False track identification method and system based on millimeter wave radar, and related equipment

Abstract

The embodiment of the invention provides a false track identification method and system based on a millimeter wave radar and related equipment, and relates to the technical field of radar detection, and the method comprises the steps: determining the target time complexity to be smaller than or equal to a first threshold value, and / or determining the target space complexity to be smaller than or equal to a second threshold value, determining a target identification area according to the driving state and / or the driving road condition of the target vehicle; according to the target track characteristics corresponding to the target identification area, identifying a target false track; wherein the false track ratio corresponding to the target identification area is greater than or equal to a third threshold value. According to the method and the device, the applicability to situations with low time complexity and / or space complexity can be improved, and the identification precision and the identification efficiency of the false track can be improved by reserving the original information of the data.

Description

Technical Field

[0001] Embodiments of the present application relate to the technical field of radar detection, and in particular, to a method, system, and related device for identifying false tracks based on millimeter-wave radar. Background Art

[0002] Millimeter-wave radar is widely used in environmental perception during vehicle driving and is very important for the detection and tracking of road targets.

[0003] In related technologies, the identification of false tracks is mostly based on multi-sensor data fusion and combined with a confidence algorithm. The above method is prone to loss of original data information, resulting in a relatively high risk of misjudging false tracks.

[0004] Therefore, there is an urgent need for a new technical solution to solve the above technical problems. Summary of the Invention

[0005] According to the embodiments of the present application, a method, system, and related device for identifying false tracks based on millimeter-wave radar are provided, which can improve the applicability to situations with lower time complexity and / or space complexity, and is beneficial to improving the identification accuracy and efficiency of false tracks by retaining the original data information.

[0006] In the first aspect of the present application, a method for identifying false tracks based on millimeter-wave radar is provided, which is applicable to a single sensor and includes: When it is determined that the target time complexity is less than or equal to the first threshold and / or the target space complexity is less than or equal to the second threshold, Determine a target recognition area according to the driving state of the target vehicle and / or the driving road conditions; Identify the target false track according to the target track features corresponding to the target recognition area; Wherein, the false track ratio corresponding to the target recognition area is greater than or equal to the third threshold.

[0007] In some feasible embodiments, the above determining the target recognition area according to the driving state of the target vehicle and / or the driving road conditions includes: When the driving state corresponds to a straight-ahead state, determining the target recognition area includes: a first target area and / or a second target area; Wherein, the first target area corresponds to a spatial area where the probability of speed distortion of the first-direction track is greater than or equal to the fourth threshold, and the second target area corresponds to a spatial area where the probability of mirroring of the second-direction track is greater than or equal to the fifth threshold; and / or, When the driving state corresponds to a turning state, determining the target recognition area includes: a third target area; Among them, the third target area corresponds to a spatial area centered on the target vehicle, with a distance radius less than or equal to a preset distance radius, and the probability of misjudging a stationary target as a dynamic target is greater than or equal to a sixth threshold value.

[0008] In some feasible embodiments, the above-mentioned target track features include: Target duration feature, target signal-to-noise ratio feature, average value feature of the radial velocity of target associated points, target heading angle feature, and / or target cross-sectional area feature.

[0009] In some feasible embodiments, the above-mentioned identifying of false target tracks according to the target track features corresponding to the target recognition area includes: Determining a first interval probability mapping sequence according to the target duration feature corresponding to the target track test data; Determining a second interval probability mapping sequence according to the target signal-to-noise ratio feature corresponding to the target track test data; and / or Determining a third interval probability mapping sequence according to the average value feature of the radial velocity of target associated points corresponding to the target track test data.

[0010] In some feasible embodiments, the above-mentioned identifying of false target tracks according to the target track features corresponding to the target recognition area further includes: Determining the falsity of the target frame according to the target duration feature corresponding to the target frame and the first interval probability mapping sequence; Determining the falsity of the target frame according to the target signal-to-noise ratio feature corresponding to the target frame and the second interval probability mapping sequence; and / or Determining the falsity of the target frame according to the average value feature of the radial velocity of target associated points corresponding to the target frame and the third interval probability mapping sequence.

[0011] In some feasible embodiments, the above method further includes: Determining a first target probability and a second target probability according to the target duration feature corresponding to the target frame and the first interval probability mapping sequence; Determining a third target probability and a fourth target probability according to the target signal-to-noise ratio feature corresponding to the target frame and the second interval probability mapping sequence; Determining a fifth target probability and a sixth target probability according to the average value feature of the radial velocity of target associated points corresponding to the target frame and the third interval probability mapping; When the product of the first target probability, the third target probability, the fifth target probability and the false track ratio corresponding to the target recognition area is greater than the product of the second target probability, the fourth target probability, the sixth target probability and the true track ratio corresponding to the target recognition area, determining that the target frame is a false frame.

