Home /Research /P‐2.11: Research on Scene 3d Reconstruction Technology Based on Multi‐sensor Fusion
PERCEPTION

P‐2.11: Research on Scene 3d Reconstruction Technology Based on Multi‐sensor Fusion

Xi Shen, Wanlin Li

Year
2023
Citations
2
Access
Open access

Abstract

3D scene provides reliable prior information for autonomous decision-making of mobile robot, which is the premise of intelligent mobile robot. 3D reconstruction technology realizes data fusion by sensing the environment and registering sensor data multiple times to the same coordinate system to generate offline 3D scene. 3D reconstruction is widely used in cultural relics reconstruction, AR tourism, automatic driving, smart home and video entertainment. This paper mainly uses lidar to fuse IMU data to realize 3D reconstruction of scene. The front-end odometer based on the fusion of lidar and IMU and the global pose optimization and mapping system based on loopback detection are designed. It improves the accuracy of the simultaneous positioning and mapping system and ensures the real-time performance

Keywords

Inertial measurement unitComputer visionComputer scienceArtificial intelligenceOdometerLidarSensor fusion3D reconstructionFuse (electrical)Mobile robot

Related papers

Browse all PERCEPTION papers