Semantic Understanding of Foggy Scenes with Purely Synthetic Data
| Autor: | Christos Sakaridis, Jan-Nico Zaech, Dengxin Dai, Luc Van Gool, Martin Hahner |
|---|---|
| Přispěvatelé: | Hahner, Martin |
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Computer Science - Artificial Intelligence Computer science Computer Vision and Pattern Recognition (cs.CV) adverse weather Computer Science - Computer Vision and Pattern Recognition ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 02 engineering and technology Plan (drawing) Machine learning computer.software_genre Synthetic data computer vision Machine Learning (cs.LG) Computer Science - Robotics autonomous driving 0502 economics and business 0202 electrical engineering electronic engineering information engineering Segmentation 050210 logistics & transportation Artificial neural network business.industry 05 social sciences Training (meteorology) Artificial Intelligence (cs.AI) machine learning 020201 artificial intelligence & image processing Artificial intelligence business computer Robotics (cs.RO) |
| Zdroj: | 2019 IEEE Intelligent Transportation Systems Conference (ITSC) |
| Popis: | This work addresses the problem of semantic scene understanding under foggy road conditions. Although marked progress has been made in semantic scene understanding over the recent years, it is mainly concentrated on clear weather outdoor scenes. Extending semantic segmentation methods to adverse weather conditions like fog is crucially important for outdoor applications such as self-driving cars. In this paper, we propose a novel method, which uses purely synthetic data to improve the performance on unseen real-world foggy scenes captured in the streets of Zurich and its surroundings. Our results highlight the potential and power of photo-realistic synthetic images for training and especially fine-tuning deep neural nets. Our contributions are threefold, 1) we created a purely synthetic, high-quality foggy dataset of 25,000 unique outdoor scenes, that we call Foggy Synscapes and plan to release publicly 2) we show that with this data we outperform previous approaches on real-world foggy test data 3) we show that a combination of our data and previously used data can even further improve the performance on real-world foggy data. 2019 IEEE Intelligent Transportation Systems Conference (ITSC) ISBN:978-1-5386-7024-8 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|