Method and device for executing recognition operation on target in area

Abstract

The invention relates to the technical field of target recognition, and particularly discloses a method and device for executing recognition operation on a target in an area, and the method comprises the steps: obtaining a recognition result through the collection moment of collection data collected by one data collector in different types of data collectors and the collection moment of collection data collected by the other data collector; according to the method, the time error of the data acquired by the other data acquisition unit is corrected, so that the timestamp error of different types of data sources can be reduced, and the acquired data of different data acquisition units at the same acquisition moment can be accurately acquired, and therefore, the information fusion effect of different types of data sources can be improved, and the accuracy of target identification can be improved.

Description

Technical Field

[0001] The present invention relates to the field of target recognition technology, and in particular to a method and device for performing recognition operations on targets in a region. Background Art

[0002] In real life, for various needs, such as safe driving and traffic optimization, it is often necessary to identify moving targets in order to achieve target tracking based on the target identification results. In order to achieve target identification, the existing methods often fuse the data collected by different types of data collectors to identify the target based on the fusion results, thereby achieving target tracking. For example, by fusing the data collected by the image collector and the data collected by the radar, the vehicle can be identified based on the fusion results, thereby achieving vehicle tracking.

[0003] However, in practice, it is found that due to the unstable frame rate of different types of data collectors, unstable network during transmission and other reasons, it is easy to cause large timestamp errors in the data acquired by various types of data collectors, thereby reducing the data fusion effect and further reducing the accuracy of target recognition.

[0004] Therefore, there is an urgent need to propose a technical solution on how to reduce the timestamp error of different types of data sources, thereby improving the information fusion effect of different types of data sources and improving the accuracy of target recognition. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide a method and device for performing identification operations on targets in an area, which can reduce the timestamp error of different types of data sources, thereby improving the information fusion effect of different types of data sources and improving the accuracy of target identification.

[0006] In order to solve the above technical problem, the first aspect of the present invention discloses a method for performing an identification operation on a target in a region, the method comprising:

[0007] Determine a reference correction object that matches a current scene in a first area, wherein the first area is provided with the reference correction object and a corrected object, wherein the reference correction object and the corrected object are different types of data collectors, wherein the reference correction object is used to perform a data collection operation on the first area to obtain collected data corresponding to the reference correction object and a collection time corresponding to the collected data, and wherein the corrected object is used to perform a data collection operation on the first area to obtain collected data corresponding to the corrected object and a collection time corresponding to the collected data;

[0008] Taking the acquisition time corresponding to the benchmark correction object as a benchmark, according to the acquisition time corresponding to the corrected object, acquiring the acquisition data that matches the acquisition time corresponding to the benchmark correction object from the acquisition data corresponding to the corrected object; wherein the acquisition data that matches the acquisition time corresponding to the benchmark correction object includes acquisition data whose acquisition time is later than the acquisition time corresponding to the benchmark correction object and acquisition data whose acquisition time is earlier than the acquisition time corresponding to the benchmark correction object;

[0009] Based on the acquisition time corresponding to the reference correction object, the acquisition data matching the acquisition time corresponding to the reference correction object, and the acquisition time corresponding to the acquisition data, a correction operation is performed on the acquisition data corresponding to the corrected object to obtain the corrected acquisition data of the corrected object at the acquisition time corresponding to the reference correction object;

[0010] The corrected collected data corresponding to the corrected object is used as a basis for performing a recognition operation on the target in the first area.

[0011] As an optional implementation, in the first aspect of the present invention, the acquisition data corresponding to the benchmark correction object is composed of at least one first sub-acquisition data, and the acquisition time corresponding to the benchmark correction object is composed of the first sub-acquisition time corresponding to all the first sub-acquisition data;

[0012] The acquisition data corresponding to the corrected object is composed of at least one second sub-acquisition data, and the acquisition moment corresponding to the corrected object is composed of the second sub-acquisition moments corresponding to all the second sub-acquisition data.

[0013] As an optional implementation, in the first aspect of the present invention, the performing of a correction operation on the collected data corresponding to the corrected object based on the collection time corresponding to the benchmark correction object, the collected data matching the collection time corresponding to the benchmark correction object, and the collection time corresponding to the collected data to obtain the corrected collected data of the corrected object at the collection time corresponding to the benchmark correction object includes:

[0014] For any first sub-collection moment corresponding to the reference correction object, based on the first sub-collection moment, from all second sub-collection moments, a first target sub-collection moment later than the first sub-collection moment and a second target sub-collection moment earlier than the first sub-collection moment are selected;

[0015] Determining a time correction parameter corresponding to the corrected object according to the first sub-collection time, the first target sub-collection time, and the second target sub-collection time;

[0016] Determine the acquisition data matching the first sub-acquisition moment according to the time correction parameter corresponding to the corrected object, the second sub-acquisition data corresponding to the first target sub-acquisition moment, and the second sub-acquisition data corresponding to the second target sub-acquisition moment;

[0017] The corrected acquisition data corresponding to the corrected object includes all acquisition data matching the first sub-acquisition moment.

[0018] As an optional embodiment, in the first aspect of the present invention, the method further comprises:

[0019] Filtering out first target acquisition data that needs to be parameter converted from the correction acquisition data corresponding to the corrected object and the acquisition data corresponding to the reference correction object;

[0020] Performing a parameter conversion operation matching the first target acquisition data on the first target acquisition data to obtain second target acquisition data after parameter conversion;

[0021] Based on the first target acquisition data and the third target acquisition data after parameter conversion, performing a fusion matching operation on the target in the first area to obtain a target matching result;

[0022] According to the target matching result, performing a feature assignment operation on the target in the first area;

[0023] The third target acquisition data is another acquisition data obtained by removing the first target acquisition data from the corrected acquisition data corresponding to the corrected object and the acquisition data corresponding to the reference correction object.

[0024] As an optional implementation, in the first aspect of the present invention, the target matching result includes a first target matching result and / or a second target matching result, wherein:

[0025] The first target matching result is used to represent all first targets that are successfully matched based on the collected data corresponding to the reference correction object and the corrected collected data corresponding to the corrected object;

[0026] The second target matching result is used to represent all second targets that are not successfully matched based on the collected data corresponding to the reference correction object and the corrected collected data corresponding to the corrected object.

[0027] As an optional implementation manner, in the first aspect of the present invention, performing a feature assignment operation on the target in the first area according to the target matching result includes:

[0028] When the target matching result includes the first target matching result, for any of the first targets, the features of the first target identified by the reference correction object and the features of the first target identified by the corrected object are added to the first target;

[0029] When the target matching result includes the second target matching result, determining a reference recognition parameter that matches the current scene of the first area, the reference recognition parameter including a reference distance, the reference distance being a distance determined based on a location of the reference correction object or a location of the corrected object;

[0030] Determine a second area according to the reference identification parameter, wherein the area range of the second area is smaller than the area range of the first area;

[0031] For any second target in the second area, determine the type of the collector that successfully identifies the second target, and when the type of the collector includes a type that matches the second area, determine a target collector that matches the type that matches the second area, and add the features identified by the target collector to the second target;

[0032] Among them, when the area range of the second area is the area formed by a distance less than or equal to the benchmark distance and the benchmark distance, the target collector is the benchmark correction object; when the area range of the second area is the area formed by a distance greater than the benchmark distance and the benchmark distance, the target collector is the corrected object.

[0033] As an optional implementation manner, in the first aspect of the present invention, performing a parameter conversion operation matching the first target acquisition data on the first target acquisition data to obtain second target acquisition data after parameter conversion includes:

[0034] When the first target acquisition data is the corrected acquisition data corresponding to the corrected object, a parameter conversion operation is performed on the first target acquisition data based on the conversion parameters matching the reference corrected object to obtain second target acquisition data after parameter conversion;

[0035] When the first target acquisition data is the acquisition data corresponding to the reference correction object, a parameter conversion operation is performed on the first target acquisition data based on the conversion parameters matching the corrected object to obtain the second target acquisition data after the parameter conversion.

