Redirigiendo al acceso original de articulo en 23 segundos...
ARTÍCULO
TITULO

IAGC: Interactive Attention Graph Convolution Network for Semantic Segmentation of Point Clouds in Building Indoor Environment

Ruoming Zhai    
Jingui Zou    
Yifeng He and Liyuan Meng    

Resumen

Point-based networks have been widely used in the semantic segmentation of point clouds owing to the powerful 3D convolution neural network (CNN) baseline. Most of the current methods resort to intermediate regular representations for reorganizing the structure of point clouds for 3D CNN networks, but they may neglect the inherent contextual information. In our work, we focus on capturing discriminative features with the interactive attention mechanism and propose a novel method consisting of the regional simplified dual attention network and global graph convolution network. Firstly, we cluster homogeneous points into superpoints and construct a superpoint graph to effectively reduce the computation complexity and greatly maintain spatial topological relations among superpoints. Secondly, we integrate cross-position attention and cross-channel attention into a single head attention module and design a novel interactive attention gating (IAG)-based multilayer perceptron (MLP) network (IAG?MLP), which is utilized for the expansion of the receptive field and augmentation of discriminative features in local embeddings. Afterwards, the combination of stacked IAG?MLP blocks and the global graph convolution network, called IAGC, is proposed to learn high-dimensional local features in superpoints and progressively update these local embeddings with the recurrent neural network (RNN) network. Our proposed framework is evaluated on three indoor open benchmarks, and the 6-fold cross-validation results of the S3DIS dataset show that the local IAG?MLP network brings about 1% and 6.1% improvement in overall accuracy (OA) and mean class intersection-over-union (mIoU), respectively, compared with the PointNet local network. Furthermore, our IAGC network outperforms other CNN-based approaches in the ScanNet V2 dataset by at least 7.9% in mIoU. The experimental results indicate that the proposed method can better capture contextual information and achieve competitive overall performance in the semantic segmentation task.

 Artículos similares

       
 
Shangyi Yan, Jingya Wang and Zhiqiang Song    
To address the shortcomings of existing deep learning models and the characteristics of microblog speech, we propose the DCCMM model to improve the effectiveness of microblog sentiment analysis. The model employs WOBERT Plus and ALBERT to dynamically enc... ver más
Revista: Future Internet

 
Jacopo Fior, Luca Cagliero and Paolo Garza    
In the last decade, cryptocurrency trading has attracted the attention of private and professional traders and investors. To forecast the financial markets, algorithmic trading systems based on Artificial Intelligence (AI) models are becoming more and mo... ver más
Revista: Future Internet

 
Minxing Zheng, Xinran Miao and Kris Sankaran    
Interpretability has attracted increasing attention in earth observation problems. We apply interactive visualization and representation analysis to guide the interpretation of glacier segmentation models. We visualize the activations from a U-Net to und... ver más

 
Tao Wan and Buhai Shi    
Offender residences have become a research focus in the crime literature. However, little attention has been paid to the interactive associations between built environment factors and the residential choices of offenders. Over the past three decades, the... ver más

 
Pawel Cybulski    
Animated cartographic visualization incorporates the concept of geomedia presented in this Special Issue. The presented study aims to examine the effectiveness of spatial pattern and temporal trend recognition on animated choropleth maps. In a controlled... ver más