Data processing method and data processing apparatus, electronic device, and storage medium

Abstract

This application provides a data processing method, a data processing apparatus, an electronic device, and a storage medium. When a second sensor cannot identify a target object, the method uses the first identification result of the first object detected by the first sensor and the associated information from the second sensor to determine whether the first identification result of the target object needs to be incorporated into the second detection information. This allows the first identification result of the target object to be incorporated into the second detection information, enabling the second sensor to identify the target object when it detects it. This avoids or mitigates the impact of the second sensor's limitations on the data analysis results. For example, it can prevent the second sensor from failing to identify the target object when it detects only a portion of it, thus avoiding inaccurate data analysis results.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a data processing method, data processing apparatus, electronic device, and storage medium. Background Technology

[0002] Various sensors installed on the vehicle can sense the surrounding environment and collect data. Based on this, they can identify and detect static and dynamic objects.

[0003] In existing technologies, the capabilities of a single sensor are often limited. For example, due to the different recognition capabilities of different sensors, some sensors may fail to recognize the target object. Even if a sensor can sense the target object, it may only detect a part of the target object and fail to identify the target. As a result, the target object cannot be identified in the sensor's detection data. When analyzing and processing the data, the lack of data can lead to inaccurate analysis results.

[0004] Therefore, when using sensors to perceive objects, technical problems may occur, such as the inability to identify target objects, leading to inaccurate data analysis results. Summary of the Invention

[0005] This application provides a data processing method, data processing apparatus, electronic device, and storage medium to alleviate the technical problem of inaccurate data analysis results caused by the inability to identify target objects.

[0006] This application provides a data processing method for probe data, the data processing method including:

[0007] Acquire first detection information from a first sensor and second detection information from a second sensor, wherein the first detection information includes a first identification result of a first object detected by the first sensor, and the first object includes a target object;

[0008] Based on the first identification result and the association information of the second sensor, it is determined that the first identification result of the target object needs to be incorporated into the second detection information; the association information includes the detection capability information of the second sensor and / or the second detection information;

[0009] The first identification result of the target object is incorporated into the second detection information.

[0010] Meanwhile, embodiments of this application provide a data processing apparatus for probe data, the data processing apparatus comprising:

[0011] The acquisition module is used to acquire first detection information from a first sensor and second detection information from a second sensor. The first detection information includes a first identification result of a first object detected by the first sensor, and the first object includes a target object.

[0012] The determining module is configured to determine, based on the first identification result and the association information of the second sensor, the first identification result of the target object that needs to be incorporated into the second detection information; the association information includes the detection capability information of the second sensor and / or the second detection information;

[0013] The integration module is used to integrate the first identification result of the target object into the second detection information.

[0014] Meanwhile, this application provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps in the data processing method for probe data as described in any of the above embodiments.

[0015] Meanwhile, this application provides a storage medium storing multiple instructions adapted for loading by a processor to execute steps in the data processing method for probe data as described in any of the above embodiments.

[0016] Beneficial Effects: This application provides a data processing method, data processing apparatus, electronic device, and storage medium. After acquiring first detection information from a first sensor and second detection information from a second sensor, the data processing method determines, based on the first identification result of a first object detected by the first sensor and the associated information from the second sensor, that the first identification result of the target object needs to be incorporated into the second detection information. This application can determine the need to incorporate the first identification result of the target object into the second detection information when the second sensor cannot identify the target object, by using the first identification result of the first object detected by the first sensor and the associated information from the second sensor. This allows the first identification result of the target object to be incorporated into the second detection information, enabling the second sensor to identify the target object when it detects it. This avoids or mitigates the impact of the second sensor's limitations on the data analysis results. For example, it can prevent the second sensor from failing to identify the target object when it detects only a portion of it, thus avoiding inaccurate data analysis results. Attached Figure Description

[0017] The technical solution and other beneficial effects of this application will become apparent from the following detailed description of specific embodiments in conjunction with the accompanying drawings.

[0018] Figure 1 This is a schematic diagram of a data processing system provided in an embodiment of this application.

[0019] Figure 2 This is a flowchart illustrating the data processing method provided in an embodiment of this application.

[0020] Figure 3 This is a schematic diagram illustrating the processing procedure of the target object provided in the embodiments of this application.

[0021] Figure 4 This is a schematic diagram of the images corresponding to the first sensor and the second sensor provided in the embodiments of this application.

[0022] Figure 5 This is a schematic diagram of the structure of the data processing apparatus provided in the embodiments of this application.

[0023] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0024] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0025] The following explains some of the terms mentioned in this manual:

[0026] Sensors, such as the first sensor and the second sensor, can be understood as any sensor capable of detecting the environment inside and / or outside the vehicle.

[0027] The first detection information refers to the information obtained by the first sensor; it usually includes the detected image data or point cloud data; the coordinate system used by the image data or point cloud data can be understood as the first coordinate system; taking image data as an example, the image data detected by the first sensor can be described as the first image or the first display image.

[0028] The second detection information refers to the information obtained by the second sensor; it usually includes the detected image data or point cloud data; the coordinate system used by the image data or point cloud data can be understood as the second coordinate system; taking image data as an example, the image data detected by the second sensor can be described as the second image or the third display image;

[0029] The first sensor is a sensor with object recognition capability, such as a smart sensor. Furthermore, in addition to the detected image data or point cloud data, the first detection information may also include the first recognition information identified therefrom.

[0030] The second sensor can be a sensor with object recognition capability or a sensor without object recognition capability; if the second sensor has object recognition capability, then the second detection information may include, in addition to the detected image data or point cloud data, the second recognition information identified therefrom.

[0031] The first recognition result can be any information obtained by object recognition from image data or point cloud data detected by the first sensor, and the object recognized by the first sensor is the first object; the first recognition result can be any information describing at least one of the following: position, quantity, type, shape, size, etc. of the first object;

[0032] The second recognition result can be any information obtained by object recognition from image data or point cloud data detected by the second sensor, and the object recognized by the second sensor is the second object; the second recognition result can be any information describing at least one of the following: position, quantity, type, shape, size, etc. of the second object;

[0033] The first object is a static and / or dynamic object identified by the first sensor from its image data or point cloud data;

[0034] The second object is a static and / or dynamic object identified by the second sensor from its image data or point cloud data;

[0035] The target object is the first object into which the recognition result needs to be incorporated into the second detection information;

[0036] Detection capability information can be understood as any information describing the detection capability of a corresponding sensor, including at least one of the following: whether it has object recognition capability, the types of objects it can recognize, the types of objects it is good at recognizing, the types of objects it cannot recognize, the types of objects it cannot recognize, the accuracy of object recognition, and the detection range.