[0036] A second aspect of the present invention discloses a device for performing an identification operation on a target in a region, the device comprising:

[0037] a determination module, configured to determine a reference correction object that matches a current scene in a first area, wherein the first area is provided with the reference correction object and a corrected object, wherein the reference correction object and the corrected object are different types of data collectors, wherein the reference correction object is configured to perform a data collection operation on the first area to obtain collected data corresponding to the reference correction object and a collection time corresponding to the collected data, and wherein the corrected object is configured to perform a data collection operation on the first area to obtain collected data corresponding to the corrected object and a collection time corresponding to the collected data;

[0038] An acquisition module is used to acquire, based on the acquisition time corresponding to the benchmark correction object and the acquisition time corresponding to the corrected object, acquisition data that matches the acquisition time corresponding to the benchmark correction object from the acquisition data corresponding to the corrected object; wherein the acquisition data that matches the acquisition time corresponding to the benchmark correction object includes acquisition data whose acquisition time is later than the acquisition time corresponding to the benchmark correction object and acquisition data whose acquisition time is earlier than the acquisition time corresponding to the benchmark correction object;

[0039] A correction module, configured to perform a correction operation on the collected data corresponding to the corrected object based on the collection time corresponding to the reference correction object, the collected data matching the collection time corresponding to the reference correction object, and the collection time corresponding to the collected data, so as to obtain the corrected collected data of the corrected object at the collection time corresponding to the reference correction object;

[0040] The corrected collected data corresponding to the corrected object is used as a basis for performing a recognition operation on the target in the first area.

[0041] As an optional implementation, in the second aspect of the present invention, the acquisition data corresponding to the benchmark correction object is composed of at least one first sub-acquisition data, and the acquisition time corresponding to the benchmark correction object is composed of the first sub-acquisition time corresponding to all the first sub-acquisition data;

[0042] The acquisition data corresponding to the corrected object is composed of at least one second sub-acquisition data, and the acquisition moment corresponding to the corrected object is composed of the second sub-acquisition moments corresponding to all the second sub-acquisition data.

[0043] As an optional implementation, in the second aspect of the present invention, the correction module performs a correction operation on the collected data corresponding to the corrected object based on the collection time corresponding to the benchmark correction object, the collected data matching the collection time corresponding to the benchmark correction object, and the collection time corresponding to the collected data, and the specific manner of obtaining the corrected collected data of the corrected object at the collection time corresponding to the benchmark correction object includes:

[0044] For any first sub-collection moment corresponding to the reference correction object, based on the first sub-collection moment, from all second sub-collection moments, a first target sub-collection moment later than the first sub-collection moment and a second target sub-collection moment earlier than the first sub-collection moment are selected;

[0045] Determining a time correction parameter corresponding to the corrected object according to the first sub-collection time, the first target sub-collection time, and the second target sub-collection time;

[0046] Determine the acquisition data matching the first sub-acquisition moment according to the time correction parameter corresponding to the corrected object, the second sub-acquisition data corresponding to the first target sub-acquisition moment, and the second sub-acquisition data corresponding to the second target sub-acquisition moment;

[0047] The corrected acquisition data corresponding to the corrected object includes all acquisition data matching the first sub-acquisition moment.

[0048] As an optional implementation, in the second aspect of the present invention, the device further includes:

[0049] A screening module, used for screening out first target acquisition data that needs to be parameter converted from the correction acquisition data corresponding to the corrected object and the acquisition data corresponding to the reference correction object;

[0050] A conversion module, used for performing a parameter conversion operation matching the first target acquisition data on the first target acquisition data to obtain second target acquisition data after parameter conversion;

[0051] A fusion matching module, configured to perform a fusion matching operation on the target in the first area based on the first target acquisition data and the third target acquisition data after parameter conversion, to obtain a target matching result;

[0052] A feature adding module, used for performing a feature assignment operation on the target in the first area according to the target matching result;

[0053] The third target acquisition data is another acquisition data obtained by removing the first target acquisition data from the corrected acquisition data corresponding to the corrected object and the acquisition data corresponding to the reference correction object.

[0054] As an optional implementation, in the second aspect of the present invention, the target matching result includes a first target matching result and / or a second target matching result, wherein:

[0055] The first target matching result is used to represent all first targets that are successfully matched based on the collected data corresponding to the reference correction object and the corrected collected data corresponding to the corrected object;

[0056] The second target matching result is used to represent all second targets that are not successfully matched based on the collected data corresponding to the reference correction object and the corrected collected data corresponding to the corrected object.

[0057] As an optional implementation, in the second aspect of the present invention, the specific manner in which the feature adding module performs the feature assignment operation on the target in the first area according to the target matching result includes:

[0058] When the target matching result includes the first target matching result, for any of the first targets, the features of the first target identified by the reference correction object and the features of the first target identified by the corrected object are added to the first target;

[0059] When the target matching result includes the second target matching result, determining a reference recognition parameter that matches the current scene of the first area, the reference recognition parameter including a reference distance, the reference distance being a distance determined based on a location of the reference correction object or a location of the corrected object;

[0060] Determine a second area according to the reference identification parameter, wherein the area range of the second area is smaller than the area range of the first area;

[0061] For any second target in the second area, determine the type of the collector that successfully identifies the second target, and when the type of the collector includes a type that matches the second area, determine a target collector that matches the type that matches the second area, and add the features identified by the target collector to the second target;

[0062] Among them, when the area range of the second area is the area formed by a distance less than or equal to the benchmark distance and the benchmark distance, the target collector is the benchmark correction object; when the area range of the second area is the area formed by a distance greater than the benchmark distance and the benchmark distance, the target collector is the corrected object.

[0063] As an optional implementation, in the second aspect of the present invention, the conversion module performs a parameter conversion operation matching the first target acquisition data on the first target acquisition data, and a specific method of obtaining the second target acquisition data after the parameter conversion includes:

[0064] When the first target acquisition data is the corrected acquisition data corresponding to the corrected object, a parameter conversion operation is performed on the first target acquisition data based on the conversion parameters matching the reference corrected object to obtain second target acquisition data after parameter conversion;

[0065] When the first target acquisition data is the acquisition data corresponding to the reference correction object, a parameter conversion operation is performed on the first target acquisition data based on the conversion parameters matching the corrected object to obtain the second target acquisition data after the parameter conversion.

[0066] A third aspect of the present invention discloses another device for performing an identification operation on a target in a region, the device comprising:

[0067] A memory storing executable program code;

[0068] a processor coupled to the memory;

[0069] The processor calls the executable program code stored in the memory to execute the method for performing identification operations on targets in a region disclosed in the first aspect of the present invention.

[0070] The fourth aspect of the present invention discloses a computer-readable storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute the method for performing identification operations on targets in a region disclosed in the first aspect of the present invention.

