Monocular Visual Odometry

Keypoint tracking for VO
  • Research project to explore the challenges and applications of Visual Odometry
  • Compared deep learning based feature extractors and traditional features for indoor and outdoor navigation tasks
  • Identified bottlenecks in VO pipeline and explored learnt feature descriptors for enhanced performance
  • Published a comprehensive survey on advancements in monocular visual odometry. Used research findings to design an application for visual odometry in Advanced Driver Assistant System (ADAS) for emergency autonomous parking. Publication under review
Robotics Research Computer Vision