Posts by Collection

portfolio

publications

Image-based Anomaly Detection within Crowds

Published in Proceedings of the 2018 Joint Workshop of Fraunhofer IOSB and Institute for Anthropomatics, Vision and Fusion Laboratory, 2019

Authorities and security services have to deal with more and more data collected during events and on public places. Two reasons for that are the rising number of huge events, as well as the expanding coverage with CCTV cameras of areas within cities. Even the number of ground crew teams, that are equipped … Read more

Human Pose Estimation for Real-World Crowded Scenarios

Published in 16th IEEE International Conference on Advanced Video and Signal Based Surveillance, 2019

Human pose estimation has recently made significant progress with the adoption of deep convolutional neural networks and many applications have attracted tremendous interest in recent years. However, many of these applications require pose estimation for human crowds, which still is a rarely addressed problem. For this purpose this work explores methods to optimize pose estimation for human crowds, focusing … Read more

What goes around comes around: Cycle-Consistency-based Short-Term Motion Prediction for Anomaly Detection using Generative Adversarial Networks

Published in 16th IEEE International Conference on Advanced Video and Signal Based Surveillances, 2019

Anomaly detection plays in many fields of research, along with the strongly related task of outlier detection, a very important role. Especially within the context of the automated analysis of video material recorded by surveillance cameras, abnormal situations can be of very different nature. For this purpose this work investigates … Read more

teaching

Crowd-level Person Pose Estimation

Bachelor Thesis, Thomas Dissert, 2018

Body pose estimation with deep learning programs on image-data is a common and heavily studied subtask in computer vision. The objective of this work is to evaluate the current state-of-the-art person pose estimators … Read more

Density-based Crowd Counting

Bachelor Thesis, Tobias Bleymehl, 2019

Density Based Crowd Couting is getting used more often to further improve the work of various areas in modern society. State-of-the-art methods accomplish better results estimating counts and positions … Read more

GAN-based Anomaly Detection

Master Thesis, Nils Murzyn, 2019

Anomaly detection plays an important role in a wide range of applications. In the field of video surveillance, image-based detection of an anomalous situation should be achieved. The requirements for … Read more

[WIP] Artificial Data for Activity Recognition

Bachelor Thesis, Kristina Katovich, 2019

Video-based activity recognition is a research field of broad interest. There exists a variety of methods that tackle this problem, most of which are working directly on image data. However, artificial / synthetic data have already proven their value for various tasks in machine learning. Kristina is therefore ivestigating whether such data can also be applied to the problem of activity recognition. Read more