On Support Relations and Semantic Scene Graphs
arXiv:1609.05834 · doi:10.1016/j.isprsjprs.2017.07.010
Abstract
Scene understanding is a popular and challenging topic in both computer vision and photogrammetry. Scene graph provides rich information for such scene understanding. This paper presents a novel approach to infer such relations and then to construct the scene graph. Support relations are estimated by considering important, previously ignored information: the physical stability and the prior support knowledge between object classes. In contrast to previous methods for extracting support relations, the proposed approach generates more accurate results, and does not require a pixel-wise semantic labeling of the scene. The semantic scene graph which describes all the contextual relations within the scene is constructed using this information. To evaluate the accuracy of these graphs, multiple different measures are formulated. The proposed algorithms are evaluated using the NYUv2 database. The results demonstrate that the inferred support relations are more precise than state-of-the-art. The scene graphs are compared against ground truth graphs.
Accepted in ISPRS Journal of Photogrammetry and Remote Sensing
References in corpus (2)
Cited by in corpus (9)
- A Comprehensive Survey of Scene Graphs: Generation and Application
- Pixels to Graphs by Associative Embedding
- Deep Variation-structured Reinforcement Learning for Visual Relationship and Attribute Detection
- The Limited Multi-Label Projection Layer
- Unbiased Scene Graph Generation via Rich and Fair Semantic Extraction
- Learning Object Detection from Captions via Textual Scene Attributes
- Relationship Oriented Affordance Learning through Manipulation Graph Construction
- Zero-Shot Scene Graph Relation Prediction through Commonsense Knowledge Integration
- ELKPPNet: An Edge-aware Neural Network with Large Kernel Pyramid Pooling for Learning Discriminative Features in Semantic Segmentation