[0071] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0072] In an embodiment of the present invention, a reference correction object matching the current scene of the first area is determined, the first area is provided with a reference correction object and a corrected object, the reference correction object and the corrected object are different types of data collectors, the reference correction object is used to perform a data collection operation on the first area, and obtain the collected data corresponding to the reference correction object and the collection time corresponding to the collected data, and the corrected object is used to perform a data collection operation on the first area, and obtain the collected data corresponding to the corrected object and the collection time corresponding to the collected data; taking the collection time corresponding to the reference correction object as a reference, according to the collection time corresponding to the corrected object, the data corresponding to the reference correction object is obtained from the collected data corresponding to the corrected object. The collected data that matches the collection time corresponding to the benchmark correction object includes the collected data whose collection time is later than the collection time corresponding to the benchmark correction object and the collected data whose collection time is earlier than the collection time corresponding to the benchmark correction object; based on the collection time corresponding to the benchmark correction object, the collected data that matches the collection time corresponding to the benchmark correction object and the collection time corresponding to the collected data, the collected data corresponding to the corrected object is corrected to obtain the corrected collected data of the corrected object at the collection time corresponding to the benchmark correction object; wherein the corrected collected data corresponding to the corrected object is used as the basis for performing the recognition operation on the target in the first area. It can be seen that the present invention corrects the time error of the data collected by another data collector through the collection time of the collected data collected by one of the different types of data collectors and the collected data and collection time collected by another data collector, which can reduce the timestamp error of different types of data sources, accurately obtain the collected data of different data collectors at the same collection time, thereby improving the information fusion effect of different types of data sources, so as to improve the accuracy of target recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0074] Figure 1 It is a flowchart of a method for performing an identification operation on a target in a region disclosed in an embodiment of the present invention;

[0075] Figure 2 is a flow chart of another method for performing an identification operation on a vehicle in a region disclosed in an embodiment of the present invention;

[0076] Figure 3It is a schematic diagram of fusing and matching radar data and image data disclosed in an embodiment of the present invention;

[0077] Figure 4 It is a schematic diagram of a scenario of fusing and matching radar data and image data disclosed in an embodiment of the present invention;

[0078] Figure 5 It is a structural schematic diagram of a device for performing an identification operation on a target in a region disclosed in an embodiment of the present invention;

[0079] Figure 6 It is a structural schematic diagram of another device for performing an identification operation on a target in a region disclosed in an embodiment of the present invention;

[0080] Figure 7 It is a structural schematic diagram of another device for performing an identification operation on a target in a region disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0081] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0082] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or end including a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units inherent to these processes, methods, products or ends.

[0083] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0084] The present invention discloses a method and device for performing identification operation on targets in a region, which can reduce the timestamp error of different types of data sources, accurately obtain the collected data of different data collectors at the same collection time, thereby improving the information fusion effect of different types of data sources, and improving the accuracy of target identification. The following are detailed descriptions.

[0085] Embodiment 1

[0086] See also Figure 1 , Figure 1 1 is a flow chart of a method for performing an identification operation on a target in a region disclosed in an embodiment of the present invention. Figure 1 The described method can be applied to any scenario where mobile targets need to be identified, such as vehicle monitoring scenarios. Figure 1 As shown, the method may include the following operations:

[0087] 101. Determine a reference correction object that matches a current scene in a first area.

[0088] In an embodiment of the present invention, optionally, a reference correction object and a corrected object are provided in the first area, the reference correction object is used to perform a data acquisition operation on the first area, and obtain the acquisition data corresponding to the reference correction object and the acquisition time corresponding to the acquisition data, and the corrected object is used to perform a data acquisition operation on the first area, and obtain the acquisition data corresponding to the corrected object and the acquisition time corresponding to the acquisition data. The reference correction object and the corrected object are different types of data collectors, such as when the reference correction object is an image collector, the corrected object is a radar collector; when the reference correction object is a radar collector, the corrected object is an image collector. Optionally, the image collector can be a monocular image collector or a multi-eye image collector. Further optionally, according to different types of current scenes, the acquisition data will be different, for example, the acquisition data collected by the radar collector and the image collector respectively can be position data.

[0089] In the embodiment of the present invention, optionally, the acquisition data corresponding to the baseline correction object consists of at least one first sub-acquisition data, and the acquisition moment corresponding to the baseline correction object consists of the first sub-acquisition moments corresponding to all the first sub-acquisition data; the acquisition data corresponding to the corrected object consists of at least one second sub-acquisition data, and the acquisition moment corresponding to the corrected object consists of the second sub-acquisition moments corresponding to all the second sub-acquisition data.

[0090] In the embodiment of the present invention, optionally, the working performance data of each data collector is analyzed according to the working performance data of each data collector within a preset time period (within three days), the target working performance of each data collector within the preset time period is obtained, and the target working performance of the two data collectors is compared, and the party with better target working performance is selected as the benchmark correction object. Among them, the working performance data includes one or more of network condition data, data collection stability data, and data collection noise condition data. For example, the more stable the network and / or the more stable the data collection and / or the smaller the noise, the better the working performance. In this way, by comparing and analyzing the working performance of each data collector, the accuracy of determining the benchmark correction object can be improved, thereby improving the accuracy of the time difference correction of the corresponding collected data, obtaining accurate and reliable correction data, and being conducive to further improving the accuracy of data fusion matching.

[0091] Further optionally, the matching accuracy of each data fusion match is obtained for each data collector as a benchmark correction object within a preset time period, and the mean matching accuracy of all matching accuracies within the preset time period is calculated, and the standard deviation matching accuracy corresponding to each data collector is calculated based on each matching accuracy and the mean matching accuracy, and the standard deviation matching accuracy of the two is compared, and a quantification operation is performed on the target work performance corresponding to each data collector to obtain quantifiable target work performance, and according to the current scene object occlusion situation in the first area and the type (such as vehicle, personnel) and / or movement situation (such as direction, speed) of the identified target, the quantified target work performance and the standard deviation matching accuracy are assigned corresponding weights, and the corresponding correction effect value is calculated based on the quantified target work performance and the corresponding weight, and the correction values ​​corresponding to each data collector are compared, and the one with the larger correction effect value is used as the benchmark correction object, wherein the larger the correction effect value, the better the correction effect obtained when correcting the other party's data based on it as the benchmark correction object. In this way, by further combining the matching accuracy and working performance of each data collector when it is used as a benchmark correction object and comprehensively analyzing the benchmark correction object to be used, the accuracy of determining the benchmark correction object can be further improved.

[0092] 102. Taking the collection time corresponding to the benchmark correction object as a benchmark, according to the collection time corresponding to the corrected object, obtain the collection data that matches the collection time corresponding to the benchmark correction object from the collection data corresponding to the corrected object; wherein the collection data that matches the collection time corresponding to the benchmark correction object includes collection data whose collection time is later than the collection time corresponding to the benchmark correction object and collection data whose collection time is earlier than the collection time corresponding to the benchmark correction object.

[0093] 103. Based on the collection time corresponding to the benchmark correction object, the collection data matching the collection time corresponding to the benchmark correction object and the collection time corresponding to the collection data, a correction operation is performed on the collection data corresponding to the corrected object to obtain the corrected collection data of the corrected object at the collection time corresponding to the benchmark correction object; wherein the corrected collection data corresponding to the corrected object is used as a basis for performing an identification operation on the target in the first area.

[0094] It can be seen that the implementation of the present invention corrects the time error of data collected by one data collector among different types of data collectors by using the collection time of the collection data collected by one data collector and the collection data and collection time collected by another data collector, which can reduce the timestamp error of different types of data sources and accurately obtain the collection data of different data collectors at the same collection time, thereby improving the information fusion effect of different types of data sources and improving the accuracy of target recognition.

[0095] In the embodiment of the present invention, optionally, based on the acquisition time corresponding to the reference correction object, the acquisition data matching the acquisition time corresponding to the reference correction object, and the acquisition time corresponding to the acquisition data, a correction operation is performed on the acquisition data corresponding to the corrected object to obtain the corrected acquisition data of the corrected object at the acquisition time corresponding to the reference correction object, including:

[0096] For any first sub-collection moment corresponding to the reference correction object, based on the first sub-collection moment, from all second sub-collection moments, select a first target sub-collection moment later than the first sub-collection moment and a second target sub-collection moment earlier than the first sub-collection moment;

[0097] Determine a time correction parameter corresponding to the object to be corrected according to the first sub-collection time, the first target sub-collection time, and the second target sub-collection time;

[0098] Determine the acquisition data matching the first sub-acquisition moment according to the time correction parameter corresponding to the corrected object, the second sub-acquisition data corresponding to the first target sub-acquisition moment, and the second sub-acquisition data corresponding to the second target sub-acquisition moment;

[0099] In this optional embodiment, the corrected acquisition data corresponding to the corrected object includes all acquisition data matching the first sub-acquisition moment, wherein the acquisition data matching each first sub-acquisition moment is the corrected acquisition data of the corrected object at the first sub-acquisition moment after time difference correction. Optionally, the number of the first target sub-acquisition moment or the second target sub-acquisition moment can be one or more.

