Image analysis and recognition system based on unmanned container

Abstract

The invention provides an image analysis and recognition system based on an unmanned container. The image analysis and recognition system comprises a container image scanning unit, an image data analysis unit, a data association matching unit, a difference parameter verification unit and an image data checking unit. The container image scanning unit comprises a goods inlet image scanning unit and an in-container image scanning unit, and the goods inlet image scanning unit is arranged in the upper portion, the left side and the right side of a channel in a goods inlet of a container, carries out image scanning on goods entering the container and sends scanned data to the image data analysis unit; the in-container image scanning unit is used for carrying out overall image scanning on goods shelves in a container at regular time and feeding back scanning data to the image data analysis unit; the image data analysis unit is internally provided with a commodity image database, image features of commodities to be entered are stored in the image database in advance, and image data are matched after the image data uploaded by the commodity inlet image scanning unit are received.

Description

Technical Field

[0001] The present invention belongs to the field of image recognition, and in particular relates to an image analysis and recognition system based on an unmanned container. Background Art

[0002] With the rapid development of e-commerce and unmanned retail, unmanned cargo containers, as an emerging retail model, have gradually entered people's field of vision. This model uses intelligent cargo container equipment and image analysis and recognition technology to realize automatic identification and transaction of goods, providing a convenient shopping experience. However, the existing unmanned cargo container technology based on image analysis still faces many problems and limitations, which restricts its widespread application and development. First of all, the performance of existing image recognition technology in complex environments is often unsatisfactory. Unmanned cargo containers are usually under various lighting conditions, and the layout inside the container and the way goods are placed may affect the accuracy of image recognition. When faced with lighting changes, product occlusion or cluttered background, existing technologies are prone to recognition errors, resulting in inaccurate recognition of goods and affecting user experience.

[0003] Traditional image recognition systems often rely on a large amount of labeled data for training, which may face the problem of insufficient data in practical applications. Especially for image recognition of specific products, obtaining high-quality labeled data is not only time-consuming and labor-intensive, but may also lead to deviations in model training, affecting the accuracy and reliability of recognition. In addition, existing systems generally lack the ability to quickly adapt to new products. In the operation of unmanned cargo containers, the frequency of product updates is high, and traditional image recognition systems need to retrain the model to adapt to new products, resulting in long response times and low operational efficiency.

[0004] The existing unmanned container system also has hidden dangers in terms of security. Due to the lack of effective identity authentication mechanism and anti-theft monitoring, it is easy for goods to be stolen or taken by mistake, causing economic losses. Many existing systems do not consider the verification of user identity and the integration of anti-theft measures based on image analysis, which reduces the security and credibility of the system.

[0005] The existing image analysis system for unmanned cargo containers also has shortcomings in processing speed. For application scenarios with high real-time requirements, traditional image processing algorithms may not be able to meet the needs of rapid identification and response, thus affecting the user's shopping experience. Especially during peak hours, users have more urgent needs for rapid identification and checkout of goods, and the response speed of traditional systems may not meet market demand.

[0006] Many existing unmanned container systems lack good user interaction design. Users may encounter problems such as inconvenient operation and unclear information during use, resulting in a poor user experience. Such systems lacking humanized design cannot effectively attract consumers' attention and use.

[0007] Therefore, developing an image analysis and recognition system based on unmanned cargo containers to overcome the shortcomings of existing technologies and improve recognition accuracy, response speed and security has become an urgent need in the industry. The new system needs to be able to operate stably in complex environments, quickly adapt to the addition of new products, provide effective identity authentication and anti-theft monitoring measures, and improve user interaction design to enhance consumers' shopping experience. By introducing advanced deep learning and computer vision technologies, combined with efficient algorithms and optimized system architecture, the future unmanned cargo container image analysis and recognition system is expected to achieve a higher level of intelligence and automation, and promote the development of the unmanned retail industry. Summary of the invention

[0008] The present invention proposes an image analysis and recognition system based on unmanned containers. This image analysis and recognition system based on unmanned containers, through its advanced design and functions, represents an important progress in unmanned retail technology towards a more efficient, intelligent and safe direction, creates conditions for providing high-quality retail services, and is expected to significantly improve the operational efficiency of unmanned containers and consumers' shopping experience.

