A METHOD FOR EXTRACTING LINES AND THEIR UNCERTAINTY FROM ACOUSTIC UNDERWATER IMAGES FOR SLAM

The extraction of reliable features is a key issue for autonomous underwater vehicle navigation. Imaging sonars can produce acoustic images of the surroundings of the vehicle. Despite of the noise, the phantom echoes and reflections, we believe that they are a good source for features since they can work in turbid water, where other sensors like vision fail. Moreover, they can cover wide areas, increasing the number of features visible within a scan. This work presents an algorithm to extract linear features from underwater structured environments including as major contributions a sonar sensor model, an adapted implementation of the Hough transform and a novel procedure to estimate feature uncertainty.