[0100] It can be seen that this embodiment can improve the efficiency and accuracy of time difference correction by screening the sub-acquisition moments before and after the sub-acquisition moment corresponding to the benchmark correction object from the sub-acquisition moments of the corrected object, and performing time difference correction on the acquisition data collected by the corrected object based on the previous and next sub-acquisition moments and the acquisition data corresponding to the sub-acquisition moments and the sub-acquisition moment corresponding to the benchmark correction object, thereby facilitating further improving the accuracy of acquiring the acquisition data of the corrected object.

[0101] In an optional embodiment, the method may further include the following steps:

[0102] Filtering out first target acquisition data that needs to be parameter-converted from the correction acquisition data corresponding to the corrected object and the acquisition data corresponding to the reference correction object;

[0103] Performing a parameter conversion operation matching the first target acquisition data on the first target acquisition data to obtain second target acquisition data after parameter conversion;

[0104] Based on the first target acquisition data and the third target acquisition data after parameter conversion, a fusion matching operation is performed on the target in the first area to obtain a target matching result;

[0105] According to the target matching result, a feature assignment operation is performed on the target in the first area;

[0106] The third target acquisition data is another acquisition data obtained by removing the first target acquisition data from the correction acquisition data corresponding to the corrected object and the acquisition data corresponding to the reference correction object.

[0107] In this optional embodiment, the target matching result optionally includes a first target matching result and / or a second target matching result, wherein: the first target matching result is used to indicate all first targets that are successfully matched based on the acquisition data corresponding to the reference correction object and the corrected acquisition data corresponding to the corrected object; the second target matching result is used to indicate all second targets that are not successfully matched based on the acquisition data corresponding to the reference correction object and the corrected acquisition data corresponding to the corrected object. Specifically, for any first target, when the corrected object is identified and recognized by the reference correction object at the same time, this target is defined as a first target; for any second target, when the reference correction object is identified but the corrected object is not identified, or when the reference correction object is not identified but the corrected object is identified, this target is defined as a second target.

[0108] In this optional embodiment, optionally, performing a parameter conversion operation matching the first target acquisition data on the first target acquisition data to obtain second target acquisition data after parameter conversion includes:

[0109] When the first target acquisition data is the corrected acquisition data corresponding to the corrected object, a parameter conversion operation is performed on the first target acquisition data based on the conversion parameters matching the reference correction object to obtain the second target acquisition data after the parameter conversion;

[0110] When the first target acquisition data is the acquisition data corresponding to the reference correction object, a parameter conversion operation is performed on the first target acquisition data based on the conversion parameters matching the corrected object to obtain the second target acquisition data after the parameter conversion.

[0111] In this optional embodiment, different types of current scenes or different types or different data collectors may have different corresponding parameter conversion operations. For example, for position data collected by an image collector, the corresponding conversion parameters may be coordinate system conversion, and the parameter conversion operation may be a position coordinate conversion operation.

[0112] In this optional embodiment, optionally, different data fusion and matching methods can be used according to different data types to fuse and match the collected data corresponding to different data collectors. For example, for position data, the Hungarian matching algorithm can be used for fusion matching. Further optionally, different types of data collectors or different targets require different features to be added. For example, for an image collector, the features to be added are visual features, such as color and shape, and for a radar collector, the features to be added are non-visual features, such as distance and speed.

[0113] In this optional embodiment, based on the first target acquisition data and the third target acquisition data after parameter conversion, a fusion matching operation is performed on the target in the first area to obtain a target matching result, specifically: for any same sub-acquisition moment, a fusion matching operation is performed on the acquisition data and the corrected acquisition data corresponding to the same sub-acquisition moment to obtain a matching result for the same sub-acquisition moment, wherein the target matching result is composed of multiple matching results of the same sub-acquisition moment.

[0114] It can be seen that this optional embodiment converts the collected data corresponding to one of the data collectors through the conversion parameters corresponding to another data collector, and fuses and matches it with the collected data corresponding to one of the data collectors that does not need to be converted. This can improve the accuracy of data fusion matching, thereby improving the accuracy of target recognition, and then adding corresponding features to the targets in the area based on different matching results to achieve accurate completion of missing target data.

[0115] In this optional embodiment, optionally, performing a feature assignment operation on the target in the first area according to the target matching result includes:

[0116] When the target matching result includes a first target matching result, for any first target, the features of the first target identified by the reference correction object and the features of the first target identified by the correction object are added to the first target;

[0117] When the target matching result includes the second target matching result, determining a reference recognition parameter that matches the current scene in the first area, the reference recognition parameter including a reference distance, the reference distance being a distance determined based on a location of a reference correction object or a location of a corrected object, such as 150 meters;

[0118] Determine a second area according to the benchmark identification parameter, wherein the area range of the second area is smaller than the area range of the first area;

[0119] For any second target in the second area, determine the type of the collector that successfully identifies the second target, and when the type of the collector includes a type that matches the second area, determine a target collector that matches the type that matches the second area, and add the features identified by the target collector to the second target;

[0120] Among them, when the area range of the second area is the area formed by the distance less than or equal to the reference distance and the reference distance, the target collector is the reference correction object; when the area range of the second area is the area formed by the distance greater than the reference distance and the reference distance, the target collector is the corrected object.

[0121] It can be seen that this optional embodiment can accurately screen out corresponding features through different target matching results, achieve accurate completion of target missing data and improve completion efficiency.

[0122] Embodiment 2

[0123] See also Figure 2 , Figure 2 It is a flowchart diagram of another method for performing an identification operation on a vehicle in an area disclosed in an embodiment of the present invention. Figure 2 The embodiment is described by taking the current scene as a vehicle monitoring scene, the reference correction object as an image collector, the corrected object as a radar collector, the collected data corresponding to the reference correction object as image data, and the collected data corresponding to the corrected object as radar data. Figure 2 As shown, the method may include the following operations:

[0124] 201. Taking the acquisition time corresponding to the image collector in the first area as a reference, according to the acquisition time corresponding to the radar collector, obtain radar data that matches the acquisition time corresponding to the image collector from the radar data corresponding to the radar collector; wherein the radar data that matches the acquisition time corresponding to the image collector includes radar data whose acquisition time is later than the acquisition time corresponding to the image collector and radar data whose acquisition time is earlier than the acquisition time corresponding to the image collector.

[0125] In the embodiment of the present invention, optionally, an image collector and a radar collector are provided in the first area, the image collector is used to perform a data acquisition operation on the first area, obtain image data corresponding to the image collector and the acquisition time corresponding to the image data, and the radar collector is used to perform a data acquisition operation on the first area, obtain radar data corresponding to the radar collector and the acquisition time corresponding to the radar data. Optionally, the image collector can be a monocular image collector or a multi-eye image collector.

