A bio-motivated vision system and artificial neural network for autonomous UAV obstacle avoidance

Petho, Mate and Nagy, Ádám and Zsedrovits, Tamás (2023) A bio-motivated vision system and artificial neural network for autonomous UAV obstacle avoidance. In: Hungarian Association for Image Analysis and Pattern Recognition - 14th Conference KÉPAF 2023, 2023.01.24-27, Gyula, Magyarország.

	Text 50.pdf - Accepted Version Restricted to Registered users only Download (1MB) | Request a copy
Preview	Text kepaf_2023_slides_zseta.pdf - Presentation Download (961kB) | Preview

Abstract

Unmanned aerial vehicles (UAVs) are becoming more and more common. They show excellent potential for multiple types of autonomous work, although they must achieve these tasks safely. For flight safety, it must be assured that the UAV will avoid collision with any objects in its flight path during autonomous operations. Computer vision and artificial neural networks are effective in many applications. However, biological vision systems and the brain areas responsible for visual processing may hold solutions capable of acquiring information effectively. We propose a novel system, which performs visual cue extraction with algorithms based on the structure and functionality of the retina and the visual cortex of the mammalian visual system, and a convolutional neural network processing data to detect a predefined obstacle using the onboard camera of the UAV. We also examined the effect of preprocessing on calculation time and recognition effectiveness.

Actions (login required)

Edit Item