[0012] In some feasible embodiments, the above method further includes: When it is determined that there are multiple false frames continuously existing in the target track and the number of false frames is greater than or equal to a preset number, the target track is determined as a target false track.

[0013] In a second aspect of the present application, a false track recognition system based on a millimeter-wave radar is provided, including: A determination unit, configured to determine a target recognition area according to the driving state of a target vehicle and / or the driving road condition when it is determined that the target time complexity is less than or equal to a first threshold and / or the target space complexity is less than or equal to a second threshold; An identification unit, configured to identify a target false track according to the target track feature corresponding to the target recognition area; Wherein, the false track ratio corresponding to the target recognition area is greater than or equal to a third threshold.

[0014] In a third aspect of the present application, an electronic device is provided, including a processor and a memory. Wherein, computer program instructions are stored in the memory, and when the computer program instructions are run by the processor, they are used to execute the false track recognition method based on a millimeter-wave radar as described in any one of the above.

[0015] In a fourth aspect of the present application, a storage medium is provided, on which program instructions are stored, and when the program instructions are run, they are used to execute the false track recognition method based on a millimeter-wave radar as described in any one of the above.

[0016] The false track recognition method, system and related devices based on a millimeter-wave radar provided by the embodiments of the present application are applicable to a single sensor. Wherein, the method includes: when it is determined that the target time complexity is less than or equal to a first threshold and / or the target space complexity is less than or equal to a second threshold, determining a target recognition area according to the driving state of the target vehicle and / or the driving road condition; identifying a target false track according to the target track feature corresponding to the target recognition area; wherein, the false track ratio corresponding to the target recognition area is greater than or equal to a third threshold. The present application can improve the applicability to situations with lower time complexity and / or space complexity, and is beneficial to improving the recognition accuracy and recognition efficiency of false tracks by retaining the original information of the data.

[0017] It should be understood that the content described in the summary of the invention is not intended to limit the key or important features of the embodiments of the present application, nor to limit the scope of the present application. Other features of the present application will become easily understandable through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In combination with the accompanying drawings and with reference to the following detailed description, the above and other features, advantages, and aspects of the embodiments of the present application will become more apparent. In the drawings, the same or similar reference numerals denote the same or similar elements, where: Figure 1 It is a flowchart of a false track recognition method based on a millimeter-wave radar provided by an embodiment of the present application; Figure 2 It is a structural diagram of a false track recognition system based on a millimeter-wave radar provided by an embodiment of the present application; Figure 3 It is a structural diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Apparently, the described embodiments are some, but not all, of the embodiments of the present disclosure. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present disclosure without creative efforts shall fall within the protection scope of the present disclosure.

[0020] In addition, the term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally represents an "or" relationship between the associated objects before and after.

[0021] Millimeter-wave radars are widely used in environmental perception during vehicle driving and are very important for the detection and tracking of road targets.

[0022] In the prior art, the recognition of false tracks is mostly based on multi-sensor data fusion and is realized by combining a confidence algorithm. There is heterogeneity among the data collected by the above multi-sensors, and feature-level fusion or decision-level fusion is likely to cause loss of the original information of the data, resulting in a relatively high risk of misjudgment of false tracks. In addition, the above methods also have problems such as high computing power requirements and high hardware costs.

[0023] Based on this, the present application provides a false track recognition method based on a millimeter-wave radar, which is applicable to a single sensor. Figure 1 It is a flowchart of a false track recognition method 100 based on a millimeter-wave radar provided by an embodiment of the present application. As Figure 1 shown, the method 100 includes: Step S1; when it is determined that the target time complexity is less than or equal to the first threshold, and / or the target space complexity is less than or equal to the second threshold, determine the target recognition area according to the driving state of the target vehicle and / or the driving road condition.

[0024] It should be noted that the above first threshold corresponds to a preset time complexity threshold; the above second threshold corresponds to a preset space complexity. Among them, the above first threshold and the above second threshold are negatively correlated with the recognition accuracy requirement of false tracks, that is, the higher the recognition accuracy requirement of false tracks, the smaller the above first threshold and the above second threshold.

[0025] Exemplarily, when it is determined that the target time complexity corresponding to the target scenario is less than or equal to the first threshold, and / or the target space complexity is less than or equal to the second threshold, determine the target recognition area according to the driving state of the target vehicle and / or the driving road condition.

