Object recognition method, system and equipment based on multi-recognition algorithm fusion and medium
Through the fusion of multiple recognition algorithms, the image data is recognized using algorithms such as YOLO, Faster R-CNN and SSD, and weights are allocated according to the recognition accuracy and stability, which solves the problem that a single algorithm is difficult to recognize in complex environments, and achieves a more accurate and robust object recognition effect.
Patent Information
- Application Number
- CN202411504724.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-26
- Publication Date
- 2025-03-07
AI Technical Summary
In the prior art, a single object detection algorithm is difficult to achieve an ideal recognition effect in an environment where the characteristics of different objects such as shape, color, texture, etc. are different, and the impact of environmental factors such as lighting, occlusion, and angle makes the recognition effect poor.
The multi-recognition algorithm fusion method is adopted to identify image data through object detection algorithms such as YOLO, Faster R-CNN and SSD, and different weights are assigned according to the recognition accuracy and stability of each algorithm, and the final recognition result is obtained through weighted summing.
It realizes all-round and multi-angle recognition of the products to be tested, improves the accuracy and robustness of object recognition, and provides a more convenient and efficient object recognition solution.
Smart Images
Figure CN119579856A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of computer vision and artificial intelligence technology, and in particular to an object recognition method, system, device and medium based on the fusion of multiple recognition algorithms. Background Art
[0002] Object recognition is one of the important tasks in the field of computer vision and is widely used in many fields such as intelligent manufacturing, intelligent security, and autonomous driving. However, due to the large differences in the shape, color, texture and other features of different objects, as well as the influence of environmental factors such as lighting, occlusion, and angle, a single target detection algorithm often cannot achieve the ideal recognition effect. Therefore, how to combine the advantages of multiple recognition algorithms to improve the accuracy and robustness of object recognition has become a hot topic and difficulty in current research. Summary of the invention
[0003] The object of the present invention is to provide an object recognition method, system, device and medium based on the fusion of multiple recognition algorithms, so as to solve all or one of the above-mentioned problems existing in the prior art.
[0004] In order to solve the above technical problems, the specific technical solutions of the present invention are as follows: In one aspect, the present invention provides an object recognition method based on multi-recognition algorithm fusion, comprising the following steps: Collect image data of the product to be inspected; YOLO, Faster R-CNN and SSD target detection algorithms are used to identify image data and obtain multiple recognition results; According to the recognition accuracy and stability of each target detection algorithm, different weights are assigned to the corresponding recognition results; Multiple recognition results are weighted and summed to obtain the final recognition result.
[0005] In one embodiment, the YOLO, Faster R-CNN and SSD algorithms are trained by deep learning models respectively before application.
[0006] In one embodiment, according to the recognition accuracy and stability of each target detection algorithm, different weights are assigned to the corresponding recognition results, including: The cross-validation method or A / B testing method is used to determine the optimal weight allocation scheme by comparing the recognition effects under different weight combinations.
[0007] In one embodiment, performing weighted summation on the multiple recognition results to obtain the final recognition result includes: The object category probability in each recognition result is multiplied by the corresponding weight, and then all weighted probabilities are summed to obtain the final object category probability distribution.
[0008] In one embodiment, it also includes: After obtaining the final recognition results, the recognition results are screened and filtered according to the preset threshold or confidence requirements.
[0009] In one embodiment, it also includes: Visualize the recognition results, including displaying the recognition results on the image by annotating boxes, category labels, or confidence scores.
[0010] On the other hand, the present invention also provides an object recognition system based on multi-recognition algorithm fusion, comprising: An image acquisition module, used to acquire image data of the product to be inspected; Algorithm recognition module, used to identify image data using YOLO, Faster R-CNN and SSD target detection algorithms; The weight allocation module is used to allocate different weights to the corresponding recognition results according to the recognition accuracy and stability of each target detection algorithm; The result fusion module is used to perform weighted summation on multiple recognition results to obtain the final recognition result; The result processing module is used to screen, filter and visualize the final recognition results.
[0011] In one embodiment, it further includes: a model updating module; The model update module is used to update and optimize the models of YOLO, Faster R-CNN and SSD target detection algorithms regularly or according to actual needs.
[0012] On the other hand, the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the object recognition method based on the fusion of multiple recognition algorithms are implemented.
[0013] On the other hand, the present invention further provides a computer device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; wherein: The memory is used to store computer programs; The processor is used to execute the steps of the object recognition method based on multi-recognition algorithm fusion by running the program stored in the memory.
