The applicability of on-line contextual calibration to a neural network based monocular collision avoidance system on a UAV

Hiba, Antal and Aleksziev, Rita and Pázmán, Koppány and Bauer, Péter and Benczúr, András and Zarándy, Ákos and Daróczy, Bálint (2019) The applicability of on-line contextual calibration to a neural network based monocular collision avoidance system on a UAV. In: 5TH IFAC CONFERENCE ON INTELLIGENT CONTROL AND AUTOMATION SCIENCES, 2019 augusztus 21-23, Belfast, Northern Ireland.

Preview

Text IFAC_ICONS_2019_repo.pdf - Submitted Version Download (2MB) | Preview

Abstract

Contextual calibration for object detection is a technique where a pretrained network collects attractive false positives during a calibration phase and use this calibration data for further training. This paper investigates the applicability of this method to a vision based onboard sense and avoid system, which requires intruder aircraft detection in camera images. Various landscape and sky backgrounds were generated by Unreal4 3D engine for calibration tests. Contextual calibration is a promising candidate for handling extreme situations which are not covered well in the training data.

Actions (login required)

Edit Item