Indoor Scene Recognition in 3D
| Autor: | Konrad Schindler, Shengyu Huang, Mikhail Usvyatsov |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Computer science Computer Vision and Pattern Recognition (cs.CV) media_common.quotation_subject Point cloud ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Computer Science - Computer Vision and Pattern Recognition 02 engineering and technology 010501 environmental sciences Semantics computer.software_genre 01 natural sciences Machine Learning (cs.LG) Computer Science - Robotics Voxel Perception 0202 electrical engineering electronic engineering information engineering Segmentation Computer vision 0105 earth and related environmental sciences media_common ComputingMethodologies_COMPUTERGRAPHICS business.industry Object (computer science) Task analysis Robot 020201 artificial intelligence & image processing Artificial intelligence business Robotics (cs.RO) computer |
| Zdroj: | IROS |
| Popis: | Recognising in what type of environment one is located is an important perception task. For instance, for a robot operating in indoors it is helpful to be aware whether it is in a kitchen, a hallway or a bedroom. Existing approaches attempt to classify the scene based on 2D images or 2.5D range images. Here, we study scene recognition from 3D point cloud (or voxel) data, and show that it greatly outperforms methods based on 2D birds-eye views. Moreover, we advocate multi-task learning as a way of improving scene recognition, building on the fact that the scene type is highly correlated with the objects in the scene, and therefore with its semantic segmentation into different object classes. In a series of ablation studies, we show that successful scene recognition is not just the recognition of individual objects unique to some scene type (such as a bathtub), but depends on several different cues, including coarse 3D geometry, colour, and the (implicit) distribution of object categories. Moreover, we demonstrate that surprisingly sparse 3D data is sufficient to classify indoor scenes with good accuracy. IROS 2020 - Camera Ready |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|