ADR Awareness Centre

The talk discusses the long-standing vision of creating autonomous robots capable of assisting humans in daily life. A crucial step toward this goal is enabling robots to learn tasks based on environmental cues or higher-level instructions.

This lecture overviews 2D Object Detection and Tracking that has many applications in autonomous car/drone vision (person, pedestrian, car tracking) and visual surveillance.

This lecture overviews 1D Convolutional Neural Networks that has many applications in 1D signal analysis.

This lecture overviews 2D Systems, as they are the primary tools for many image processing and analysis operations.  It covers the following topics in detail: Two-Dimensional Discrete LTI Systems. 2D convolutions. 2D correlation.

This lecture overviews 3D image and video displays  that has many applications in stero vision, 3D cinema and 3D TV.

A fully autonomous system can: a) gain information about the environment, b) work for an extended period without human intervention, c) move either all or part of itself throughout its operating environment without human assistance and d) avoid situa

This lecture overviews Computational Cinematography that has many applications in filming, notably in drone cinematography.

This lecture overviews  digital images, image processing and image analysis. 1D signals, 2D signals (images), 3D signals (videos, medical volumes) are presented. Multichannel images, e.g., color and multispectral images come next.

No matter their exact form, AI Science and Engineering and its sister disciplines have many great challenges to address.

Stereoscopic and multiview imaging will be explored in depth, as they have tremendous applications in many applications, ranging from autonomous car/drone/robot/vessel vision to Surveying Engineering to Medical Imaging.

Image-based 3D Shape Reconstruction, Stereo and multiview imaging principles will be overviewed. The following topics will be covered: Feature extraction and matching. Triangulation and Bundle Adjustment. Mathematics of structure from motion.

Reinforcement learning is an appealing subject. Firstly, it is a very general concept: an agent interacts with an environment with the goal to maximize the rewards it receives from the environment.