Minimal Kapur cross-entropy-based image segmentation for distribution grid inspection using improved INFO optimization algorithm

Distribution grid network has problems such as long mileage, large scale, complex surrounding environment, and aging of equipment. It is the development trend of power distribution network operation and maintenance to use unmanned aerial vehicles to patrol and combine with image processing technology for intelligent detection of equipment status. Image segmentation is well-known technique for extracting defect regions of equipment from distribution network inspection images. Therefore, this paper proposes an efficient a novel multilevel thresholding segmentation method to improve the fault diagnosis process with an improved weighted mean of vectors optimization (IINFO) algorithm. The IINFO algorithm adopts various measures to improve the optimization results, including Gaussian mutation to increase the local search ability and range of the optimal individual, Cauchy mutation to enhance the global search ability of its vector individual, reflective learning operators to strengthen self-learning and avoid local optimal solutions, and parallel operation to improve the utilization of computational resources. Moreover, two-dimensional Kapur cross-entropy is used as an objective function to solve the multilevel thresholding problem. The proposed method is evaluated using benchmark functions and distribution network inspection image datasets and is compared with 12 other metaheuristic algorithms. The results demonstrate that the proposed method has better performance and a higher ability to find optimal solutions compared to the other algorithms. These findings suggest that our method may be useful in improving the accuracy and efficiency of distribution network inspections and have significant potential for practical applications.