Translational invariance induced by pooling operations is an inherent property of convolutional neural networks, which facilitates numerous computer vision tasks such as classification. Yet to leverage rotational invariant tasks, convolutional architectures require specific rotational invariant layers or extensive data augmentation to learn from diverse rotated versions of a given spatial configuration. Unwrapping the image into its polar coordinates provides a more explicit representation to train a convolutional architecture as the rotational invariance becomes translational, hence the visually distinct but otherwise equivalent rotated versions of a given scene can be learnt from a single image. We show with two common vision-based solar irradiance forecasting challenges (i.e. using ground-taken sky images or satellite images), that this preprocessing step significantly improves prediction results by standardising the scene representation, while decreasing training time by a factor of 4 compared to augmenting data with rotations. In addition, this transformation magnifies the area surrounding the centre of the rotation, leading to more accurate short-term irradiance predictions.
翻译:集中操作引发的翻译差异是进化神经网络的固有属性,它有利于许多计算机视觉任务,如分类等。然而,在利用轮动不定的任务时,进化结构需要特定的旋转变异层或广泛的数据增强,以便从一个特定空间配置的不同旋转版本中学习。将图像包装到极地坐标中可以更清晰地显示对进化结构的训练,因为轮动变异变成翻译,因此从一个图像中可以学习一个特定场景的视觉不同但其他相等的旋转版本。我们展示了两种共同的基于愿景的太阳辐照预测挑战(即使用地面摄取的天空图像或卫星图像),这一预处理步骤通过对场面代表进行标准化,极大地改进了预测结果,同时将培训时间减少4倍,而以旋转方式增加数据。此外,这种转变放大了轮动中心周围的面积,导致更准确的短期辐照预测。