[0037] The target information range can be understood as the portion corresponding to the target object defined in the image data and / or point cloud data of the second detection information. For example, if the second detection information includes the second image detected by the second sensor, the target information range can be characterized as a box marked in the second image.

[0038] The adjusted information range can be understood as the portion corresponding to the target object defined in the image data and / or point cloud data of the second detection information. The adjusted information range is obtained by adjusting the target information range. For example, if the second detection information includes the second image detected by the second sensor, the target information range can be characterized as a box marked in the second image.

[0039] The object information range can be understood as the portion corresponding to the second object defined in the image data and / or point cloud data of the second detection information. For example, if the second detection information includes the second image detected by the second sensor, the object information range can be characterized as a box marked in the second image.

[0040] Please see Figure 1 , Figure 1 This is a schematic diagram of a data processing system provided in an embodiment of this application. The system may include communication between devices connected via a network or gateway. The network may be a wide area network (WAN), a local area network (LAN), or a combination of both. Data transmission is achieved using a wireless link, which will not be elaborated further. The devices include a data acquisition device 11, an electronic device 12, and a display device 13.

[0041] The data acquisition device 11 includes, but is not limited to, sensors, including, but not limited to, millimeter-wave radar, lidar, mono / dual-lens cameras, and satellite navigation, for collecting data; specifically, the data acquisition device 11 may include a first sensor and a second sensor, the first sensor may be a camera, and the second sensor may be radar.

[0042] Electronic device 12 includes, but is not limited to, data servers and communication servers. Data servers and communication servers can be deployed on local servers or partially or entirely on remote servers.

[0043] Display equipment 13 includes, but is not limited to, mobile terminals, laptops, personal computers, holographic projection devices, virtual reality display devices, vehicle-mounted display devices, and displays for displaying images.

[0044] The electronic device 12 can acquire first detection information from a first sensor and second detection information from a second sensor. The first detection information includes a first identification result of a first object detected by the first sensor, and the first object includes a target object. Based on the first identification result and the association information of the second sensor, it is determined that the first identification result of the target object needs to be incorporated into the second detection information. The association information includes the detection capability information of the second sensor and / or the second detection information. The first identification result of the target object is incorporated into the second detection information.

[0045] It should be noted that, Figure 1 The system scenario diagram shown is merely an example. The servers and scenarios described in this application embodiment are for the purpose of more clearly illustrating the technical solutions of this application embodiment and do not constitute a limitation on the technical solutions provided by this application embodiment. As those skilled in the art will know, with the evolution of systems and the emergence of new business scenarios, the technical solutions provided by this application embodiment are also applicable to similar technical problems. Detailed descriptions are provided below. It should be noted that the order of description of the following embodiments is not intended to limit the preferred order of embodiments.

[0046] Figure 2 Please refer to the flowchart illustrating the data processing method for the detection data provided in the embodiments of this application. Figure 2 The data processing method includes the following steps:

[0047] 201: Obtain the first detection information from the first sensor and the second detection information from the second sensor. The first detection information includes the first identification result of the first object detected by the first sensor. The first object includes the target object.

[0048] Specifically, the first detection information can be information detected in real time by the first sensor, or information stored after detection by the first sensor. When the first sensor is working, it collects external information or internal messages from its carrier (e.g., a vehicle), obtaining the first detection message. Based on the analysis and processing of this first detection information, the relationship between the vehicle and its external environment, as well as information about the vehicle itself and its internal components, can be determined, and prompts can be provided based on this information to assist driving. Similarly, the second detection information includes information detected by the second sensor.

[0049] Specifically, when the first sensor is a camera, the first detection information may include image information; when the first sensor is a radar, the first detection information may include point cloud information; similarly, the second detection information may include image information and / or point cloud information.

[0050] In one embodiment, when acquiring the first detection information of the first sensor, the first sensor can be automatically acquired after it is turned on. For example, if the first sensor is installed on a vehicle, it will be turned on when the vehicle is turned on or off. In this case, the first detection information of the first sensor can be acquired in real time when the first sensor is turned on. Similarly, the second detection information of the second sensor can be acquired in real time.

[0051] In one embodiment, the first detection information of the first sensor can be sent to the electronic device in real time. When it is necessary to obtain the first detection information of the first sensor, the electronic device can also retrieve the first detection information of the first sensor from the storage unit. Similarly, the second detection information of the second sensor can be sent to the electronic device in real time or stored and then retrieved by the electronic device.

[0052] In one embodiment, a command can be sent to a first sensor to instruct it to detect first detection information, and the first detection information returned by the first sensor can be received. Specifically, a command can be sent to the first sensor to activate it and cause it to return real-time or historical detection information, thus obtaining the first detection information. Similarly, a command can be sent to a second sensor to obtain the second detection information returned by the second sensor.

[0053] Specifically, the command sent to the first sensor can carry a command identifier, such as the identifier of the person or object to be acquired, enabling the first sensor to adjust its angle or direction in real time as needed. Alternatively, the first sensor can send detection information corresponding to the command identifier from multiple data sources, allowing for processing based on the first detection information. Similarly, the command sent to the second sensor can carry a command identifier.

[0054] Specifically, the first identification result of the first object refers to the information of the object identified in the first detection information of the first sensor. For example, the first detection information may include information about various targets detected by the first sensor, such as pedestrian information and vehicle information. Then, pedestrians and vehicles are both first objects, and the information of pedestrians and vehicles is the first identification result. The information of pedestrians and vehicles may include at least one of their location, quantity, type, shape, and size. Similarly, the second identification result of the second object is the information of the object identified in the second detection information.

[0055] Specifically, the first and second recognition results can be obtained by the corresponding sensors and fed back to the electronic device, or they can be obtained by the electronic device based on the image data, point cloud data, etc. detected by the sensors.

[0056] 202: Based on the first identification result and the association information of the second sensor, determine the first identification result of the target object that needs to be incorporated into the second detection information; the association information includes the detection capability information of the second sensor and / or the second detection information.

