VirtualWorlds as Proxy for Multi-object Tracking Analysis
| Autor: | Yohann Cabon, Qiao Wang, Adrien Gaidon, Eleonora Vig |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
050210 logistics & transportation
Cloning (programming) Computer science business.industry Deep learning 05 social sciences Optical flow 02 engineering and technology Machine learning computer.software_genre Metaverse Object detection Computer graphics Data acquisition Video tracking 0502 economics and business 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Artificial intelligence business computer |
| Zdroj: | CVPR |
| DOI: | 10.1109/cvpr.2016.470 |
| Popis: | Modern computer vision algorithms typically require expensive data acquisition and accurate manual labeling. In this work, we instead leverage the recent progress in computer graphics to generate fully labeled, dynamic, and photo-realistic proxy virtual worlds. We propose an efficient real-to-virtual world cloning method, and validate our approach by building and publicly releasing a new video dataset, called "Virtual KITTI" 1, automatically labeled with accurate ground truth for object detection, tracking, scene and instance segmentation, depth, and optical flow. We provide quantitative experimental evidence suggesting that (i) modern deep learning algorithms pre-trained on real data behave similarly in real and virtual worlds, and (ii) pre-training on virtual data improves performance. As the gap between real and virtual worlds is small, virtual worlds enable measuring the impact of various weather and imaging conditions on recognition performance, all other things being equal. We show these factors may affect drastically otherwise high-performing deep models for tracking. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|