Analysis of robotic environment using low resolution image sequence

Mobile robots have been widely used in agricultural, industrial and military applications and areas where human intervention is not possible. These robots are equipped with sensors and image capturing devices to collect time series data from the environment. The data thus collected are analyzed to obtain vital information about the environment. This paper presents an experimental study using low resolution image data captured from a set of complex robotic scenarios. Features such as color and texture are extracted from the images. The scenarios are then clustered based of the extracted features using k-medoids algorithm. Clustering accuracy has been analyzed with different image resolutions and feature extraction methods.