An industrial robot image processing method based on image fusion

Abstract

The present invention discloses an industrial robot image processing method based on image fusion, which relates to the field of image processing technology, including collecting image data of the industrial robot during operation through a multimodal sensor and performing preprocessing; constructing an adaptive image fusion algorithm for image fusion, and enhancing and optimizing the fused image through a deep learning algorithm; evaluating the optimization effect of the fused image and implementing processing measures according to the evaluation results. The beneficial effects of the present invention are as follows: the present invention collects image data of the industrial robot during operation for image fusion processing, optimizes the fused image in combination with deep learning technology, and performs optimized image evaluation to form a final image processing result output, thereby enabling the industrial robot to achieve better image processing and improve the image processing quality. At the same time, the energy efficiency of the industrial robot is optimized on the premise of ensuring the image processing quality, effectively saving energy and reducing the energy consumption of image processing.

Description

Technical Field

[0001] The invention relates to the technical field of image processing, and in particular to an industrial robot image processing method based on image fusion. Background Art

[0002] In recent years, the rapid development of industrial automation and intelligent manufacturing has put forward higher requirements on the performance of industrial robots, especially in image processing and visual systems. Image fusion technology, as one of the key technologies to improve the performance of industrial robot visual systems, has become a hot topic of research. This technology generates a more accurate and detailed visual representation by integrating image data collected by multiple sensors, thereby enhancing the robot's recognition, positioning and decision-making capabilities. With the improvement of computing power and the advancement of algorithms, deep learning technologies including convolutional neural networks (CNN) and generative adversarial networks (GAN) have been widely used in the image fusion process, further improving the quality and application effect of fused images. In addition, with the development of the Industrial Internet of Things (IoT), a large amount of image data needs to be effectively processed and securely stored, which poses new challenges and requirements for image processing methods. Existing technologies lack sufficient adaptive capabilities in the field of industrial robot image processing, and it is difficult to dynamically adjust the fusion strategy for different working environments and task requirements. The energy efficiency and feasibility in actual industrial applications are challenged. Summary of the invention

[0003] In view of the problems existing in the above-mentioned existing industrial robot image processing method based on image fusion, the present invention is proposed.

[0004] Therefore, the problem to be solved by the present invention is that the existing technology lacks sufficient adaptive capabilities in the field of industrial robot image processing, and it is difficult to dynamically adjust the fusion strategy according to different working environments and task requirements, and the energy efficiency and feasibility in actual industrial applications are challenged.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: an industrial robot image processing method based on image fusion, which includes collecting image data of the industrial robot during operation through a multimodal sensor and performing preprocessing; constructing an adaptive image fusion algorithm for image fusion, and enhancing and optimizing the fused image through a deep learning algorithm; evaluating the optimization effect of the fused image and implementing processing measures based on the evaluation results; optimizing the energy efficiency of industrial robot image processing; storing the data and implementing security protection.

[0006] As a preferred solution of the industrial robot image processing method based on image fusion described in the present invention, wherein: the collection of image data during the operation of the industrial robot by multimodal sensors and preprocessing refers to installing infrared sensors, laser sensors, visual cameras and GPS positioning devices on the industrial robot to collect multimodal image data during the operation of the industrial robot, and cleaning and filtering the collected data and converting it into a unified format.

[0007] As a preferred solution of the industrial robot image processing method based on image fusion described in the present invention, wherein: the construction of an adaptive image fusion algorithm for image fusion refers to constructing an adaptive image fusion algorithm to perform image fusion on the collected image data:

[0008]

[0009] β i =γ*T i +δ

[0010] Where G is the fused image, I i is the i-th collected image data, n is the type of collected image data, α i is the weight based on image clarity, S i For image I i The clarity score, μ S is the average value of all image clarity scores, σ S is the standard deviation of all image sharpness scores, β i is the information enhancement index, T i For image I i The texture complexity score of is, and γ and δ are adjustment parameters.

[0011] As a preferred solution of the industrial robot image processing method based on image fusion described in the present invention, wherein: the enhancement and optimization of the fused image by the deep learning algorithm refers to inputting the fused image into the deep learning algorithm for image enhancement and optimization after image fusion:

[0012]

[0013] Where R is the optimized fused image, N is the total number of fused images, λ is the enhancement coefficient, tanh is the hyperbolic tangent function, and F j (I i ) is the feature extractor, ω j is the weight of the jth feature extractor, M is the number of feature extractors, P*Q is the image size, I i (p, q) is the image I i The pixel value at position (p, q), τ is the standard deviation of the Gaussian blur.