[0009] The technical solution of the present invention is implemented as follows: an image analysis and recognition system based on an unmanned container, comprising a container image scanning unit, an image data analysis unit, a data association matching unit, a difference parameter verification unit and an image data verification unit;

[0010] The container image scanning unit includes an inlet image scanning unit and an in-cabinet image scanning unit. The inlet image scanning unit is arranged in the upper part and the left and right sides of the channel in the inlet of the container, and simultaneously scans the items entering the container and sends the scanned data to the image data analysis unit; the in-cabinet image scanning unit periodically scans the entire shelf in the container and feeds the scanned data back to the image data analysis unit;

[0011] The image data analysis unit has a built-in commodity image database, and the image features of the commodity to be entered are stored in the image database in advance. After receiving the image data uploaded by the image scanning unit at the cargo entrance, the image data is matched. When the match is successful, the commodity enters the container normally. When the match is unsuccessful, the matching data and the image data are synchronously sent to the data association matching unit; when receiving the image uploaded by the image scanning unit in the cabinet, the vacant space in the shelf is identified, the vacant space in the shelf is marked, and the vacant space information is output;

[0012] The data association matching unit calls the image features in the commodity database, and performs secondary analysis on the image features of each commodity, selects at least three feature areas in the image features to establish a feature parameter deformation model, repeatedly verifies the image data that does not match the image scanning unit in the cargo port and the commodity image database, selects the feature areas in the unmatched image data to compare with the feature areas of the corresponding commodities after secondary analysis in the commodity database, and sets a feature overlap threshold for each type of commodity according to the commodity type. When the comparison data exceeds the set threshold, it is determined that the commodity comparison is successful, and the commodity is imported into the container; when the comparison data is lower than the set threshold, it is determined that the commodity comparison fails, and a no-entry signal is sent to the unmanned container, and the commodity is imported into the shelf to be recycled;

[0013] The difference parameter verification unit retrieves the feature parameter deformation model data in the associated matching unit, imports the difference parameters into the feature parameter deformation model, and performs a regular verification on the feature area in the feature parameter deformation model through the imported difference parameters, and after each verification is completed, the verification result together with the verification time is synchronously fed back to the image data verification unit;

[0014] The image data verification unit classifies the verification results of the difference parameter verification unit, records the imported difference parameters and time data for qualified verification results, records the change values ​​of the characteristic parameters for unqualified verification results, feeds back the change values ​​to the user, and provides data reference for the set threshold.

[0015] Compared with existing technologies, this image analysis and recognition system based on unmanned cargo containers has many significant innovations and advantages. The system forms an efficient and complete commodity identification and management system by constructing multiple functional modules, including a cargo container image scanning unit, an image data analysis unit, a data association matching unit, a difference parameter verification unit, and an image data verification unit. Traditional unmanned cargo container systems often lack such a systematic design and usually rely on simple image capture and basic barcode scanning, which cannot achieve comprehensive monitoring and management of commodities.

[0016] The container image scanning unit is set up with an inlet image scanning unit and an in-cabinet image scanning unit. This dual scanning design greatly improves the monitoring accuracy of the system. The inlet scanning ensures that every item entering the container can be identified in real time, while the in-cabinet scanning ensures continuous monitoring of the shelf status. Compared with existing technologies, many systems can only perform a one-time detection after the goods enter, and cannot provide real-time updated information, resulting in inaccurate inventory management.

[0017] The image data analysis unit of the system has a built-in product image database, which can perform matching after receiving the image data uploaded by scanning the image of the purchase port. This active matching mechanism improves the accuracy of product entry and avoids the situation of incorrect storage of mismatched products. Traditional systems generally rely on passive barcode scanning, which cannot fully analyze the appearance characteristics of the product, which can easily lead to misjudgment and erroneous operation. In addition, the data association matching unit enhances the system's ability to recognize product features by secondary analysis of product image features and establishing a feature parameter deformation model. This in-depth analysis not only improves the accuracy of matching, but also enables the system to maintain efficient recognition when the appearance of the product changes slightly, which is relatively lacking in the existing technology. Many traditional devices only rely on raw image data for simple matching and lack sensitivity to changes in image features, resulting in a decrease in recognition rate in dynamic environments.

