Object detection method and device, computing equipment and storage medium

Abstract

The embodiment of the invention provides an object detection method and device, computing equipment and a storage medium, and relates to the technical field of object detection, and the method comprises the steps: determining a plurality of part scanning detection processes according to the part features of a target object, and each part scanning detection process comprises a part feature scanning process and a part feature detection process; executing the component scanning detection processes according to the component execution sequence, and executing the next component scanning detection process if the detection result represents that the corresponding component characteristics are detected to be qualified under the condition that the detection process of each component scanning detection process is executed; and if the detection result represents that the corresponding part feature detection is unqualified, stopping executing the part scanning detection process and outputting an abnormal result. Scanning and detection are combined, real-time decision making and control can be achieved, the detection efficiency is improved, and the problem that problem tracing is difficult is solved.

Description

Technical Field

[0001] This disclosure relates to the field of object detection technology, and in particular to an object detection method, apparatus, computing device and storage medium. Background Technology

[0002] In the industrial manufacturing sector, the quality inspection of objects is crucial. The traditional mainstream solution is to use specialized inspection tools. Inspection tools have the advantages of high inspection accuracy and ease of operation, but their design and manufacturing costs are high, the cycle time is long, the storage and management costs are high, and one type of inspection tool is usually only for one specific part, resulting in poor flexibility.

[0003] With the development of 3D scanning and 3D inspection technologies in recent years, full-size point cloud data of objects can be obtained through 3D scanning equipment and then compared with standard CAD models to achieve comprehensive and flexible inspection. However, this method requires inspectors to first scan the entire object or a specific area based on their experience, generating complete point cloud data, and then importing it into professional inspection software for data alignment, feature extraction, and tolerance analysis. Although it can obtain full-size information, the disconnect between scanning and inspection can easily lead to invalid scanning and rework. Summary of the Invention

[0004] To address, or at least partially address, the aforementioned technical problems, this disclosure provides an object detection method, apparatus, computing device, and storage medium that combine scanning and detection to enable real-time decision-making and control, improve detection efficiency, and solve the problem of difficult traceability.

[0005] This disclosure provides an object detection method, which includes: Multiple component scanning and detection processes are determined based on the component features of the target object. Each component scanning and detection process includes a scanning process for the component features and a detection process. The component scanning and detection processes are executed in the order of component execution. If the detection result indicates that the corresponding component feature detection is qualified after the detection process of each component scanning and detection process is completed, the next component scanning and detection process is executed. If the detection result indicates that the corresponding component feature detection is unqualified, the execution of the component scanning and detection process is stopped and an abnormal result is output.

[0006] This disclosure also provides an object detection device, which includes: The sequence determination module is used to determine multiple component scanning and detection processes based on the component features of the target object. Each component scanning and detection process includes a scanning process for the component features and a detection process. The scanning and detection module is used to execute the component scanning and detection processes according to the component execution order. Specifically, after the detection process of each component scanning and detection process is completed, if the detection result indicates that the corresponding component feature detection is qualified, the next component scanning and detection process is executed; if the detection result indicates that the corresponding component feature detection is unqualified, the execution of the component scanning and detection process is stopped and an abnormal result is output.

[0007] This disclosure also provides a computing device, which includes: a processor; a memory for storing processor-executable instructions; and a processor for reading executable instructions from the memory and executing the instructions to implement the object detection method provided in this disclosure.

[0008] This disclosure also provides a computer-readable storage medium storing a computer program for performing the object detection method provided in this disclosure.

[0009] This application improves the applicability of the detection process by pre-configured component scanning and detection procedures and adapting them to different objects. It separates the scanning and detection processes for multiple component features and combines the scanning and detection of individual component features, strictly adhering to the scanning and detection process. The subsequent process is determined based on the scanning and detection results of each feature, achieving a real-time decision-making and control mechanism. It strictly follows the detection process, proceeding to the next feature only when the previous feature is detected as qualified, and terminating the process directly when a feature is detected as abnormal. This minimizes unnecessary work and saves time and resources. Furthermore, by pinpointing abnormal detection issues to each feature, it greatly improves the efficiency of subsequent troubleshooting. Attached Figure Description

[0010] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0011] Figure 1 This is a schematic flowchart of an object detection method provided in an embodiment of the present disclosure; Figure 2 A flowchart illustrating another object detection method provided in this embodiment of the present disclosure; Figure 3 A schematic flowchart illustrating yet another object detection method provided in this disclosure embodiment; Figure 4This is a schematic diagram of the structure of an object detection device provided in an embodiment of the present disclosure; Figure 5 This is a schematic diagram of the structure of a computing device provided in an embodiment of the present disclosure. Detailed Implementation

