2021/07/15 by Chen-Chou Lo, Patrick Vandewalle · 1 citation
Computer Science · Engineering · #Advanced Vision and Imaging #Artificial intelligence #Computer science #Computer vision #Data pre-processing #Deep learning #Geography #Lidar #Monocular #Optical measurement and interference techniques #Pattern recognition (psychology) #Preprocessor #Radar #Radar imaging #Remote sensing #Robotics and Sensor-Based Localization #cs.AI #cs.CV #eess.IV #eess.SP
paper · pdf · doi:10.1109/icip42928.2021.9506550
Accepted to ICIP2021
arxiv created 2021/07/15 · openalex publication_date 2021/07/15 · openalex created_date 2021/08/30 · arxiv updated 2022/03/01 · openalex updated_date 2026/08/05
We integrate sparse radar data into a monocular depth estimation model and introduce a novel preprocessing method for reducing the sparseness and limited field of view provided by radar. We explore the intrinsic error of different radar modalities and show our proposed method results in more data points with reduced error. We further propose a novel method for estimating dense depth maps from monocular 2D images and sparse radar measurements using deep learning based on the deep ordinal regression network by Fu et al. Radar data are integrated by first converting the sparse 2D points to a height-extended 3D measurement and then including it into the network using a late fusion approach. Experiments are conducted on the nuScenes dataset. Our experiments demonstrate state-of-the-art performance in both day and night scenes.