[0126] In the embodiment of the present invention, optionally, the image data corresponding to the image collector is composed of at least one sub-image data, and the acquisition time corresponding to the image collector is composed of the first sub-acquisition time corresponding to all the sub-image data; the radar data corresponding to the radar collector is composed of at least one sub-radar data, and the acquisition time corresponding to the radar collector is composed of the second sub-acquisition time corresponding to all the sub-radar data. Taking the acquisition time corresponding to the image collector in the first area as a reference, according to the acquisition time corresponding to the radar collector, radar data matching the acquisition time corresponding to the image collector is obtained from the radar data corresponding to the radar collector. Specifically, for any first sub-acquisition time corresponding to the image collector, taking the first sub-acquisition time as a reference, according to all the second sub-acquisition times corresponding to the radar collector, sub-radar data matching the first sub-acquisition time is obtained from the radar data corresponding to the radar collector.

[0127] 202. Based on the acquisition time corresponding to the image collector, the radar data matching the acquisition time corresponding to the image collector, and the acquisition time corresponding to the radar data, a correction operation is performed on the radar data corresponding to the radar collector to obtain the corrected radar data of the radar collector at the acquisition time corresponding to the image collector; wherein the corrected radar data corresponding to the radar collector is used as a basis for performing an identification operation on the vehicle in the first area.

[0128] It can be seen that the implementation of the present invention corrects the time error of the radar data collected by the radar collector through the collection time corresponding to the image collector and the radar data and collection time collected by the radar collector, which can reduce the timestamp error of different types of data sources, and accurately obtain the collection data of different data collectors at the same collection time, thereby improving the information fusion effect of different types of data sources, so as to improve the accuracy of vehicle recognition.

[0129] In the embodiment of the present invention, optionally, based on the acquisition time corresponding to the image collector, the radar data matching the acquisition time corresponding to the image collector, and the acquisition time corresponding to the radar data, a correction operation is performed on the radar data corresponding to the radar collector to obtain the corrected radar data of the radar collector at the acquisition time corresponding to the image collector, including:

[0130] For any first sub-collection moment corresponding to the image collector, based on the first sub-collection moment, from all second sub-collection moments, select a first target sub-collection moment whose time is later than the first sub-collection moment and a second target sub-collection moment whose time is earlier than the first sub-collection moment;

[0131] Determine a time correction parameter corresponding to the radar collector according to the first sub-collection time, the first target sub-collection time, and the second target sub-collection time;

[0132] Determine the sub-radar data matching the first sub-collection moment according to the time correction parameter corresponding to the radar collector, the sub-radar data corresponding to the first target sub-collection moment, and the sub-radar data corresponding to the second target sub-collection moment;

[0133] In this optional embodiment, the corrected radar data corresponding to the radar collector includes all sub-radar data matching the first sub-collection moment, wherein each sub-radar data matching the first sub-collection moment is the corrected radar data of the radar collector at the first sub-collection moment after time difference correction.

[0134] In the embodiment of the present invention, Figure 3 As shown, Figure 3 FIG. 1 is a schematic diagram of a radar data and image data fusion matching method disclosed in an embodiment of the present invention. Figure 3As shown, it is a schematic diagram of the radar data before correction. The horizontal axis represents the time acquisition moment t. Before data fusion and matching, the acquisition moment of the image collector is used as the benchmark, that is, at the acquisition moment when Ki-2, Ki-1, Ki, etc. acquire the image data (video frame data), the radar data of the nearest neighbor with the timestamp before the acquisition moment is synchronously selected for data fusion and matching. Taking the Ki-2 acquisition moment as an example, the image data of the image collector is acquired at this acquisition moment, and the radar data acquired by the radar collector at the Kj-3 acquisition moment is synchronously acquired and fused with the image data; at the Ki-1 acquisition moment, the radar data at the Kj-1 acquisition moment is acquired for fusion; and at the Ki acquisition moment, since no radar data is acquired between the Ki-1 and Ki acquisition moments, the image data is simply relied on as the input for fusion matching to update the features of the fused vehicle. Combined with Figure 3 The radar data correction is specifically described. The radar data must be matched with the image data at the Ki-2 acquisition time. The data actually collected by the radar collector is the radar data between the Kj-3 and Kj-2 acquisition times. The radar correction data M of the radar collector at the Ki-2 acquisition time is obtained by linear interpolation (M=a*(1-t)+b*t) using the data of the radar collector at the Kj-3 acquisition time and the Kj-2 acquisition time. Therefore, a at this time is the radar data of the radar collector at the Kj-3 acquisition time, b is the radar data of the radar collector at the Kj-2 acquisition time, 1-t is (Kj-2-Ki-2) / (Kj-2-Kj-3), and t is (Ki-2-Kj-3) / (Kj-2-Kj-3). Then the radar correction data M is fused and matched with the image data of the image collector at the Ki-2 acquisition time.

[0135] It can be seen that this embodiment can improve the efficiency and accuracy of time difference correction by screening the sub-acquisition moments before and after the sub-acquisition moment corresponding to the image collector from the sub-acquisition moments of the radar collector, and performing time difference correction on the acquisition data collected by the radar collector based on the before and after sub-acquisition moments and the acquisition data corresponding to the sub-acquisition moments, and the sub-acquisition moments corresponding to the image collector, thereby facilitating further improving the accuracy of acquiring the acquisition data of the radar collector.

[0136] In an optional embodiment, the method may further include the following steps:

[0137] Filtering out first target data that needs to be parameter converted from the corrected radar data corresponding to the radar collector and the image data corresponding to the image collector;

[0138] Performing a parameter conversion operation matching the first target data on the first target data to obtain second target data after parameter conversion;

[0139] Based on the first target data and the third target data after parameter conversion, a fusion matching operation is performed on the vehicles in the first area to obtain a vehicle matching result;

[0140] According to the vehicle matching result, a feature assignment operation is performed on the vehicles in the first area;

[0141] The third target data is another data obtained by removing the first target data from the corrected radar data corresponding to the radar collector and the image data corresponding to the image collector.

[0142] In this optional embodiment, the vehicle matching result may include a first vehicle matching result and / or a second vehicle matching result, wherein: the first vehicle matching result is used to indicate all first vehicles that are successfully matched based on the image data corresponding to the image collector and the corrected radar data corresponding to the radar collector; the second vehicle matching result is used to indicate all second vehicles that are not successfully matched based on the image data corresponding to the image collector and the corrected radar data corresponding to the radar collector. Specifically, for any first vehicle, when the radar collector recognizes it and is recognized by the image collector at the same time, this target is defined as a first vehicle; for any second vehicle, when the image collector recognizes it but the radar collector does not recognize it, or when the image collector does not recognize it but the radar collector recognizes it, this target is defined as a second vehicle.

[0143] In this optional embodiment, optionally, performing a parameter conversion operation matching the first target data on the first target data to obtain second target data after parameter conversion includes:

[0144] When the first target acquisition data is the corrected radar data corresponding to the radar collector, a parameter conversion operation is performed on the first target data based on the conversion parameters matched with the image collector to obtain the second target data after the parameter conversion;

[0145] When the first target acquisition data is image data corresponding to the image collector, a parameter conversion operation is performed on the first target data based on conversion parameters matching the radar collector to obtain second target data after parameter conversion.