[0012] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0013] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0014] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0015] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0016] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0017] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0018] In traditional object inspection, users rely on the corresponding work instructions for the inspection tools. The lack of standardized process guidance and entry criteria makes troubleshooting difficult when inspections fail. It's impossible to quickly pinpoint whether the problem lies with the scan data, the baseline, or the feature itself. Furthermore, it relies excessively on operator experience to judge scanning parameters and quality, demanding high technical skills from operators and proving difficult to learn. 3D scanning and inspection technologies follow a linear "scan first, process later" model: inspectors first scan the entire object or a specific area based on experience, generating complete point cloud data. This data is then imported into specialized inspection software for data alignment, feature extraction, and tolerance analysis. Full-size scanning generates massive amounts of dense point cloud data, resulting in large data volumes, slow processing, and high demands on computer hardware. This leads to a disconnect between scanning and inspection, easily causing invalid scans and rework, and lacks process control, resulting in unclear problem localization.

[0019] To address the aforementioned problems, this disclosure provides an object detection method, comprising: determining multiple component scanning and detection processes based on the identification of component features of a target object, each component scanning and detection process including a scanning process for component features and a detection process; executing the component scanning and detection processes in the order of component execution, wherein, upon completion of the detection process of each component scanning and detection process, if the detection result indicates that the corresponding component feature detection is qualified, then the next component scanning and detection process is executed; if the detection result indicates that the corresponding component feature detection is unqualified, then the execution of the component scanning and detection process is stopped and an abnormal result is output. This method can minimize unnecessary work, save time and resources; at the same time, by pinpointing the abnormal detection problem to each feature, it can greatly improve the efficiency of subsequent troubleshooting.

[0020] The method will be described below with reference to specific embodiments.

[0021] Figure 1 This is a flowchart illustrating an object detection method provided in an embodiment of the present disclosure. The method can be executed by an object detection device, which can be implemented using software and / or hardware, and is generally integrated into a computing device. Figure 1 As shown, the method includes: S101. Determine the scanning and detection process for multiple components based on the component characteristics of the target object.

[0022] Specifically, a component scanning and detection process is set up for each component feature of the target object. Each component scanning and detection process includes a scanning process for the component features and a detection process.

[0023] For example, the identifiers of component features are set according to the execution order of components, namely component feature 1, component feature 2, and component feature N. The component scanning and detection process for component feature 1 consists of scanning component feature 1 and detecting component feature 1.

[0024] In one possible implementation, the detection process for the same component feature is executed after the scanning process. In another possible implementation, the detection process and the scanning process for the same component feature are performed simultaneously.

[0025] Furthermore, the component features include reference features and features to be measured.

[0026] Among them, the datum feature is the core reference element that defines the geometry, dimensional tolerances, and assembly relationships of the target object. Understandably, a specific location on the target object with well-defined geometric properties provides a unique reference for the position, orientation, and dimensions of other features, and serves as a reference scale during object assembly.

[0027] In one possible implementation, datum features include planar datum features, hole / shaft datum features, edge / groove datum features, etc. Examples include datum A (plane) and datum B (hole).

[0028] For example, the mounting surface and mating surface of the target object can be used as planar reference features to determine the height or perpendicularity; the center of the positioning hole of the target object and the axis of the shaft part can be used as hole / shaft reference features to determine the center position or coaxiality; the contour edge and the side of the slot of the target object can be used as edge / slot reference features to determine the symmetry or distance dimension.

[0029] In another possible implementation, the benchmark features also include combined benchmark features.

[0030] For example, multiple single features, such as two parallel planes or three orthogonal planes, can be combined to form a reference feature, which can provide a more stable reference system.

[0031] Specifically, a benchmark scanning and detection process is set for each benchmark feature, and each benchmark scanning and detection process includes a scanning process for the benchmark feature and a detection process.

[0032] For example, for datum plane A, the datum scanning inspection process is "scan datum plane A → inspect datum plane A", and for datum hole B, the datum scanning inspection process is "scan datum hole B → inspect datum hole B". The features to be tested are functional geometric features other than datum features, used to verify whether they meet design requirements. Understandably, in addition to basic assembly functions, other geometric structures of the target object that enable functions such as transmission and sealing must also be considered, and their position, size, shape, and other parameters must be inspected to ensure they meet design requirements.