[0026] It should be noted that by determining the target recognition area according to the driving state of the target vehicle and / or the driving road condition when it is determined that the target time complexity is less than or equal to the first threshold, it is beneficial to improve the operation efficiency and response speed of this method, reduce the delay rate of this method, so as to complete the determination of the above target recognition area in a relatively short time. And / or, by determining the target recognition area according to the driving state of the target vehicle and / or the driving road condition when it is determined that the target space complexity is less than or equal to the second threshold, it is beneficial to reduce the memory resources required during the execution of this method, thereby reducing the hardware cost during the execution of this method.

[0027] It should be noted that among them, the false track ratio corresponding to the target recognition area is greater than or equal to the third threshold, that is, the target recognition area is a spatial area with a relatively high occurrence frequency of false tracks determined according to the statistics of a large amount of road test data. Among them, the range of the above spatial area can be determined according to the installation position of the millimeter wave radar. The above large amount of road test data can include: test data with a mileage of greater than or equal to 1000 km.

[0028] Among them, the false track ratio corresponding to the above target recognition area can be determined according to the ratio of the sum of the continuous existence times of each false track in the target spatial area to the total driving time of the vehicle.

[0029] Among them, the above third threshold can be determined according to the recognition accuracy requirement of false tracks, and the above third threshold is negatively correlated with the recognition accuracy requirement of false tracks, that is, the higher the recognition accuracy requirement of false tracks, the smaller the above third threshold.

[0030] In some feasible embodiments, determining the target recognition area according to the driving state of the target vehicle and / or the driving road condition includes: when the driving state corresponds to a straight-ahead state, determining that the target recognition area includes: a first target area and / or a second target area; wherein, the first target area corresponds to a spatial area where the probability of speed distortion occurring in the first-direction track is greater than or equal to a fourth threshold, and the second target area corresponds to a spatial area where the probability of mirroring occurring in the second-direction track is greater than or equal to a fifth threshold.

[0031] It should be noted that the above-mentioned fourth threshold and the above-mentioned fifth threshold are negatively correlated with the recognition accuracy requirement of false tracks, that is, the higher the recognition accuracy requirement of false tracks, the smaller the above-mentioned fourth threshold and the above-mentioned fifth threshold.

[0032] Exemplarily, when it is determined that the driving state of the target vehicle corresponds to a straight-ahead state, it can be determined that the target recognition area includes: the first target area, that is, the spatial area in front of the target vehicle where false tracks with speed anomalies are likely to occur, and / or the second target area, that is, the spatial area on the side of the target vehicle where mirror false tracks are likely to occur.

[0033] It should be noted that the above-mentioned first target area can be a rectangular spatial area, and the above-mentioned second target area can be a strip-shaped spatial area.

[0034] In some feasible embodiments, determining the target recognition area according to the driving state of the target vehicle and / or the driving road condition, and / or further includes: when the driving state corresponds to a turning state, determining that the target recognition area includes: a third target area; wherein, the third target area corresponds to a spatial area centered on the target vehicle, with a distance radius less than or equal to a preset distance radius, and the probability of misjudging a stationary target as a dynamic target is greater than or equal to a sixth threshold.

[0035] It should be noted that the above-mentioned sixth threshold is negatively correlated with the recognition accuracy requirement of false tracks, that is, the higher the recognition accuracy requirement of false tracks, the smaller the above-mentioned sixth threshold. The above-mentioned preset distance radius can be determined according to the installation position of the millimeter-wave radar.

[0036] Exemplarily, when it is determined that the driving state of the target vehicle corresponds to a turning state, it is determined that the target recognition area includes: the third target area, that is, the spatial area centered on the target vehicle, with a distance radius less than or equal to a preset distance radius, where stationary targets are prone to false movement.

[0037] It should be noted that the above-mentioned third target area can be a fan-shaped spatial area.

[0038] It should be noted that in the case where the driving road condition of the target vehicle corresponds to the urban interchange road condition or the rural mountainous road condition, the above-mentioned target recognition area can be determined according to the actual situation.

[0039] Thus, the above method can accurately and automatically determine the target recognition area according to the driving state of the target vehicle and / or the driving road condition, which is used to identify the target false track. It is beneficial to improve the recognition accuracy and efficiency of the target false track by improving the matching degree between the target recognition area and the driving state of the target vehicle and / or the driving road condition.

[0040] Step S2: Identify the target false track according to the target track feature corresponding to the target recognition area.