[0146] In this optional embodiment, optionally, for the position data collected by the image collector, the corresponding conversion parameters can be a coordinate system conversion, and the parameter conversion operation is a position coordinate conversion operation. Further optionally, it is preferred to convert the radar correction data corresponding to the radar collector to the coordinates corresponding to the image collector. And before the position coordinate conversion, the coordinate system has been calibrated, wherein the calibration method is based on fitting multiple sets of radar point coordinates (world coordinates) and their corresponding image point coordinates to obtain the corresponding coordinate system, or other methods, without limitation. And optionally, for the position data, the Hungarian matching algorithm can be used for fusion matching. Optionally, Figure 4 FIG. 1 is a schematic diagram of a scenario in which radar data and image data are fused and matched according to an embodiment of the present invention. Figure 4 As shown in the figure, after the radar data corresponding to the radar collector is corrected and converted from three-dimensional coordinates to image coordinates, the position in the image is the red dot position in the figure, and the green rectangular box in the image is the two-dimensional vehicle position information detected based on the image. Therefore, it is necessary to match the target detected by the radar with the target detected by the image, that is, the red dot target is matched with the green rectangular box target. The distance calculation method of each red dot position and each green box is as follows: if the red dot is inside the green box, the distance is recorded as 0. If the red dot is not inside the green box, the distance from the red dot to the nearest block of the green box is calculated (if the block distance is greater than the width or height of the green box, the distance is set to a maximum value, indicating that the distance between the two targets is too far, and the later fusion matching algorithm will not recognize the two targets as the same target). If there are M red points and N green boxes, a distance matrix of size M*N can be generated and input into the Hungarian matching algorithm for matching to obtain the vehicle matching result. For the red position with the nearest green box and the distance is less than or equal to the width or height of the green box, the two are successfully matched and are the same target. Otherwise, they are not successfully matched and are not the same target.

[0147] In this optional embodiment, based on the first target data and the third target data after parameter conversion, a fusion matching operation is performed on the vehicles in the first area to obtain a vehicle matching result, specifically: for any same sub-acquisition moment, a fusion matching operation is performed on the collected data and the corrected radar data corresponding to the same sub-acquisition moment to obtain the matching result of the same sub-acquisition moment, wherein the vehicle matching result is composed of multiple matching results of the same sub-acquisition moment.

[0148] It can be seen that this optional embodiment can improve the accuracy of position data fusion matching by converting the radar correction data corresponding to the radar collector into the coordinates corresponding to the image collector, and fusing and matching the converted position data with the position data collected by the corresponding image collector at the same time, thereby improving the accuracy of vehicle identification, and then adding corresponding features to the vehicles in the area according to different matching results to achieve accurate completion of missing vehicle data.

[0149] In this optional embodiment, optionally, according to the vehicle matching result, performing a feature assignment operation on the vehicle in the first area includes:

[0150] When the vehicle matching result includes the first vehicle matching result, for any first vehicle, the features of the first vehicle identified by the image collector and the features of the first vehicle identified by the radar collector are added to the first vehicle;

[0151] When the vehicle matching result includes the second vehicle matching result, determining a benchmark identification parameter that matches the current scene in the first area, the benchmark identification parameter includes a benchmark distance, the benchmark distance is a distance determined based on the position of the image collector or the position of the radar collector, such as 150 meters;

[0152] Determine a second area according to the benchmark identification parameter, wherein the area range of the second area is smaller than the area range of the first area;

[0153] For any second vehicle in the second area, determine the type of the collector that successfully identifies the second vehicle, and when the type of the collector includes a type that matches the second area, determine a target collector that matches the type that matches the second area, and add the features identified by the target collector to the second vehicle;

[0154] Among them, when the area range of the second area is the area formed by the distance less than or equal to the reference distance and the reference distance, the target collector is an image collector; when the area range of the second area is the area formed by the distance greater than the reference distance and the reference distance, the target collector is a radar collector.

[0155] In this optional embodiment, for any first vehicle that is successfully matched, visual features (such as vehicle color, vehicle shape, license plate, vehicle model, etc.) and non-visual features (such as speed, distance, acceleration, angle, etc.) are optionally added to the first vehicle. For a second vehicle that is not successfully matched, if the image collector detects the second vehicle within a specific distance range (such as within 150 meters), but the second vehicle is not matched to the radar target, only the visual feature information (such as vehicle color, vehicle shape, license plate, vehicle model, etc.) is retained after fusion, and no radar features are assigned; if the second vehicle is not detected visually, regardless of whether the radar acquires the second vehicle, it is deemed that the second vehicle is not detected after fusion. Outside a specific range (for example, 150 meters), due to occlusion and other problems, the visual effect cannot be guaranteed. For the second vehicle that is not matched successfully, if the radar detects the second vehicle but the second vehicle is not matched to any visual second vehicle, only the radar feature information (such as speed, distance, acceleration, angle, etc.) is retained after fusion, and no visual features are given; if the second vehicle is not detected, regardless of whether the second vehicle is acquired visually, it is deemed that the second vehicle is not detected after fusion.

[0156] It can be seen that this optional embodiment can accurately screen out corresponding features through different vehicle matching results, achieve accurate completion of target missing data and improve completion efficiency.

[0157] It should be noted that, for the description of other technical contents, please refer to the detailed description of other contents in Example 1, which will not be repeated here.

[0158] Embodiment 3

[0159] See also Figure 5 , Figure 5 is a schematic diagram of a structure of a device for performing an identification operation on a target in a region disclosed in an embodiment of the present invention. Figure 5 The described device can be applied to any scenario where target recognition is required, such as vehicle monitoring scenario. Figure 5 As shown, the device may include:

[0160] Determination module 301 is used to determine a baseline correction object that matches the current scene of the first area. The first area is provided with a baseline correction object and a corrected object. The baseline correction object is used to perform data acquisition operations on the first area to obtain acquisition data corresponding to the baseline correction object and an acquisition time corresponding to the acquisition data. The corrected object is used to perform data acquisition operations on the first area to obtain acquisition data corresponding to the corrected object and an acquisition time corresponding to the acquisition data. The baseline correction object and the corrected object are different types of data collectors. For example, when the baseline correction object is an image collector, the corrected object is a radar collector; when the baseline correction object is a radar collector, the corrected object is an image collector. Optionally, the image collector may be a monocular image collector or a multi-eye image collector. Further optionally, the acquisition data may be different according to different types of current scenes. For example, the acquisition data collected by the radar collector and the image collector may be location data.

[0161] The acquisition module 302 is used to acquire the acquisition data that matches the acquisition time corresponding to the benchmark correction object from the acquisition data corresponding to the corrected object, based on the acquisition time corresponding to the benchmark correction object; wherein the acquisition data that matches the acquisition time corresponding to the benchmark correction object includes acquisition data whose acquisition time is later than the acquisition time corresponding to the benchmark correction object and acquisition data whose acquisition time is earlier than the acquisition time corresponding to the benchmark correction object;

[0162] The correction module 303 is used to perform a correction operation on the collection data corresponding to the corrected object based on the collection time corresponding to the baseline correction object, the collection data matching the collection time corresponding to the baseline correction object, and the collection time corresponding to the collection data, so as to obtain the corrected collection data of the corrected object at the collection time corresponding to the baseline correction object; wherein the corrected collection data corresponding to the corrected object is used as a basis for performing an identification operation on the target in the first area.

[0163] In the embodiment of the present invention, optionally, the acquisition data corresponding to the baseline correction object consists of at least one first sub-acquisition data, and the acquisition moment corresponding to the baseline correction object consists of the first sub-acquisition moments corresponding to all the first sub-acquisition data; the acquisition data corresponding to the corrected object consists of at least one second sub-acquisition data, and the acquisition moment corresponding to the corrected object consists of the second sub-acquisition moments corresponding to all the second sub-acquisition data.

[0164] It can be seen that implementation Figure 5 The described device corrects the time error of data collected by one of the different types of data collectors by using the collection time of the data collected by one of the data collectors and the collection data and collection time collected by another data collector. This can reduce the timestamp error of different types of data sources and accurately obtain the collection data of different data collectors at the same collection time, thereby improving the information fusion effect of different types of data sources and improving the accuracy of target recognition.