[0033] In one possible implementation, the features to be measured include size features, shape features, positional relationship features, surface quality features, etc.

[0034] For example, the diameter of the axis of the target object, the distance between planes, the depth / width of the groove, the diameter of the hole, etc. can be used as size features; the flatness of the plane of the target object, the roundness of the cylindrical surface, the straightness of the axis, etc. can be used as shape features; the position of the hole of the target object relative to the reference, the perpendicularity / parallelism of the plane, the coaxiality of multiple features, etc. can be used as positional relationship features; the surface roughness of the target object, the presence of scratches / burrs, etc. can be used as surface quality features.

[0035] The detection process for a feature to be tested is a pre-built standard process for scanning and detecting multiple features to be tested, including pairs of sub-processes for multiple features to be tested arranged in a preset order.

[0036] Specifically, a scan detection process is set up for each feature to be tested, and each scan detection process includes a scan process for the feature to be tested and a detection process.

[0037] For example, for feature 1 to be tested, the generated scan detection process is "scan feature 1 to be tested → detect feature 1 to be tested".

[0038] S102. Execute the component scanning and testing process according to the component execution order.

[0039] Obtain the execution order of components. The execution order of components can be set and adjusted by the user, or it can be set and adjusted according to the relationship between component characteristics.

[0040] Specifically, a component scanning and inspection process for multiple component features is executed strictly in the order of component execution. Upon completion of each component scanning and inspection process, if the inspection result indicates that the corresponding component feature is qualified, the next component scanning and inspection process is executed; if the inspection result indicates that the corresponding component feature is unqualified, the component scanning and inspection process is stopped and an abnormal result is output. Abnormal results include, but are not limited to, abnormal prompts and abnormal reports.

[0041] For example, the complete component scanning and inspection process for multiple component features is as follows: scan component feature 1, inspect component feature 1, scan component feature 2, inspect component feature 2, scan component feature N, inspect component feature N. When inspecting component feature 2 fails the inspection, the step of scanning component feature N is stopped, and an abnormal result indicating that component feature 2 is abnormal is output.

[0042] In one possible implementation, the benchmark scanning detection process is executed according to the benchmark execution order. Upon completion of each benchmark scanning detection process, if the detection result indicates that the corresponding benchmark feature detection is qualified, the next benchmark scanning detection process is executed; if the detection result indicates that the corresponding benchmark feature detection is unqualified, the benchmark scanning detection process is stopped and an abnormal result is output. If all benchmark feature detections are qualified, the test scanning detection process is executed according to the test execution order. Specifically, upon completion of each test scanning detection process, if the detection result indicates that the corresponding test feature detection is qualified, the next test scanning detection process is executed; if the detection result indicates that the corresponding test feature detection is unqualified, the test scanning detection process is stopped and an abnormal result is output.

[0043] Furthermore, the system receives component feature adjustment instructions and adjusts the component scanning and detection process based on these instructions. These instructions include adding component features, deleting component features, and adjusting the component execution order.

[0044] In this implementation, a pre-configured component scanning and detection process is used, and the process is adapted to different objects to improve the applicability of the detection process. The scanning and detection process for multiple component features is separated, and the scanning and detection of individual component features are combined. The scanning and detection process is strictly executed, and the subsequent process is determined based on the scanning and detection results of each feature, realizing a real-time decision-making and control mechanism. The detection process is strictly followed. When a feature is detected as qualified, the scanning of the next feature is performed. When a feature is detected as abnormal, the process is terminated directly, which can minimize ineffective work and save time and resources. At the same time, the abnormal detection problem is pinpointed to each feature, which can greatly improve the efficiency of subsequent investigation.

[0045] Figure 2 This is a flowchart illustrating another object detection method provided in an embodiment of this disclosure. This method can be executed by an object detection device, which can be implemented in software and / or hardware, and is generally integrated into a computing device. Figure 1 As shown, the method includes: S201. Determine the execution order of multiple benchmark scanning detection processes based on benchmark features, and determine the execution order of multiple scan detection processes to be tested based on the features to be tested.

[0046] Specifically, please refer to Figure 1 Step S102 will not be described in detail here.

[0047] S202. Perform a frame scan on the target object to obtain frame point information.

[0048] The target object is subjected to overall 3D scanning detection, the coordinates of the 3D frame points of the target object are constructed, and the key contour features on the target object are identified. The component features are determined based on the frame point information.

