception multi-target performance statistics algorithm to perform performance statistics on multiple perception estimation targets to determine a perception multi-target performance statistics result.

[0126] The main steps of the perceptual multi-target performance statistics algorithm include: first, obtaining the difference matrix between the perceptual estimated multi-target matrix and the perceptual true multi-target matrix; then using the difference matrix to match the perceptual estimated multi-target and the perceptual true multi-target; finally, setting a difference threshold to remove the perceptual estimated targets with particularly large difference errors after matching, and determining the perceptual multi-target performance statistics.

[0127] Whether the performance statistics structure is a single parameter, a joint of two parameters, or a joint of multiple parameters is determined by the perception estimation algorithm and the perception recognition algorithm. If a single parameter is estimated and recognized in the perception estimation and recognition stage, the performance statistics are also performed on a single parameter. For example, the distance, speed, and angle are estimated and recognized separately, and the subsequent performance statistics also obtain the perception accuracy and detection performance of the three separately. If dual / multiple parameters are jointly estimated and recognized in the perception estimation and recognition stage, the performance statistics are also performed on a dual / multiple parameter joint basis. For example, distance-speed, distance-angle, or horizontal arrival angle-vertical arrival angle are perceived, estimated, and recognized in pairs, and the performance statistics are also performed jointly.

[0128] The performance statistics can be used to verify the reliability of the synaesthesia system design, including adjusting the perception transmitter configuration, the perception receiver perception algorithm, and the perception receiver recognition algorithm, and dynamically adjust each part according to the performance statistics and scenario business requirements.

[0129] In some embodiments, the method further comprises:

[0130] A perceptual estimation algorithm used for perceptual estimation is adjusted based on perceptual multi-objective performance statistics.

[0131] In some embodiments, the method further comprises:

[0132] The time-frequency resources and / or coding sequences used to transmit the perception signal are adjusted based on the perception multi-objective performance statistics.

[0133] In some embodiments, the method further comprises:

[0134] The threshold of the perceptual recognition algorithm used for perceptual multi-target recognition is adjusted based on the perceptual multi-target performance statistical results.

[0135] For example, in smart transportation scenarios, different businesses have different requirements for perception functions, and the configuration of the entire system can be adjusted based on the statistical results of perception performance.

[0136] For real-time monitoring services, more attention is paid to the overall situation of road traffic, that is, the detection rate requirement is high and the perception accuracy requirement is low. In this scenario, the overall system configuration of the service in the next period of time can be adjusted based on the detection performance results in the previous period. For example, the configuration of the time and frequency resources of the perception transmitter can be reduced, a simple but limited-performance perception estimation algorithm can be selected, and the threshold of the perception recognition algorithm can be relaxed.

[0137] For environmental map reconstruction services, more attention is paid to the high-precision details of the road environment, that is, the perception accuracy requirement is very high. In this scenario, the overall system configuration of the service for the next period of time can be adjusted according to the perception accuracy results of the previous period. For example, the configuration of the time and frequency resources of the perception transmitter can be increased, a higher-precision perception estimation algorithm can be selected, and the threshold of the perception recognition algorithm can be reduced.

[0138] For another example, in a smart factory, different objects have different requirements for different perception functions, and the configuration of the entire system can be adjusted according to the perception performance statistics. Unlike smart transportation, perception accuracy and perception detection performance are not necessarily required at the same time in a smart factory.

[0139] When the sensing object is a product, the sensing detection performance is more important, especially for assembly line products, whose positions and movement trajectories are basically fixed, so more emphasis is placed on product counting and the performance statistics of sensing accuracy can be ignored. In this scenario, based on the detection performance results of the product some time ago, the relevant configurations of the sensing transmitter and the sensing receiver can be reasonably adjusted to obtain more accurate detection performance statistics.

[0140] When the sensing object is an intelligent robot, the sensing accuracy is more important. First, the number of robots is limited, so there is no need to conduct detection performance statistics. Second, the movement and operation of intelligent robots are an important part of the normal operation of the factory. Improving the relevant sensing accuracy is conducive to mastering the working status of the robot and timely predicting or discovering abnormal phenomena. In this scenario, based on the detection performance results of the product some time ago, the relevant configurations of the sensing transmitter and the sensing receiver can be reasonably adjusted to obtain more accurate sensing accuracy statistics.

[0141] The perceptual multi-target performance statistics method provided in the present application first performs perceptual estimation on the perceptual signal to determine a perceptual two-dimensional map, then performs perceptual multi-target identification on the perceptual two-dimensional map to obtain multiple perceptual estimation targets, and finally performs performance statistics on the multiple perceptual estimation targets to determine the perceptual multi-target performance statistics results, thereby meeting the actual scenario requirements of perceptual multi-targets.

[0142] In some embodiments, performing performance statistics on multiple perception estimation targets and determining a perception multi-target performance statistics result includes:

[0143] After multiple multi-target matching and difference threshold judgment, the final remaining difference set is obtained;

[0144] The perceptual multi-objective performance statistics are determined based on the final remaining difference set.

[0145] Specifically, in the embodiments of the present application,

[0146] In some embodiments, performing multi-target matching and performing difference threshold determination includes:

[0147] Generate a perception estimation multi-target matrix, and determine a difference matrix between the perception estimation multi-target matrix and the perception true multi-target matrix;

[0148] Matching the perceived estimated multi-targets and the perceived real multi-targets based on the difference matrix to determine a second perceived estimated multi-target vector, a second perceived real multi-target vector, and a difference vector;

[0149] Based on a preset difference threshold, the differences in the matched difference vector that are greater than the difference threshold are removed, the perceived estimated targets corresponding to the differences in the second perceived estimated multi-target vector, and the perceived real targets corresponding to the differences in the second perceived real multi-target vector.