[0018] The introduction of the difference parameter verification unit is a highlight of the system. By periodically verifying the characteristic parameter deformation model, the system can dynamically monitor changes in product characteristics to ensure the long-term reliability and accuracy of the system. Traditional systems often lack this dynamic verification mechanism, resulting in a decrease in recognition accuracy after long-term operation, affecting overall performance. Fifth, the image data verification unit provides an effective feedback mechanism by classifying the verification results and recording qualified and unqualified verification results. This function not only provides users with accurate data references, but also enhances the transparency and trust of the system. Existing technologies are generally weak in this regard, lacking effective monitoring and feedback mechanisms, which affects the user experience.

[0019] The design of the system fully considers user needs and actual application scenarios. By providing detailed verification results and change values, the system not only helps users understand the status of goods in real time, but also provides a reference for subsequent operations. This kind of humanized design is often lacking in traditional unmanned container systems, which affects user satisfaction and usage experience.

[0020] As a preferred embodiment, the container image scanning unit takes the center point of the channel inside the cargo port of the container as the focus, and the cargo port image scanning unit is installed around the focus in the upper part and the left and right inner walls of the channel inside the cargo port of the container, and the cargo port image scanning unit is a high-definition camera.

[0021] As a preferred embodiment, after the image scanning unit at the purchase port uploads the image data, the image data analysis unit preprocesses the received image, and the preprocessing performs denoising, enhancement and format standardization on the image data, and then retrieves the color, shape and texture information in the image data, and compares it with the features in the built-in product image database, and calculates the similarity between the uploaded image and the product image features in the database through feature point matching.

[0022] As a preferred implementation, the feature parameter deformation model extracts the geometric shape and color features of the feature area before establishment, generates model parameters using an algorithm, builds the feature parameter deformation model based on the model parameters, and sets the feature overlap threshold based on historical data and product characteristic analysis.

[0023] After adopting the above technical solution, the beneficial effect of the present invention is that the image analysis and recognition system based on the unmanned container realizes efficient and accurate commodity identification and management through the collaborative work of multiple modules. The container image scanning unit can scan the commodities entering the container and the shelf conditions in the cabinet in all directions, ensuring real-time monitoring of inventory status and timely updating of data. The image data analysis unit uses the built-in commodity image database for accurate matching to ensure that only commodities that meet the standards can enter the container smoothly, thereby reducing errors and losses. The data association matching unit improves the flexibility and accuracy of commodity identification through secondary analysis and the establishment of a feature parameter deformation model, and can effectively respond to changes in the appearance of commodities. The difference parameter verification unit ensures the stability of the feature parameters through regular verification, further improving the reliability of the system. The image data verification unit classifies and records the verification results and promptly feeds back to the user, so that managers can better grasp the inventory changes and commodity characteristics and optimize the container management process. Overall, the system not only improves the automation level of unmanned containers, but also enhances the accuracy and safety of commodity management, providing strong support for the development of the unmanned retail industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0025] Figure 1 It is a flow chart of the system of the present invention. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] Example:

[0028] like Figure 1As shown, an image analysis and recognition system based on unmanned cargo containers includes a cargo container image scanning unit, an image data analysis unit, a data association matching unit, a difference parameter verification unit and an image data verification unit;

[0029] The container image scanning unit includes an inlet image scanning unit and an in-cabinet image scanning unit. The inlet image scanning unit is arranged in the upper part and the left and right sides of the channel in the inlet of the container, and simultaneously scans the items entering the container and sends the scanned data to the image data analysis unit; the in-cabinet image scanning unit periodically scans the entire shelf in the container and feeds the scanned data back to the image data analysis unit;

[0030] The image data analysis unit has a built-in commodity image database, and the image features of the commodity to be entered are stored in the image database in advance. After receiving the image data uploaded by the image scanning unit at the cargo entrance, the image data is matched. When the match is successful, the commodity enters the container normally. When the match is unsuccessful, the matching data and the image data are synchronously sent to the data association matching unit; when receiving the image uploaded by the image scanning unit in the cabinet, the vacant space in the shelf is identified, the vacant space in the shelf is marked, and the vacant space information is output;