[0049] Specifically, the target object is scanned as a whole using 3D point cloud scanning technology to construct a master coordinate system, and a CAD model of the target object is generated based on the 3D point cloud data of each frame point. The 3D point cloud data of each frame point includes X, Y, and Z spatial coordinate information.

[0050] This step can obtain the coordinates of the three-dimensional spatial frame points of the target object, providing basic data for subsequent modeling, scanning, size detection and deviation analysis.

[0051] S203. Execute the baseline scanning and detection process according to the baseline execution order.

[0052] Obtain the baseline execution order, which can be set and adjusted by the user or based on the relationship of baseline features.

[0053] In one possible implementation, the baseline execution order of the baseline scanning detection process is determined according to the dependencies of the baseline features.

[0054] For example, when the reference hole B is on the reference plane A, the reference scanning detection process corresponding to the reference plane A is in the order of the reference scanning detection process, and the reference scanning detection process of the reference hole B is in the order of the reference.

[0055] In another possible implementation, the execution order of the baseline scanning detection process is determined based on the baseline feature anomaly rate. The baseline scanning detection process is sorted from largest to smallest according to the historical anomaly rate of each baseline feature on the target object.

[0056] For example, when the historical anomaly rate of reference hole B is greater than that of reference plane A, the reference scanning detection process of reference hole B is performed first, and the reference scanning detection process of reference plane A is performed later.

[0057] The benchmark scanning and detection process is executed strictly according to the benchmark execution sequence. Specifically, for each benchmark scanning and detection process, the position of the benchmark features is determined based on the 3D coordinate information in the frame point information, and targeted scanning is performed to extract key feature parameters, obtaining the corresponding benchmark feature scanning information. For each detection step within the benchmark scanning and detection process, it is determined whether the benchmark feature scanning information meets the design requirements.

[0058] In one possible implementation, the baseline feature scanning information is compared with the baseline feature standard information required by the design, and the deviation is checked to see if it is within the allowable deviation range. If the deviation is within the allowable deviation range, the baseline feature is judged to be normal; if the deviation exceeds the allowable deviation range, the baseline feature is judged to be abnormal.

[0059] Specifically, the first benchmark scanning and detection process is determined according to the benchmark execution sequence. The first benchmark feature is scanned and detected to ensure it meets the design requirements. If the first benchmark feature does not meet the design requirements, it is determined to be abnormal, the detection is stopped, and step S206 is executed. If the first benchmark feature meets the design requirements, it is determined to be normal, and the second benchmark feature is then scanned and detected to ensure it meets the design requirements. If the second benchmark feature does not meet the design requirements, it is determined to be abnormal, the detection is stopped, and step S206 is executed. If the second benchmark feature meets the design requirements, it is determined to be normal, and the third benchmark feature is then scanned and detected to ensure it meets the design requirements.

[0060] Following this pattern, the baseline scanning and detection process is executed strictly according to the baseline execution order. When the previous baseline feature scan and detection is normal, the next baseline scanning and detection process is entered until all baseline features are detected normally, and step S204 is executed. Alternatively, if there is an abnormal baseline feature detection, step S206 is executed.

[0061] S204. When the reference feature detection is qualified, perform an alignment operation on multiple reference features and check whether they are aligned.

[0062] Specifically, taking the primary datum feature in the design requirements as the core and secondary datum features, tertiary datum features, etc., as auxiliary features, the relative position requirements of each datum feature are obtained, thus obtaining a datum template. The datum feature scanning information of each datum feature obtained in step S203 is extracted, and the datum feature scanning information is aligned and matched with the datum template. When the datum feature scanning information and the datum template are successfully matched, multiple datum features are aligned; otherwise, multiple datum features are not aligned.

[0063] In one possible implementation, the alignment deviation between the reference feature scanning information and the reference template is calculated, and it is detected whether the alignment deviation of each reference feature is within the allowable deviation range. If the alignment deviations are all within the allowable deviation range, it is determined that multiple reference features are aligned, and step S205 is executed; if the alignment deviation of one reference feature exceeds the allowable deviation range, it is determined that multiple reference features are not aligned, and step S206 is executed.

[0064] S205. When multiple reference features are aligned, the scanning and detection process is executed in the order of execution to be tested.

[0065] Obtain the execution order to be tested. The execution order to be tested can be set and adjusted by the user, or it can be set and adjusted according to the relationship of the features to be tested.