[0150] In some embodiments, generating a perceptual estimation multi-objective matrix includes:

[0151] Determining a first perceptual estimation multi-target vector based on the perceptual estimation result;

[0152] The first perceptual estimation multi-target vector is repeated M rows to generate a perceptual estimation multi-target matrix; wherein M represents the number of perceived real multi-targets.

[0153] In some embodiments, performing multi-target matching and performing difference threshold determination further includes:

[0154] The preset first perceived true multi-target vector is transposed and repeated N columns to generate a perceived true multi-target matrix; wherein N represents the number of perceived estimated multi-targets.

[0155] In some embodiments, determining the perceptual multi-objective performance statistics based on the final remaining difference set includes:

[0156] Based on the final remaining difference set, determine the number of targets L that exist and are successfully estimated D , the number of targets detected but without true value L FA and the number of targets L that exist but are not detected MD ;

[0157] Based on the L D , the L FA and the L MD Determine the perceptual multi-objective performance statistics.

[0158] The following takes single parameter performance statistics as an example. When single parameter performance statistics are used, the perceived estimation parameter can be any one of distance, speed, angle, etc. Assuming that the parameter is recorded as s, the M parameters of the perceived real multi-target can be represented by the first perceived real multi-target vector S, recorded as S = [s1,…,s M], the N parameters obtained by perceptual estimation of multi-targets can be represented by the first perceptual estimation multi-target vector S′, denoted as S′=[s′1,…,s′ N ]. The sizes of S and S′ are 1×M and 1×N respectively, where N represents the number of perceived real multi-targets and N represents the number of perceived estimated multi-targets.

[0159] The steps of performing performance statistics on multiple perception estimation targets and determining the perception multi-target performance statistics results are as follows:

[0160] (1) First, the perceived estimated multi-targets and the perceived real multi-targets after a single multi-target recognition are matched, including the following steps 1 to 3.

[0161] Step 1: Generate the perception estimation multi-target matrix and the perception true multi-target matrix, and then subtract them to obtain the difference matrix.

[0162] Specifically, S is transposed from a 1×N row vector to an M×1 column vector, and then repeated for N columns to obtain an M×N perceived ground truth multi-target matrix, denoted as S Matrix .

[0163] Repeat S′ from the 1×N row vector directly to M rows to obtain the M×N perceptual estimation multi-target matrix, denoted as S′ Matrix .

[0164] S′ SMatrix and S Matrix Subtract and take the absolute value to get the difference matrix S″ Matrix , that is, S″ Matrix =|S′ Matrix -S Matrix |.

[0165] It should be noted that the essence of step 1 is to traverse all estimated values ​​and all true values ​​to obtain the absolute value of the difference.

[0166] Step 2: Use the minimum value and index of each column of the difference matrix to match the perceived estimated multi-targets and the perceived real multi-targets.

[0167] Specifically, find S″ Matrix The minimum value of each column in is denoted by S″ min , and its corresponding row index, denoted as I1, S″ min The size of and I1 are both 1×N. That is, find the closest true value and index to each estimated value. Since the true value is found from the estimated value, this step can ensure that there will not be multiple true values ​​corresponding to one estimated value.

[0168] Remove the duplicate values ​​in the obtained row index and get a new index value, recorded as I2. This is because different estimated values ​​may be closest to the same true value. According to the order in I2, take the value from S to get the new perceived true multi-target S. new ; For each value in I2, find its corresponding position in I1, record it as I3; find S″ according to the value in I3 min If there are multiple values ​​of I3 corresponding to each value in I2, the corresponding S″ can be taken min The index corresponding to the smallest difference in is recorded as I4. That is, find the estimated value closest to the true value and ensure that there will not be multiple estimated values ​​matching the same estimated value.

[0169] Take values ​​from S′ according to the order in I4 to obtain the new perception estimation multi-target S′ new ; According to the order in I4, from S" min Take the value from the middle and get the new difference S″ new ; S obtained in step 2 new , S′ new are mutually matched, and S″ new It is also the corresponding difference after matching.

[0170] Step 3: Set the difference threshold and remove the perception estimation targets and corresponding differences whose difference after matching is greater than the difference threshold.

[0171] Specifically, even if an estimated value is the closest to a true value among all estimated values, it is still not the estimated value that actually corresponds to the true value. After matching, there may still be very large differences. For example, a point that is very far away may be completely submerged in noise due to low signal strength. In this case, it is difficult to find the estimated value that actually corresponds to the true value.

[0172] To avoid this situation, the embodiment of the present application may set a difference threshold σ, which may be set according to the resolution and false alarm rate, for example, several times the resolution of the perception parameter; or, further adjusted according to the false alarm rate of previous statistics.

[0173] When S″ new When there is a value greater than σ in S new , S′ new The corresponding value in is replaced by a special value as a marker, which can be set to an irrational number or S new , S′ new , S″ new Values ​​that cannot be obtained under any circumstances are not directly removed for the sake of subsequent statistical performance.

[0174] (2) Then, multiple target recognitions are performed, difference threshold judgments are made, and finally performance statistics are performed, including the following steps 4 to 5.

[0175] Step 4: Set the difference threshold and make a difference threshold judgment on the multi-target recognition results.

[0176] Specifically, assume that the total number of perceived real multi-targets is M total , the total number of perceived and estimated multi-targets is N total , after multiple multi-target recognitions, all S new , S new , S″ new Value, S new , S′ new , S″ new The length is L total , where the length of the special value used as a marker is L err , the remaining values ​​that have been matched and meet the difference threshold σ constitute the final remaining difference set, which can be recorded as S final , S′ final , S″ final , S final , S′ final , S″ final The length is L D .L D Indicates the number of targets that exist and are successfully estimated, L D =L total -L err , L FA Indicates the number of targets detected even though the true value does not exist, L FA =N total -L D , L MD Indicates the number of real targets that exist but are not detected, L MD =M total -L D .

[0177] Step 5: Obtain various statistical performance results.

