Abstract
An architecture that is inspired by a human’s capability to autonomously navigate an environment based on visual landmark recognition is presented. It consists of pre-attentive and attentive stages that allow visual landmarks to be recognized reliably under both clean and cluttered backgrounds. The pre-attentive stage provides an efficient means for real-time image processing by selectively focusing on regions of interest within input images. The attentive stage has a memory feedback modulation mechanism that allows visual knowledge of landmarks in the memory to interact and guide different stages in the architecture for efficient feature extraction and landmark recognition. The results show that the architecture is able to reliably recognise both occluded and non-occluded visual landmarks in complex backgrounds.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have