Improving Deep Learning Change Detection in Automotive Radar Maps by Data Augmentation

In this paper, we deal with the task of change detection for environment maps based on automotive radar sensors. As our main contribution, map misalignment common in the real world due to bad positioning is taken into account as part of the prediction. The data augmentation strategies proposed in this paper imparts the knowledge of rotation and translation invariance into the baseline convolutional neural network based siamese architecture, trained with radar maps of highway scenes focusing on construction zones on the road. Using our proposed strategies, our model outperformed the baseline by attaining 18% and 13% higher average F1 scores with respect to rotational and translational misalignments.