[0165] In the embodiment of the present invention, optionally, the correction module 301 performs a correction operation on the collected data corresponding to the corrected object based on the collection time corresponding to the reference correction object, the collected data matching the collection time corresponding to the reference correction object, and the collection time corresponding to the collected data, and the specific manner of obtaining the corrected collected data of the corrected object at the collection time corresponding to the reference correction object includes:

[0166] For any first sub-collection moment corresponding to the reference correction object, based on the first sub-collection moment, from all second sub-collection moments, select a first target sub-collection moment later than the first sub-collection moment and a second target sub-collection moment earlier than the first sub-collection moment;

[0167] Determine a time correction parameter corresponding to the object to be corrected according to the first sub-collection time, the first target sub-collection time, and the second target sub-collection time;

[0168] Determine the acquisition data matching the first sub-acquisition moment according to the time correction parameter corresponding to the corrected object, the second sub-acquisition data corresponding to the first target sub-acquisition moment, and the second sub-acquisition data corresponding to the second target sub-acquisition moment;

[0169] In this optional embodiment, the corrected acquisition data corresponding to the corrected object includes all acquisition data matching the first sub-acquisition moment, wherein the acquisition data matching each first sub-acquisition moment is the corrected acquisition data of the corrected object at the first sub-acquisition moment after time difference correction. Optionally, the number of the first target sub-acquisition moment or the second target sub-acquisition moment can be one or more.

[0170] It can be seen that this embodiment can improve the efficiency and accuracy of time difference correction by screening the sub-acquisition moments before and after the sub-acquisition moment corresponding to the benchmark correction object from the sub-acquisition moments of the corrected object, and performing time difference correction on the acquisition data collected by the corrected object based on the previous and next sub-acquisition moments and the acquisition data corresponding to the sub-acquisition moments and the sub-acquisition moment corresponding to the benchmark correction object, thereby facilitating further improving the accuracy of acquiring the acquisition data of the corrected object.

[0171] In an optional embodiment, if Figure 6 As shown, Figure 6 is a schematic diagram of the structure of another device for performing an identification operation on a target in a region disclosed in an embodiment of the present invention, such as Figure 6 As shown, the device also includes:

[0172] A screening module 304 is used to screen out first target collected data that needs to be parameter converted from the corrected collected data corresponding to the corrected object and the collected data corresponding to the reference corrected object;

[0173] The conversion module 305 is used to perform a parameter conversion operation matching the first target acquisition data on the first target acquisition data to obtain second target acquisition data after parameter conversion;

[0174] A fusion matching module 306 is used to perform a fusion matching operation on the target in the first area based on the first target collected data and the third target collected data after parameter conversion to obtain a target matching result;

[0175] A feature adding module 307, used to perform a feature assignment operation on the target in the first area according to the target matching result;

[0176] The third target acquisition data is another acquisition data obtained by removing the first target acquisition data from the correction acquisition data corresponding to the corrected object and the acquisition data corresponding to the reference correction object.

[0177] In this optional embodiment, the target matching result optionally includes a first target matching result and / or a second target matching result, wherein: the first target matching result is used to indicate all first targets that are successfully matched based on the acquisition data corresponding to the reference correction object and the corrected acquisition data corresponding to the corrected object; the second target matching result is used to indicate all second targets that are not successfully matched based on the acquisition data corresponding to the reference correction object and the corrected acquisition data corresponding to the corrected object. Specifically, for any first target, when the corrected object is identified and recognized by the reference correction object at the same time, this target is defined as a first target; for any second target, when the reference correction object is identified but the corrected object is not identified, or when the reference correction object is not identified but the corrected object is identified, this target is defined as a second target.

[0178] In this optional embodiment, optionally, the conversion module 305 performs a parameter conversion operation on the first target acquisition data that matches the first target acquisition data, and obtains the second target acquisition data after the parameter conversion in a specific manner including:

[0179] When the first target acquisition data is the corrected acquisition data corresponding to the corrected object, a parameter conversion operation is performed on the first target acquisition data based on the conversion parameters matching the reference correction object to obtain the second target acquisition data after the parameter conversion;

[0180] When the first target acquisition data is the acquisition data corresponding to the reference correction object, a parameter conversion operation is performed on the first target acquisition data based on the conversion parameters matching the corrected object to obtain the second target acquisition data after the parameter conversion.

[0181] In this optional embodiment, different types of current scenes or different types or different data collectors may have different corresponding parameter conversion operations. For example, for position data collected by an image collector, the corresponding conversion parameters may be coordinate system conversion, and the parameter conversion operation may be a position coordinate conversion operation.

[0182] In this optional embodiment, optionally, different data fusion and matching methods can be used according to different data types to fuse and match the collected data corresponding to different data collectors. For example, for position data, the Hungarian matching algorithm can be used for fusion matching. Further optionally, different types of data collectors or different targets require different features to be added. For example, for an image collector, the features to be added are visual features, such as color and shape, and for a radar collector, the features to be added are non-visual features, such as distance and speed.

[0183] In this optional embodiment, based on the first target acquisition data and the third target acquisition data after parameter conversion, a fusion matching operation is performed on the target in the first area to obtain a target matching result, specifically: for any same sub-acquisition moment, a fusion matching operation is performed on the acquisition data and the corrected acquisition data corresponding to the same sub-acquisition moment to obtain a matching result for the same sub-acquisition moment, wherein the target matching result is composed of multiple matching results of the same sub-acquisition moment.

[0184] It can be seen that this optional embodiment converts the collected data corresponding to one of the data collectors through the conversion parameters corresponding to another data collector, and fuses and matches it with the collected data corresponding to one of the data collectors that does not need to be converted. This can improve the accuracy of data fusion matching, thereby improving the accuracy of target recognition, and then adding corresponding features to the targets in the area based on different matching results to achieve accurate completion of missing target data.

[0185] In this optional embodiment, the feature adding module 307 may optionally perform a feature assignment operation on the target in the first area according to the target matching result in a specific manner including:

[0186] When the target matching result includes a first target matching result, for any first target, the features of the first target identified by the reference correction object and the features of the first target identified by the correction object are added to the first target;

[0187] When the target matching result includes the second target matching result, determining a reference recognition parameter that matches the current scene in the first area, the reference recognition parameter including a reference distance, the reference distance being a distance determined based on a location of a reference correction object or a location of a corrected object, such as 150 meters;

[0188] Determine a second area according to the benchmark identification parameter, wherein the area range of the second area is smaller than the area range of the first area;

[0189] For any second target in the second area, determine the type of the collector that successfully identifies the second target, and when the type of the collector includes a type that matches the second area, determine a target collector that matches the type that matches the second area, and add the features identified by the target collector to the second target;

[0190] Among them, when the area range of the second area is the area formed by the distance less than or equal to the reference distance and the reference distance, the target collector is the reference correction object; when the area range of the second area is the area formed by the distance greater than the reference distance and the reference distance, the target collector is the corrected object.

[0191] It can be seen that this optional embodiment can accurately screen out corresponding features through different target matching results, achieve accurate completion of target missing data and improve completion efficiency.

[0192] Embodiment 3

[0193] See also Figure 7 , Figure 7 1 is a schematic diagram of another device for performing identification operation on a target in a region disclosed in an embodiment of the present invention. The device can be applied to any scenario where target identification is required, such as a vehicle monitoring scenario. Figure 7 As shown, the device may include:

[0194] A memory 401 storing executable program codes;

[0195] a processor 402 coupled to the memory 401;

[0196] The processor 402 calls the executable program code stored in the memory 401 to execute the steps of the method for performing an identification operation on a target in a region described in the first or second embodiment of the present invention.

[0197] Embodiment 4

[0198] An embodiment of the present invention discloses a computer-readable storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute the steps of the method for performing identification operations on targets in a region described in Embodiment 1 or Embodiment 2 of the present invention.

[0199] Embodiment 5

[0200] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps in the method for performing an identification operation on a target in an area described in Embodiment 1 or Embodiment 2.

