Bag of words (BoW) generation from given features for optimizing feature matching in V-SLAM application

Abstract

The project aims at generation of Bag of words from given features for optimizing feature matching in V-SLAM application. Simultaneous localization and mapping (SLAM) is the process where an ego vehicle builds a global map of their current environment and uses this map to navigate or deduce its location at any point in time. Visual SLAM is a specific type of SLAM that performs location and mapping functions by leveraging vision based sensors (like monocular or stereo camera) when neither the environment nor the location of the sensor is known. This report illustrates the use of BoW vocabulary for loop detection. A BoW based vocabulary is generated using feature extractor/descriptor by reading a database of images. Also, the report analyses the effect of varying direct index levels on an independent framework known as DLoopDetector. The vocabulary generation and evaluation frameworks are understood, modified for relevant features and experimented upon wrt various parameter choices involved.