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

Image domain adaption of simulated data for human pose estimation

Published in Proc. SPIE 11543, Artificial Intelligence and Machine Learning in Defense Applications II, 2020

Leveraging the power of deep neural networks, single-person pose estimation has made substantial progress throughout the last years. More recently, multi-person pose estimation has also become of growing importance, mainly driven by the high demand for reliable video surveillance systems in public security. To keep up with these demands, certain efforts have been made to improve the performance of such systems, which is yet limited by the insufficient amount of available training data. This work addresses … Read more

Part Affinity Field based Activity Recognition

Published in Proceedings of the 2019 Joint Workshop of Fraunhofer IOSB and Institute for Anthropomatics, Vision and Fusion Laboratory, 2020

This report presents work and results on Activity Recognition using Part Affinity Fields for real-time surveillance applications. Starting with a short introduction to the motivation, this report gives a detailed overview over the key idea … Read more

VisDrone-CC2020: The Vision Meets Drone Crowd Counting Challenge Results

Published in Bartoli A., Fusiello A. (eds) Computer Vision – ECCV 2020 Workshops, 2020

Crowd counting on the drone platform is an interesting topic in computer vision, which brings new challenges such as small object inference, background clutter and wide viewpoint. However, there are few algorithms focusing on crowd counting on the drone-captured data due to the lack of comprehensive datasets. To this end, we collect a large-scale dataset and organize the Vision Meets Drone Crowd Counting Challenge (VisDrone-CC2020) in conjunction with the 16th European Conference on Computer Vision (ECCV 2020) to promote the developments … 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

Multi-Person Pose Estimation using synthetically generated Data

Master Thesis, Andreas Blattmann, 2019

Pose estimation is a quiet challenging task in the field of crowd monitoring. The promising JTA dataset provides an easy way to generate many poses with annotated ground truth keypoints. However, the gap between synthetical and real data ist quite big, therefore Andreas tries to minimize the distance between both domains. Read more

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

Multi-Keypoint Tracking on Synthetic Crowd Data

Bachelor Thesis, Oliver Becker, 2020

Due to the great advances in machine learning, many complex problems now become tractable. One such problem is pose estimation, which has attracted a lot of attention recently. Image-based pose estimation aims … Read more

Crowd Density Estimation from Aerial Imagery

Master Thesis, Florian Krüger, 2020

Through crowd density estimation, an estimate for the number of individuals in an image can be obtained. State-of-the-art methods yield precise estimates by utilizing deep learning architectures exclusively. Aerial imagery is … Read more