[0041] Exemplarily, based on the electromagnetic wave scattering principle, the target track features corresponding to multiple target recognition areas can be determined to identify the target false track, where the target track features corresponding to the above multiple target recognition areas may be different.

[0042] Specifically, the recognition operation can be performed on all target recognition areas until each track in the target recognition area has been recognized and processed.

[0043] In some feasible embodiments, the above target track features include: target duration feature, target signal-to-noise ratio feature, average value feature of the radial velocity of the target correlation point, target heading angle feature, and / or target scattering cross-section feature.

[0044] Exemplarily, the target false track can be identified according to the target duration feature, target signal-to-noise ratio feature, average value feature of the radial velocity of the target correlation point, target heading angle feature, and / or target scattering cross-section feature corresponding to the target recognition area.

[0045] It should be noted that the main causes of false tracks mainly include: insufficient angular resolution, strong reflection objects, multipath, and reflection, etc. Thus, by identifying the target false track according to the target duration feature, target signal-to-noise ratio feature, average value feature of the radial velocity of the target correlation point, target heading angle feature, and / or target scattering cross-section feature corresponding to the target recognition area, it is beneficial to further improve the recognition accuracy and efficiency of the target false track.

[0046] Based on this, the false track recognition method based on millimeter-wave radar provided by the embodiments of the present application is applicable to a single sensor, and includes: when it is determined that the target time complexity is less than or equal to the first threshold, and / or the target space complexity is less than or equal to the second threshold, automatically and accurately determining the target recognition area according to the driving state of the target vehicle and / or the driving road conditions; automatically and accurately identifying the target false track according to the target track feature corresponding to the target recognition area; wherein, the false track ratio corresponding to the target recognition area is greater than or equal to the third threshold. The present application can improve the applicability to scenarios with lower time complexity and / or space complexity. The present application is conducive to avoiding heterogeneity between data without performing additional fusion operations on the data, and is conducive to accurately retaining the original information of the data while reducing the hardware cost and computing power requirements, thereby improving the recognition accuracy and efficiency of false tracks.

[0047] In some feasible implementation manners, step S2; the above-mentioned identifying the target false track according to the target track feature corresponding to the target recognition area includes: Step S2a; determining the first interval probability mapping sequence according to the target duration feature corresponding to the target track test data.

[0048] Exemplarily, the above-mentioned target duration feature may include: the existence duration feature before the start of the track.

[0049] Exemplarily, the first interval sequence may be divided and generated according to the target duration feature, and according to the above-mentioned first interval sequence, the first probability sequence may be determined to generate the first interval probability mapping sequence.

[0050] Specifically, it may be divided and generated according to the target duration feature different intervals to generate the above-mentioned first interval sequence, and based on the Bayesian algorithm, the probability sequence of the occurrence of false tracks and the probability sequence of the occurrence of true tracks corresponding to the first interval sequence are determined. According to the probability sequence of the occurrence of false tracks and the probability sequence of the occurrence of true tracks corresponding to the first interval sequence, the first probability sequence is determined. According to the mapping relationship between the above-mentioned different intervals and the above-mentioned first probability sequence, the first interval probability mapping sequence is determined.

[0051] Among them, the probability sequence of the occurrence of false tracks corresponding to the above-mentioned first interval sequence may be expressed as: (1)

[0052] Among them, the probability sequence of the occurrence of true tracks corresponding to the above-mentioned first interval sequence may be expressed as: (2) It should be noted that the sum of the probability sequence corresponding to the false track appearance in the above first interval sequence and the corresponding elements of the above first interval sequence is 1.

[0053] Step S2b; determine the second interval probability mapping sequence according to the target signal-to-noise ratio characteristics corresponding to the target track test data.

[0054] Exemplarily, the second interval sequence can be divided and generated according to the target signal-to-noise ratio characteristics, and the second probability sequence can be determined according to the above second interval sequence to generate the second interval probability mapping sequence.

[0055] Specifically, it can be divided and generated according to the target duration characteristics a number of different intervals to generate the above second interval sequence, determine the probability sequence of false track appearance and the probability sequence of true track appearance corresponding to the second interval sequence based on the Bayesian algorithm, determine the second probability sequence according to the probability sequence of false track appearance and the probability sequence of true track appearance corresponding to the second interval sequence, and determine the second interval probability mapping sequence according to the mapping relationship between the above number of different intervals and the above second probability sequence.