[0066] In one possible implementation, the execution order of the scanning and detection process is determined according to the dependencies of the features to be tested.

[0067] In another possible implementation, the execution order of the scanning and detection process is determined according to the anomaly rate of the feature to be tested. The scanning and detection process is sorted from largest to smallest based on the historical anomaly rate of each feature to be tested on the target object.

[0068] For specific examples, please refer to the benchmark scanning detection process sorting method for benchmark features, which will not be repeated here.

[0069] The scanning and detection process is executed strictly according to the order of execution. Specifically, for each scanning and detection process, the position of the feature to be tested is determined based on the 3D coordinate information in the frame point information, and targeted scanning is performed to extract key feature parameters, obtaining the corresponding feature scanning information. For each detection process within the scanning and detection process, it is determined whether the feature scanning information meets the design requirements.

[0070] In one possible implementation, the scanning information of the feature to be tested is compared with the standard information of the feature to be tested required by the design, and the deviation is checked to see if it is within the allowable deviation range. If the deviation is within the allowable deviation range, the feature to be tested is judged to be normal. If the deviation exceeds the allowable deviation range, the feature to be tested is judged to be abnormal.

[0071] Specifically, the first test feature is determined according to the execution order, and the first test feature is scanned and tested to see if it meets the design requirements. If the first test feature does not meet the design requirements, it is determined that the first test feature is abnormal, the detection is stopped, and step S206 is executed. If the first test feature meets the design requirements, it is determined that the first test feature is normal, and then the second test feature is scanned and tested to see if it meets the design requirements. If the second test feature does not meet the design requirements, it is determined that the second test feature is abnormal, the detection is stopped, and step S206 is executed. If the second test feature meets the design requirements, it is determined that the second test feature is normal, and then the third test feature is scanned and tested to see if it meets the design requirements.

[0072] Following this pattern, the scanning and detection process is executed strictly according to the order of the tests. When the previous test feature is scanned and detected normally, the next test sub-process is entered until all test features are detected normally. The process ends and outputs that the target object is normal or that there is an abnormal test feature detection, and then step S206 is executed.

[0073] S206. When the reference feature is abnormal, or multiple reference features are not aligned, or the feature to be tested is abnormal, an abnormal result will be output.

[0074] If an anomaly exists in a reference feature in step S203, or multiple reference features are misaligned in step S204, or an anomaly exists in a feature to be tested in step S205, the detection is terminated and an anomaly result is output. The anomaly result includes, but is not limited to, anomaly prompts and anomaly reports.

[0075] Specifically, when any process in the above steps detects an anomaly, an anomaly prompt message, an anomaly detection result, and the corresponding anomaly step number are generated. The anomaly prompt message, anomaly detection result, and anomaly step number are packaged to generate an anomaly report, and the anomaly prompt and anomaly report are output.

[0076] In this implementation, the applicability of the detection process is improved by pre-configuring the baseline scanning detection process and the detection process to be tested, and setting the process according to the adaptability of different objects. Based on the object's frame points, each feature information is further identified, reducing scanning difficulty, improving scanning quality, and reducing scanning workload. Real-time and rapid processing can be achieved on portable mobile scanning devices. The scanning and detection of individual features are combined, and the subsequent process is determined based on the scanning and detection results of each feature, realizing a real-time decision-making and control mechanism. The detection process is strictly executed, and when a feature is abnormal, the process is terminated directly, which can minimize ineffective work and save time and resources. At the same time, the anomaly detection problem is accurate to each feature, which can greatly improve the efficiency of subsequent investigation.

[0077] In the above implementation, the target object is partially scanned and detected according to the established benchmark scanning and detection process and the detection process to be tested.

[0078] In one possible implementation, each target object corresponds to a fixed baseline scanning detection process and a test scanning detection process.

[0079] In another possible implementation, the baseline scanning detection process and / or the scanning detection process to be tested for each target object can be adjusted based on the real-time detection situation.

[0080] Specifically, the system receives reference feature adjustment instructions and adjusts the reference scanning and detection process based on these instructions. These reference feature adjustment instructions include adding reference features, deleting reference features, and adjusting the reference execution order.

[0081] The system receives instructions to adjust the features to be tested and adjusts the scanning and detection process accordingly. These instructions include adding features, deleting features, and adjusting the execution order of the tests.

[0082] In the actual application of the target object, when design content is added or reduced, correspondingly, scanning detection is added or removed. When the anomaly rate of one or more baseline features changes, the execution order of the baselines is adjusted according to the updated anomaly rate; when the anomaly rate of one or more features to be tested changes, the execution order of the features to be tested is adjusted according to the updated anomaly rate.