[0014] The beneficial effects of the technical solution of the present invention are: The object recognition method based on the fusion of multiple recognition algorithms described in the present invention can integrate multiple target detection algorithms, utilize their respective advantages, perform all-round and multi-angle recognition of the product to be detected, and weightedly sum multiple recognition results to obtain a more accurate and reliable final recognition result. It not only realizes the fusion and complementarity of multiple recognition algorithms, and improves the accuracy and robustness of object recognition; it also further optimizes the recognition effect through steps such as weight allocation, result fusion and visualization display, and provides users with a more convenient and efficient object recognition solution. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0016] Figure 1 is a flowchart of the object recognition method based on multi-recognition algorithm fusion described in Example 1 of the present invention; Figure 2 is a schematic diagram of the architecture of an object recognition system based on multi-recognition algorithm fusion according to Embodiment 2 of the present invention; Figure 3 is a schematic diagram of the structure of the computer device described in Example 4 of the present invention; The symbols in the accompanying drawings are explained as follows: 1501, processor; 1502, communication interface; 1503, memory; 1504, communication bus. DETAILED DESCRIPTION
[0017] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings so that the advantages and features of the present invention can be more easily understood by those skilled in the art, thereby making a clearer and more definite definition of the protection scope of the present invention.
[0018] In the description of the present invention, it should be noted that the embodiments described in the present invention are only part of the embodiments of the present invention, rather than all of the embodiments; based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present invention.
[0019] The terms "first", "second", etc. in the specification and claims of this article and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of this article described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, device, product or equipment that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment. Example 1
[0020] This embodiment provides an object recognition method based on the fusion of multiple recognition algorithms. Figure 1 As shown, the following steps are included: In an intelligent manufacturing scenario, the method of the present invention first collects image data of the product to be detected through an image acquisition module. Then, multiple target detection algorithms such as YOLO, Faster R-CNN and SSD are applied to identify the image data. Among them, the YOLO algorithm can quickly locate and identify most objects in the image with its fast and accurate characteristics; the Faster R-CNN algorithm can accurately identify objects in complex backgrounds with its high precision and strong robustness; the SSD algorithm combines the advantages of the first two, which is both fast and accurate.
[0021] Furthermore, different weights are assigned to the corresponding recognition results according to the recognition accuracy and stability of each target detection algorithm. For example, through cross-validation or A / B testing, it is found that the YOLO algorithm performs well in recognition speed, but its recognition accuracy is slightly lower in some complex scenarios, so it is assigned a lower weight; while the Faster R-CNN algorithm performs well in recognition accuracy, but its speed is slower, so it is assigned a higher weight; the SSD algorithm is between the two and is assigned a medium weight.
[0022] Furthermore, multiple recognition results are weighted and summed to obtain the final recognition result. The specific implementation method is: multiply the object category probability in each recognition result by the corresponding weight, and then sum all weighted probabilities to obtain the final object category probability distribution. For example, for a certain product to be detected, the probability that the YOLO algorithm identifies it as "Part A" is 0.7, the probability that the Faster R-CNN algorithm identifies it as "Part A" is 0.9, and the probability that the SSD algorithm identifies it as "Part A" is 0.85. According to the weight distribution, the final recognition result is "Part A" with a high confidence level.
[0023] Furthermore, the recognition results are screened, filtered and visualized. For example, according to the preset threshold or confidence requirements, the recognition results are screened and filtered to remove the recognition results with low confidence; at the same time, the recognition results are intuitively displayed on the image through annotation boxes, category labels or confidence scores, providing accurate and reliable basis for the subsequent intelligent manufacturing process.
[0024] Furthermore, through the above technical scheme, the present invention not only realizes the fusion and complementarity of multiple recognition algorithms, improving the accuracy and robustness of object recognition; it also further optimizes the recognition effect through steps such as weight allocation, result fusion and visualization display, providing users with a more convenient and efficient object recognition solution.
[0025] It should be noted that the examples herein are only for explaining the present invention and are not intended to limit the protection scope of the present invention. Example 2
[0026] This embodiment is based on the same inventive concept as the object recognition method based on the fusion of multiple recognition algorithms described in Embodiment 1, and provides an object recognition system based on the fusion of multiple recognition algorithms, such as Figure 2 As shown, including: An image acquisition module, used to acquire image data of the product to be inspected; Algorithm recognition module, used to identify image data using YOLO, Faster R-CNN and SSD target detection algorithms; The weight allocation module is used to allocate different weights to the corresponding recognition results according to the recognition accuracy and stability of each target detection algorithm; The result fusion module is used to perform weighted summation on multiple recognition results to obtain the final recognition result; The result processing module is used to screen, filter and visualize the final recognition results.
