A positioning method, device and equipment for a repaired object and a readable storage medium

Abstract

The application discloses a positioning method, device and equipment of a repaired object and a computer readable storage medium, belongs to the field of image recognition, and is used for assisting positioning of a repaired object in a vehicle. A target object to be repaired and a plane coordinate detection value of the target object in a vehicle structure coordinate system can be determined according to multiple images of the repaired vehicle, then a first part set of a part to which the plane coordinate detection value belongs is found out, then the parts in the first part set are removed according to the factor of distance from the geometric center to obtain a second part set, finally, the identity information of a part corresponding to the target object is determined according to matching between image features of the target object and preset image features of the parts in the second part set, the target object can be positioned through the identity information, the method can accurately assist a worker in positioning the repaired object, the correct object can be ensured to be repaired, the maintenance efficiency is improved, and the safety hidden danger is eliminated.

Description

Technical Field

[0001] This invention relates to the field of image recognition, and in particular to a method for locating an object under repair. This invention also relates to a device, equipment, and computer-readable storage medium for locating an object under repair. Background Technology

[0002] In the process of car repair, staff generally need to use their experience to judge and find the object that needs to be repaired (parts or circuit test points). However, if the staff lacks professional knowledge about vehicles, they will find it difficult to accurately find the object that needs to be repaired. In other words, the staff may find the wrong object to repair and start the repair, which reduces repair efficiency and poses safety hazards.

[0003] Therefore, how to provide a solution to the above-mentioned technical problems is a problem that needs to be solved by those skilled in the art. Summary of the Invention

[0004] The purpose of this invention is to provide a method for locating an object to be repaired. This method can accurately assist workers in locating the object to be repaired, thereby ensuring that the correct object is repaired, improving repair efficiency, and eliminating safety hazards. Another purpose of this invention is to provide a device, equipment, and computer-readable storage medium for locating an object to be repaired. This method can accurately assist workers in locating the object to be repaired, thereby ensuring that the correct object is repaired, improving repair efficiency, and eliminating safety hazards.

[0005] To solve the above-mentioned technical problems, the present invention provides a method for locating an object to be repaired, comprising:

[0006] Based on the acquired multi-frame images of the vehicle under repair, the target object to be repaired is determined, and the planar coordinate detection value of the target object in the vehicle structural coordinate system is determined.

[0007] From the preset parts database corresponding to the model of the vehicle being repaired, determine the parts whose boundary range includes the plane coordinate detection value, and use them as the first set of parts;

[0008] In the first set of parts, parts whose difference between the geometric center coordinates and the plane coordinates detection values ​​is greater than a first preset difference threshold are removed from the first set of parts to obtain a second set of parts;

[0009] The acquired image features of the target object are matched with the preset image features of each part in the second part set to determine the identity information of the part corresponding to the target object, so as to identify the target object through the identity information.

[0010] Preferably, the target object to be repaired includes the moved parts and the circuit test points to be tested.

[0011] Preferably, when the target object is a circuit detection point to be detected, after matching the acquired image features of the target object with the preset image features of each part in the second part set to determine the identity information of the part corresponding to the target object, the method for locating the object to be repaired further includes:

[0012] Identify all circuit detection points on the parts corresponding to the target object and use them as the first set of candidate circuit detection points;

[0013] Determine the first distance between the detected planar coordinates and the geometric center coordinates of the part corresponding to the target object;

[0014] The circuit detection points in the first set of candidate circuit detection points whose distance from the preset planar coordinate value to the geometric center coordinate value of the corresponding part of the target object is greater than the first distance are removed from the first set of candidate circuit detection points to obtain the second set of candidate circuit detection points.

[0015] Determine the coordinates of the geometric center of the plane on the part corresponding to the target object and its second distance from the plane coordinate detection value;

[0016] The circuit detection point with the smallest difference between the distance between the preset plane coordinate value and the coordinate value of the geometric center of the plane where the target object is located, and the second distance, is selected as the circuit detection point to be repaired.

[0017] Preferably, the process of constructing the preset parts database is as follows:

[0018] Vehicle structure models for each type of vehicle are constructed in advance based on the structural parameters of each type of vehicle;

[0019] Based on the vehicle structure coordinate system and the vehicle structure model, the geometric center coordinates and boundary ranges of each part in each type of vehicle are obtained.

