SRNet: A 3D Scene Recognition Network using Static Graph and Dense Semantic Fusion

dc.contributor.authorFan, Zhaoxinen_US
dc.contributor.authorLiu, Hongyanen_US
dc.contributor.authorHe, Junen_US
dc.contributor.authorSun, Qien_US
dc.contributor.authorDu, Xiaoyongen_US
dc.contributor.editorEisemann, Elmar and Jacobson, Alec and Zhang, Fang-Lueen_US
dc.date.accessioned2020-10-29T18:50:55Z
dc.date.available2020-10-29T18:50:55Z
dc.date.issued2020
dc.description.abstractPoint cloud based 3D scene recognition is fundamental to many real world applications such as Simultaneous Localization and Mapping (SLAM). However, most of existing methods do not take full advantage of the contextual semantic features of scenes. And their recognition abilities are severely affected by dynamic noise such as points of cars and pedestrians in the scene. To tackle these issues, we propose a new Scene Recognition Network, namely SRNet. In this model, to learn local features without being affected by dynamic noise, we propose Static Graph Convolution (SGC) module, which are then stacked as our backbone. Next, to further avoid dynamic noise, we introduce a Spatial Attention Module (SAM) to make the feature descriptor pay more attention to immovable local areas that are more relevant to our task. Finally, in order to make a more profound sense of the scene, we design a Dense Semantic Fusion (DSF) strategy to integrate multi-level features during feature propagation, which helps the model deepen its understanding of the contextual semantics of scenes. By utilizing these designs, SRNet can map scenes to discriminative and generalizable feature vectors, which are then used for finding matching pairs. Experimental studies demonstrate that SRNet achieves new state-of-the-art on scene recognition and shows good generalization ability to other point cloud based tasks.en_US
dc.description.number7
dc.description.sectionheadersRecognition
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume39
dc.identifier.doi10.1111/cgf.14146
dc.identifier.issn1467-8659
dc.identifier.pages301-311
dc.identifier.urihttps://doi.org/10.1111/cgf.14146
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14146
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectComputing methodologies
dc.subjectScene understanding
dc.subjectPoint
dc.subjectbased models
dc.titleSRNet: A 3D Scene Recognition Network using Static Graph and Dense Semantic Fusionen_US
Files
Collections