Drone Vision for Infrastructure Inspection

This lecture overviews the use of drones for infrastructure inspection and maintenance. Various types of inspection, e.g., using visual cameras, LIDAR or thermal cameras are reviewed. Primary application area is electric line inspection. Line detection and tracking and drone perching are examined. Human action recognition and co-working assistance are overviewed.

Should you require access to the resource, please contact the author directly.

Deep Video Summarization

Nowadays, both social media sites, Media Archiving and Management (MAM) systems, and broadcaster mediatheques store huge amounts of video information. It search can be very tedious, whether for journalistic purposes or just for selecting a video to watch and entertain. Therefore, fast video browsing is an essentialservice to be provided in a www environment. One way to do it is through video summarization. It can create a picture gallery of each video, thus greatly facilitating its browsing. This gallery should contain both representative and informative key video frames. The same can be done by video skimming, which retains only themost representative and informative video snippets. Movie trailers is a primary example of video skimming. Recently, deep learning (DNN) techniques have been extensively employed in video summarization. They typically exploit both spatial and temporal video information,e.g., by using combine CNN and LSTM video modeling approaches. Adversarial DNN and GAN methods have also been used in video summarization. This lecture will overview all recent advances in the use of Deep learning for video summarization.

Should you require access to the resource, please contact the author directly.

Image Features

Region Segmentation

This lecture overviews Region Segmentation and Texture Description that have many applications in in image analysis, notably in shape description and object recognition It covers the following topics in detail: Image segmentation by thresholding. Region growing techniques. Split techniques and Quadtrees. Split /merge techniques. Relaxation algorithms in region analysis. Neural region segmentation.

Should you require access to the resource, please contact the author directly.

Edge Detection

This lecture overviews Edge Detection that has many applications in image analysis, notably shape description and object recognition. It covers the following topics in detail: Edge detection using numerical differentiation or image statistics. Hough transform for straight line and circle detection. Edge thresholding. Edge following algorithms using heuristic, graph-based and dynamic programming approaches. Object contour detection and contour following algorithms, including Active Contours.  Edge and contour detection using neural networks are also reviewed.

Should you require access to the resource, please contact the author directly.

Structure from Motion

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. UAV image capturing. Optimal UAV flight trajectory/flight height/viewing angle/image overlap ratio. Pre/post-processing for 3D reconstruction: flat surface smoothing/mesh modification/isolated point removal.  Structure from motion applications: 3D face reconstruction from uncalibrated video. 3D landscape reconstruction. 3D building/monument reconstruction and modeling. SfM has many applications, ranging from autonomous car/drone/robot/vessel vision to Surveying Engineering to Medical Imaging.

Should you require access to the resource, please contact the author directly.