[0201] The device embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, i.e., they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0202] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or partly contributed to the prior art in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0203] Finally, it should be noted that the method and device for performing identification operations on targets in an area disclosed in the embodiments of the present invention are only preferred embodiments of the present invention, and are only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for performing an identification operation on a target in an area, characterized in that: The method comprises: Determine a reference correction object that matches a current scene in a first area, wherein the first area is provided with the reference correction object and a corrected object, wherein the reference correction object and the corrected object are different types of data collectors, wherein the reference correction object is used to perform a data collection operation on the first area to obtain collected data corresponding to the reference correction object and a collection time corresponding to the collected data, and wherein the corrected object is used to perform a data collection operation on the first area to obtain collected data corresponding to the corrected object and a collection time corresponding to the collected data; Taking the acquisition time corresponding to the benchmark correction object as a benchmark, according to the acquisition time corresponding to the corrected object, acquiring the acquisition data that matches the acquisition time corresponding to the benchmark correction object from the acquisition data corresponding to the corrected object; wherein the acquisition data that matches the acquisition time corresponding to the benchmark correction object includes acquisition data whose acquisition time is later than the acquisition time corresponding to the benchmark correction object and acquisition data whose acquisition time is earlier than the acquisition time corresponding to the benchmark correction object; Based on the acquisition time corresponding to the reference correction object, the acquisition data matching the acquisition time corresponding to the reference correction object, and the acquisition time corresponding to the acquisition data, a correction operation is performed on the acquisition data corresponding to the corrected object to obtain the corrected acquisition data of the corrected object at the acquisition time corresponding to the reference correction object; The corrected collected data corresponding to the corrected object is used as a basis for performing a recognition operation on the target in the first area.

2. The method for performing identification operation on a target in a region according to claim 1, characterized in that: The acquisition data corresponding to the reference correction object is composed of at least one first sub-acquisition data, and the acquisition time corresponding to the reference correction object is composed of the first sub-acquisition time corresponding to all the first sub-acquisition data; The acquisition data corresponding to the corrected object is composed of at least one second sub-acquisition data, and the acquisition moment corresponding to the corrected object is composed of the second sub-acquisition moments corresponding to all the second sub-acquisition data.

3. The method for performing identification operation on a target in a region according to claim 2, characterized in that: The method of performing a correction operation on the collected data corresponding to the corrected object based on the collection time corresponding to the reference correction object, the collected data matching the collection time corresponding to the reference correction object, and the collection time corresponding to the collected data, to obtain the corrected collected data of the corrected object at the collection time corresponding to the reference correction object, comprises: For any first sub-collection moment corresponding to the reference correction object, based on the first sub-collection moment, from all second sub-collection moments, a first target sub-collection moment later than the first sub-collection moment and a second target sub-collection moment earlier than the first sub-collection moment are selected; Determining a time correction parameter corresponding to the corrected object according to the first sub-collection time, the first target sub-collection time, and the second target sub-collection time; Determine the acquisition data matching the first sub-acquisition moment according to the time correction parameter corresponding to the corrected object, the second sub-acquisition data corresponding to the first target sub-acquisition moment, and the second sub-acquisition data corresponding to the second target sub-acquisition moment; The corrected acquisition data corresponding to the corrected object includes all acquisition data matching the first sub-acquisition moment.

4. The method for performing an identification operation on a target in a region according to any one of claims 1 to 3, characterized in that: The method further comprises: Filtering out first target acquisition data that needs to be parameter converted from the correction acquisition data corresponding to the corrected object and the acquisition data corresponding to the reference correction object; Performing a parameter conversion operation matching the first target acquisition data on the first target acquisition data to obtain second target acquisition data after parameter conversion; Based on the first target acquisition data and the third target acquisition data after parameter conversion, performing a fusion matching operation on the target in the first area to obtain a target matching result; According to the target matching result, performing a feature assignment operation on the target in the first area; The third target acquisition data is another acquisition data obtained by removing the first target acquisition data from the corrected acquisition data corresponding to the corrected object and the acquisition data corresponding to the reference correction object.

5. The method for performing identification operation on a target in a region according to claim 4, characterized in that: The target matching result includes a first target matching result and / or a second target matching result, wherein: The first target matching result is used to represent all first targets that are successfully matched based on the collected data corresponding to the reference correction object and the corrected collected data corresponding to the corrected object; The second target matching result is used to represent all second targets that are not successfully matched based on the collected data corresponding to the reference correction object and the corrected collected data corresponding to the corrected object.

6. The method for performing identification operation on a target in a region according to claim 5, characterized in that: The performing a feature assignment operation on the target in the first area according to the target matching result includes: When the target matching result includes the first target matching result, for any of the first targets, the features of the first target identified by the reference correction object and the features of the first target identified by the corrected object are added to the first target; When the target matching result includes the second target matching result, determining a reference recognition parameter that matches the current scene of the first area, the reference recognition parameter including a reference distance, the reference distance being a distance determined based on a location of the reference correction object or a location of the corrected object; Determine a second area according to the reference identification parameter, wherein the area range of the second area is smaller than the area range of the first area; For any second target in the second area, determine the type of the collector that successfully identifies the second target, and when the type of the collector includes a type that matches the second area, determine a target collector that matches the type that matches the second area, and add the features identified by the target collector to the second target; Among them, when the area range of the second area is the area formed by a distance less than or equal to the benchmark distance and the benchmark distance, the target collector is the benchmark correction object; when the area range of the second area is the area formed by a distance greater than the benchmark distance and the benchmark distance, the target collector is the corrected object.

7. The method for performing an identification operation on a target in a region according to any one of claims 4 to 6, characterized in that: The performing a parameter conversion operation on the first target acquisition data that matches the first target acquisition data to obtain second target acquisition data after parameter conversion includes: When the first target acquisition data is the corrected acquisition data corresponding to the corrected object, a parameter conversion operation is performed on the first target acquisition data based on the conversion parameters matching the reference corrected object to obtain second target acquisition data after parameter conversion; When the first target acquisition data is the acquisition data corresponding to the reference correction object, a parameter conversion operation is performed on the first target acquisition data based on the conversion parameters matching the corrected object to obtain the second target acquisition data after the parameter conversion.

8. A device for performing an identification operation on a target in an area, characterized in that: The device comprises: a determination module, configured to determine a reference correction object that matches a current scene in a first area, wherein the first area is provided with the reference correction object and a corrected object, wherein the reference correction object and the corrected object are different types of data collectors, wherein the reference correction object is configured to perform a data collection operation on the first area to obtain collected data corresponding to the reference correction object and a collection time corresponding to the collected data, and wherein the corrected object is configured to perform a data collection operation on the first area to obtain collected data corresponding to the corrected object and a collection time corresponding to the collected data; An acquisition module is used to acquire, based on the acquisition time corresponding to the benchmark correction object and the acquisition time corresponding to the corrected object, acquisition data that matches the acquisition time corresponding to the benchmark correction object from the acquisition data corresponding to the corrected object; wherein the acquisition data that matches the acquisition time corresponding to the benchmark correction object includes acquisition data whose acquisition time is later than the acquisition time corresponding to the benchmark correction object and acquisition data whose acquisition time is earlier than the acquisition time corresponding to the benchmark correction object; A correction module, configured to perform a correction operation on the collected data corresponding to the corrected object based on the collection time corresponding to the reference correction object, the collected data matching the collection time corresponding to the reference correction object, and the collection time corresponding to the collected data, so as to obtain the corrected collected data of the corrected object at the collection time corresponding to the reference correction object; The corrected collected data corresponding to the corrected object is used as a basis for performing a recognition operation on the target in the first area.

9. A device for performing an identification operation on a target in an area, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the method for performing an identification operation on a target in a region as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the method for performing an identification operation on a target in a region as described in any one of claims 1 to 7.

Images