[0056] Among them, the probability sequence of false track appearance corresponding to the above second interval sequence can be expressed as: (3) Among them, the probability sequence of true track appearance corresponding to the above second interval sequence can be expressed as: (4) It should be noted that the sum of the probability sequence of false track appearance corresponding to the above second interval sequence and the corresponding elements of the above second interval sequence is 1. For example: the above and the above sum to 1.

[0057] And / or, step S2c; determine the third interval probability mapping sequence according to the average value characteristic of the radial velocity of the target associated point corresponding to the target track test data.

[0058] It should be noted that the single dot produced by the millimeter-wave radar cannot confirm whether it belongs to the same target. Therefore, the above target associated point can be determined based on a preset algorithm to determine the above third interval probability mapping sequence. Among them, the above preset algorithm includes: DBSCAN algorithm and Nearest Neighbor (NN) algorithm.

[0059] Exemplarily, based on the DBSCAN algorithm, the target adjacent traces can be determined and merged to determine the initial value of the target track; taking the initial value of the target track as the starting point of the target track, based on the nearest neighbor algorithm, the above-mentioned target associated traces can be determined to determine the above-mentioned third interval probability mapping sequence. Among them, the above-mentioned target associated traces correspond to the traces whose Euclidean distance from the above-mentioned target track is less than the preset distance. It can be understood that the above-mentioned target associated traces correspond to the above-mentioned target track, and the above-mentioned preset distance can be defined according to the actual scenario.

[0060] Exemplarily, according to the target signal-to-noise ratio characteristics, the third interval sequence can be divided and generated, and according to the above-mentioned third interval sequence, the third probability sequence can be determined to generate the third interval probability mapping sequence.

[0061] Specifically, it can be divided and generated according to the target duration characteristics a number of different intervals to generate the above-mentioned third interval sequence, and based on the Bayesian algorithm, the probability sequence of false track appearance and the probability sequence of true track appearance corresponding to the third interval sequence are determined. According to the probability sequence of false track appearance and the probability sequence of true track appearance corresponding to the third interval sequence, the third probability sequence is determined. According to the mapping relationship between the number of different intervals and the above-mentioned third probability sequence, the third interval probability mapping sequence is determined.

[0062] Among them, the probability sequence of false track appearance corresponding to the above-mentioned third interval sequence can be expressed as: (5) Among them, the probability sequence of true track appearance corresponding to the above-mentioned third interval sequence can be expressed as: (6) It should be noted that the sum of the probability sequence of false track appearance corresponding to the above-mentioned third interval sequence and the corresponding elements of the above-mentioned third interval sequence is 1. For example: the above and the above sum to 1.

[0063] Thus, the above method can accurately and automatically determine the first interval probability mapping sequence according to the target duration characteristics; accurately and automatically determine the second interval probability mapping sequence according to the target signal-to-noise ratio characteristics; accurately and automatically determine the third interval probability mapping sequence according to the average value characteristics of the radial velocity of the target associated traces, providing data support for accurately identifying target false traces according to the first interval probability mapping sequence, the second interval probability mapping sequence, and / or the third interval probability mapping sequence.

[0064] In some feasible embodiments, the above step S2; identifying the target false track according to the target track characteristics corresponding to the target recognition area further includes: Step S2d; Determine the falsity of the target frame according to the target duration feature corresponding to the target frame and the first interval probability mapping sequence.

[0065] Exemplarily, when the target duration feature corresponding to the target frame is in the th interval, the probability that the target frame is a false frame can be determined according to the first interval probability mapping sequence as , and the probability that the target frame is a non-false frame, that is, a true frame, is . When the probability that the target frame is a false frame is greater than the probability that the target frame is a non-false frame, that is, a true frame, which is , the target frame can be determined to be a false frame. When the probability that the target frame is a false frame is less than or equal to the probability that the target frame is a non-false frame, that is, a true frame, which is , the target frame can be determined to be a non-false frame, that is, a true frame.

[0066] Specifically, when the existence duration feature before the start corresponding to the target frame is in the th interval, the probability that the target frame is a false frame can be determined according to the first interval probability mapping sequence as , and the probability that the target frame is a non-false frame, that is, a true frame, is . When the probability that the target frame is a false frame is greater than the probability that the target frame is a non-false frame, that is, a true frame, which is , the target frame can be determined to be a false frame. When the probability that the target frame is a false frame is less than or equal to the probability that the target frame is a non-false frame, that is, a true frame, which is , the target frame can be determined to be a non-false frame, that is, a true frame.

[0067] Step S2e; Determine the falsity of the target frame according to the target signal-to-noise ratio feature corresponding to the target frame and the second interval probability mapping sequence.