[0083] This application also provides a specific example of an object detection system. The object detection system can be implemented in software and / or hardware, and is generally integrated into a computing device.

[0084] The object detection system includes a process creation platform and a process execution engine.

[0085] The process creation platform is used to define inspection processes, associate features, set parameters and rules, and generate executable process scripts, i.e., to create processes. Figure 1 or Figure 2 The object detection method flow is shown. The inspection flow includes a reference feature detection flow and a target feature detection flow; the associated features include reference features and target features; the set parameters include design requirement parameters; and the set rules include scanning detection rules.

[0086] The process execution engine is a state controller used to load and parse process scripts, drive device hardware and user interface, guide the user step-by-step through the entire inspection task, and enable real-time decision-making. Figure 1 or Figure 2 The flowchart of the object detection method is shown.

[0087] Optionally, the process execution engine is integrated into a dedicated 3D scanning device with a touchscreen, such as a laser scanner or a structured light scanner.

[0088] In one specific implementation, the target object is a component, and the process creation platform creates a component detection method process that includes the following steps: Step a1: Importing and defining features of the CAD model.

[0089] It presents a graphical interface, allowing users to import CAD models of target parts and define all the part features that need to be considered, including multiple baseline features and multiple features to be measured.

[0090] For example, the reference features include a reference plane A and a reference hole B. The features to be measured include feature 1 and feature 2.

[0091] Step a2: Construct the "atomic" subprocess pair.

[0092] This step defines the smallest unit of the component feature inspection process as a "scan-inspection" sub-process pair, i.e., the component scan-inspection process. A reference scan-inspection process and a test scan-inspection process are constructed separately. For example, a reference inspection process of "scanning reference plane A → inspecting reference plane A" and a reference scan-inspection process of "scanning reference hole B → inspecting reference hole B".

[0093] Step a3, process arrangement and logic setting.

[0094] Users can drag and drop components in the component scanning and detection process via a graphical interface, adjusting the execution order of components.

[0095] Specifically, the baseline scanning detection process and the scanning detection process to be tested are dragged and sorted, and a strict dependency relationship is set, that is, the "scanning" stage of the next scanning detection process can only be entered after the "detection" result of the previous scanning detection process is qualified.

[0096] Step a4: Generate an executable workflow script.

[0097] The process creation platform packages and compiles the information from steps a1 to a3 into a structured process script file and sends it to the dedicated 3D scanning device of the process execution engine.

[0098] The process execution engine parses the process script file and drives the dedicated 3D scanning equipment to complete the scanning and inspection work step by step. The equipment touchscreen guides the execution of only the smallest scanning and inspection process at a time (e.g., "Please scan reference plane A"). After the scan is completed, the equipment automatically performs inspection analysis and displays the results. After the "inspection" stage of each scanning and inspection process, a real-time decision is made. If the inspection is qualified, the process execution engine automatically starts the "scanning" guidance of the next scanning and inspection process. If the inspection is unqualified, the process execution engine immediately terminates the entire process and accurately reports the error on the touchscreen, achieving step-level problem isolation and localization.

[0099] For example, the error report when an error occurs is "Error: The position of the reference hole B is out of tolerance. The process terminates at step 2 / 8".

[0100] Please see Figure 3 , Figure 3 This is a schematic flowchart of another object detection method provided in an embodiment of the present disclosure.

[0101] like Figure 3As shown, firstly, a dedicated 3D scanning device is used to scan the frame points of the target object. Then, according to the reference scanning and detection process, reference A is scanned and detected. If the detection fails, an anomaly is reported and the process ends. If the detection passes, reference B is scanned and detected. If the detection fails, an anomaly is reported and the process ends. If the detection passes, the next reference feature is scanned until reference N is detected. Further, an alignment operation is performed. If the reference feature alignment fails, an anomaly is reported and the process ends. If the alignment passes, the feature to be tested (M) is scanned and detected according to the detection process. If the detection fails, an anomaly is reported and the process ends. If the detection passes, the next feature to be tested (M) is scanned until M is detected and the process ends.

