MapSegNet: A Fully Automated Model Based on the Encoder-Decoder Architecture for Indoor Map Segmentation
Authors:
Open Access
- 16 July 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 101530-101542
Abstract
Image segmentation in robotics is an ongoing research field in which neural networks have shown promising performance. In this paper, we introduce MapSegNet, a deep convolutional neural network for indoor map segmentation, which is able to segment the indoor maps into smaller units, including rooms, corridors, windows, and furniture. The proposed model consists of an encoder phase to capture context and a corresponding decoder phase to increase the resolution of feature maps to the original resolution. A design for skip connections is introduced with fused multi-scale feature maps between the encoder and the decoder phases. The proposed skip connection increases the flow of information between the phases and improves the model generalization. We evaluate empirical studies based on abstract maps and detailed maps. While abstract maps include empty rooms and corridors, the detailed maps contain indoor space with more objects such as furniture. We investigate the effectiveness of the proposed method by employing various indoor maps and compare its performance with similar neural network models on multiple datasets. The results show that the proposed model is able to achieve more accurate recognition or lower computation cost compared to other state-of-the-art segmentation techniques.Keywords
Funding Information
- National Natural Science Foundation of China (91848111)
- Chinese Academy of Science-The World Academy of Sciences (CAS-TWAS) President’s Fellowship
This publication has 25 references indexed in Scilit:
- Large Kernel Matters — Improve Semantic Segmentation by Global Convolutional Network2017
- Parsing floor plan images2017
- Automatic Skin Lesion Segmentation Using Deep Fully Convolutional Networks With Jaccard DistanceIEEE Transactions on Medical Imaging, 2017
- G-MS2F: GoogLeNet based multi-stage feature fusion of deep CNN for scene recognitionNeurocomputing, 2017
- SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Room segmentation: Survey, implementation, and analysis2016
- Fully convolutional networks for semantic segmentation2015
- Distance Transform-Based Skeleton Extraction and Its Applications in Sensor NetworksIEEE Transactions on Parallel and Distributed Systems, 2012
- A contour code feature based segmentation for handwriting recognition2005
- Augmenting topology-based maps with geometric informationRobotics and Autonomous Systems, 2002