[0068] Exemplarily, when the target signal-to-noise ratio feature corresponding to the target frame is in the th interval, the probability that the target frame is a false frame can be determined according to the second interval probability mapping sequence as , and the probability that the target frame is a non-false frame, that is, a true frame, is . When the probability that the target frame is a false frame is greater than the probability that the target frame is a non-false frame, that is, a true frame, which is , the target frame can be determined to be a false frame. When the probability that the target frame is a false frame is less than or equal to the probability that the target frame is a non-false frame, that is, a true frame, is In this case, it can be determined that the target frame is a non-false frame, that is, a true frame.

[0069] And / or Step S2f; Determine the falsity of the target frame according to the average value feature of the radial velocity of the target association points corresponding to the target frame and the third interval probability mapping sequence.

[0070] Exemplarily, when the average value feature of the radial velocity of the target association points corresponding to the target frame is in the th interval, the probability that the target frame is a false frame can be determined according to the third interval probability mapping sequence as , and the probability that the target frame is a non-false frame, that is, a true frame, is When it is determined that the probability that the target frame is a false frame is greater than the probability that the target frame is a non-false frame, that is, a true frame, which is , it can be determined that the target frame is a false frame. When it is determined that the probability that the target frame is a false frame is less than or equal to the probability that the target frame is a non-false frame, that is, a true frame, which is , it can be determined that the target frame is a non-false frame, that is, a true frame.

[0071] Thus, the above method can accurately and automatically identify false frames in the target track according to the target duration feature and the first interval probability mapping sequence corresponding to the target frame, the target signal-to-noise ratio feature and the second interval probability mapping sequence corresponding to the target frame, and / or the average value feature of the radial velocity of the target association points corresponding to the target frame and the third interval probability mapping sequence, providing data support for accurately identifying false target tracks.

[0072] In some feasible embodiments, the above method further includes: Step S2g; Determine the first target probability and the second target probability according to the target duration feature and the first interval probability mapping sequence corresponding to the target frame.

[0073] Exemplarily, when the target duration feature corresponding to the target frame is in the th interval, the first target probability, that is, the probability that the target frame is a false frame, can be determined according to the first interval probability mapping sequence as , and the second target probability, that is, the probability that the target frame is a true frame, is .

[0074] Step S2h; Determine the third target probability and the fourth target probability according to the target signal-to-noise ratio feature and the second interval probability mapping sequence corresponding to the target frame.

[0075] Exemplarily, when the target duration feature corresponding to the target frame is in the In the case of a certain number of intervals, the third target probability, that is, the probability that the target frame is a false frame, can be determined according to the second interval probability mapping sequence as , and the second target probability, that is, the probability that the target frame is a true frame, is .

[0076] Step S2i: Determine the fifth target probability and the sixth target probability according to the average value feature of the radial velocity of the target association point corresponding to the target frame and the third interval probability mapping.

[0077] Exemplarily, when the average value feature of the radial velocity of the target association point corresponding to the target frame is in the th interval, the fifth target probability, that is, the probability that the target frame is a false frame, can be determined according to the third interval probability mapping sequence as , and the sixth target probability, that is, the probability that the target frame is a true frame, is .

[0078] Step S2j: Determine that the target frame is a false frame when the product of the first target probability, the third target probability, the fifth target probability, and the false track ratio corresponding to the target recognition area is greater than the product of the second target probability, the fourth target probability, the sixth target probability, and the true track ratio corresponding to the target recognition area.

[0079] It should be noted that the false track ratio corresponding to the above target recognition area can be determined according to the ratio of the sum of the persistent times of each false track in the target space area to the total driving time of the vehicle. The false track ratio corresponding to the above target recognition area can be represented by ; the true track ratio corresponding to the above target recognition area can be determined according to the ratio of the sum of the persistent times of each true track in the target space area to the total driving time of the vehicle. The true track ratio corresponding to the above target recognition area can be represented by . Among them, the false track ratio corresponding to the above target recognition area and the true track ratio corresponding to the above target recognition area sum to 1.

[0080] Exemplarily, the falsity of the target frame can be judged according to the following formula: (7) where is the first target probability, is the third target probability, is the fifth target probability, is the false track ratio corresponding to the target recognition area, is the second target probability, is the fourth target probability, is the sixth target probability. is the actual track ratio corresponding to the target identification area.

[0081] Therefore, the above method can realize accurate and automatic identification of false frames in the target track based on the first target probability, the second target probability, the third target probability, the fourth target probability, the fifth target probability, the sixth target probability, the false track ratio corresponding to the target identification area, and the true track ratio corresponding to the target identification area, thereby providing data support for accurate identification of target false tracks.