[0057] Specifically, when determining whether the first identification result of the target object needs to be incorporated into the second detection information, this can be determined based on the association information of the second sensor. Specifically, the detection capability information of the second sensor includes the second sensor's detection capability for different types of objects and / or the second sensor's detection range. For example, if the second sensor has poor detection capability for vehicles, its detection capability for vehicles can be recorded as the second sensor's detection capability information; similarly, its detection range can also be recorded as the second sensor's detection capability information.

[0058] Specifically, for example, if the detection capability information of the first sensor indicates that it has recognition capability, while the detection capability information of the second sensor indicates that it has no recognition capability, then it can be determined based on the detection capability information of the second sensor that the first recognition result of the target object needs to be integrated into the second detection information. Similarly, if the first sensor can recognize people, while the second sensor can only recognize vehicles; or if the accuracy of the first sensor in recognizing people is higher than that of the second sensor in recognizing people, it can be determined based on the detection capability information of the second sensor that the first recognition result of the target object needs to be integrated into the second detection information. In one embodiment, the first recognition result of the target object is wholly or partially overlapped with a first region in the first coordinate system of the first sensor, and the first region and the second region in the second coordinate system of the second sensor are used to characterize the overlapping detection range of the first sensor and the second sensor; the second detection information includes the second recognition result of the second object detected by the second sensor;

[0059] The step of determining, based on the first identification result and the association information of the second sensor, that the first identification result of the target object needs to be incorporated into the second detection information includes:

[0060] By comparing the first identification result in the first region with the second identification result in the second region, it is determined that the first identification result of the target object needs to be incorporated into the second detection information.

[0061] Specifically, when determining whether the first identification result of the target object needs to be incorporated into the second detection information, it can be determined based on the first identification result of the first region and the second identification result of the second region, thereby avoiding the problem of inaccurate analysis results due to missing data in the subsequent data analysis process.

[0062] Specifically, taking the first identification result of the first object, including the calibration result of the first object, as an example, such as... Figure 3As shown, the first sensor 31 is mounted on the vehicle 331. Within the first field of view of the first sensor 31, there are multiple first objects, including a target object 332. When the first sensor 31 detects a first object, it can determine the coordinates of the first object in a first coordinate system; that is, it can determine the coordinates of the target object in the first coordinate system and reconstruct the target object from the image based on its coordinates. For example... Figure 3 The first displayed image 311 is used to reconstruct the target object 332. Simultaneously, the calibration result of the target object 332 can be determined, for example... Figure 3 In the second display image 312, the target object 332 is identified by a first identification box 313. Correspondingly, at the data level, the calibration result of the first object is the coordinates of the two points diagonally opposite to the first identification box in the first coordinate system. Therefore, the first recognition result can be determined based on the calibration result of the first object.

[0063] Specifically, the first recognition result of the first object may also include information indicating the object type, which can be displayed as color or text in an image, and recorded as a color ID and / or text at the data level. Similarly, the second recognition result of the second object may include information indicating the object type.

[0064] Specifically, taking the second identification result of the second object as the calibration result of the second object as an example, Figure 3 For example, if the second sensor 32 is mounted on the vehicle 331, and a portion of the target object 332 exists within the field of view of the second sensor 32, then the portion of the target object 332 can be reconstructed from the image using the coordinates of that portion. Figure 3 The third image 321 is used to reconstruct part of the target object 332. However, since the second sensor cannot identify the target object 332, it is impossible to calibrate part of the target object 332. As a result, the calibration result of part of the target object 332 is missing in the second detection information. That is, the first identification result of the target object is missing in the second detection information. Therefore, the first identification result of the target object that needs to be integrated into the second detection information is determined.

[0065] This application embodiment addresses the first identification result of a missing target object in the second detection information. By comparing the first identification result with the second identification result, and after determining the target information range of the target object, a portion of the target object can be labeled, for example... Figure 3 In the fourth display image 322, the target object 332 is marked with a second identification box 323, thereby determining the first identification result of the target object incorporated into the second detection information, and incorporating the first identification result of the target object into the second detection information.

[0066] It should be noted that, in fact, the first sensor can acquire a three-dimensional image of the target object and can also acquire a video containing the target object. Correspondingly, the second sensor can reconstruct the target object from the three-dimensional image. Therefore, the embodiments of this application do not limit the first sensor to only acquiring and reconstructing a two-dimensional image of the target object. Similarly, the second sensor can also reconstruct a three-dimensional image of the target object.

[0067] Specifically, the overlapping detection range of the first sensor and the second sensor means that the first sensor has a viewing angle range and the second sensor has a viewing angle range, and the two will overlap. The corresponding overlapping areas are the parts located in the first coordinate system and the second coordinate system, respectively, which are the first region and the second region.

[0068] Specifically, the second region corresponding to the first region refers to the overlapping of the viewing range corresponding to the first region and the viewing range corresponding to the second region, which will not be elaborated further in the following embodiments.

[0069] Specifically, such as Figure 4 As shown, taking the first display image 311 defined by the first coordinate system as an example, a first region of the first coordinate system can be obtained, such as the first region 311a in the first display image 311 in the first coordinate system. Simultaneously, a second region of the second coordinate system can be obtained, such as the second region 321a in the third display image 321 in the second coordinate system. The first region 311a and the second region 321a characterize the overlapping detection range of the first sensor and the second sensor. Therefore, the target object 332 can be detected in the first region 311a. When the target object 332 is detected in the first region 311a, considering the overlap in the viewing angles of the first sensor and the second sensor, the target object 332 may appear in the second region, for example... Figure 4 If the arm 333 of the target object 332 appears, the second detection information can be detected based on the target object 332. The target object is detected within the second detection information. Then, the calibration result of the first object is processed based on the detection result to determine the target information range of the target object.

[0070] Specifically, the first and second regions can be defined manually based on experience or experimental results, or they can change automatically in combination with depth of field and perspective effects. For example, a region measuring one-quarter the size of the first image can be taken as the first region.

[0071] Specifically, Figure 4 The example provided is that the target object is completely located in the first region, but the embodiments of this application are not limited to this. For example, the target object may be partially located in the first region.

[0072] In one embodiment, the first region and the second region can be determined by the following steps:

[0073] Extract the first feature points of the first image and the second feature points of the second image at each of the N time points. Then, for each time point, find matching first and second feature points as first and second target feature points by matching the first and second feature points. These can be understood as feature points describing the same object. Then, a first reference region and a second reference region can be delineated based on the first and second target feature points. The coverage of the first reference region can be adapted to cover all first target feature points. The wider the distribution of the first target feature points, the larger the first reference region. The coverage of the second reference region can be adapted to cover all second target feature points. The wider the distribution of the second target feature points, the larger the second reference region.