[0014] As a preferred solution of the industrial robot image processing method based on image fusion described in the present invention, wherein: the implementation of processing measures according to the evaluation results refers to constructing a comprehensive evaluation model to obtain the optimized image evaluation result E and then compare it with the judgment threshold E1:

[0015] If E>E1, it means that the image quality of the optimized image R is improved compared with the image G before optimization. The optimized image R is bound to the evaluation result and output as the final image processing result of the industrial robot. The image fusion algorithm and deep learning algorithm are regularly tested to generate regular test reports and sent to the staff for manual review and confirmation.

[0016] If E≤E1, it means that the image quality of the optimized image R has not been comprehensively improved compared with the image G before optimization. The industrial robot collects image data again through the multimodal sensor for pre-processing and performs image fusion steps and fused image optimization steps, and performs image optimization evaluation after optimization. If the evaluation result is still E≤E1, the image fusion algorithm and the deep learning algorithm are deeply tested, and the image fusion and image optimization tests are repeated after adjusting the weight coefficients until E>E1. After the algorithm adjustment is completed, the industrial robot collects data again for image fusion optimization and outputs it as the final image processing result.

[0017] As a preferred solution of the industrial robot image processing method based on image fusion described in the present invention, wherein: the said optimization of the industrial robot image processing energy efficiency refers to optimizing the industrial robot image processing energy efficiency after image fusion and image optimization while ensuring image quality:

[0018] First calculate the PSNR indicator:

[0019]

[0020] Where MSE is the mean square error, A and B are the number of rows and columns of image pixels, G(i, j) and R(i, j) are the pixel values ​​of the image before and after optimization at position (i, j), MAX is I is the maximum pixel value of the image;

[0021] Combine PSNR to optimize the energy efficiency of industrial robots:

[0022]

[0023] Where K is the energy efficiency of the industrial robot, ε is the weight coefficient of image quality, P is the average power consumption of the industrial robot in the image processing process, θ is the weight coefficient of energy consumption, and t is the time to complete the image processing task. The calculation is performed iteratively, and the weight coefficient is adjusted to minimize K. All contents are output and executed as the industrial robot energy consumption optimization strategy.

[0024] As a preferred solution of the industrial robot image processing method based on image fusion described in the present invention, wherein: the data storage and security protection implementation refers to storing the collected image data, fused images, optimized fused images, optimized fused image evaluation results and processing measures, and industrial robot energy consumption optimization strategies in a database and setting access rights and access passwords for data protection, while monitoring and recording the entire data access process, and scanning the data after the data access is completed to generate a data statistical log for synchronous storage.

[0025] A computer device comprises: a memory and a processor; the memory stores a computer program, wherein the processor implements the steps of the above-mentioned industrial robot image processing method based on image fusion when executing the computer program.

[0026] A computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of the industrial robot image processing method based on image fusion.

[0027] The beneficial effects of the present invention are as follows: the present invention collects image data during the operation of the industrial robot to perform image fusion processing, optimizes the fused image with deep learning technology, and performs optimized image evaluation to form a final image processing result output, thereby enabling the industrial robot to achieve better image processing and improve the image processing quality. At the same time, the energy efficiency of the industrial robot is optimized while ensuring the image processing quality, thereby effectively saving energy and reducing image processing energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0029] Figure 1 Schematic diagram of the flow of industrial robot image processing method based on image fusion.

[0030] Figure 2 Schematic diagram of image processing for industrial robot image processing method based on image fusion. DETAILED DESCRIPTION

[0031] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0032] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0033] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0034] Example 1

[0035] Reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and this embodiment provides an industrial robot image processing method based on image fusion. The industrial robot image processing method based on image fusion includes the following steps:

[0036] S1, collect image data of industrial robots during operation through multimodal sensors and perform preprocessing;

[0037] Specifically, collecting image data of an industrial robot during operation through a multimodal sensor and preprocessing the data means installing an infrared sensor, a laser sensor, a visual camera, and a GPS positioning device on the industrial robot to collect multimodal image data during the operation of the industrial robot, and cleaning and filtering the collected data and converting it into a unified format.