[0102] This embodiment provides a streamlined, guided object detection method and system. It features a visually orchestrated process pair on the process creation platform and a process execution engine that parses and executes the process step-by-step. On the process creation platform, the inspection process is decomposed into a series of logically ordered, criteria-based atomic "scan-detect" process pairs, which serve as the basic units for constructing a complete inspection process. The process execution engine guides execution step-by-step on dedicated equipment. Based on the detection results of each process pair, a real-time decision-making and control mechanism determines whether the process should continue or terminate immediately. Within a dedicated 3D scanning device with a touchscreen, it manages the status of complex sub-processes, step indexes, and jump logic, thereby reducing operational difficulty, increasing the first-time success rate, achieving precise problem step-level localization, and optimizing data volume through targeted scanning.

[0103] To implement the above embodiments, this disclosure also proposes an object detection device.

[0104] Figure 4 This is a schematic diagram of the structure of an object detection device provided in an embodiment of this disclosure. The device can be implemented by software and / or hardware, and is generally integrated into a computing device. Figure 4 As shown, the device includes: The sequence determination module 401 is used to determine multiple component scanning and detection processes based on the component features of the target object. Each component scanning and detection process includes a scanning process for the component features and a detection process.

[0105] The scanning and detection module 402 is used to execute the component scanning and detection process according to the component execution order. When the detection process of each component scanning and detection process is completed, if the detection result indicates that the corresponding component feature detection is qualified, the next component scanning and detection process is executed; if the detection result indicates that the corresponding component feature detection is unqualified, the execution of the component scanning and detection process is stopped and an abnormal result is output.

[0106] In one possible implementation, the scanning detection module 402 includes: The first scanning detection unit is used to execute the benchmark scanning detection process according to the benchmark execution order. If the detection result indicates that the corresponding benchmark feature detection is qualified after the completion of each benchmark scanning detection process, the next benchmark scanning detection process is executed; if the detection result indicates that the corresponding benchmark feature detection is unqualified, the benchmark scanning detection process is stopped and an abnormal result is output.

[0107] The second scanning detection unit is used to execute the scanning detection process according to the order of the tests if all reference features are qualified. Specifically, if the detection result indicates that the corresponding feature is qualified after the completion of each scanning detection process, the next scanning detection process is executed; if the detection result indicates that the corresponding feature is unqualified, the scanning detection process is stopped and an abnormal result is output.

[0108] In one possible implementation, the second scanning detection unit includes: The alignment subunit is used to align and match the datum feature scanning information of multiple datum features obtained by scanning with the datum template if all datum features pass the detection.

[0109] The matching subunit is used to execute the scanning detection process according to the order of execution to be tested if the reference feature scanning information matches the reference template successfully.

[0110] The output sub-unit is used to stop the component scanning and inspection process and output abnormal results if the reference feature scanning information fails to match the reference template.

[0111] In one possible implementation, the object detection device further includes: The adjustment module is used to receive component feature adjustment instructions and adjust the component scanning and detection process based on the component feature adjustment instructions; the component feature adjustment instructions include adding component features, deleting component features, and adjusting the component execution order.

[0112] In one possible implementation, the object detection device further includes: The frame scanning unit is used to perform frame scanning on the target object to obtain frame point information; and to determine component features based on the frame point information.

[0113] In one possible implementation, the object detection device further includes: The graphical module is used to present a graphical interface; it generates the component execution order of the component scanning and detection process based on the user's drag-and-drop commands.

[0114] The object detection device provided in this disclosure can execute the object detection method provided in any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects of executing the method.

[0115] To implement the above embodiments, this disclosure also proposes a computer program product, including a computer program / instructions, which, when executed by a processor, implements the object detection method in the above embodiments.

[0116] Figure 5 This is a schematic diagram of the structure of a computing device provided in an embodiment of the present disclosure.

[0117] The following is a detailed reference. Figure 5 The diagram illustrates a structural schematic suitable for implementing the computing device 500 in the embodiments of this disclosure. The computing device 500 in the embodiments of this disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The computing device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0118] like Figure 5 As shown, the computing device 500 may include a processor (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 502 or a program loaded from memory 508 into random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of the computing device 500. The processor 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0119] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 508 including, for example, magnetic tapes, hard disks, etc.; and communication devices 509. Communication device 509 allows computing device 500 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 5 A computing device 500 with various devices is shown; however, it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or included alternatively.

[0120] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a memory 508, or installed from a ROM 502. When the computer program is executed by the processor 501, it performs the functions defined in the object detection method of embodiments of this disclosure.

[0121] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0122] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0123] The aforementioned computer-readable medium may be included in the aforementioned computing device; or it may exist independently and not assembled into the computing device.