[0074] Based on this, N first reference regions and N second reference regions can be obtained. Then, based on these N first reference regions and N second reference regions, the range of the first region in the first image and the range of the second region in the second image can be determined. For example, the first reference region with the largest area can be taken as the first region, and the second region can be taken as the second region. Alternatively, the area of ​​the first region can be made larger than the area of ​​the largest first reference region, for example, the area of ​​the first region is 110% of the area of ​​the largest first reference region. And / or, the area of ​​the second region can be made larger than the area of ​​the largest second reference region, for example, the area of ​​the second region is 110% of the area of ​​the largest second reference region.

[0075] For example, if a vehicle and three people are found as feature points in the first image and designated as the first feature point, and a vehicle and one person are found as feature points in the second image and designated as the second feature point, and the feature points in the second image coincide with the feature points in the first image, then the feature point in the first image that coincides with the feature point in the second image can be designated as the first target feature point, and the feature point in the second image that coincides with the feature point in the first image can be designated as the second target feature point. Correspondingly, a first reference region and a second reference region containing the first and second target feature points can be determined respectively. Then, the first region and the second region can be determined based on the first reference region and the second reference region, for example... Figure 4 The region to the right of the dashed line in the left-middle image can contain all the first target feature points, so this region can be used as the first reference region, and the first region can be determined accordingly. For example, [the region can be defined as follows]. Figure 4 The first region is obtained by shifting the dashed line to the left in the left figure; similarly, the second region can be determined.

[0076] In a further example, the first reference region, the second reference region, the first region, and the second region can all be rectangular, with three sides of the rectangle coinciding with the three edges of the corresponding image (e.g., the first image and the second image). Therefore, determining the first reference region, the second reference region, the first region, and the second region is equivalent to determining the position of the remaining side of the rectangle. Figure 4 For reference, the first reference area, the second reference area, the first area, and the second area are determined by shifting the dotted line to the left and right.

[0077] In one example, the first and second regions can be pre-defined using the above steps. Only after the first and second regions are determined can steps 201 to 203 be executed. In other examples, it is also possible to apply the above steps during the execution of steps 201 to 203, for example, by implementing the above steps intermittently, thereby achieving real-time updates of the first and second regions.

[0078] By following the above steps, we can ensure that the scope of the first and second zones can be accurately adapted to the actual detection conditions of the vehicle.

[0079] Specifically, when a target object is detected in the first region, the target object in the second detection information is detected. If the target object is detected, there is no need to integrate the first identification result of the target object into the second detection information, thus avoiding wasting resources. If the target object is not detected, the first identification result can be processed so that the second sensor can determine the target information range and integrate the first identification result of the target object into the second detection information, thereby avoiding the problem of inaccurate analysis results due to missing data in the subsequent data analysis process.

[0080] In one embodiment, the step of determining the first identification result of the target object that needs to be incorporated into the second detection information by comparing the first identification result in the first region with the second identification result in the second region includes:

[0081] Based on the first identification result in the first region and the second identification result in the second region, determine whether the number of the first object in the first region has changed relative to the number of the second object;

[0082] When the number of first objects in the first region changes relative to the number of second objects, the most recently identified first object in the first region is taken as the target object, and it is determined that the first identification result of the target object needs to be incorporated into the second detection information.

[0083] Specifically, when the number of first objects identified in the first region is greater than the number of second objects identified in the second region, it indicates that the second sensor has partially confirmed data. In this case, the most recently identified first object in the first region can be incorporated into the second detection information as the target object. This avoids inaccurate data analysis results due to the second sensor's inability to identify the target object. Furthermore, during this process, the number of objects in the first and second regions can be determined and compared. Processing is then performed based on the comparison results, thus avoiding resource waste when the first identification result of the target object is not needed and is incorporated into the second detection information.

[0084] Specifically, before determining whether the first identification result of the target object needs to be incorporated into the second detection information, it is possible to first determine whether the first identification result of the target object needs to be incorporated into the second detection information by comparing the first quantity and the second quantity. For example, directly comparing the first quantity and the second quantity, for example, if the first quantity is n1 and the second quantity is n2, then comparing n1 and n2, if n1 = n2, it is determined that there is no need to incorporate the first identification result of the target object into the second detection information to avoid wasting resources. If n1 > n2, the first identification result of the target object is incorporated into the second detection information to avoid the problem of inaccurate analysis results due to missing data in the subsequent data analysis process.

[0085] Specifically, when comparing the first and second quantities, a threshold can also be used for comparison. For example, if the difference between the first and second quantities is greater than the threshold, the first identification result of the target object is incorporated into the second detection information to avoid inaccurate analysis results due to missing data in the subsequent data analysis process. If the difference between the first and second quantities is less than or equal to the threshold, it is determined that there is no need to incorporate the first identification result of the target object into the second detection information to avoid wasting resources.

[0086] In one embodiment, prior to the step of comparing the first quantity and the second quantity, the method further includes: monitoring the first quantity and the second quantity, determining the changes in the first quantity and the second quantity; when the quantity of the first object in the first region changes relative to the quantity of the second object, taking the most recently identified first object in the first region as the target object, and determining that a first identification result of the target object needs to be incorporated into the second detection information. By monitoring the changes in the first quantity and the second quantity, and incorporating the most recently identified first object in the first region as the target object into the second detection information when the quantity of the first object in the first region changes relative to the quantity of the second object, the method avoids inaccurate data analysis results caused by the second detection information of the second sensor failing to identify the target object.

[0087] Specifically, by monitoring changes in the number of first objects in the first region and changes in the number of second objects in the second region, for example, if the number of first objects in the first region increases while the number of second objects in the second region remains unchanged or decreases, or if the number of first objects in the first region remains unchanged while the number of second objects in the second region decreases, or if the decrease in the number of second objects in the second region exceeds the decrease in the number of first objects in the first region, it can be determined that the first identification result of the target object needs to be incorporated into the second detection information. This avoids the second detection information in the display area of ​​the second sensor failing to identify the target object, resulting in inaccurate data analysis results.