[0031] The data association matching unit calls the image features in the commodity database, and performs secondary analysis on the image features of each commodity, selects at least three feature areas in the image features to establish a feature parameter deformation model, repeatedly verifies the image data that does not match the image scanning unit in the cargo port and the commodity image database, selects the feature areas in the unmatched image data to compare with the feature areas of the corresponding commodities after secondary analysis in the commodity database, and sets a feature overlap threshold for each type of commodity according to the commodity type. When the comparison data exceeds the set threshold, it is determined that the commodity comparison is successful, and the commodity is imported into the container; when the comparison data is lower than the set threshold, it is determined that the commodity comparison fails, and a no-entry signal is sent to the unmanned container, and the commodity is imported into the shelf to be recycled;

[0032] The difference parameter verification unit retrieves the feature parameter deformation model data in the associated matching unit, imports the difference parameters into the feature parameter deformation model, and performs a regular verification on the feature area in the feature parameter deformation model through the imported difference parameters, and after each verification is completed, the verification result together with the verification time is synchronously fed back to the image data verification unit;

[0033] The image data verification unit classifies the verification results of the difference parameter verification unit, records the imported difference parameters and time data for qualified verification results, records the change values ​​of the characteristic parameters for unqualified verification results, feeds back the change values ​​to the user, and provides data reference for the set threshold.

[0034] The working principle of the image analysis and recognition system based on unmanned cargo containers mainly revolves around image scanning, data analysis, matching and verification, so as to realize intelligent commodity identification and management. The container image scanning unit is divided into an inlet image scanning unit and an in-cabinet image scanning unit. The inlet image scanning unit is responsible for real-time scanning of commodities entering the container and sending the acquired image data to the image data analysis unit. The in-cabinet image scanning unit periodically scans the shelf as a whole and feedbacks the status and vacancy information of commodities on the shelf. The image data analysis unit has a built-in commodity image database, which stores the image features of various commodities. After receiving the image data uploaded by the inlet, the system will perform a preliminary match. If the match is successful, the commodity will enter the container normally; if the match fails, the relevant data will be sent to the data association matching unit for further processing. In the data association matching unit, the system performs a secondary analysis on the unmatched commodity images, selects at least three feature areas to establish a feature parameter deformation model, and compares it with the feature areas in the commodity database. Depending on the type of product, the system sets a feature overlap threshold. If the comparison data exceeds the threshold, the comparison is considered successful and the product enters the container; otherwise, the comparison is considered a failure, a no-entry signal is sent, and the product is directed to the shelf for recycling.

[0035] The difference parameter verification unit is responsible for retrieving the feature parameter deformation model data, importing the difference parameters and performing regular verification, and feeding back the verification results and time to the image data verification unit. The image data verification unit classifies these verification results, records qualified and unqualified results, and feeds back the change values ​​of the feature parameters to the user and provides data reference.

[0036] Compared with current technologies, the advantages of this workflow lie in its efficiency and accuracy. Through real-time image scanning and intelligent data analysis, the system can quickly identify goods and dynamically manage them, reduce manual intervention, and improve the efficiency of commodity circulation. At the same time, the introduction of secondary analysis and feature parameter deformation model enhances the system's adaptability to changes in different environments, thereby improving the accuracy of recognition. The difference parameter verification mechanism ensures the continuous optimization of the system, and provides support for subsequent data analysis by continuously recording and feedback of feature changes, forming a virtuous circle. This comprehensive technical application has greatly improved the intelligence level of unmanned cargo containers and provided a more efficient and reliable solution for the retail industry.

[0037] The container image scanning unit takes the center point of the channel in the cargo port of the container as the focus, and the cargo port image scanning unit is installed around the focus in the upper part and the left and right inner walls of the channel in the cargo port of the container. The cargo port image scanning unit is a high-definition camera.