[0178] Specifically, using the final remaining difference set S″ final The Cumulative Distribution Function (CDF) curve corresponding to the perception parameter can be obtained, that is, the statistical performance of the perception parameter can be obtained. For example, when the perception parameter is distance, the distance estimation accuracy of the multi-target perception system under various confidence levels can be obtained.

[0179] At the same time, the detection success rate, false alarm rate, and misalarm rate of the synaesthesia system can be calculated.

[0180] Among them, the detection success rate is expressed as P D Indicates that P D =L D / (L D +L FA +L MD ), the false alarm rate is P FA Indicates that P FA =L FA / (L D +L FA +L MD ), the missed detection rate is P MD Indicates that P MD =L MD / (L D +L FA +L MD ).

[0181] It should be noted that before performance statistics, the number of multi-targets obtained by each perception estimation after multi-target recognition is not necessarily equal to the number of perceived real multi-targets. Assume that the number of perceived estimated multi-targets obtained by the perception receiving end after the multi-target recognition algorithm is N, and the number of perceived real multi-targets is M. Ideally, N = M, but N>M and N<M may exist, and even when N = M, the perceived estimated multi-targets and the perceived real multi-targets may not match one by one.

[0182] Next, we take the dual-parameter joint performance statistics as an example. When the dual-parameter joint performance statistics are performed, the statistical perception estimation dual parameters can be any set of distance-speed, distance-angle, or horizontal arrival angle-vertical arrival angle. Assume that the dual parameter is recorded as s i and j , then the M parameters of the perceived real multi-target can be expressed by the first perceived real multi-target vector S i and S j Indicates, denoted by S i =[s i1 ,…,s iM ],S j =[s j1 ,…,s jM ]; The N parameters obtained by perceiving and estimating multiple targets can be used to estimate the multi-target vector S′ i and S′ j Denote it as S′ i =[s′ i1 ,…,s′ iN ],S′ j =[s′ j1 ,…,s′ jN ]. i and S jThere is a one-to-one correspondence, and the size is 1×M; S′ i and S′ j There is also a one-to-one correspondence, and the size is 1 × N. Among them, M represents the number of perceived real multi-targets, and N represents the number of perceived estimated multi-targets.

[0183] The steps of performing performance statistics on multiple perception estimation targets and determining the perception multi-target performance statistics results are as follows:

[0184] (1) First, the perceived estimated multi-targets and the perceived real multi-targets after a single multi-target recognition are matched, including the following steps 1 to 3.

[0185] Unlike single parameters, dual parameters are estimated jointly, that is, they are one-to-one corresponding, so they are also matched jointly, and one of the parameters needs to be the main matching object. i and S′ i As the main matching object, S j and S′ j Taking the secondary matching object as an example, the secondary matching object can be processed accordingly with the matching result of the primary matching object.

[0186] Step 1: Generate the perception estimation multi-target matrix and the perception real multi-target matrix, and then subtract them to get the difference matrix between them (same as single parameter, multi-parameter also only needs to use the main matching object S i Perform this step).

[0187] Specifically, S i Transpose the 1×M row vector to an M×1 column vector, and then repeat N columns to obtain an M×N perceived true multi-target matrix, denoted as S Matrix，i .

[0188] S′ i Directly repeat M rows from the 1×N row vector to obtain the M×N perceptual estimation multi-target matrix, denoted as S′ Matrix，i .

[0189] S′ Matrix，i and S Matrix，i Subtract and take the absolute value to get the difference matrix S″ Matrix，i , that is, S″ Matrix，i =|S′ Matrix，i -S Matrix，i |.

[0190] It should be noted that the essence of step 1 is to traverse all estimated values ​​and all true values ​​to obtain the absolute value of the difference.

[0191] Step 2: Use the minimum value and index of each column of the difference matrix to match the perceived estimated multi-targets and the perceived real multi-targets (the search for the minimum value and index is the same as that for a single parameter, but different from that for a single parameter during matching. The dual parameters are matched simultaneously, that is, the matched real value index and estimated value index found by the primary matching object are applicable to both the primary matching object and the secondary matching object).

[0192] Specifically, find S″ Matrix，i The minimum value of each column in is denoted by S″ min，i , and its corresponding row index, denoted as I 1，i , S″ min，i and I 1，i The size of is 1×N. That is, find the closest true value and index to each estimated value. Since the true value is found from the estimated value, this step can ensure that there will not be multiple true values ​​corresponding to one estimated value.

[0193] Remove duplicate values ​​from the obtained row index and get a new index value, denoted as I 2，i This is because different estimated values ​​may be closest to the same true value. 2，i The sorting in S i and S j Take the value from the above equation to get the new perceived real multi-target S new，i and S new，j ; For I 2，i For each value in I, find its 1，i The corresponding position in is denoted as I 3，i According to I 3，i Find the value of S″ min，i The corresponding difference in I 2，i Each value in I 3，i There are multiple values, corresponding to S″ min，i The index corresponding to the smallest difference in is denoted by I 4，i That is, find the estimated value that is closest to the true value and ensure that there will not be multiple estimated values ​​matching the same estimated value.

[0194] Press I 4，i The sorting in S′ i and S′ j Take the value from the middle and get the new perception estimation multi-target S′ new，i and S′ new，j ;Press I 4，i The sorting in S″ min，i Take the value from the middle and get the new difference S″ new，i ; S′ new，j and S new，j Subtract and get the new difference S″ new，i ; S obtained in step 2 new，i, S′ new，i , S new，j , S′ new，j These four are matched, corresponding to the true value and estimated value of the dual parameter of the same perceptual target, and S″ new， i and S″ new，j It is also the corresponding difference after matching.

[0195] Step 3: Set the difference threshold and remove the perception estimation targets and corresponding differences whose difference after matching is greater than the difference threshold.

