Building an Autonomous Indoor Visual SLAM System using an iRobot - PowerPoint PPT Presentation

Building an Autonomous Indoor Visual SLAM System using an iRobot and Kinect Chase Lewis Mentor: Xin Li, Kang Zhang

Kinect and iRobot System

– Simultaneous Localization and Mapping – Creating a 3d map while tracking the location of the robot in said map – Algorithms and image processing techniques S.L.A.M

Point Cloud Conversion

– Algorithms – Speeded Up Robust Feature (SURF) – Random Sample Consensus (RANSAC) Feature Detection

Stitching

Self-Driving Cars

Remote Exploration

Questions?

– This material is based upon work supported by the National Science Foundation under award OCI-1560410 with additional support from the Center for Computation & Technology at Louisiana State University. Acknowledgements

– OpenCV: http://opencv.org/ References – Kinect Image Library: http://vision.in.tum.de/ – Feature Detection Support: http://pyimagesearch.com/