[0020] Image features and corresponding geometric center coordinates of each part in each type of vehicle are obtained from both a vertically downward view and a vertically upward view, and the image features are used as preset image features.

[0021] The geometric center coordinates, boundary range, preset image features, and corresponding geometric center coordinates of each part in each type of vehicle are used to construct a preset parts database for that type of vehicle.

[0022] Preferably, the step of determining the target object to be repaired based on the acquired multi-frame images of the vehicle under repair and determining the planar coordinate detection value of the target object in the vehicle structural coordinate system specifically involves:

[0023] The target object to be repaired is determined by using the three-frame difference method based on the multi-frame images of the vehicle being repaired, and the plane coordinate detection value of the target object in the vehicle structural coordinate system is determined.

[0024] Preferably, the step of determining the target object to be repaired based on the acquired multi-frame images of the vehicle under repair and determining the planar coordinate detection value of the target object in the vehicle structural coordinate system specifically involves:

[0025] The vehicle model is determined based on the identification image of the vehicle being repaired;

[0026] The target object to be repaired is determined based on the image of the vehicle from a vertical downward or vertical upward perspective, and the plane coordinate detection value of the target object in the vehicle structural coordinate system is determined.

[0027] Preferably, the identity information is the name of the part corresponding to the target object and its position mark in the vehicle structure model diagram corresponding to the vehicle being repaired.

[0028] To solve the above-mentioned technical problems, the present invention also provides a positioning device for an object to be repaired, comprising:

[0029] The first determining module is used to determine the target object to be repaired based on the acquired multi-frame images of the vehicle to be repaired and to determine the plane coordinate detection value of the target object in the vehicle structure coordinate system.

[0030] The second determining module is used to determine, from the preset parts database corresponding to the model of the vehicle being repaired, the parts whose boundary range includes the plane coordinate detection value, and to use them as the first set of parts;

[0031] The elimination module is used to remove parts from the first part set whose difference between the geometric center coordinate value and the plane coordinate detection value is greater than a first preset difference threshold, thereby obtaining a second part set.

[0032] The identification module is used to match the acquired image features of the target object with the preset image features of each part in the second parts set to determine the identity information of the part corresponding to the target object, so as to identify the target object through the identity information.

[0033] To solve the above-mentioned technical problems, the present invention also provides a positioning device for an object to be repaired, comprising:

[0034] Memory, used to store computer programs;

[0035] A processor is configured to execute the computer program to implement the steps of the method for locating the object being repaired as described above.

[0036] To address the aforementioned technical problems, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the positioning method for the object under repair as described above.

[0037] This invention provides a method for locating a repaired object. Based on multiple frames of images of the vehicle being repaired, this application determines the target object and its planar coordinate detection value in the vehicle's structural coordinate system. Then, it identifies a first set of parts to which the planar coordinate detection value belongs. Next, parts in the first set are eliminated based on their distance from the geometric center, resulting in a second set of parts. Finally, the image features of the target object are matched with the preset image features of each part in the second set to determine the identity information of the corresponding part. This allows for the location of the target object using its identity information. This method accurately assists workers in locating the repaired object, ensuring the correct object is repaired, improving repair efficiency, and eliminating safety hazards.

[0038] The present invention also provides a positioning device, equipment and computer-readable storage medium for a repaired object, which has the same beneficial effects as the above-described positioning method for a repaired object. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the prior art and embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 A flowchart illustrating a method for locating a repaired object provided by the present invention;

[0041] Figure 2 A schematic diagram of a vehicle structure model provided by the present invention;

[0042] Figure 3 This is a schematic diagram of the structure of a positioning device for a repaired object provided by the present invention;

[0043] Figure 4 This is a schematic diagram of the structure of a positioning device for a repaired object provided by the present invention. Detailed Implementation

[0044] The core of this invention is to provide a method for locating an object to be repaired. This method can accurately assist workers in locating the object to be repaired, thereby ensuring that the correct object is repaired, improving repair efficiency, and eliminating safety hazards. Another core aspect of this invention is to provide a device, equipment, and computer-readable storage medium for locating an object to be repaired. This method can accurately assist workers in locating the object to be repaired, thereby ensuring that the correct object is repaired, improving repair efficiency, and eliminating safety hazards.