[0196] Specifically, even if an estimated value is the closest to a true value among all estimated values, it is still not the estimated value that actually corresponds to the true value. After matching, there may still be very large differences. For example, a point that is very far away may be completely submerged in noise due to low signal strength. In this case, it is difficult to find the estimated value that actually corresponds to the true value.

[0197] To avoid this situation, the embodiment of the present application can set the difference threshold σ i and σ j The difference threshold σ i and σ j It can be set according to the resolution and false alarm rate, for example, several times the resolution of the perception parameter; or further adjusted according to the false alarm rate calculated in the previous statistics.

[0198] When S″ new，i There exists a value greater than σ i When the value of new，i , S′ new，i The corresponding value in is replaced by a special value as a marker, which can be set to an irrational number or S new，i , S′ new，i , S″ new，i Values ​​that cannot be obtained under any circumstances are not directly removed for the sake of subsequent statistical performance.

[0199] S″ new，j When the difference threshold is σ j The processing method is similar to S″ new，i Similarly, the special value used as a marker can be set to the same value or different values. Since these are two arrays, whether the special value is the same or not has no effect on the two arrays.

[0200] (2) Then, multiple target recognitions are performed, difference threshold judgments are made, and finally performance statistics are performed, including the following steps 4 to 5.

[0201] Step 4: Set two difference thresholds corresponding to the dual parameters and perform difference threshold judgment on the multi-target recognition results.

[0202] Specifically, assume that the total number of perceived real multi-targets is M total , the total number of perceived and estimated multi-targets is N total , after multiple multi-target recognitions, all S new，i , S′ new，i , S″ new，i and S new，j , S new，j , S new，j , S new，i , S new，i , S new，i and S new，j , S new，j 、s new，j The length is L total .

[0203] For S″ new，i Assume that the number of special values ​​with a label is L err，i , the remaining ones have been matched and meet the difference threshold σ i The values ​​of constitute the final remaining difference set, which can be recorded as S final，i , S′ final，i , S″ final，i , S final，i , S′ final，i , S″ final，i The length is L D，i .L D，i Indicates the number of targets that exist and are successfully estimated, L D，i =L total -L err，i , L FA，i Indicates the number of targets detected even though the true value does not exist, L FA，i =N total -L D，i , L MD，i Indicates the number of real targets that exist but are not detected, L MD，i =M total -L D，i .

[0204] For S″ new，j Assume that the number of special values ​​with a label is L err，j , the remaining ones have been matched and meet the difference threshold σ j The values ​​of constitute the final remaining difference set, which can be recorded as S final，j , S′ final，j , S″ final，j , S final，j , S′ final，j , S″ final，j The length is L D，j .L D，jIndicates the number of targets that exist and are successfully estimated, L D，j =L total -L err，j , L FA，j Indicates the number of targets detected even though the true value does not exist, L FA，j =N total -L D，j , L MD，j Indicates the number of real targets that exist but are not detected, L FA，j =N total -L D，j .

[0205] It should be noted that: due to S i and S j The resolutions corresponding to the two parameters are often different and the difference is large. i and σ j Generally different, so L err，i and L err，j Generally not equal, L D，i and L D，j Also generally not equal.

[0206] Step 5: Obtain various statistical performance results.

[0207] Specifically, using the final remaining difference set S″ final，i and S″ final，j The CDF curves corresponding to the dual perception parameters can be obtained, that is, the statistical performance of the dual perception parameters can be obtained. For example, when the dual perception parameters are distance-speed, the distance estimation accuracy and speed estimation accuracy of the multi-target perception system under various confidence levels can be obtained.

[0208] At the same time, the detection success rate, false alarm rate, and misalarm rate of the synaesthesia system for each of the perception dual parameters can be calculated.

[0209] Among them, S i The detection success rate is expressed as P D，i Indicates that P D，i =L D，i / (L D，i +L FA，i +L MD，i ), S j The detection success rate is expressed as P D，j Indicates that P D，j =L D，j / (L D，j +L FA，j +L MD，j );S I The false alarm rate is expressed as P FA， I means P FA，i =LFA，i / (L D，i +L FA，i +L MD，i ), S j The false alarm rate is expressed as P FA，j Indicates that P FA，j =L FA，j / (L D，j +L FA，j +L MD，j );S i The missed detection rate is expressed as P MD，i Indicates that P MD，i =L MD，i / (L D，i +L FA，i +L MD，i ), S j The missed detection rate is expressed as P MD，j Indicates that P MD，j =L MD，j / (L D，j +L FA，j +L MD，j ).

[0210] It should be noted that the combined performance statistics of the two parameters can also be obtained. new，i and S″ new，j , find the positions of the special values ​​with their own marks, merge these positions, and the length of the merged position is L union，err , then in S″ new，i and S″ new，j The value corresponding to the merge position is removed in the above example. In this case, S is removed. i and S j If any of the two parameters does not meet the value corresponding to the difference threshold, the union of the two parameters is guaranteed. Assume that the difference values ​​after removal are S″ union，i and S″ union，j , S″ union，i and S″ union，j Length is L union，D .L union，D Indicates the number of targets for which both parameters are true and have been successfully estimated, L union，FA Indicates the number of targets detected even though the true value of any of the two parameters does not exist, L union，FA =N total -L union，D , L union，MD Indicates the number of targets that exist but are not detected in any of the two parameters, L union，MD =M total -L union，D .

[0211] Similarly, using S″ union，i and S″union，j The CDF curves corresponding to the two perception parameters can be obtained, that is, the statistical performance of each of the two perception parameters can be obtained.

[0212] At the same time, the detection success rate, false alarm rate, and misalarm rate of the synaesthesia system for each of the perception dual parameters can be calculated.

[0213] Among them, S i and S j The joint detection success rate is expressed as P union，D Indicates that P union，D =L union，D / (L union，D +L union，FA +L unIon，MD );S i and S j The joint false alarm rate is expressed as P union，FA Indicates that P union，FA =L union，FA / (L union，D +L union，FA +L union，MD );S i and S j The joint missed detection rate is expressed as P union，MD Indicates that P union，MD =L union，MD / (L unIon，D +L union，FA +L union，MD ).