[0088] Specifically, in this embodiment, when the first sensor can identify and calibrate the target object, the detection ranges of the first and second sensors may overlap. The target object may appear within the detection range of the second sensor. Although the second sensor cannot identify the target object, the target information range of the target object can be determined through the first identification result of the first sensor and the correlation information of the second sensor. Thus, a portion of the target object can be calibrated in the second sensor, and the target object can be identified. This ensures that when the target object cannot be identified in the second sensor, the target object in the second sensor can be determined through the identification result of the first sensor, avoiding the problem of inaccurate data analysis results caused by the sensor being unable to identify the target object when it detects a portion of it.

[0089] 203: Incorporate the first identification result of the target object into the second detection information.

[0090] Specifically, by incorporating the first identification result of the target object into the second detection information, the inaccurate data analysis results can be avoided by preventing the second detection information in the display area of ​​the second sensor from failing to identify the target object.

[0091] In one embodiment, the step of incorporating the first identification result of the target object into the second detection information includes:

[0092] According to the specified calibration information, the first recognition result of the target object is projected from the first coordinate system of the first sensor to the second coordinate system of the second sensor to obtain the target projection result of the target object in the second coordinate system; the specified calibration information is used to characterize the spatial projection relationship between the first coordinate system and the second coordinate system;

[0093] Based on the target projection result, the target information range corresponding to the target object is determined in the second detection information. By projecting the first identification result onto the second coordinate system to obtain the target projection result, the target information range of the target object can be determined, thereby identifying the target object in the second detection information and avoiding inaccurate data analysis results due to the inability to identify the target object.

[0094] Specifically, when projecting the first recognition result to the second coordinate system, the projection can be performed using a reference coordinate system. For example, when projecting an image from the first coordinate system of the first sensor to the second coordinate system of the second sensor, it is necessary to first determine the depth map of each point in the image relative to the first sensor. Then, based on the depth map and the first coordinate system, the image in the first coordinate system is projected to the camera coordinate system of the first sensor to obtain the first projection information. Then, the first projection information is projected from the camera coordinate system of the first sensor to the world coordinate system (which can be used as a reference coordinate system) to obtain the second projection information. Then, the second projection information is projected from the world coordinate system to the camera coordinate system of the second sensor to obtain the third projection information. Finally, the third projection information is projected from the camera coordinate system of the second sensor to the second coordinate system to obtain the target projection result.

[0095] Specifically, the specified calibration information is the information that characterizes the spatial projection relationship between the first coordinate system and the second coordinate system. The specified calibration information can be determined by referring to the projection process in the above embodiments.

[0096] Specifically, after determining the target projection result, the target information range can be determined, thereby identifying the target object in the second detection information.

[0097] In one embodiment, the first identification result of the first object includes a first quantity of the first object, and the second identification result of the second object includes a second quantity of the second object;

[0098] The step of determining that the first identification result of the target object needs to be incorporated into the second detection information by comparing the first identification result in the first region with the second identification result in the second region includes: when the first number is greater than the second number, determining that the first identification result of the target object needs to be incorporated into the second detection information, and determining all the first objects in the first number as target objects;

[0099] Following the step of incorporating the first identification result of the target object into the second detection information, the method further includes:

[0100] If the overlap between the first identification result of any target object and the second identification result of any second object in the second detection information is higher than the overlap threshold after the first identification result of any target object is integrated into the second detection information, then the first identification result of the target object integrated into the second detection information is cleared.

[0101] Specifically, when integrating the first identification result of the target object into the second detection information, all first objects can be directly treated as target objects, and the first identification result of the first object can be integrated into the second detection information. Considering that the first identification result of the first object and the second identification result of the second object may overlap, the first identification result in the second detection information with the second identification result of the second object with an overlap degree higher than the overlap degree threshold can be searched. When the overlap degree between the first identification result and the second identification result in the second detection information is found to be higher than the overlap degree threshold, it indicates that the first identification result and the second identification result are duplicated. The overlapping first identification result of the target object can then be cleared. This can avoid the second detection information from missing target objects and avoid duplicate information in the second detection information, which would consume too many resources.

[0102] Specifically, when clearing the first recognition result of overlapping target objects, taking the first recognition result as the bounding box in the image as an example, the bounding box in the image can be deleted, and the data corresponding to the bounding box can be deleted at the data level to avoid data duplication occupying resources.

[0103] Specifically, the overlap threshold can be determined manually based on experience and experimental results. For example, if the overlap between the first and second identification results is greater than 90%, the objects identified by the first and second identification results are the same, and the overlap threshold can be set to 90%.

[0104] In one embodiment, the second detection information further includes a second image detected by the second sensor and a second recognition result, wherein the second recognition result includes determining the object information range of each second object in the second image;

[0105] The step of incorporating the first identification result of the target object into the second detection information includes:

[0106] The second image is displayed in the human-computer interaction unit, along with the target information range of each target object and the object information range of each second object marked on the second image.

[0107] In response to user operation of the human-computer interaction unit, the target information range is adjusted to obtain an adjusted information range corresponding to the target object; and a first labeled image and a second labeled image are determined for training the region adjustment model; the adjustment includes at least one of the following: size adjustment, position adjustment, shape adjustment, and clearing of the target information range;

[0108] in:

[0109] The first labeled image includes the second image, the adjusted information range of the target object labeled in the second image, and the object information range of each second object labeled in the second image;

[0110] The second labeled image includes the second image, the target information range of the target object labeled in the second image, and the object information range of each second object labeled in the second image;

[0111] The region adjustment model is trained through the following steps:

[0112] The second labeled image is input into the region adjustment model, and a third labeled image output by the region adjustment model is obtained. The third labeled image includes the second image and the information range of each second object and at least some target objects labeled in the second image.

[0113] The region adjustment model is adjusted based on the difference between the third labeled image and the first labeled image.

[0114] When there is a deviation in the target information range, the target information range can be adjusted to make the first identification result of the target incorporated into the second detection information accurate, thus avoiding the problem of inaccurate data analysis results caused by inaccurate identification.

[0115] Specifically, when determining whether there is a deviation in the target information range, the deviation can be determined by displaying the second image and the object information range of the second object in the second detection information.

[0116] Specifically, for example, a second image, the target information range, and the object information range can be displayed in the human-computer interaction department. By viewing each image displayed in the human-computer interaction department, it can be determined whether there is a deviation in the target information range. If there is a deviation in the target information range, the target information range can be adjusted to avoid the problem of inaccurate data analysis results due to inaccurate labeling.

