Depth Completion with Morphological Operations: An Intermediate Approach to Enhance Monocular Depth Estimation

• Raul Mendes USP
• Eduardo Ribeiro USP
• Nícolas Rosa USP
• Valdir Grassi Jr USP

Resumo

In the context of self-driving cars, Convolutional Neural Networks (CNNs) have improved the Single Image Depth Estimation (SIDE) field by predicting maps with accurate depth information for autonomous navigation. However, these networks are generally trained with sparse samples, generated by LIDAR laser scans, and they run at a high computational cost, demanding powerful GPUs. In this paper, we address the SIDE and depth completion tasks jointly, focusing on the design of a lightweight method to be applied in real selfdriving scenarios. We introduce a fast and efficient densification algorithm, based on closing morphology, and we also propose a deep network pipeline that uses the densified reference depth maps for training. When compared to state-of-the-art methods, our network has fewer parameters, higher inference speed and yet comparable accuracy. We conduct a series of experiments in the widely exploited and public available KITTI Depth Benchmark.

Palavras-chave: Estimation, Feature extraction, Training, Task analysis, Cameras, Autonomous automobiles, Sensors