Depth Estimation from Monocular Images and Sparse Radar Data
| Autor: | Luc Van Gool, Dengxin Dai, Juan-Ting Lin |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer science Computer Vision and Pattern Recognition (cs.CV) medicine.medical_treatment Computer Science - Computer Vision and Pattern Recognition ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 010501 environmental sciences 01 natural sciences law.invention law Component (UML) Radar imaging 0502 economics and business medicine Computer vision 050207 economics Radar 0105 earth and related environmental sciences Monocular business.industry 05 social sciences Ablation Lidar RGB color model Artificial intelligence Noise (video) business |
| Zdroj: | IROS 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) |
| DOI: | 10.1109/iros45743.2020.9340998 |
| Popis: | In this paper, we explore the possibility of achieving a more accurate depth estimation by fusing monocular images and Radar points using a deep neural network. We give a comprehensive study of the fusion between RGB images and Radar measurements from different aspects and proposed a working solution based on the observations. We find that the noise existing in Radar measurements is one of the main key reasons that prevents one from applying the existing fusion methods developed for LiDAR data and images to the new fusion problem between Radar data and images. The experiments are conducted on the nuScenes dataset, which is one of the first datasets which features Camera, Radar, and LiDAR recordings in diverse scenes and weather conditions. Extensive experiments demonstrate that our method outperforms existing fusion methods. We also provide detailed ablation studies to show the effectiveness of each component in our method. © 2020 IEEE. 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|