Our Blog

Deep Learning and Computer Vision for Drone Imaging

MULTIDRONE, the Artificial Intelligence and Information Analysis Lab (AUTH) and the ICARUS.auth Special Interest Group organized a 3-days event entitled “Programming short course and workshop on Deep Learning and Computer Vision for Drone Imaging” from August 28-30, 2019.

P. Noussi lecture on object detection

The event was organized in three parts, which provided an in-depth presentation of programming tools and techniques for various computer vision and deep learning problems encountered in drone imaging.

Part A focused on Deep Learning, providing a solid background on Deep Neural Networks (DNN) topics, notably convolutional NNs (CNNs) and deep learning for object detection. Also, various DNN programming tools were presented, e.g., PyTorch, Keras, Tensorflow.

Part B focused on computer vision algorithms, namely on 2D target tracking, 3D target localization techniques (giving the attendants the opportunity to master state of the art video trackers), parallel GPU, multi-core CPU architectures and GPU programming (CUDA). As drones execute missions (e.g., AV shooting, inspection).

Part C lectures focused on drone mission planning and control. Before mission execution, it is best simulated, using drone mission simulation tools. Such simulations were presented using AirSim, ROS and Gazebo simulations. Each part consisted of lectures and programming workshops with hands-on lab exercises.

I.Karakostas lecture on object tracking

The lecturers were mainly delivered by post-doc researchers and PhD students from Aristotle University of Thessaloniki, University of Seville and University of Lisbon (V. Nousi, V. Sampaio, M. Malaca, A, Torres, I. Karakostas, P. Kaplanoglou, C. Symeonidis). I Pitas (AUTH) and J. Capitan (USE) also delivered lectures. The audience consisted of 54 people, with 14 of them being post-doc researchers or PhD students from various European universities and the rest 40 being Greek bachelor or MSc students in Electrical Engineering, Computer Science, Mechanical Engineering, Physics. The course was very well rated by the participants.

Tags: , ,

This is a unique website which will require a more modern browser to work! Please upgrade today!

WP to LinkedIn Auto Publish Powered By : XYZScripts.com