[0038] In the prior art, many image scanning systems of unmanned containers usually use a single camera or a fixed-angle visual system, which results in a limited field of view for image capture when goods enter, which can easily cause some goods to be blocked or inaccurately identified. The inlet image scanning unit of this system is arranged around the center point of the channel in the inlet of the container, and multiple high-definition cameras are installed around the upper part and the inner walls of the left and right sides of the channel. This multi-angle layout design significantly improves the coverage and clarity of image scanning. In this way, the system can capture multi-directional images of goods entering the container in real time, avoiding the recognition blind spots that may be caused by a single perspective, thereby improving the accuracy and efficiency of product recognition. In addition, the use of high-definition cameras ensures image quality, can extract product features more accurately, and further enhances the effect of the recognition algorithm. By optimizing the layout of the scanning unit and improving the image quality, this system overcomes the limitations of the prior art and provides a more comprehensive and efficient product recognition solution.

[0039] After the image scanning unit at the purchase port uploads the image data, the image data analysis unit preprocesses the received image, performs denoising, enhancement and format standardization on the image data, then retrieves the color, shape and texture information in the image data, compares it with the features in the built-in product image database, and calculates the similarity between the uploaded image and the product image features in the database through feature point matching.

[0040] The technology has significant advantages over the prior art in that the preprocessing process performed by the image data analysis unit after the image scanning unit at the cargo port uploads the image data. The prior art usually lacks systematicity and comprehensiveness in the image processing stage, and often only performs basic denoising processing, and fails to effectively enhance and standardize the image in an all-round way, which affects the subsequent feature extraction and matching process, and further affects the accuracy and efficiency of commodity identification. However, this technology ensures that the uploaded image has higher quality and consistency before feature extraction by integrating the preprocessing steps of denoising, enhancement and format standardization, which lays a solid foundation for subsequent analysis. Specifically, denoising can effectively eliminate interference information in the image and improve the clarity of the image; while enhancement processing helps to highlight the key features in the image, making the color, shape and texture information more obvious, thereby improving the accuracy of feature extraction. In addition, format standardization ensures that images from different sources can be processed with a unified standard, reducing matching errors caused by format differences.

[0041] In the feature matching stage, the technology retrieves the color, shape and texture information in the image data and compares it with the features in the built-in product image database. The systematic nature of this process further improves the efficiency and accuracy of product recognition. Existing technologies often rely on only a single feature for matching and lack a comprehensive analysis of multi-dimensional features, resulting in low recognition rates in complex environments. However, this technology can accurately capture the uniqueness of products through the comprehensive use of multi-dimensional features, and can significantly improve recognition accuracy even among similar products. Feature point matching calculates the similarity between the uploaded image and the product image features in the database, providing a scientific basis for subsequent automatic recognition and classification.

[0042] Through comprehensive preprocessing of image data and comprehensive analysis of multi-dimensional features, this technology is superior to existing technologies in terms of accuracy, efficiency and adaptability of commodity identification, and has demonstrated more reliable and efficient characteristics in practical applications. The innovation of this method not only improves the success rate of commodity identification, but also provides more accurate data support for subsequent intelligent management and analysis, and promotes the development and application of related technologies.

[0043] The feature parameter deformation model extracts the geometric shape and color features of the feature area before establishment, generates model parameters using an algorithm, builds the feature parameter deformation model according to the model parameters, and sets the feature overlap threshold based on historical data and product characteristic analysis.

[0044] The method for establishing the feature parameter deformation model has significant innovation and advantages compared to the existing technology. Traditional technologies are often limited to simple geometric shape or color feature extraction in the feature extraction stage, and lack comprehensive analysis of the feature area, resulting in limited adaptability and accuracy of the model in complex environments or feature deformation conditions. However, this technology ensures a comprehensive and in-depth understanding of the product characteristics by first comprehensively extracting the geometric shape and color features of the feature area before establishing the model. This comprehensive extraction method enables the model to more comprehensively reflect the actual characteristics of the product, laying a solid foundation for the subsequent construction of the deformation model.

[0045] In the process of generating model parameters, the technology uses advanced algorithms that can effectively convert the extracted features into model parameters. The intelligence and automation of this process significantly improve the efficiency and accuracy of model construction. In contrast, existing technologies often rely on manual experience or fixed rules to set model parameters, which is prone to the influence of subjective factors and is less efficient when processing complex data. The algorithm-driven technology of this technology can eliminate errors caused by human intervention to a greater extent, making the generation of model parameters more scientific and objective.