[0045] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0046] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating a method for locating a repairable object provided by the present invention. The method for locating the repairable object includes:

[0047] S101: Determine the target object to be repaired based on the acquired multi-frame images of the vehicle to be repaired, and determine the plane coordinate detection value of the target object in the vehicle structure coordinate system.

[0048] Specifically, considering the technical problems mentioned above, and taking into account that when a worker is repairing a vehicle, they usually already know which specific object needs repair, but due to a lack of experience, they may find the wrong object and begin repairs, which is obviously inappropriate. Therefore, this application aims to identify the target object being repaired by the worker and determine their identity during the operation, so that the worker can determine whether they are repairing the correct target object by identifying their identity, thereby ensuring that the correct object is repaired, improving repair efficiency, and eliminating safety hazards.

[0049] Specifically, during the repair process, the staff will inevitably perform some operations on the vehicle, which means that the image of the vehicle will be different from the "static state without staff operation". Therefore, in this step, the target object to be repaired and its planar coordinate detection value in the vehicle structure coordinate system can be determined based on the acquired multi-frame images of the vehicle to be repaired. Here, determining the target object to be repaired can be understood as determining the position of the target object to be repaired in the image, but its identity has not yet been determined. In subsequent steps, the identity of the target object can be further determined by the "planar coordinate detection value of the determined target object in the vehicle structure coordinate system".

[0050] It is worth mentioning that, considering that the parts in the vehicle are arranged in layers parallel to the ground, and that the workers may carry out maintenance operations from either "top to bottom" or "bottom to top", the images obtained in this application can include either a "top to bottom" or "bottom to top" perspective. The specific situation can be determined according to the worker's specific maintenance angle. For example, when the worker is repairing the chassis of the vehicle, an image from a "bottom to top" perspective can be captured. In a series of images, due to the worker's operation, there will inevitably be some differences in the images. The position of the target object in the image can be determined by the differences in the image.

[0051] S102: From the preset parts database corresponding to the model of the vehicle being repaired, determine the parts whose boundary range contains the plane coordinate detection value, and use them as the first set of parts;

[0052] Specifically, since the aforementioned steps have determined the plane coordinate detection value of the target object in the vehicle structural coordinate system, this step can retrieve the data from the preset parts database corresponding to the model of the vehicle being repaired, and determine the parts whose boundary range includes the plane coordinate detection value. This can also be understood as the boundary range of which parts the plane coordinate of the target object belongs to, thereby finding the first set of parts. The true identity of the target object is hidden in a certain part in this set.

[0053] S103: Remove parts from the first part set whose difference between the geometric center coordinate value and the plane coordinate detection value is greater than a first preset difference threshold, and obtain the second part set;

[0054] Specifically, considering that the first set of parts is determined only by the planar coordinate detection value of the target object, several parts in the first set of parts may belong to a series of parts in the longitudinal direction of the "planar coordinate detection value" position in the vehicle. In other words, the spacing between several parts in the first set of parts is relatively obvious. Therefore, parts in the first set of parts whose difference between the geometric center coordinate value and the planar coordinate detection value is greater than the first preset difference threshold can be removed from the first set of parts to obtain the second set of parts.

[0055] The first preset difference threshold can be set independently, and this embodiment of the invention does not limit it.

[0056] S104: Match the acquired image features of the target object with the preset image features of each part in the second part set to determine the identity information of the part corresponding to the target object, so as to identify the target object through the identity information.

[0057] Specifically, if the number of parts in the second set of parts determined after step S103 is greater than 1, this step can be executed. Considering that the image features of different parts are different, this step can match the collected image features of the target object with the preset image features of each part in the second set of parts to determine the identity information of the part corresponding to the target object, so as to identify the target object through the identity information.

[0058] Of course, if the number of parts in the second set of parts determined after step S103 is equal to 1, the identity information of the parts in the second set of parts can be directly determined and used as the identity information of the parts corresponding to the target object.