[0038] By integrating multiple sensors on industrial robots, information about the surrounding environment can be collected from different dimensions during operation. This multi-dimensional information acquisition method is more comprehensive than a single-modal sensor and can provide richer environmental data. Infrared sensors can provide effective image information at night or under low-light conditions, while laser sensors can accurately measure the distance and shape of objects in complex backgrounds. The combined use of this information greatly improves the adaptability and operational accuracy of industrial robots in complex environments. The collected multimodal data requires a series of preprocessing steps before use, including cleaning, filtering, and conversion to a unified format. The cleaning and filtering steps remove noise and irrelevant information to ensure that the data used for subsequent processing is accurate and reliable. Conversion to a unified format refers to converting data collected by different sensors into a standardized data format. This step is crucial for subsequent data fusion and analysis. Through these preprocessing steps, it can be ensured that the data from different sensors can be effectively integrated and used, improving the efficiency of data processing and the quality of image processing.

[0039] S2, construct an adaptive image fusion algorithm to perform image fusion, and enhance and optimize the fused image through a deep learning algorithm;

[0040] Specifically, constructing an adaptive image fusion algorithm to perform image fusion refers to constructing an adaptive image fusion algorithm to perform image fusion on the collected image data:

[0041]

[0042] β i =γ*T i +δ

[0043] Where G is the fused image, I i is the i-th collected image data, n is the type of collected image data, α i is the weight based on image clarity, which is used to adjust the contribution of the image in the fusion process. i For image I i The clarity score can be obtained through the edge detection algorithm, μ S is the average value of all image clarity scores, σ S is the standard deviation of all image clarity scores, used for normalization weight calculation, β i is the information enhancement index, which is adaptively adjusted according to the image texture complexity to enhance the detail information in the image. i For image I i The texture complexity score is obtained through the texture analysis algorithm. γ and δ are adjustment parameters used to control the degree of information enhancement.

[0044] By considering the clarity score of each image, the algorithm is able to adaptively assign weights to each input image, which means that images with higher clarity will have a greater impact in the fusion process, thus ensuring that the fused image has higher overall clarity. This is especially important for industrial robots to perform precision tasks such as component assembly or quality inspection, because clear visual information directly affects the accuracy and efficiency of operations. Through the texture complexity score and information enhancement index, the algorithm is able to identify and emphasize the detailed information in the image. In industrial applications, this helps to improve the robot's ability to recognize the surface texture of objects, especially when performing material classification, defect detection or complex component identification. The introduction of adjustment parameters provides further flexibility for the algorithm, allowing the algorithm to adjust the degree of information enhancement according to the needs of specific application scenarios, which means that the algorithm can be optimized according to the specific requirements of the task or the specific characteristics of the image to provide the best visual results.

[0045] Furthermore, enhancing and optimizing the fused image through a deep learning algorithm means that after image fusion, the fused image is input into a deep learning algorithm for image enhancement optimization:

[0046]

[0047] Where R is the optimized fused image, N is the total number of fused images, λ is the enhancement coefficient, tanh is the hyperbolic tangent function used to introduce nonlinear enhancement effect, and F j (I i ) is the feature extractor, ω j is the weight of the jth feature extractor, M is the number of feature extractors, P*Q is the image size, I i (p, q) is the image I i The pixel value at position (p, q), τ is the standard deviation of controlling Gaussian blur, which is used to simulate the local perception ability in the feature extraction process.

[0048] By enhancing and optimizing the fused image through deep learning algorithms, the clarity, contrast and detail of the image can be significantly improved, which is crucial for industrial robots to perform fine operations such as component recognition, assembly and quality inspection. The feature extractor in the deep learning model can automatically identify key features and patterns in the image without the need for manual design or predefined features. This not only improves the efficiency of image processing, but also improves the accuracy of recognition and analysis. By adjusting the enhancement coefficient and hyperbolic tangent function, the intensity and range of the enhancement effect can be flexibly controlled to adapt to different application scenarios and needs. This adjustability makes the image enhancement process more flexible and efficient. By applying Gaussian blur, the local perception ability in the feature extraction process is simulated, which helps to balance the retention of image details and the suppression of noise. This balance is very important for improving the overall visual quality of the image.

[0049] S3, evaluate the optimization effect of the fused image and implement treatment measures based on the evaluation results;

[0050] Furthermore, implementing treatment measures according to the evaluation results refers to constructing a comprehensive evaluation model to obtain the optimized image evaluation result E and then comparing it with the judgment threshold E1:

[0051] If E>E1, it means that the image quality of the optimized image R is improved compared with the image G before optimization. The optimized image R is bound to the evaluation result and output as the final image processing result of the industrial robot. The image fusion algorithm and deep learning algorithm are regularly tested to generate regular test reports and sent to the staff for manual review and confirmation.