[0117] Specifically, the human-computer interaction unit can be a display area on the carrier corresponding to the second sensor, or it can be a display area on the display unit corresponding to the second sensor. For example, if the second sensor is installed on a vehicle and the vehicle has a display screen, the second image, target information range, and object information range can be displayed in the display area corresponding to the display screen. The human-computer interaction unit can also be a display area on the display unit corresponding to the second sensor. For example, the data in the second sensor can be stored and sent to a display device, such as a mobile terminal or personal computer, through upload or download. The second image, target information range, and object information range can then be displayed in the corresponding display area, allowing various personnel to process the data based on the display results.

[0118] Specifically, when displaying the second image, the target information range, and the object information range in the display area, such as Figure 3 As shown, taking the second image as the fourth display image 322 and the target information range as the second identification box 323 as an example, it is possible to determine whether the target information range needs to be modified based on the degree of matching between the second identification box 323 and the target object 332, so as to avoid inaccurate data analysis results due to inaccurate identification of the target object in the second detection information of the second sensor.

[0119] Specifically, such as Figure 3 As shown, the target information range is Figure 3 Taking the second identifier box as an example, we can see that the target object is identified by the second identifier box 323 in the figure. Due to the possibility of inaccurate parameters in the specified calibration information, the second identifier box may not match the target object. For example, the second identifier box may not completely identify the target object, or only a part of the target object may be inside the second identifier box, or the size of the second identifier box may be more than 10 times the size of the target object. As a result, the second identifier box may not be able to accurately identify the target object. In this case, it is necessary to adjust the second identifier box, such as by increasing or decreasing the size of the second identifier box or adjusting its position, so that the display box can accurately identify the target object.

[0120] Specifically, in response to user operations on the human-computer interaction unit, the operations on the human-computer interaction unit can be, for example, adjusting the display box by clicking or dragging the mouse, thereby determining the adjusted information range.

[0121] Specifically, when adjusting the target information range, a region adjustment model can be trained to adjust the target information range. During training, the region adjustment model can be trained to adjust size, position, shape, and clear the target information range.

[0122] In one embodiment, the step of adjusting the target information range when there is a deviation in the target information range to obtain an adjusted information range corresponding to the target object includes:

[0123] The target information range is adjusted using a region adjustment model to obtain the adjusted information range corresponding to the target object. By modifying the target information range using the region adjustment model, the target information range can be automatically modified when it does not match the target object, avoiding inaccurate labeling of the target information range that could lead to inconvenience in viewing and errors during processing.

[0124] Specifically, after determining the adjusted information range, the specified calibration information can be corrected, thereby making the target information range determined based on the first identification result more accurate.

[0125] Specifically, based on the adjusted information range, the calibration data of the target object can be determined. Then, the first feature data of the target object can be extracted, such as multiple feature points n1, n2, ... of the arm. Then, based on the target information range, the feature points corresponding to these feature points in the reference coordinate system can be determined, for example, n1. ， n2 ， ..., to obtain the second feature data, and at the same time, the feature points of the person in the reference coordinate system, including the feature points of the person in the reference coordinate system determined by the first sensor, such as N1, N2, ..., are obtained to obtain the third feature data. Then, the second feature data and the third feature data are matched. Since both will form a person's arm, they can still be matched even if their feature points are different. Therefore, the data corresponding to the second feature data can be determined in the third feature data, and this data is used as the fourth feature data. Then, the specified calibration information can be corrected according to the offset data of the fourth feature data and the second feature data.

[0126] Specifically, the embodiments of this application are not limited to determining the position and image of the object identified by the second sensor only through the object identified by the first sensor, but can also determine the position and image of the object identified by the first sensor through the object identified by the second sensor.

[0127] Specifically, for example, if the first sensor identifies the first person and determines the first identification result of the first person, but the first sensor cannot identify the second person, while the second sensor cannot identify the first person, but can identify the second identification result of the second person, then the first identification result of the first person can be integrated into the second detection information, and the second identification result of the second person can be integrated into the first detection information.

[0128] Specifically, when the first sensor can only detect people or has a weak ability to detect other objects, and the second sensor can only detect vehicles or has a weak ability to detect other objects, the first and second sensors can complement each other's sensing capabilities. This can solve the problem of inaccurate data analysis results when the target object is present in the sensor.

[0129] It should be noted that the embodiments of this application are described using a first sensor and a second sensor, but the embodiments of this application are not limited to this. For example, a third sensor or a fourth sensor may also be used. In one example application scenario, the first detection information and the second detection information of the first sensor and the second sensor can be collected uniformly by a recorder and then transmitted to an electronic device via 4G, 5G, Wi-Fi, or other means. The electronic device can then be used to execute a data processing method for the detection data.

[0130] Furthermore, the electronic device can execute this method in real time, accompanying the detection process of the first and second sensors, or it can process the detection information after it has been collected.

[0131] This application provides a data processing method. When a second sensor cannot identify a target object, the method uses the first identification result of the first object detected by the first sensor and the associated information of the second sensor to determine whether the first identification result of the target object needs to be incorporated into the second detection information. This allows the first identification result of the target object to be incorporated into the second detection information, enabling the second sensor to identify the target object when it detects it. This avoids or mitigates the impact of the second sensor's shortcomings on the data analysis results. For example, it can prevent the problem of inaccurate data analysis results caused by the second sensor's inability to identify the target object when it detects only a portion of it.

[0132] Correspondingly, Figure 5 Please refer to the schematic diagram of the data processing device for the detection data provided in the embodiments of this application. Figure 5 The data processing device includes the following modules:

[0133] The acquisition module 401 is used to acquire first detection information from a first sensor and second detection information from a second sensor. The first detection information includes a first identification result of a first object detected by the first sensor, and the first object includes a target object.

[0134] The determining module 402 is used to determine, based on the first identification result and the association information of the second sensor, the first identification result of the target object that needs to be incorporated into the second detection information; the association information includes the detection capability information of the second sensor and / or the second detection information;

[0135] The integration module 403 is used to integrate the first identification result of the target object into the second detection information.

[0136] In one embodiment, the integration module 403 is used to project the first recognition result of the target object from the first coordinate system of the first sensor to the second coordinate system of the second sensor according to the specified calibration information, so as to obtain the target projection result of the target object in the second coordinate system; the specified calibration information is used to characterize the spatial projection relationship between the first coordinate system and the second coordinate system;

[0137] Based on the target projection result, the target information range corresponding to the target object is determined in the second detection information.