[0059] Once the identification information of the part corresponding to the target object is determined, the identification information can be displayed through a prompter so that staff can be informed in a timely manner and assist in determining whether the target object being repaired is correct.

[0060] This invention provides a method for locating a repaired object. Based on multiple frames of images of the vehicle being repaired, this application determines the target object and its planar coordinate detection value in the vehicle's structural coordinate system. Then, it identifies a first set of parts to which the planar coordinate detection value belongs. Next, parts in the first set are eliminated based on their distance from the geometric center, resulting in a second set of parts. Finally, the image features of the target object are matched with the preset image features of each part in the second set to determine the identity information of the corresponding part. This allows for the location of the target object using its identity information. This method accurately assists workers in locating the repaired object, ensuring the correct object is repaired, improving repair efficiency, and eliminating safety hazards.

[0061] Based on the above embodiments:

[0062] In a preferred embodiment, the target objects to be repaired include the moved parts and the circuit test points to be tested.

[0063] Specifically, the target objects to be repaired can typically include moved parts and circuit test points to be tested. For moved parts, the final identified identity information is the part to be repaired, while for circuit test points, the final identified identity information is the identity information of the part to which the circuit test point to be repaired belongs.

[0064] Specifically, when the target object to be repaired is a circuit testing point, the circuit testing tool can be identified first through the image. Then, the contact point between the circuit testing tool and the vehicle parts can be taken as the target object when the tool remains stationary for a certain period of time in a "testing state".

[0065] As a preferred embodiment, when the target object is a circuit test point to be detected, after matching the acquired image features of the target object with the preset image features of each part in the second part set to determine the identity information of the part corresponding to the target object, the method for locating the object to be repaired further includes:

[0066] Identify all circuit test points on the parts corresponding to the target object and use them as the first set of candidate circuit test points;

[0067] Specifically, when the target object is a circuit detection point to be detected, since the part whose identity information is finally determined may contain more than one circuit detection point, in order to more accurately determine the circuit detection point under repair, in this embodiment of the invention, all circuit detection points on the part corresponding to the target object can be determined and used as a first set of candidate circuit detection points, so as to determine a unique circuit detection point from them.

[0068] Determine the first distance between the plane coordinate detection value and the geometric center coordinate value of the corresponding part of the target object;

[0069] Specifically, considering that although the plane coordinate detection value has a certain error, it also has high reference value, the circuit detection points can be eliminated by comparing the plane coordinate detection value with the preset plane coordinate values ​​of each circuit detection point in the first set of candidate circuit detection points. Therefore, in this embodiment of the invention, the first distance between the plane coordinate detection value and the geometric center coordinate value of the corresponding part of the target object is first determined.

[0070] In the first set of candidate circuit detection points, circuit detection points whose distance from the preset planar coordinate value to the geometric center coordinate value of the corresponding part of the target object is greater than the first distance difference threshold are removed from the first set of candidate circuit detection points to obtain the second set of candidate circuit detection points.

[0071] Specifically, considering that circuit detection points that differ significantly from the planar coordinate detection values ​​can be excluded first, in this embodiment of the invention, circuit detection points in the first candidate circuit detection point set whose distance between the preset planar coordinate value and the geometric center coordinate value of the corresponding part of the target object is greater than the first distance difference threshold can be removed from the first candidate circuit detection point set to obtain the second candidate circuit detection point set, thereby reducing the selection range.

[0072] Determine the coordinates of the geometric center of the plane on the part corresponding to the target object and its second distance from the plane coordinate detection value;

[0073] Specifically, in order to further determine the unique circuit detection point, considering that for the plane on the part corresponding to the target object, the distance between the target object and the geometric center of the plane is less than the distance between the target object and the geometric center of the part, the circuit detection point can be screened more accurately by judging the "distance difference between the target object and each candidate circuit detection point and the geometric center of the plane". Therefore, the embodiment of the present invention can first determine the coordinate value of the geometric center of the plane on the part corresponding to the target object and its second distance from the plane coordinate detection value.

[0074] Among the second set of alternative circuit test points, the circuit test point with the smallest difference between the distance between the preset plane coordinate value and the coordinate value of the geometric center of the plane where the target object is located and the second distance is selected as the test point of the circuit to be repaired.

