Power transmission line dataset

This dataset is composed by both real and sythetic images of power transmission lines, which can be fed to deep neural networks training and applied to line's inspection task. The images are divided into three distinct classes, representing power lines with different geometric properties. The real world acquired images were labeled as circuito_real (real circuit), while the synthetic ones were identified as circuito_simples (simple circuit) or circuito_duplo (double circuit). There are 290 total images for each class, 232 inteded for training and 58 aimed for validation/testing.

本数据集由输电线路的真实图像与合成图像共同组成，可用于深度神经网络（deep neural networks）的训练，并可应用于输电线路巡检任务。数据集图像被划分为三个独立类别，分别对应具有不同几何特性的输电线路。其中，实地采集的真实图像被标注为circuito_real（real circuit，真实线路），合成图像则被标记为circuito_simples（simple circuit，单回线路）或circuito_duplo（double circuit，双回线路）。每个类别总计包含290张图像，其中232张用于训练，剩余58张用于验证与测试。