A5081324708- Video Surveillance and Tracking Methods
- Human Pose and Action Recognition
- Context-Aware Activity Recognition Systems
- Currency Recognition and Detection
- Image Processing and 3D Reconstruction
- 3D Surveying and Cultural Heritage
- Cultural Heritage Materials Analysis
- Advanced Vision and Imaging
- Digital Media Forensic Detection
- Advanced Image and Video Retrieval Techniques
- Gait Recognition and Analysis
- Face recognition and analysis
- Industrial Vision Systems and Defect Detection
- Indoor and Outdoor Localization Technologies
- Robotics and Sensor-Based Localization
- Face and Expression Recognition
- Hand Gesture Recognition Systems
- Infrared Target Detection Methodologies
- Generative Adversarial Networks and Image Synthesis
- Technology Use by Older Adults
- Image Retrieval and Classification Techniques
- Anomaly Detection Techniques and Applications
- Image and Object Detection Techniques
- Archaeological Research and Protection
- 3D Shape Modeling and Analysis
TU Wien
2015-2024
University of Vienna
2008-2022
Institute of Electrical and Electronics Engineers
2019
Gorgias Press (United States)
2019
Vrije Universiteit Brussel
2019
VRVis GmbH (Austria)
2013-2016
University of Applied Sciences Technikum Wien
2015
Forschungszentrum Jülich
1976-1994
The ability to recognize facial expressions automatically enables novel applications in human-computer interaction and other areas. Consequently, there has been active research this field, with several recent works utilizing Convolutional Neural Networks (CNNs) for feature extraction inference. These differ significantly terms of CNN architectures factors. Based on the reported results alone, performance impact these factors is unclear. In paper, we review state art image-based expression...
Over the last few years, novel color and depth sensors have pushed boundaries of robot perception significantly. Today, several new depth-sensing products are replacing earlier, well-examined red-green-blue-depth (RGBD) sensors, which reached end their product life cycle no longer available. The properties not yet been investigated, it is unclear how they will compare to earlier RGBD sensors.
Minimal residual disease (MRD) as measured by multiparameter flow cytometry (FCM) is an independent and strong prognostic factor in B-cell acute lymphoblastic leukemia (B-ALL). However, reliable cytometric detection of MRD strongly depends on operator skills expert knowledge. Hence, objective, automated tool for FCM-MRD quantification, able to overcome the technical diversity analytical subjectivity, would be most helpful. We developed a supervised machine learning approach using combination...
Background Ambient assisted living (AAL) is a common name for various artificial intelligence (AI)—infused applications and platforms that support their users in need multiple activities, from health to daily living. These systems use different approaches learn about make automated decisions, known as AI models, personalizing services increasing outcomes. Given the numerous developed deployed people with needs, conditions, dispositions toward technology, it critical obtain clear...
We present a public dataset with the aim to facilitate research on computer-vision-based Printed Circuit Board (PCB) analysis, focus recycling-related applications. The contains 748 images of PCBs from recycling facility, captured under representative conditions using professional DSLR camera. For all these we provide accurate segmentation information for depicted as well bounding box Integrated (IC) chips (9313 samples). Furthermore, textual labels subset 1740 IC samples. By including...
This paper introduces the 3D Measurement and Virtual Reconstruction of Ancient Lost Worlds Europe system (3D MURALE). It consists a set tools for recording, reconstructing, encoding, visualising database searching/querying that operate on buildings, building parts, statues, statue pottery, stratigraphy, terrain geometry texture material texture. The are loosely linked together by common which they all have facility to store access data. describes overall architecture MURALE then briefly...
A major obstacle to the broader use of 3D object reconstruction and modeling is extent manual intervention needed. Such interventions are currently extensive exist throughout every phase a project: collection images, image management, establishment sensor position orientation, extracting geometric information describing an object, merging geometric, texture semantic data. We present fully automated approach pottery based on fragment profile, which cross-section in direction rotational axis...
Recent interest has been shown in performance evaluation of visual surveillance systems. The main purpose on computer vision systems is the statistical testing and tuning order to improve algorithm's reliability robustness. In this paper we investigate use empirical discrepancy metrics for quantitative analysis motion segmentation algorithms. We are concerned with case an airport's apron, that area where aircrafts parked serviced by specialized ground support vehicles. Robust detection...
This paper deals with a novel method for object tracking. In the first step interest points are detected and feature descriptors around them calculated. Sets of known created, allowing tracking based on point matching. The set representation is updated online at every step. Our uses one-shot learning frame, so no offline supervised required. Following an recognition approach there need background model or motion model, abrupt non-stationary cameras. We compare our to Mean Shift Tracking via...
We propose a holistic system to classify ancient Roman Republican coins based on their reverse-side motifs. The bag-of-visual-words (BoW) model is enriched with spatial information increase the discriminative power of coin image representation. This achieved by combining pooling scheme co-occurrence encoding visual words. specifically address required geometric invariance properties image-based classification, as from different collections can be located at differing locations, have various...