[0075] Specifically, after obtaining the second distance, the circuit test point with the smallest difference between the distance between the preset planar coordinate value and the coordinate value of the geometric center of the plane where the target object is located and the second distance can be selected from the second set of alternative circuit test points. This determines the specific identity of the circuit test point being repaired, which helps staff to verify whether the circuit test point currently being repaired is correct.

[0076] For a better explanation of the embodiments of the present invention, please refer to Figure 2 , Figure 2 A schematic diagram of a vehicle structure model provided by the present invention, as a preferred embodiment, shows the following process for constructing a pre-defined parts database:

[0077] Vehicle structure models for each type of vehicle are constructed in advance based on the structural parameters of each type of vehicle;

[0078] Based on the vehicle structure coordinate system and the vehicle structure model, the geometric center coordinates and boundary ranges of each part in each type of vehicle are obtained.

[0079] Image features and corresponding geometric center coordinates of each part in each type of vehicle are obtained from both vertical downward and vertical upward perspectives, and the image features are used as preset image features.

[0080] The geometric center coordinates, boundary range, preset image features, and corresponding geometric center coordinates of each part in each type of vehicle are used to construct a preset parts database for that type of vehicle.

[0081] Specifically, firstly, vehicle structure models for each type of vehicle are constructed based on their structural parameters. Then, based on the vehicle structure coordinate system and the vehicle structure model, the geometric center coordinates and boundary ranges of each part in each type of vehicle are obtained. Considering that the aforementioned steps require the use of image features of the part surface and the geometric center coordinates on the surface image, the image features and corresponding geometric center coordinates of each part in each type of vehicle can be obtained from both a vertically downward view and a vertically upward view, and these image features are used as preset image features. Finally, the geometric center coordinates, boundary ranges, preset image features, and corresponding geometric center coordinates of each part in each type of vehicle are used to construct a preset part database for that type of vehicle.

[0082] The specific details of the preset parts database are as follows:

[0083] (1) Obtain various vehicle structural parameters, including the dimensions of the main frame of the vehicle and the dimensions of each component, and establish a vehicle structural model.

[0084] (2) Take the vehicle chassis plane as the XOY plane, take the corner of the rectangle circumscribed by the outer contour line of the vehicle top view as the 0 point, and take the vertical and horizontal planes upward as the Z axis.

[0085] (3) Obtain the coordinate values ​​of the geometric center of each component in the vehicle coordinate system.

[0086] (4) Generate the coordinates of the eight corners of the external cuboid of each component to determine the range to which the component belongs (the boundary range of the component).

[0087] (5) The internal structure layout of the vehicle adopts a layered coordinate model of parts from top to bottom (from bottom to top).

[0088] Taking a top-down layered coordinate model of a part as an example, the process of constructing a layered coordinate model of a part is as follows:

[0089] ①When all components are not disassembled, obtain the planar structural model of the outermost surface from top to bottom.

[0090] ② Remove each part of the top layer in sequence and build a planar structural model.

[0091] ③ Remove all parts from the top layer and build a planar structural model.

[0092] ④ Repeat steps ② and ③ to create planar structural models of the parts in layers 2, 3, 4, and n.

[0093] ⑤ For the vehicle wiring section, only the connection points between the wiring and the parts are considered, and the connection points are marked.

[0094] As a preferred embodiment, the target object to be repaired is determined based on the acquired multi-frame images of the vehicle being repaired, and the plane coordinate detection value of the target object in the vehicle structural coordinate system is determined as follows:

[0095] The three-frame difference method is used to determine the target object to be repaired based on the multi-frame images of the vehicle being repaired, and to determine the plane coordinate detection value of the target object in the vehicle structural coordinate system.

[0096] Specifically, the three-frame difference method has advantages such as high accuracy and fast calculation speed.

[0097] Of course, in addition to the three-frame difference method, other methods can be used to implement this step, and the embodiments of the present invention are not limited here.

[0098] As a preferred embodiment, the target object to be repaired is determined based on the acquired multi-frame images of the vehicle being repaired, and the plane coordinate detection value of the target object in the vehicle structural coordinate system is determined as follows:

[0099] The vehicle model is determined based on the identification image of the vehicle being repaired;

[0100] The target object to be repaired is determined based on the image of the vehicle from a vertical downward or vertical upward perspective, and the plane coordinate detection value of the target object in the vehicle structural coordinate system is determined.