[0138] In one embodiment, the first identification result of the target object is wholly or partially overlapped with a first region in the first coordinate system of the first sensor, and the first region and the second region in the second coordinate system of the second sensor are used to characterize the overlapping detection range of the first sensor and the second sensor; the second detection information includes the second identification result of the second object detected by the second sensor; the determining module 402 is used to determine, by comparing the first identification result in the first region with the second identification result in the second region, that the first identification result of the target object needs to be incorporated into the second detection information.

[0139] In one embodiment, the first identification result of the first object includes a first quantity of the first object, and the second identification result of the second object includes a second quantity of the second object; the determining module 402 is used to determine that the first identification result of the target object needs to be incorporated into the second detection information when the first quantity is greater than the second quantity, and to determine all the first objects of the first quantity as target objects; the data processing device for the detection data further includes a deduplication module, which is used to remove the first identification result of any target object incorporated into the second detection information when the overlap between the first identification result of any target object incorporated into the second detection information and the second identification result of any second object in the second detection information is higher than the overlap threshold.

[0140] In one embodiment, the determining module 402 is configured to determine whether the number of first objects in the first region has changed relative to the number of second objects based on the first identification result in the first region and the second identification result in the second region; when the number of first objects in the first region has changed relative to the number of second objects, the most recently identified first object in the first region is taken as the target object, and it is determined that the first identification result of the target object needs to be incorporated into the second detection information.

[0141] In one embodiment, the second detection information further includes a second image detected by the second sensor and a second recognition result, wherein the second recognition result includes the object information range of each second object determined in the second image; the integration module 403 is used to display the second image, and the target information range of each target object and the object information range of each second object annotated in the second image in the human-computer interaction unit; in response to the user's operation on the human-computer interaction unit, the target information range is adjusted to obtain the adjusted information range corresponding to the target object; and a first annotation image and a second annotation image are determined for training the region adjustment model; the adjustment includes at least one of the following: size adjustment, position adjustment, shape adjustment, and clearing of the target information range; wherein: the first annotation image The first labeled image includes the second image, and the adjusted information range of the target object labeled on the second image, and the object information range of each second object labeled on the second image; the second labeled image includes the second image, and the target information range of the target object labeled on the second image, and the object information range of each second object labeled on the second image; the data processing device for the probe data further includes a training module, which is used to input the second labeled image into the region adjustment model and obtain a third labeled image output by the region adjustment model, the third labeled image including the second image, and the information range of each second object and at least some target objects labeled on the second image; the region adjustment model is adjusted according to the difference between the third labeled image and the first labeled image.

[0142] In one embodiment, the integration module 403 is used to adjust the target information range using a region adjustment model to obtain an adjusted information range corresponding to the target object.

[0143] Accordingly, embodiments of this application also provide an electronic device, such as... Figure 6As shown, the electronic device may include a radio frequency (RF) circuit 501, a memory 502 including one or more computer-readable storage media, an input unit 503, a display unit 504, a sensor 505, an audio circuit 506, a wireless Fidelity (WiFi) module 507, a processor 508 including one or more processing cores, and a power supply 509, among other components. Those skilled in the art will understand that... Figure 6 The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain parts, or have different component arrangements. Wherein:

[0144] RF circuit 501 can be used for receiving and transmitting signals during information transmission or calls. Specifically, it receives downlink information from the base station and hands it over to one or more processors 508 for processing; additionally, it transmits uplink data to the base station. Memory 502 can be used to store software programs and modules. Processor 508 executes various functional applications and data processing by running the software programs and modules stored in memory 502. Input unit 503 can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical, or trackball signal inputs related to user settings and function control.

[0145] Display unit 504 can be used to display information input by the user or information provided to the user, as well as various graphical user interfaces of the server. These graphical user interfaces can be composed of graphics, text, icons, videos, and any combination thereof.

[0146] The electronic device may also include at least one sensor 505, such as a light sensor, a motion sensor, and other sensors. Audio circuitry 506 includes a speaker that provides an audio interface between the user and the electronic device.

[0147] WiFi is a short-range wireless transmission technology. Electronic devices using the WiFi module 507 can help users send and receive emails, browse web pages, and access streaming media, providing users with wireless broadband internet access. Although Figure 6 WiFi module 507 is shown, but it is understood that it is not a necessary component of the electronic device and can be omitted as needed without changing the nature of the application.

[0148] The processor 508 is the control center of the electronic device. It connects various parts of the phone through various interfaces and lines. By running or executing software programs and / or modules stored in the memory 502, and calling data stored in the memory 502, it performs various functions of the electronic device and processes data, thereby monitoring the phone as a whole.

[0149] The electronic device also includes a power supply 509 (such as a battery) that supplies power to various components. Preferably, the power supply can be logically connected to the processor 508 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system.

[0150] Although not shown, the electronic device may also include a camera, Bluetooth module, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 508 in the electronic device loads the executable files corresponding to the processes of one or more applications into the memory 502 according to the following instructions, and the processor 508 runs the applications stored in the memory 502 to achieve the following functions:

[0151] Acquire first detection information from a first sensor and second detection information from a second sensor. The first detection information includes a first identification result of a first object detected by the first sensor, and the first object includes a target object. Based on the first identification result and the association information of the second sensor, determine that the first identification result of the target object needs to be incorporated into the second detection information. The association information includes the detection capability information of the second sensor and / or the second detection information. Incorporate the first identification result of the target object into the second detection information.

[0152] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the detailed description above, and they will not be repeated here.

[0153] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be accomplished by instructions, or by instructions controlling related hardware. These instructions can be stored in a storage medium and loaded and executed by a processor.

[0154] Therefore, embodiments of this application provide a storage medium storing multiple instructions that can be loaded by a processor to achieve the following functions:

[0155] Acquire first detection information from a first sensor and second detection information from a second sensor. The first detection information includes a first identification result of a first object detected by the first sensor, and the first object includes a target object. Based on the first identification result and the association information of the second sensor, determine that the first identification result of the target object needs to be incorporated into the second detection information. The association information includes the detection capability information of the second sensor and / or the second detection information. Incorporate the first identification result of the target object into the second detection information.