[0124] The aforementioned computer-readable medium carries one or more programs, which, when executed by the computing device, cause the computing device to perform the aforementioned object detection method.

[0125] The computing device can be programmed with computer program code in one or more programming languages ​​or a combination thereof to perform the operations of this disclosure. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0126] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0127] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units are not, in some cases, intended to limit the specific unit.

[0128] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0129] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0130] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0131] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0132] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. An object detection method, characterized in that, The method includes: Multiple component scanning and detection processes are determined based on the component features of the target object. Each component scanning and detection process includes a scanning process for the component features and a detection process. The component scanning and detection process is executed in the order of component execution. If the detection result indicates that the corresponding component feature detection is qualified after the completion of each component scanning and detection process, the next component scanning and detection process is executed; if the detection result indicates that the corresponding component feature detection is unqualified, the execution of the component scanning and detection process is stopped and an abnormal result is output.

2. The object detection method according to claim 1, characterized in that, The component features include reference features and features to be tested. The component scanning and detection process includes a reference scanning and detection process and a features to be tested scanning and detection process. Executing the component scanning and detection process according to the component execution order includes: The benchmark scanning detection process is executed according to the benchmark execution order. If the detection result indicates that the corresponding benchmark feature detection is qualified after the completion of each benchmark scanning detection process, the next benchmark scanning detection process is executed; if the detection result indicates that the corresponding benchmark feature detection is unqualified, the execution of the benchmark scanning detection process is stopped and an abnormal result is output. If all the benchmark features are qualified, the scan detection process is executed according to the order of the tests. If the detection result indicates that the corresponding feature is qualified, the next scan detection process is executed. If the detection result indicates that the corresponding feature is unqualified, the scan detection process is stopped and an abnormal result is output.

3. The object detection method according to claim 2, characterized in that, If all the benchmark features pass the detection, the scanning detection process is executed according to the order of the tests, including: If all the aforementioned reference features pass the detection, the reference feature scanning information of the multiple reference features obtained by scanning will be aligned and matched with the reference template; If the reference feature scanning information matches the reference template successfully, the scan detection process to be tested is executed according to the order of execution to be tested; If the reference feature scanning information fails to match the reference template, the component scanning and detection process will be stopped and an abnormal result will be output.

4. The object detection method according to claim 1, characterized in that, The method further includes: Receive component feature adjustment instructions and adjust the component scanning and detection process based on the component feature adjustment instructions; the component feature adjustment instructions include adding component features, deleting component features, and adjusting the execution order of the components.

5. The object detection method according to claim 1, characterized in that, Before executing the component scanning and detection process according to the component execution order, the process also includes: The target object is subjected to frame scanning to obtain frame point information; The component features of the target object are determined based on the frame point information.

6. The object detection method according to claim 1, characterized in that, Presents a graphical interface; The component scanning and detection process is dragged and dropped based on the user's drag and drop instructions, generating the component execution order of the component scanning and detection process.

7. An object detection device, characterized in that, The device includes: a sequence determination module, used to determine multiple component scanning and detection processes based on the component features of the target object, wherein each component scanning and detection process includes a scanning process for the component features and a detection process; The scanning and detection module is used to execute the component scanning and detection process according to the execution order of the components. If the detection result indicates that the corresponding component feature detection is qualified after the completion of the detection process of each component scanning and detection process, the next component scanning and detection process is executed; if the detection result indicates that the corresponding component feature detection is unqualified, the execution of the component scanning and detection process is stopped and an abnormal result is output.

8. The object detection device according to claim 7, characterized in that, The scanning detection module includes: The first scanning detection unit is used to execute the benchmark scanning detection process according to the benchmark execution order. If the detection result indicates that the corresponding benchmark feature detection is qualified after the completion of the detection process of each benchmark scanning detection process, the next benchmark scanning detection process is executed; if the detection result indicates that the corresponding benchmark feature detection is unqualified, the execution of the benchmark scanning detection process is stopped and an abnormal result is output. The second scanning detection unit is used to execute the scanning detection process according to the order of the tests if all the reference features are qualified. Specifically, if the detection result indicates that the corresponding feature is qualified after the completion of each scanning detection process, the next scanning detection process is executed; if the detection result indicates that the corresponding feature is unqualified, the scanning detection process is stopped and an abnormal result is output.

9. A computing device, characterized in that, The computing device includes: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the object detection method as described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to perform the object detection method according to any one of claims 1 to 6.

Images