[0214] It should be noted that the dual parameters can be further expanded to multiple parameters, for example, three parameters of distance-speed-AOA, four parameters of distance-speed-ZOA-AOA. Similarly, one of the parameters can be used as the main matching object, and all the others can be used as secondary matching objects, and the joint performance statistical method of the dual parameters can be referred to, which will not be repeated in the embodiments of this application.

[0215] The method for perceiving multi-target performance statistics proposed in the embodiment of the present application can effectively perform multi-target matching and performance statistics after the perceiving multi-target recognition algorithm, which is more in line with the actual scenario requirements of perceiving multi-targets.

[0216] Figure 3 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application, such as Figure 3 As shown, the electronic device includes a memory 320, a transceiver 300, and a processor 310, wherein:

[0217] The memory 320 is used to store computer programs; the transceiver 300 is used to send and receive data under the control of the processor 310; the processor 310 is used to read the computer program in the memory 320 and perform the following operations:

[0218] Performing perception estimation on the perception signal to determine a perception two-dimensional map;

[0219] Performing perceptual multi-target recognition on the perceptual two-dimensional image to obtain multiple perceptual estimation targets;

[0220] The performance statistics of multiple perception estimation targets are performed to determine the perception multi-target performance statistics results.

[0221] Among them, Figure 3 In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically linking together various circuits of one or more processors represented by processor 310 and memory represented by memory 320. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 300 may be a plurality of components, namely, a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium, such as a wireless channel, a wired channel, an optical cable, and the like. The processor 310 is responsible for managing the bus architecture and general processing, and the memory 320 may store data used by the processor 310 when performing operations.

[0222] The processor 310 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or a complex programmable logic device (CPLD). The processor may also adopt a multi-core architecture.

[0223] In some embodiments, performing performance statistics on multiple perception estimation targets and determining a perception multi-target performance statistics result includes:

[0224] After multiple multi-target matching and difference threshold judgment, the final remaining difference set is obtained;

[0225] The perceptual multi-objective performance statistics are determined based on the final remaining difference set.

[0226] In some embodiments, performing multi-target matching and performing difference threshold determination includes:

[0227] Generate a perception estimation multi-target matrix, and determine a difference matrix between the perception estimation multi-target matrix and the perception true multi-target matrix;

[0228] Matching the perceived estimated multi-targets and the perceived real multi-targets based on the difference matrix to determine a second perceived estimated multi-target vector, a second perceived real multi-target vector, and a difference vector;

[0229] Based on a preset difference threshold, the differences in the matched difference vector that are greater than the difference threshold are removed, the perceived estimated targets corresponding to the differences in the second perceived estimated multi-target vector, and the perceived real targets corresponding to the differences in the second perceived real multi-target vector.

[0230] In some embodiments, generating a perceptual estimation multi-objective matrix includes:

[0231] Determining a first perceptual estimation multi-target vector based on the perceptual estimation result;

[0232] The first perceptual estimation multi-target vector is repeated M rows to generate a perceptual estimation multi-target matrix; wherein M represents the number of perceived real multi-targets.

[0233] In some embodiments, performing multi-target matching and performing difference threshold determination further includes:

[0234] The preset first perceived true multi-target vector is transposed and repeated N columns to generate a perceived true multi-target matrix; wherein N represents the number of perceived estimated multi-targets.

[0235] In some embodiments, determining the perceptual multi-objective performance statistics based on the final remaining difference set includes:

[0236] Based on the final remaining difference set, determine the number of targets L that exist and are successfully estimated D , the number of targets detected but without true value L FA and the number of targets L that exist but are not detected MD ;

[0237] Based on the L D , the L FA and the L MD Determine the perceptual multi-objective performance statistics.

[0238] In some embodiments, the perceived multi-objective performance statistics include one or more of the following:

[0239] Perceptual accuracy;

[0240] Detection success rate;

[0241] False alarm rate;

[0242] Missed detection rate.

[0243] In some embodiments, the processor is further configured to read the computer program in the memory and perform the following operations:

[0244] A perceptual estimation algorithm used for perceptual estimation is adjusted based on perceptual multi-objective performance statistics.

[0245] In some embodiments, the processor is further configured to read the computer program in the memory and perform the following operations:

[0246] The time-frequency resources and / or coding sequences used to transmit the perception signal are adjusted based on the perception multi-objective performance statistics.

[0247] In some embodiments, the processor is further configured to read the computer program in the memory and perform the following operations:

[0248] The threshold of the perceptual recognition algorithm used for perceptual multi-target recognition is adjusted based on the perceptual multi-target performance statistical results.

[0249] Specifically, the above-mentioned electronic device provided in the embodiment of the present application can implement all the method steps implemented by the method embodiment in which the execution subject is a perception receiver, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0250] Figure 4 is a schematic diagram of a device for perceiving multi-objective performance statistics provided by an embodiment of the present application, such as Figure 4 As shown, the embodiment of the present application provides a perceptual multi-objective performance statistics device, including a perceptual estimation module 401, a perceptual identification module 402 and a performance statistics module 403, wherein:

[0251] A perception estimation module, used for performing perception estimation on the perception signal and determining a perception two-dimensional map;

[0252] A perception recognition module, used for performing perception multi-target recognition on the perception two-dimensional image to obtain multiple perception estimation targets;

[0253] The performance statistics module is used to perform performance statistics on multiple perception estimation targets and determine the perception multi-target performance statistics results.

[0254] In some embodiments, the performance statistics module includes a matching submodule and a determining submodule;

[0255] The matching submodule is used to obtain the final remaining difference set after performing multiple target matching and performing difference threshold judgment for multiple times;

[0256] The determination submodule is used to determine the perceptual multi-objective performance statistics based on the final remaining difference set.