[0156] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0157] The storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0158] Since the instructions stored in the storage medium can execute the steps of any of the methods provided in the embodiments of this application, the beneficial effects that any of the methods provided in the embodiments of this application can achieve can be realized, as detailed in the preceding embodiments, and will not be repeated here.

[0159] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0160] The data processing method, data processing apparatus, electronic device, and storage medium provided in the embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the technical solutions and core ideas of this application. Those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A data processing method of detecting data, characterized by, include: Acquire first detection information from a first sensor and second detection information from a second sensor, wherein the first detection information includes a first identification result of a first object detected by the first sensor, and the first object includes a target object; Based on the first identification result and the association information of the second sensor, it is determined that the first identification result of the target object needs to be incorporated into the second detection information; The associated information includes the detection capability information of the second sensor and the second detection information; The detection capability information of the second sensor includes the detection capability of the second sensor for different types of objects and / or the detection range of the second sensor; The first identification result of the target object is incorporated into the second detection information; The first identification result of the target object is wholly or partially overlapping with the first region of the first coordinate system of the first sensor, and the first region and the second region in the second coordinate system of the second sensor are used to characterize the overlapping detection range of the first sensor and the second sensor; the second detection information includes the second identification result of the second object detected by the second sensor; The step of determining, based on the first identification result and the association information of the second sensor, that the first identification result of the target object needs to be incorporated into the second detection information includes: By comparing the first identification result in the first region with the second identification result in the second region, it is determined that the first identification result of the target object needs to be incorporated into the second detection information; the first identification result of the first object includes the first number of the first object, and the second identification result of the second object includes the second number of the second object; The step of determining whether the first identification result of the target object needs to be incorporated into the second detection information by comparing the first identification result in the first region with the second identification result in the second region includes: When the first quantity is greater than the second quantity, it is determined that the first identification result of the target object needs to be incorporated into the second detection information, and all the first objects of the first quantity are determined as the target object.

2. The data processing method for probe data as described in claim 1, characterized in that, The step of incorporating the first identification result of the target object into the second detection information includes: According to the specified calibration information, the first recognition result of the target object is projected from the first coordinate system of the first sensor to the second coordinate system of the second sensor to obtain the target projection result of the target object in the second coordinate system; the specified calibration information is used to characterize the spatial projection relationship between the first coordinate system and the second coordinate system; Based on the target projection result, the target information range corresponding to the target object is determined in the second detection information.

3. The data processing method for probe data as described in claim 1, characterized in that, Following the step of incorporating the first identification result of the target object into the second detection information, the method further includes: If the overlap between the first identification result of any target object and the second identification result of any second object in the second detection information is higher than the overlap threshold after the first identification result of any target object is integrated into the second detection information, then the first identification result of the target object integrated into the second detection information is cleared.

4. The data processing method for probe data as described in claim 1, characterized in that, The step of determining whether the first identification result of the target object needs to be incorporated into the second detection information by comparing the first identification result in the first region with the second identification result in the second region includes: Based on the first identification result in the first region and the second identification result in the second region, determine whether the number of the first object in the first region has changed relative to the number of the second object; When the number of first objects in the first region changes relative to the number of second objects, the most recently identified first object in the first region is taken as the target object, and it is determined that the first identification result of the target object needs to be incorporated into the second detection information.

5. The data processing method for probe data as described in claim 2, characterized in that, The second detection information also includes the second image detected by the second sensor and the second recognition result, wherein the second recognition result includes the object information range of each second object determined in the second image; The step of incorporating the first identification result of the target object into the second detection information includes: The second image is displayed in the human-computer interaction unit, along with the target information range of each target object and the object information range of each second object marked on the second image. In response to user operation of the human-computer interaction unit, the target information range is adjusted to obtain an adjusted information range corresponding to the target object; and a first labeled image and a second labeled image are determined for training the region adjustment model; the adjustment includes at least one of the following: size adjustment, position adjustment, shape adjustment, and clearing of the target information range; in: The first labeled image includes the second image, the adjusted information range of the target object labeled in the second image, and the object information range of each second object labeled in the second image; The second labeled image includes the second image, the target information range of the target object labeled in the second image, and the object information range of each second object labeled in the second image; The region adjustment model is trained through the following steps: The second labeled image is input into the region adjustment model, and a third labeled image output by the region adjustment model is obtained. The third labeled image includes the second image and the information range of each second object and at least some target objects labeled in the second image. The region adjustment model is adjusted based on the difference between the third labeled image and the first labeled image.

6. The data processing method for probe data as described in claim 5, characterized in that, When there is a deviation in the target information range, the step of adjusting the target information range to obtain an adjusted information range corresponding to the target object includes: The target information range is adjusted using a region adjustment model to obtain the adjusted information range corresponding to the target object.

7. A data processing device for detecting data, characterized in that, include: The acquisition module is used to acquire first detection information from a first sensor and second detection information from a second sensor. The first detection information includes a first identification result of a first object detected by the first sensor, and the first object includes a target object. The determining module is configured to determine, based on the first identification result and the association information of the second sensor, the first identification result of the target object that needs to be incorporated into the second detection information; the association information includes the detection capability information of the second sensor and the second detection information; The detection capability information of the second sensor includes the detection capability of the second sensor for different types of objects and / or the detection range of the second sensor; An integration module is used to integrate the first identification result of the target object into the second detection information; The first identification result of the target object is wholly or partially overlapping with the first region of the first coordinate system of the first sensor, and the first region and the second region in the second coordinate system of the second sensor are used to characterize the overlapping detection range of the first sensor and the second sensor; the second detection information includes the second identification result of the second object detected by the second sensor; The step of determining, based on the first identification result and the association information of the second sensor, to determine which first identification result of the target object needs to be incorporated into the second detection information includes: By comparing the first identification result in the first region with the second identification result in the second region, it is determined that the first identification result of the target object needs to be incorporated into the second detection information; The first identification result of the first object includes the first quantity of the first object, and the second identification result of the second object includes the second quantity of the second object; The determining module determines the step of integrating the first identification result of the target object into the second detection information by comparing the first identification result in the first region with the second identification result in the second region, including: When the first quantity is greater than the second quantity, it is determined that the first identification result of the target object needs to be incorporated into the second detection information, and all the first objects of the first quantity are determined as the target object.

8. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the data processing method for probe data as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium stores a plurality of instructions, which are adapted for loading by a processor to execute the steps in the data processing method for probe data as described in any one of claims 1 to 6.

Images