[0027] In one embodiment, it further includes: a model updating module; The model update module is used to update and optimize the models of YOLO, Faster R-CNN and SSD target detection algorithms regularly or according to actual needs. Example 3
[0028] This embodiment provides a computer-readable storage medium, including: The storage medium is used to store computer software instructions used to implement the object recognition method based on the fusion of multiple recognition algorithms described in the above-mentioned embodiment 1, which includes a program for executing the above-mentioned program set for the object recognition method based on the fusion of multiple recognition algorithms; specifically, the executable program can be built into the object recognition system based on the fusion of multiple recognition algorithms described in embodiment 2, so that the object recognition system based on the fusion of multiple recognition algorithms can implement the object recognition method based on the fusion of multiple recognition algorithms described in embodiment 1 by executing the built-in executable program.
[0029] In addition, the computer-readable storage medium of this embodiment may adopt any combination of one or more computer-readable storage media, wherein the computer-readable storage medium includes electrical, optical, electromagnetic, infrared or semiconductor systems, devices or components, or any combination thereof. Example 4
[0030] This embodiment provides an electronic device, such as Figure 3 As shown, the electronic device may include: a processor 1501 , a communication interface 1502 , a memory 1503 and a communication bus 1504 , wherein the processor 1501 , the communication interface 1502 , and the memory 1503 communicate with each other via the communication bus 1504 .
[0031] Memory 1503, used for storing computer programs; The processor 1501 is used to implement the steps of the object recognition method based on the fusion of multiple recognition algorithms described in the above-mentioned embodiment 1 when executing the computer program stored in the memory 1503.
[0032] As an embodiment of the present invention, the communication bus mentioned in the above terminal can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0033] As an implementation mode of the present invention, the communication interface is used for communication between the above-mentioned terminal and other devices.
[0034] As an embodiment of the present invention, the memory may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.
[0035] As an embodiment of the present invention, the above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.
[0036] It should be understood that in the various embodiments of this document, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this document.
[0037] It should also be understood that in the embodiments of this article, the term "and / or" is only a description of the association relationship of the associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.
[0038] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this article.
[0039] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0040] In the several embodiments provided herein, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or can be electrical, mechanical or other forms of connection.
[0041] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of this article.
[0042] In addition, each functional unit in each embodiment of this invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of software functional unit.
[0043] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this article is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of this article. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.
[0044] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.
Claims
1. An object recognition method based on multi-recognition algorithm fusion, characterized in that: The following steps are involved: Collect image data of the product to be inspected; YOLO, Faster R-CNN and SSD target detection algorithms are used to identify image data and obtain multiple recognition results; According to the recognition accuracy and stability of each target detection algorithm, different weights are assigned to the corresponding recognition results; Multiple recognition results are weighted and summed to obtain the final recognition result.
2. The object recognition method based on multi-recognition algorithm fusion according to claim 1, characterized in that: The YOLO, Faster R-CNN and SSD algorithms are trained respectively by deep learning models before application.
3. The object recognition method based on multi-recognition algorithm fusion according to claim 1, characterized in that: According to the recognition accuracy and stability of each target detection algorithm, different weights are assigned to the corresponding recognition results, including: The cross-validation method or A / B testing method is used to determine the optimal weight allocation scheme by comparing the recognition effects under different weight combinations.
4. The object recognition method based on multi-recognition algorithm fusion according to claim 1, characterized in that: The weighted summation of the multiple recognition results to obtain the final recognition result includes: The object category probability in each recognition result is multiplied by the corresponding weight, and then all weighted probabilities are summed to obtain the final object category probability distribution.
5. The object recognition method based on multi-recognition algorithm fusion according to claim 1, characterized in that: Also includes: After obtaining the final recognition results, the recognition results are screened and filtered according to the preset threshold or confidence requirements.
6. The object recognition method based on multi-recognition algorithm fusion according to claim 1, characterized in that: Also includes: Visualize the recognition results, including displaying the recognition results on the image by annotating boxes, category labels, or confidence scores.
7. An object recognition system based on the fusion of multiple recognition algorithms, characterized in that: include: An image acquisition module, used to acquire image data of the product to be inspected; Algorithm recognition module, used to identify image data using YOLO, Faster R-CNN and SSD target detection algorithms; The weight allocation module is used to allocate different weights to the corresponding recognition results according to the recognition accuracy and stability of each target detection algorithm; The result fusion module is used to perform weighted summation on multiple recognition results to obtain the final recognition result; The result processing module is used to screen, filter and visualize the final recognition results.
8. The object recognition system based on multi-recognition algorithm fusion according to claim 7, characterized in that: Also includes: model update module; The model update module is used to update and optimize the models of YOLO, Faster R-CNN and SSD target detection algorithms regularly or according to actual needs.
9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the object recognition method based on the fusion of multiple recognition algorithms described in any one of claims 1 to 6 are implemented.
10. A computer device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; wherein: The memory is used to store computer programs; The processor is used to execute the steps of the object recognition method based on multi-recognition algorithm fusion according to any one of claims 1 to 6 by running the program stored in the memory.