[0257] In some embodiments, the matching submodule includes a first generating unit, a matching unit, and a removing unit;

[0258] The first generating unit is used to generate a perception estimation multi-target matrix and determine a difference matrix between the perception estimation multi-target matrix and the perception true multi-target matrix;

[0259] The matching unit is used to match the perception estimation multi-target and the perception real multi-target based on the difference matrix, and determine the second perception estimation multi-target vector, the second perception real multi-target vector and the difference vector;

[0260] The removal unit is used to remove the differences in the matched difference vector that are greater than the difference threshold based on a preset difference threshold, the perceived estimated targets corresponding to the differences in the second perceived estimated multi-target vector, and the perceived real targets corresponding to the differences in the second perceived real multi-target vector.

[0261] In some embodiments, the first generating unit includes a determining subunit and a generating subunit;

[0262] The determining subunit is used to determine a first perceptual estimation multi-target vector based on the perceptual estimation result;

[0263] The generating subunit is used to repeat the first perceptual estimation multi-target vector by M rows to generate a perceptual estimation multi-target matrix; wherein M represents the number of perceived real multi-targets.

[0264] In some embodiments, the matching submodule further includes a second generation unit;

[0265] The second generating unit is used to transpose the preset first perceived real multi-target vector, and then repeat N columns to generate a perceived real multi-target matrix; wherein N represents the number of perceived estimated multi-targets.

[0266] In some embodiments, the determination submodule includes a first determination unit and a second determination unit;

[0267] The first determination unit is used to determine the number of targets L that exist and are successfully estimated based on the final remaining difference set. D , the number of targets detected but without true value L FA and the number of targets L that exist but are not detected MD ;

[0268] The second determining unit is configured to determine the D , the L FA and the L MD Determine the perceptual multi-objective performance statistics.

[0269] In some embodiments, the perceived multi-objective performance statistics include one or more of the following:

[0270] Perceptual accuracy;

[0271] Detection success rate;

[0272] False alarm rate;

[0273] Missed detection rate.

[0274] In some embodiments, the apparatus further comprises a first adjustment module;

[0275] The first adjustment module is used to adjust the perception estimation algorithm used for perception estimation based on the perception multi-objective performance statistical results.

[0276] In some embodiments, the apparatus further comprises a second adjustment module;

[0277] The second adjustment module is used to adjust the time-frequency resources and / or coding sequences used to transmit the perception signal based on the perception multi-objective performance statistics result.

[0278] In some embodiments, the apparatus further comprises a third adjustment module;

[0279] The third adjustment module is used to adjust the threshold of the perception recognition algorithm used for perceptual multi-target recognition based on the perception multi-target performance statistics.

[0280] Specifically, the above-mentioned perceptual multi-objective performance statistics device provided in the embodiment of the present application can implement all the method steps implemented by the method embodiment in which the execution subject is a perceptual receiver, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as those of the method embodiment will not be described in detail here.

[0281] It should be noted that the division of units / modules in the above embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, the functional units in the various embodiments of the present application may be integrated into a processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated units may be implemented in the form of hardware or in the form of software functional units.

[0282] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a processor-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the relevant technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0283] In some embodiments, a non-transitory readable storage medium is also provided, wherein the non-transitory readable storage medium stores a computer program, and the computer program is used to enable a processor to execute the perceptual multi-objective performance statistics method provided by the above-mentioned method embodiments.

[0284] Specifically, the above-mentioned non-transitory readable storage medium provided in the embodiment of the present application can implement all the method steps implemented by the above-mentioned method embodiments, and can achieve the same technical effects. The parts and beneficial effects that are the same as the method embodiments in this embodiment will not be described in detail here.

[0285] It should be noted that the non-transitory readable storage medium can be any available medium or data storage device that can be accessed by the processor, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NAND FLASH), solid-state drive (SSD)), etc.

[0286] In some embodiments, a processor-readable storage medium is also provided, wherein the processor-readable storage medium stores a computer program, and the computer program is used to enable a processor to execute the perceptual multi-objective performance statistics method provided by the above-mentioned method embodiments.

[0287] Specifically, the processor-readable storage medium provided in the embodiment of the present application can implement all the method steps implemented in the above-mentioned method embodiments, and can achieve the same technical effects. The parts and beneficial effects that are the same as those in the method embodiments will not be described in detail herein.

[0288] In some embodiments, a computer-readable storage medium is also provided, wherein the computer-readable storage medium stores a computer program, and the computer program is used to enable a computer to execute the perceptual multi-objective performance statistics method provided by the above-mentioned method embodiments.

[0289] Specifically, the above-mentioned computer-readable storage medium provided in the embodiment of the present application can implement all the method steps implemented by the above-mentioned method embodiments, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0290] In some embodiments, a communication device is further provided, in which a computer program is stored, and the computer program is used to enable the communication device to execute the perceptual multi-objective performance statistics method provided by the above-mentioned method embodiments.

[0291] Specifically, the above-mentioned communication device provided in the embodiment of the present application can implement all the method steps implemented by the above-mentioned method embodiments, and can achieve the same technical effects. The parts and beneficial effects that are the same as the method embodiments in this embodiment will not be described in detail here.

[0292] In some embodiments, a chip product is also provided, in which a computer program is stored, and the computer program is used to enable the chip product to execute the perceptual multi-objective performance statistics method provided by the above-mentioned method embodiments.

[0293] Specifically, the above-mentioned chip product provided in the embodiment of the present application can implement all the method steps implemented by the above-mentioned method embodiments, and can achieve the same technical effects. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0294] It should also be noted that the terms "first", "second", etc. in the embodiments of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first" and "second" are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more.

