Power distribution network inspection image segmentation method and system based on kapur entropy

• Main Authors: CHEN WEI, ZHU JIRAN, ZHAO MIAO, HUANG ZHIHONG, YI MIN, ZHANG ZHIDAN, PENG SIMIN, DENG WEI, ZHOU HENGYI, MO WENHUI, BANDAI, LI JINLIANG, WANG ZOUJUN, ZHANG DI, LIANG GUANXUAN, YANG MIAO, ZHOU KEHUI, DUAN XUJIN, SONG XINGRONG, TANG HAIGUO, YOU KAI
• Format: Patent
• Language: Chinese; English
• Published: 27.12.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention relates to the technical field of power distribution network inspection, in particular to a power distribution network inspection image segmentation method and system based on kapur entropy, and the method does not need any truth value to extract objects contained in an image. Kapur entropy is used as a target function to determine the fitness of each generation of Hallis eagle population. The Logistic chaotic mapping is utilized to perform chaotic initialization on the feature vectors, so that the diversity of understanding is increased, the image can be effectively preprocessed, and the processing and analysis precision, low error rate and high efficiency of the power distribution network inspection image in the later period are improved. 本发明涉及配电网巡检技术领域，尤其涉及一种基于kapur熵的配电网巡检图像分割方法及系统，该方法不需要任何真值来提取图像中包含的对象。使用了Kapur熵为目标函数，以确定每一代哈里斯鹰种群的适应度。利用Logistic混沌映射对特征向量进行了混沌初始化，增加了解的多样性，能够有效对图像进行预处理，提高后期配电网巡检图像的处理与分析的精度、低误差率和高效性。