[0052] If E≤E1, it means that the image quality of the optimized image R has not been comprehensively improved compared with the image G before optimization. The industrial robot collects image data again through the multimodal sensor for pre-processing and performs image fusion steps and fused image optimization steps, and performs image optimization evaluation after optimization. If the evaluation result is still E≤E1, the image fusion algorithm and the deep learning algorithm are deeply tested, and the image fusion and image optimization tests are repeated after adjusting the weight coefficients until E>E1. After the algorithm adjustment is completed, the industrial robot collects data again for image fusion optimization and outputs it as the final image processing result.

[0053] Through the application of comprehensive evaluation models and judgment thresholds, it can be ensured that the quality of the optimized image meets or exceeds the preset standards. This is crucial for industrial robots to perform precise tasks such as component identification and quality inspection. If the quality of the optimized image does not meet expectations, the process allows the image data to be re-collected and optimized until the quality requirements are met. This adaptive adjustment mechanism increases the flexibility and robustness of the image processing process. Through regular inspections and manual reviews, potential problems with image fusion algorithms and deep learning algorithms can be discovered in a timely manner, and corresponding adjustments and optimizations can be made, which helps to continuously improve the performance of the algorithm and ensure its effective application in the long term. Regular inspection reports and algorithm adjustments provide a basis for continuously improving the quality of image processing. By continuously optimizing algorithm parameters and processing processes, it can adapt to different working environments and task requirements and improve the performance of the visual system of industrial robots.

[0054] S4. Optimize the energy efficiency of industrial robot image processing;

[0055] Specifically, optimizing the image processing energy efficiency of industrial robots means optimizing the image processing energy efficiency of industrial robots after image fusion and image optimization while ensuring image quality:

[0056] First calculate the PSNR indicator:

[0057]

[0058] Where MSE is the mean square error, A and B are the number of rows and columns of image pixels, G(i, j) and R(i, j) are the pixel values ​​of the image before and after optimization at position (i, j), MAX is I For an 8-bit image, MAX is the maximum pixel value of the image. I =255, PSNR is an indicator to measure the quality of image reconstruction, and a high value indicates high quality;

[0059] Combine PSNR to optimize the energy efficiency of industrial robots:

[0060]

[0061] Where K is the energy efficiency of the industrial robot, ε is the weight coefficient of image quality, P is the average power consumption of the industrial robot in the image processing process, θ is the weight coefficient of energy consumption, and t is the time to complete the image processing task. The calculation is performed iteratively, and the weight coefficient is adjusted to minimize K. All contents are output and executed as the industrial robot energy consumption optimization strategy.

[0062] By calculating the PSNR indicator and combining it with the energy efficiency optimization model, the energy efficiency of industrial robots can be significantly improved without sacrificing image quality. This balance is crucial to finding the best compromise between energy costs and operational efficiency. By iterative calculation and adjustment of weight coefficients, the image processing algorithm can be continuously optimized to achieve higher energy efficiency, which not only helps to reduce the operating costs of industrial robots, but also helps to reduce the impact on the environment. Taking energy efficiency optimization as part of the energy consumption optimization strategy for industrial robots can provide an energy-saving and emission reduction solution for industrial automation systems. This strategy helps companies build a more sustainable production process. Optimizing image processing energy efficiency not only reduces energy consumption, but also improves the overall performance of the robot processor by reducing the computational burden on it, which enables the robot to perform other tasks more effectively and improve production efficiency.

[0063] S5. Store the data and implement security protection;

[0064] Specifically, storing data and implementing security protection means storing the collected image data, fused images, optimized fused images, optimized fused image evaluation results and processing measures, and industrial robot energy consumption optimization strategies in a database and setting access permissions and access passwords for data protection. At the same time, the data access process is monitored and recorded throughout the entire process, and after the data access is completed, the data is scanned to generate a data statistical log for synchronous storage.

[0065] By implementing the above measures, sensitive image data and processing results in industrial robot systems can be effectively protected, data leakage and unauthorized access can be prevented, data security and privacy can be ensured, and all relevant data can be systematically stored and managed, which helps to improve the efficiency of data retrieval and use. Access rights and password settings can also ensure orderly access to data, avoid data conflicts and incorrect use. By monitoring the data access process and scanning after completion, the integrity and reliability of the data can be effectively maintained, data tampering and damage can be prevented, and the accuracy of image processing and energy optimization strategies can be guaranteed. The generated monitoring records and statistical logs provide support for compliance with data protection regulations, and also provide a reliable data basis for internal audits and security analysis, which helps to promptly discover and resolve security risks.

