Feature based simultaneous localisation and mapping
- Resource Type
- Conference
- Authors
- Gayathri, T. R.; Aneesh, R. P.; Nayar, Gayathri R.
- Source
- 2017 IEEE International Conference on Circuits and Systems (ICCS) Circuits and Systems (ICCS), 2017 IEEE International Conference on. :419-422 Dec, 2017
- Subject
- Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Fields, Waves and Electromagnetics
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Simultaneous localization and mapping
Feature extraction
Conferences
Testing
Technological innovation
Cameras
Simultaneous localisation and mapping (SLAM)
Plücker line co-ordinates
Orthonormal representation
Stereo Camera
Depth Estimation
Image Proceesing
Robotics
- Language
Simultaneous Localisation and Mapping (SLAM) is a new technique in Robotics used to track moving objects. In this paper, a graph based SLAM is proposed to map the trajectory with line features. This system extracts both line and point features from the scene. The line features are used mostly because point features are less informative. This algorithm is designed and developed with line features by modeling the moving objects. The position of these objects is identified with indoor and outdoor datasets. ‘Kitty’ dataset are used for testing this algorithm. Stereovision cameras are used to capture the real time data. The shape, color and depth features are also extracted to plot the trajectory. This method has been successfully implemented with real time data.