[0295] In the embodiments of the present application, the term "and / or" describes the association relationship of the associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0296] "Determine B based on A" in the embodiments of the present application means that the factor A should be considered when determining B. It is not limited to "B can be determined based on A alone", but should also include: "Determine B based on A and C", "Determine B based on A, C and E", "Determine C based on A, and further determine B based on C", etc. In addition, it can also include taking A as a condition for determining B, for example, "When A meets the first condition, use the first method to determine B"; for another example, "When A meets the second condition, determine B", etc.; for another example, "When A meets the third condition, determine B based on the first parameter", etc. Of course, it can also be a condition that takes A as a factor for determining B, for example, "When A meets the first condition, use the first method to determine C, and further determine B based on C", etc.

[0297] In the embodiments of the present application, the term "plurality" refers to two or more than two, and other quantifiers are similar.

[0298] The technical solution provided in the embodiment of the present application can be applicable to a variety of systems, especially 5G systems. For example, the applicable system can be a global system of mobile communication (GSM) system, a code division multiple access (CDMA) system, a wideband code division multiple access (WCDMA) general packet radio service (GPRS) system, a long term evolution (LTE) system, a LTE frequency division duplex (FDD) system, a LTE time division duplex (TDD) system, an advanced long term evolution (LTE-A) system, a universal mobile telecommunication system (UMTS), a world-wide interoperability for microwave access (WiMAX) system, a 5G new radio (NR) system, etc. These various systems include terminal equipment and network equipment. The system may also include a core network part, such as an evolved packet system (EPS), a 5G system (5GS), etc.

[0299] The terminal device involved in the embodiment of the present application may be a device that provides voice and / or data connectivity to a user, a handheld device with a wireless connection function, or other processing devices connected to a wireless modem. In different systems, the name of the terminal device may also be different. For example, in a 5G system, the terminal device may be called a user equipment (UE). A wireless terminal device can communicate with one or more core networks (CN) via a radio access network (RAN). The wireless terminal device may be a mobile terminal device, such as a mobile phone (or a "cellular" phone) and a computer with a mobile terminal device. For example, it may be a portable, pocket-sized, handheld, computer-built-in or vehicle-mounted mobile device that exchanges language and / or data with a wireless access network. For example, personal communication service (PCS) phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs) and other devices. The wireless terminal device may also be referred to as a system, a subscriber unit, a subscriber station, a mobile station, a mobile station, a remote station, an access point, a remote terminal device, an access terminal device, a user terminal device, a user agent, and a user device, but is not limited in the embodiments of the present application.

[0300] The network device involved in the embodiment of the present application may be a base station, which may include multiple cells providing services for the terminal. Depending on the specific application scenario, the base station may also be called an access point, or may be a device in the access network that communicates with the wireless terminal device through one or more sectors on the air interface, or other names. The network device may be used to interchange received air frames with Internet Protocol (IP) packets, and serve as a router between the wireless terminal device and the rest of the access network, wherein the rest of the access network may include an Internet Protocol (IP) communication network. The network device may also coordinate the attribute management of the air interface. For example, the network device involved in the embodiments of the present application may be a network device (Base Transceiver Station, BTS) in the Global System for Mobile communications (Global System for Mobile communications, GSM) or Code Division Multiple Access (Code Division Multiple Access, CDMA), or a network device (NodeB) in Wide-band Code Division Multiple Access (WCDMA), or an evolutionary network device (evolutional Node B, eNB or e-NodeB) in the long term evolution (long term evolution, LTE) system, a 5G base station (gNB) in the 5G network architecture (next generation system), or a home evolved Node B (Home evolved Node B, HeNB), a relay node, a home base station (femto), a pico base station (pico), etc., which is not limited in the embodiments of the present application. In some network structures, the network device may include a centralized unit (CU) node and a distributed unit (DU) node, and the centralized unit and the distributed unit may also be arranged geographically separately.

[0301] Network devices and terminal devices can each use one or more antennas for multi-input multi-output (MIMO) transmission. MIMO transmission can be single-user MIMO (SU-MIMO) or multi-user MIMO (MU-MIMO). Depending on the form and number of antenna combinations, MIMO transmission can be 2D-MIMO, 3D-MIMO, FD-MIMO or massive-MIMO, or it can be diversity transmission, precoding transmission or beamforming transmission, etc.

[0302] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) that contain computer-usable program code.

[0303] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer executable instructions. These computer executable instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0304] These processor executable instructions may also be stored in a processor readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the processor readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0305] These processor-executable instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable device to implement the process. Figure 1A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0306] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for perceiving multi-objective performance statistics, characterized in that: include: Performing perceptual estimation on the perceptual signal to determine a perceptual two-dimensional map; Performing perceptual multi-target recognition on the perceptual two-dimensional image to obtain multiple perceptual estimation targets; The performance statistics of multiple perception estimation targets are performed to determine the perception multi-target performance statistics results.

2. The method for statistically analyzing multi-objective performance of perception according to claim 1, characterized in that: Perform performance statistics on multiple perception estimation targets and determine the perception multi-target performance statistics results, including: After multiple multi-target matching and difference threshold judgment, the final remaining difference set is obtained; The perceptual multi-objective performance statistics are determined based on the final remaining difference set.

3. The method for statistically analyzing multi-objective performance of perception according to claim 2, characterized in that: Perform multi-target matching and difference threshold judgment, including: Generate a perception estimation multi-target matrix, and determine a difference matrix between the perception estimation multi-target matrix and the perception true multi-target matrix; Matching the perceived estimated multi-targets and the perceived real multi-targets based on the difference matrix to determine a second perceived estimated multi-target vector, a second perceived real multi-target vector, and a difference vector; Based on a preset difference threshold, the differences in the matched difference vector that are greater than the difference threshold are removed, the perceived estimated targets corresponding to the differences in the second perceived estimated multi-target vector, and the perceived real targets corresponding to the differences in the second perceived real multi-target vector.

