Introduction of a human based attention model for robotic navigation

Abstract

In robotics, vision based navigation techniques are desirable as cameras are relatively cheap sensors that provide a rich range of information about an environment. However, visual based navigation is still hindered by place recognition performance in long time navigation situations. For example, the comparison of locations between day and night or sun and rain are tasks where common feature extraction techniques fail. Humans are considered capable of long term visual navigation. As part of this system humans fixate on various locations to gather salient visual information from a scene. It is hypothesised by mimicking human fixation, place recognition performance can be improved. This paper presents the initial investigation towards utilising a state-of-the-art vision attention model to locate salient regions within an image useful for place recognition performance. The preliminary results demonstrate that the visual attention model can reduce the total amount of the image used by 18% and still achieve similar place recognition performance to utilising the whole image. The results have also shown good place recognition performance with only 45% of the image, achieving 53% accuracy compared with the best performance of existing techniques 60% with 100% of the image.