Laser & Optoelectronics Progress, Volume. 59, Issue 18, 1811003(2022)
Visual Simultaneous Localization and Mapping Method of Semantic Octree Map Toward Indoor Dynamic Scenes
Fig. 1. Structure of proposed vSLAM system
Fig. 2. Network structure of FAST-SCNN[10]
Fig. 3. Result of semantic segmentation. (a) Original drawing; (b) segmented output
Fig. 4. Outliers removing. (a) All feature points; (b) effect after removing moving points
Fig. 5. Diagram of octree map
Fig. 6. Semantic octree map building process
Fig. 7. Dining Rooms image sequence and its semantic segmentation results
Fig. 8. Point cloud. (a) Original point cloud; (b) filtered point cloud
Fig. 9. Semantic point cloud and semantic octree map. (a) Semantic point cloud; (b) semantic octree map
Fig. 10. Comparison of ATE. (a) ORB-SLAM2; (b) proposed system
Fig. 11. Comparison of relative translation error. (a) ORB-SLAM2; (b) proposed system
Fig. 12. Semantic octree map building effect. (a) Original frame sequence; (b) semantic octree map
Fig. 13. Feature points extraction of proposed system in two scenes
Fig. 14. Semantic segmentation results of proposed system in two scenes
Fig. 15. Moving point removing effect of proposed system in two scenes
Fig. 16. Map building effect of proposed system
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Get Citation
Copy Citation Text
Rongfen Zhang, Wenhao Yuan, Jin Lu, Yuhong Liu. Visual Simultaneous Localization and Mapping Method of Semantic Octree Map Toward Indoor Dynamic Scenes[J]. Laser & Optoelectronics Progress, 2022, 59(18): 1811003
Category: Imaging Systems
Received: May. 21, 2021
Accepted: Jun. 16, 2021
Published Online: Aug. 22, 2022
The Author Email: Zhang Rongfen (rfzhang@gzu.edu.cn)