4. The method for statistically analyzing multi-objective performance of perception according to claim 3, characterized in that: Generate a perceptual estimation multi-target matrix, including: Determining a first perceptual estimation multi-target vector based on the perceptual estimation result; The first perceptual estimation multi-target vector is repeated M rows to generate a perceptual estimation multi-target matrix; wherein M represents the number of perceived real multi-targets.

5. The method for statistically analyzing multi-objective performance of perception according to claim 3, characterized in that: Perform multi-target matching and difference threshold judgment, including: The preset first perceived true multi-target vector is transposed and repeated N columns to generate a perceived true multi-target matrix; wherein N represents the number of perceived estimated multi-targets.

6. The method for perceptual multi-objective performance statistics according to claim 2, characterized in that: The perception multi-objective performance statistics are determined based on the final remaining difference set, including: Based on the final remaining difference set, determine the number of targets L that exist and are successfully estimated D , the number of targets detected but without true value L FA and the number of targets L that exist but are not detected MD ; Based on the L D , the L FA and the L MD Determine the perceptual multi-objective performance statistics.

7. The method for perceptual multi-objective performance statistics according to any one of claims 1 to 6, characterized in that: The perceptual multi-objective performance statistical results include one or more of the following: Perceptual accuracy; Detection success rate; False alarm rate; Missed detection rate.

8. The method for perceptual multi-objective performance statistics according to any one of claims 1 to 6, characterized in that: The method further comprises: A perceptual estimation algorithm used for perceptual estimation is adjusted based on perceptual multi-objective performance statistics.

9. The method for perceptual multi-objective performance statistics according to any one of claims 1 to 6, characterized in that: The method further comprises: The time-frequency resources and / or coding sequences used to transmit the perception signal are adjusted based on the perception multi-objective performance statistics.

10. The method for perceptual multi-objective performance statistics according to any one of claims 1 to 6, characterized in that: The method further comprises: The threshold of the perceptual recognition algorithm used for perceptual multi-target recognition is adjusted based on the perceptual multi-target performance statistical results.

11. An electronic device, characterized in that: Including memory, transceiver, processor; a memory for storing a computer program; a transceiver for transmitting and receiving data under the control of the processor; A processor is configured to read the computer program in the memory and perform the following operations: Performing perceptual estimation on the perceptual signal to determine a perceptual two-dimensional map; Performing perceptual multi-target recognition on the perceptual two-dimensional image to obtain multiple perceptual estimation targets; The performance statistics of multiple perception estimation targets are performed to determine the perception multi-target performance statistics results.

12. The electronic device according to claim 11, characterized in that: Perform performance statistics on multiple perception estimation targets and determine the perception multi-target performance statistics results, including: After multiple multi-target matching and difference threshold judgment, the final remaining difference set is obtained; The perceptual multi-objective performance statistics are determined based on the final remaining difference set.

13. The electronic device according to claim 12, characterized in that: Perform multi-target matching and difference threshold judgment, including: Generate a perception estimation multi-target matrix, and determine a difference matrix between the perception estimation multi-target matrix and the perception true multi-target matrix; Matching the perceived estimated multi-targets and the perceived real multi-targets based on the difference matrix to determine a second perceived estimated multi-target vector, a second perceived real multi-target vector, and a difference vector; Based on a preset difference threshold, the differences in the matched difference vector that are greater than the difference threshold are removed, the perceived estimated targets corresponding to the differences in the second perceived estimated multi-target vector, and the perceived real targets corresponding to the differences in the second perceived real multi-target vector.

14. The electronic device according to claim 13, characterized in that: Generate a perceptual estimation multi-target matrix, including: Determining a first perceptual estimation multi-target vector based on the perceptual estimation result; The first perceptual estimation multi-target vector is repeated M rows to generate a perceptual estimation multi-target matrix; wherein M represents the number of perceived real multi-targets.

15. The electronic device according to claim 13, characterized in that: Perform multi-target matching and difference threshold judgment, including: The preset first perceived true multi-target vector is transposed and repeated N columns to generate a perceived true multi-target matrix; wherein N represents the number of perceived estimated multi-targets.

16. The electronic device according to claim 12, characterized in that: The perception multi-objective performance statistics are determined based on the final remaining difference set, including: Based on the final remaining difference set, determine the number of targets L that exist and are successfully estimated D , the number of targets detected but without true value L FA and the number of targets L that exist but are not detected MD ; Based on the L D , the L FA and the L MD Determine the perceptual multi-objective performance statistics.

17. The electronic device according to any one of claims 11 to 16, characterized in that: The perceptual multi-objective performance statistical results include one or more of the following: Perceptual accuracy; Detection success rate; False alarm rate; Missed detection rate.

18. The electronic device according to any one of claims 11 to 16, characterized in that: The processor is further configured to read the computer program in the memory and perform the following operations: A perceptual estimation algorithm used for perceptual estimation is adjusted based on perceptual multi-objective performance statistics.

19. The electronic device according to any one of claims 11 to 16, characterized in that: The processor is further configured to read the computer program in the memory and perform the following operations: The time-frequency resources and / or coding sequences used to transmit the perception signal are adjusted based on the perception multi-objective performance statistics.

20. The electronic device according to any one of claims 11 to 16, characterized in that: The processor is further configured to read the computer program in the memory and perform the following operations: The threshold of the perceptual recognition algorithm used for perceptual multi-target recognition is adjusted based on the perceptual multi-target performance statistical results.

21. A device for perceiving multi-objective performance statistics, characterized in that: include: A perception estimation module, used for performing perception estimation on the perception signal and determining a perception two-dimensional map; A perception recognition module, used for performing perception multi-target recognition on the perception two-dimensional image to obtain multiple perception estimation targets; The performance statistics module is used to perform performance statistics on multiple perception estimation targets and determine the perception multi-target performance statistics results.

22. A non-transitory readable storage medium, characterized in that: The non-transitory readable storage medium stores a computer program, and the computer program is used to enable a processor to execute the perceptual multi-objective performance statistics method according to any one of claims 1 to 10.

Images