[0082] It should be noted that the above steps S2a to S2j can be implemented based on a Bayesian classifier, so as to achieve stable classification of the target frame according to the target duration feature, the target signal-to-noise ratio feature, and / or the average value feature of the radial velocity of the target associated point, so as to determine the falsity of the target frame. Among them, the above Bayesian classifier can calculate the posterior probability of the target frame by using the Bayesian formula through the prior probability of the target frame, that is, determine the probability that the target frame belongs to a false frame or a real frame, and select the corresponding category with the maximum posterior probability as the category to which the target frame belongs.

[0083] In some feasible implementations, the above method further includes: Step S2k: When it is determined that there are multiple false frames in succession in the target track, and the number of false frames is greater than or equal to a preset number, the target track is determined to be a target false track.

[0084] It should be noted that the above-mentioned preset number is negatively correlated with the recognition accuracy requirement of the false track, that is, the higher the recognition accuracy requirement of the false track is, the smaller the above-mentioned preset number is.

[0085] Exemplarily, when it is determined that a plurality of false frames exist continuously in the target track, and the number of the false frames is greater than or equal to 3, the target track is determined to be a target false track.

[0086] Therefore, the above method can accurately identify the target false track according to the number of false frames, thereby improving the recognition accuracy and recognition efficiency of the target false track.

[0087] In some feasible implementations, the above method further includes: Step S3: when it is determined that the target track is a false target track, canceling the alarm signal and / or deleting the target track.

[0088] It should be noted that, when the target track is determined to be a target false track, the alarm signal is controlled to be released at the current moment, and / or, when the target track is determined to be a target false track, the target track is deleted and is not at the start.

[0089] Therefore, the above method can accurately reduce the false alarm probability of the intelligent driving system.

[0090] It should be noted that when it is determined that the target track is the target true track, the alarm signal is not lifted, and / or when it is determined that the target track is the target true track, the normal start and output of the target track are controlled.

[0091] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0092] The above is the introduction of the method embodiments. The following further illustrates the solution of the present application through system embodiments.

[0093] According to the second aspect of the present application, the present application provides a false track recognition system based on a millimeter-wave radar. Figure 2 It is a structural schematic diagram of a false track recognition system 200 provided for an embodiment of the present application, as Figure 2 shown, the system 200 includes: a determination unit 210 and an identification unit 220.

[0094] The determination unit 210 is configured to determine a target recognition area according to the driving state and / or driving road conditions of the target vehicle when it is determined that the target time complexity is less than or equal to a first threshold, and / or the target space complexity is less than or equal to a second threshold; The identification unit 220 is configured to identify a target false track according to the target track feature corresponding to the target recognition area; Wherein, the false track ratio corresponding to the target recognition area is greater than or equal to a third threshold.

[0095] Exemplarily, Figure 3 shows a structural schematic diagram of a terminal device or a server suitable for implementing the embodiments of the present application.

[0096] As Figure 3As shown, the terminal device or server includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage section 308 into the random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the terminal device or server are also stored. The CPU 301, ROM 302, and RAM 303 are connected to each other via a bus 304. The input / output (I / O) interface 305 is also connected to the bus 304.

[0097] The following components are connected to the I / O interface 305: an input section 306 including a keyboard, a mouse, etc.; an output section 307 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read from it can be installed into the storage section 308 as needed.

[0098] In particular, according to an embodiment of the present application, the above method flow steps can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program device, which includes a computer program carried on a machine-readable medium, and the computer program includes program codes for performing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network via the communication section 309, and / or installed from the removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, the above functions defined in the system of the present application are executed.

[0099] It should be noted that the computer-readable medium shown in this application can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of a computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this application, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0100] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program devices according to various embodiments of this application. In this regard, each block in a flowchart or block diagram can represent a module, a program segment, or a part of code, and the foregoing module, program segment, or part of code contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks can occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0101] The units or modules involved in the embodiments described in this application can be implemented in software or in hardware. The described units or modules can also be provided in a processor. Among them, the names of these units or modules do not, in some cases, constitute a limitation on the units or modules themselves.

[0102] As another aspect, this application also provides a computer-readable storage medium, which can be included in the electronic device described in the foregoing embodiments; or can exist alone without being assembled into the electronic device. The foregoing computer-readable storage medium stores one or more programs, and when the foregoing programs are executed by one or more processors, they implement the methods described in this application.