[0066] Example 2

[0067] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for 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 methods described in each embodiment of the present invention. 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, etc., which can store program codes.

[0068] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0069] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0070] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0071] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An industrial robot image processing method based on image fusion, characterized in that: include, Collect and pre-process image data of industrial robots during operation through multimodal sensors; Construct an adaptive image fusion algorithm to perform image fusion, and enhance and optimize the fused image through a deep learning algorithm; Evaluate the optimization effect of fused images and implement processing measures based on the evaluation results; Optimizing the energy efficiency of industrial robot image processing; Store and securely protect data; The collecting and preprocessing of the image data of the industrial robot during operation by multimodal sensors refers to installing infrared sensors, laser sensors, visual cameras and GPS positioning devices on the industrial robot to collect multimodal image data during the operation of the industrial robot, and cleaning and filtering the collected data and converting them into a unified format; The constructing of an adaptive image fusion algorithm to perform image fusion refers to constructing an adaptive image fusion algorithm to perform image fusion on the collected image data: b i =γ*T i +d Where G is the fused image, I i is the i-th collected image data, n is the type of collected image data, α i is the weight based on image clarity, S i For image I i The clarity score, μ S is the average value of all image clarity scores, σ S is the standard deviation of all image sharpness scores, β i is the information enhancement index, T i For image I i The texture complexity score of , γ and δ are adjustment parameters; The enhancement and optimization of the fused image by the deep learning algorithm refers to inputting the fused image into the deep learning algorithm for image enhancement and optimization after image fusion: Where R is the optimized fused image, N is the total number of fused images, λ is the enhancement coefficient, tanh is the hyperbolic tangent function, and F j (I i ) is the feature extractor, ω j is the weight of the jth feature extractor, M is the number of feature extractors, P*Q is the image size, I i (p, q) is the image I i The pixel value at position (p, q), τ is the standard deviation of the Gaussian blur; The implementation of treatment measures according to the evaluation results refers to constructing a comprehensive evaluation model to obtain the optimized image evaluation result E and then comparing it with the judgment threshold E1: If E>E1, it means that the image quality of the optimized image R is improved compared with the image G before optimization. The optimized image R is bound to the evaluation result and output as the final image processing result of the industrial robot. The image fusion algorithm and deep learning algorithm are regularly tested to generate regular test reports and sent to the staff for manual review and confirmation. If E≤E1, it means that the image quality of the optimized image R has not been comprehensively improved compared with the image G before optimization. The industrial robot re-collects image data through the multimodal sensor for pre-processing and performs image fusion steps and fused image optimization steps, and performs image optimization evaluation after optimization. If the evaluation result is still E≤E1, the image fusion algorithm and the deep learning algorithm are deeply tested, and the image fusion and image optimization tests are repeated after adjusting the weight coefficients until E>E1. After the algorithm adjustment is completed, the industrial robot re-collects data for image fusion optimization and outputs it as the final image processing result; Optimizing the image processing energy efficiency of industrial robots refers to optimizing the image processing energy efficiency of industrial robots after image fusion and image optimization, while ensuring image quality: First calculate the PSNR indicator: Where MSE is the mean square error, A and B are the number of rows and columns of image pixels, G(i, j) and R(i, j) are the pixel values ​​of the image before and after optimization at position (i, j), MAX is I is the maximum pixel value of the image; Combine PSNR to optimize the energy efficiency of industrial robots: Where K is the energy efficiency of the industrial robot, ε is the weight coefficient of image quality, P is the average power consumption of the industrial robot in the image processing process, θ is the weight coefficient of energy consumption, and t is the time to complete the image processing task. The calculation is performed iteratively, and the weight coefficient is adjusted to minimize K. All contents are output and executed as the industrial robot energy consumption optimization strategy.

2. The industrial robot image processing method based on image fusion according to claim 1, characterized in that: The data storage and security protection mentioned above refers to storing the collected image data, fused images, optimized fused images, optimized fused image evaluation results and processing measures, and industrial robot energy consumption optimization strategies in a database and setting access permissions and access passwords for data protection. At the same time, the data access process is monitored and recorded throughout, and after the data access is completed, the data is scanned to generate a data statistical log for synchronous storage.

3. A computer device comprising: Memory and processor; The memory stores a computer program, wherein the processor implements the steps of the method according to any one of claims 1 and 2 when executing the computer program.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 and 2 are implemented.

Images