[0101] Specifically, in order to accurately locate the object being repaired, it is first necessary to determine the model of the vehicle being repaired. Then, the data corresponding to that model can be retrieved from the parts database to proceed with the steps in this application.

[0102] The identification image can be of various types, such as an image of a vehicle license plate, etc., and this embodiment of the invention does not limit it.

[0103] In a preferred embodiment, the identity information is the name of the part corresponding to the target object and its position mark in the vehicle structure model diagram corresponding to the vehicle being repaired.

[0104] Specifically, in order to help staff understand the part information corresponding to the target object they are repairing more quickly and accurately, the identity information in this embodiment of the invention is the name of the part corresponding to the target object and its position mark in the vehicle structure model diagram of the vehicle being repaired. For example, when the part is the left front tire, the left front tire can be marked with a special color in the vehicle structure model diagram.

[0105] Of course, besides this type of identity information, identity information can be of many other types, and this embodiment of the invention does not limit the specific types.

[0106] Please refer to Figure 3 , Figure 3 This is a schematic diagram of a positioning device for a repaired object provided by the present invention. The positioning device for the repaired object includes:

[0107] The first determining module 31 is used to determine the target object to be repaired based on the acquired multi-frame images of the vehicle to be repaired and to determine the plane coordinate detection value of the target object in the vehicle structure coordinate system.

[0108] The second determining module 32 is used to determine, from the preset parts database corresponding to the model of the vehicle being repaired, the parts whose boundary range contains the plane coordinate detection value, and to use them as the first set of parts;

[0109] The elimination module 33 is used to remove parts from the first part set whose difference between the geometric center coordinate value and the plane coordinate detection value is greater than a first preset difference threshold, so as to obtain a second part set.

[0110] The identification module 34 is used to match the acquired image features of the target object with the preset image features of each part in the second part set to determine the identity information of the part corresponding to the target object, so as to identify the target object through the identity information.

[0111] For a description of the positioning device for the object under repair provided in this embodiment of the invention, please refer to the aforementioned embodiment of the positioning method for the object under repair. This embodiment of the invention will not be repeated here.

[0112] Please refer to Figure 4 , Figure 4 This is a schematic diagram of a positioning device for a repaired object provided by the present invention. The positioning device for the repaired object includes:

[0113] Memory 41 is used to store computer programs;

[0114] The processor 42 is used to execute a computer program to implement the steps of the method for locating the object to be repaired as described in the foregoing embodiments.

[0115] For a description of the positioning device for the object under repair provided in the embodiments of the present invention, please refer to the aforementioned embodiments of the positioning method for the object under repair. The embodiments of the present invention will not be repeated here.

[0116] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method for locating the object to be repaired as described in the foregoing embodiments.

[0117] For a description of the computer-readable storage medium provided in the embodiments of the present invention, please refer to the aforementioned embodiments of the method for locating the object to be repaired; the embodiments of the present invention will not be repeated here.

[0118] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section. It should also be noted that in this specification, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising a..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0119] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A positioning method of an object to be repaired, characterized by, The method comprises the following steps: determining a target object to be repaired and a planar coordinate detection value of the target object in a vehicle structure coordinate system according to a plurality of images of the vehicle to be repaired; the target object to be repaired comprises a moved part and a detected circuit detection point; determining a part whose boundary range contains the planar coordinate detection value from a preset part database corresponding to the vehicle model of the vehicle to be repaired, and taking the part as a first part set; the preset part database contains the boundary range, the geometric center coordinate value and the preset image feature of each part; the first part set contains a plurality of parts in the vehicle corresponding to the longitudinal layered layout of the planar coordinate detection value; removing the part whose difference between the geometric center coordinate value and the planar coordinate detection value is greater than a first preset difference threshold from the first part set to obtain a second part set; matching the image feature of the target object with the preset image feature of each part in the second part set to determine the identity information of the part corresponding to the target object, so as to determine the target object through the identity information; the identity information is used to prompt the staff to judge whether the target object being repaired is correct.