[0103] The above description is only a preferred embodiment of this application and an explanation of the technical principles applied. Those skilled in the art should understand that the scope of the application involved in this application is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the foregoing application concept. For example, the technical solutions formed by mutually replacing the above features with the technical features (but not limited to) having similar functions described in this application.

Claims

1. A method for identifying false tracks based on millimeter-wave radar, characterized in that, Applicable to a single sensor, including: When it is determined that the target time complexity is less than or equal to the first threshold, and / or the target space complexity is less than or equal to the second threshold, Determine the target recognition area according to the driving state of the target vehicle and / or the driving road condition; Identify the target false track according to the target track feature corresponding to the target recognition area; Wherein, the false track ratio corresponding to the target recognition area is greater than or equal to the third threshold.

2. The false track recognition method based on millimeter-wave radar according to claim 1, characterized in that The determining the target recognition area according to the driving state of the target vehicle and / or the driving road condition includes: When the driving state corresponds to a straight-ahead state, determining that the target recognition area includes: a first target area and / or a second target area; Wherein, the first target area corresponds to a spatial area where the probability of speed distortion of the first-direction track is greater than or equal to the fourth threshold, and the second target area corresponds to a spatial area where the probability of mirroring of the second-direction track is greater than or equal to the fifth threshold; And / or When the driving state corresponds to a turning state, determining that the target recognition area includes: a third target area; Wherein, the third target area corresponds to a spatial area centered on the target vehicle, with a distance radius less than or equal to a preset distance radius, and the probability of misjudging a stationary target as a dynamic target is greater than or equal to the sixth threshold.

3. The false track recognition method based on millimeter-wave radar according to claim 1, characterized in that The target track features include: Target duration feature, target signal-to-noise ratio feature, average value feature of the radial velocity of target associated points, target heading angle feature, and / or target scattering cross-sectional area feature.

4. The false track recognition method based on millimeter-wave radar according to claim 3, characterized in that The identifying the target false track according to the target track feature corresponding to the target recognition area includes: Determine the first interval probability mapping sequence according to the target duration feature corresponding to the target track test data; Determine the second interval probability mapping sequence according to the target signal-to-noise ratio feature corresponding to the target track test data; And / or Determine the third interval probability mapping sequence according to the average value feature of the radial velocity of target associated points corresponding to the target track test data.

5. The false track recognition method based on millimeter-wave radar according to claim 4, characterized in that, The identifying the target false track according to the target track feature corresponding to the target recognition area further includes: Determine the falsity of the target frame according to the target duration feature corresponding to the target frame and the first interval probability mapping sequence; Determine the falsity of the target frame according to the target signal-to-noise ratio feature corresponding to the target frame and the second interval probability mapping sequence; And / or Determine the falsity of the target frame according to the average value feature of the radial velocity of target associated points corresponding to the target frame and the third interval probability mapping sequence.

6. The false track recognition method based on millimeter wave radar according to claim 5, characterized in that, It further includes: Determine the first target probability and the second target probability according to the target duration feature corresponding to the target frame and the first interval probability mapping sequence; Determine the third target probability and the fourth target probability according to the target signal-to-noise ratio feature corresponding to the target frame and the second interval probability mapping sequence; Determine the fifth target probability and the sixth target probability according to the average value feature of the radial velocity of target associated points corresponding to the target frame and the third interval probability mapping. When the product of the first target probability, the third target probability, the fifth target probability, and the false track ratio corresponding to the target recognition area is greater than the product of the second target probability, the fourth target probability, the sixth target probability, and the true track ratio corresponding to the target recognition area, determine that the target frame is a false frame.

7. The false track recognition method based on millimeter-wave radar according to claim 6, characterized in that, It further includes: When it is determined that there are multiple consecutive false frames in the target track, and the number of false frames is greater than or equal to a preset number, then determine that the target track is a target false track.

8. A false track recognition system based on millimeter-wave radar, characterized in that, It includes: A determination unit, configured to determine a target recognition area according to the driving state and / or driving road conditions of a target vehicle when it is determined that the target time complexity is less than or equal to a first threshold and / or the target space complexity is less than or equal to a second threshold; An identification unit, configured to identify a target false track according to the target track feature corresponding to the target recognition area; Wherein, the false track ratio corresponding to the target recognition area is greater than or equal to a third threshold.

9. An electronic device, comprising a memory and a processor, wherein a computer program is stored on the memory, characterized in that, When the processor executes the computer program, it implements the false track recognition method based on a millimeter-wave radar according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the false track recognition method based on a millimeter-wave radar according to any one of claims 1 to 7.

Images