[0046] The strategy of setting feature overlap thresholds based on historical data and product characteristics analysis is also a highlight of this technology. Existing technologies usually use fixed thresholds for feature matching, and fail to consider changes in product characteristics and historical data, which may lead to misidentification or missed identification in actual applications. This technology analyzes historical data, combines the characteristics of the product, and dynamically adjusts the feature overlap threshold, so that the model can maintain good adaptability and accuracy in different environments and conditions. This flexible threshold setting method greatly improves the reliability of feature recognition, ensuring that a high recognition rate can be maintained under different products and changing conditions.

[0047] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An image analysis and recognition system based on unmanned cargo containers, characterized in that: It includes a container image scanning unit, an image data analysis unit, a data association matching unit, a difference parameter verification unit and an image data verification unit; The container image scanning unit includes an inlet image scanning unit and an in-cabinet image scanning unit. The inlet image scanning unit is arranged in the upper part and the left and right sides of the channel in the inlet of the container, and simultaneously scans the items entering the container and sends the scanned data to the image data analysis unit; the in-cabinet image scanning unit periodically scans the entire shelf in the container and feeds the scanned data back to the image data analysis unit; The image data analysis unit has a built-in commodity image database, and the image features of the commodity to be entered are stored in the image database in advance. After receiving the image data uploaded by the image scanning unit at the cargo entrance, the image data is matched. When the match is successful, the commodity enters the container normally. When the match is unsuccessful, the matching data and the image data are synchronously sent to the data association matching unit; when receiving the image uploaded by the image scanning unit in the cabinet, the vacant space in the shelf is identified, the vacant space in the shelf is marked, and the vacant space information is output; The data association matching unit calls the image features in the commodity database, and performs secondary analysis on the image features of each commodity, selects at least three feature areas in the image features to establish a feature parameter deformation model, repeatedly verifies the image data that does not match the image scanning unit in the cargo port and the commodity image database, selects the feature areas in the unmatched image data to compare with the feature areas of the corresponding commodities after secondary analysis in the commodity database, and sets a feature overlap threshold for each type of commodity according to the commodity type. When the comparison data exceeds the set threshold, it is determined that the commodity comparison is successful, and the commodity is imported into the container; when the comparison data is lower than the set threshold, it is determined that the commodity comparison fails, and a no-entry signal is sent to the unmanned container, and the commodity is imported into the shelf to be recycled; The difference parameter verification unit retrieves the feature parameter deformation model data in the associated matching unit, imports the difference parameters into the feature parameter deformation model, and performs a regular verification on the feature area in the feature parameter deformation model through the imported difference parameters, and after each verification is completed, the verification result together with the verification time is synchronously fed back to the image data verification unit; The image data verification unit classifies the verification results of the difference parameter verification unit, records the imported difference parameters and time data for qualified verification results, records the change values ​​of the characteristic parameters for unqualified verification results, feeds back the change values ​​to the user, and provides data reference for the set threshold.

2. The image analysis and recognition system based on unmanned cargo containers as claimed in claim 1, characterized in that: The container image scanning unit takes the center point of the channel in the cargo port of the container as the focus, and the cargo port image scanning unit is installed around the focus in the upper part and the left and right inner walls of the channel in the cargo port of the container. The cargo port image scanning unit is a high-definition camera.

3. The image analysis and recognition system based on unmanned cargo containers as claimed in claim 1, characterized in that: After the image scanning unit at the purchase port uploads the image data, the image data analysis unit preprocesses the received image, performs denoising, enhancement and format standardization on the image data, then retrieves the color, shape and texture information in the image data, compares it with the features in the built-in product image database, and calculates the similarity between the uploaded image and the product image features in the database through feature point matching.

4. The image analysis and recognition system based on unmanned cargo containers as claimed in claim 1, characterized in that: The feature parameter deformation model extracts the geometric shape and color features of the feature area before establishment, generates model parameters using an algorithm, builds the feature parameter deformation model according to the model parameters, and sets the feature overlap threshold based on historical data and product characteristic analysis.

Images