2. The method of positioning a subject under repair according to claim 1, wherein, When the target object is a detected circuit detection point, after the matching of the image feature of the target object with the preset image feature of each part in the second part set to determine the identity information of the part corresponding to the target object, the positioning method of the repaired object further comprises: determining all circuit detection points on the part corresponding to the target object and taking them as a first alternative circuit detection point set; determining a first distance between the planar coordinate detection value and the geometric center coordinate value of the part corresponding to the target object; removing the circuit detection point whose distance between the preset planar coordinate value and the geometric center coordinate value of the part corresponding to the target object is greater than a second preset difference threshold from the first alternative circuit detection point set to obtain a second alternative circuit detection point set; determining the coordinate value of the geometric center of the plane where the target object is located on the part corresponding to the target object and a second distance between the coordinate value and the planar coordinate detection value; taking the circuit detection point whose distance between the preset planar coordinate value and the coordinate value of the geometric center of the plane where the target object is located is the smallest in the second alternative circuit detection point set as the repaired circuit detection point.

3. The method of positioning a subject for service of claim 2, wherein, The construction process of the preset part database is as follows: constructing a vehicle structure model of each type of vehicle in advance according to the structure parameters of each type of vehicle; obtaining the geometric center coordinate value and the part boundary range of each part in each type of vehicle based on the vehicle structure coordinate system and the vehicle structure model; obtaining the image feature and the corresponding geometric center coordinate value of each part in each type of vehicle from a vertical downward view and a vertical upward view respectively, and taking the image feature as a preset image feature; The geometric center coordinate value, the part boundary range, the preset image feature and the geometric center coordinate value corresponding to the preset image feature of each part in each type of vehicle are constructed into a preset part database of the type of vehicle.

4. The method of positioning a subject for service of claim 3, wherein, The target object being repaired is determined according to the obtained multiple images of the vehicle being repaired, and the planar coordinate detection value of the target object in the vehicle structure coordinate system is determined. The target object being repaired is determined according to the obtained multiple images of the vehicle being repaired, and the planar coordinate detection value of the target object in the vehicle structure coordinate system is determined.

5. The method of positioning a subject for service of claim 4, wherein, The target object being repaired is determined according to the obtained multiple images of the vehicle being repaired, and the planar coordinate detection value of the target object in the vehicle structure coordinate system is determined. The vehicle type of the vehicle being repaired is determined according to the identity image of the vehicle being repaired. The target object being repaired is determined according to the image of the vehicle being repaired in the vertical downward view or the vertical upward view, and the planar coordinate detection value of the target object in the vehicle structure coordinate system is determined.

6. The method of positioning a subject under repair according to any one of claims 1 to 5, wherein, The identity information is the name of the part corresponding to the target object and the position mark in the vehicle structure model diagram corresponding to the vehicle being repaired.

7. A positioning device for an object to be repaired, characterized in that Comprise: The first determination module is used for determining the target object being repaired and the planar coordinate detection value of the target object in the vehicle structure coordinate system according to the obtained multiple images of the vehicle being repaired; the target object being repaired comprises a moved part and a detected circuit detection point; The second determination module is used for determining the part whose part boundary range contains the planar coordinate detection value from the preset part database corresponding to the vehicle type of the vehicle being repaired, and taking it as a first part set; The preset part database contains the boundary range, the geometric center coordinate value and the preset image feature of each part; the first part set contains multiple parts in the vehicle corresponding to the longitudinal layered layout of the planar coordinate detection value; The elimination module is used for eliminating the part whose difference between the geometric center coordinate value and the planar coordinate detection value is greater than a first preset difference threshold from the first part set to obtain a second part set; The identification module is used for matching the image feature of the target object with the preset image feature of each part in the second part set, determining the identity information of the part corresponding to the target object, and determining the target object through the identity information; the identity information is used to prompt the staff to judge whether the target object being repaired is correct.

8. A positioning apparatus of an object to be repaired, characterized by comprising: Comprise: The memory is used for storing the computer program; The processor is used for executing the computer program to realize the steps of the positioning method of the repaired object in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer program is stored on the computer readable storage medium, and the computer program is executed by the processor to realize the steps of the positioning method of the repaired object in any one of claims 1 to 6.

Images