
Research Article
A Method of Indoor Space Layout for Home Stay Based on Binocular Vision SLAM
@INPROCEEDINGS{10.1007/978-3-031-50571-3_28, author={Liushi Qin and Zhengfeng Huang}, title={A Method of Indoor Space Layout for Home Stay Based on Binocular Vision SLAM}, proceedings={Multimedia Technology and Enhanced Learning. 5th EAI International Conference, ICMTEL 2023, Leicester, UK, April 28-29, 2023, Proceedings, Part I}, proceedings_a={ICMTEL}, year={2024}, month={2}, keywords={Binocular Vision SLAM Home Stay Room Spatial Layout}, doi={10.1007/978-3-031-50571-3_28} }
- Liushi Qin
Zhengfeng Huang
Year: 2024
A Method of Indoor Space Layout for Home Stay Based on Binocular Vision SLAM
ICMTEL
Springer
DOI: 10.1007/978-3-031-50571-3_28
Abstract
Reasonable layout method can ensure reasonable spatial layout and data accuracy. Traditional layout methods can not guarantee the accuracy of feature data in complex spatial environment, which leads to unreasonable layout. In order to solve this problem, a method of indoor space layout of home stay based on binocular vision SLAM is proposed. According to the RGB color image of a given indoor scene, the interior room layout boundary of the scene is detected, and the foreground and background are segmented. Use Kinect to obtain spatial point cloud data to avoid data loss. The geometric simulation model of spatial features is established to realize the projection from spatial points to image plane. The binocular vision SLAM point and line feature selection method is adopted to make the point and line features cluster evenly. Match features, analyze the constraint relationship between the projected line segment and the line segment to be matched. The visual area of each functional area is calculated, and the indoor space layout model is constructed by combining the anthropometric technology. According to the geometric characteristics of layout containers and the attributes of layout objects, the open layout of indoor space is realized. The experimental results show that the clustering effect of this method is good, and the maximum space utilization rate can reach 92%, which increases the spatial interaction and openness, and is consistent with the ideal layout effect.