We have conceived a novel compound multicopter (helicopter type utilizing multiple different size propellers for separate lift and attitude control) configuration specifically for flight through narrow corridors. Its design combines the contradictory requirements of limited width, high agility and long endurance while carrying a significant payload. This *Research supported by Kulab (Propolis) and KULeuven (FWO-project 6.0404.10).

Recent technical advances in Unmanned Aerial Vehicles (UAV) made a realm of applications possible. In this paper we focus on the application of following a walking pedestrian in real-time, using optimised pedestrian detection and object tracking. For this we use an on-board embedded system, offering an optimal ratio of computational power and weight. We extend the commonly used ground plane estimation technique, used to reduce the search space, based on the sensor data off the UAV. The integration of the ground plane constraint obtains a significant speed-up over the already optimised Aggregate Channel Feature (ACF) detector. To compensate for the frames without detections, we use a particle tracker based on color information. We successfully validated our system on a flying UAV.

No abstract

Nowadays, complex image processing algorithms are a necessity to make UAVs more autonomous. Currently, the processing of images of the on-board camera is often performed on a ground station, thus severely limiting the operating range. On-board processing has numerous advantages, however determining a good trade-off between speed, power consumption and weight of a specific hardware platform for onboard processing is hard. Many hardware platforms exist, and finding the most suited one for a specific vision algorithm is difficult. We present a framework that automatically determines the most-suited hardware platform given an arbitrary complex vision algorithm. Our framework estimates the speed, power consumption and flight time of this algorithm for multiple hardware platforms on a specific UAV. We demonstrate this methodology on two real-life cases and give an overview of the present top processing CPU-based platforms for on-board UAV image processing.

Nowadays, many lectures and presentations are recorded and broadcasted for teleteaching applications. When no human camera crew is present, the most obvious choice is for static cameras. In order to enhance the viewing experience, more advanced systems automatically track and steer the camera towards the lecturer. In this paper we propose an even more advanced system that tracks the lecturer while taking cinematographic rules into account. On top of that, the lecturer can be filmed in different types of shots. Our system is able to detect and track the position of the lecturer, even with non-static backgrounds and in difficult illumination. We developed an action axis determination system, needed to apply cinematographic rules and to steer the Pan-Tilt-Zoom (PTZ) camera towards the lecturer.