Knowledge Graphs Meet Geometry for Semi-supervised Monocular Depth Estimation
Autor: | Mengyuan Wang, Shuliang Wang, Fusheng Jin, Yu Zhao |
---|---|
Rok vydání: | 2020 |
Předmět: |
0209 industrial biotechnology
Monocular Artificial neural network business.industry Computer science Supervised learning 02 engineering and technology Machine learning computer.software_genre Object detection 020901 industrial engineering & automation Knowledge graph 0202 electrical engineering electronic engineering information engineering Unsupervised learning Semantic memory 020201 artificial intelligence & image processing Segmentation Artificial intelligence business computer |
Zdroj: | Knowledge Science, Engineering and Management ISBN: 9783030551292 KSEM (1) |
Popis: | Depth estimation from a single image plays an important role in computer vision. Using semantic information for depth estimation becomes a research hotspot. The traditional neural network-based semantic method only divides the image according to the features, and cannot understand the deep background knowledge about the real world. In recent years, the knowledge graph is proposed and used for model semantic knowledge. In this paper, we enhance the traditional depth prediction method by analyzing the semantic information of the image through the knowledge graph. Background knowledge from the knowledge graph is used to enhance the results of semantic segmentation, and further improve the depth estimation results. We conducted experiments on the KITTI driving dataset, and the results showed that our method outperformed the previous unsupervised learning methods and supervised learning methods. The result of the Apollo dataset demonstrates that our method can perform in the common case. |
Databáze: | OpenAIRE |
Externí odkaz: |