Search results: Found 10

Listing 1 - 10 of 10
Sort by
Human worker activity recognition in industrial environments

Author:
ISBN: 9783866446434 Year: Pages: XII, 176 p. DOI: 10.5445/KSP/1000022235 Language: ENGLISH
Publisher: KIT Scientific Publishing
Subject: Technology (General)
Added to DOAB on : 2019-07-30 20:01:58
License:

Loading...
Export citation

Choose an application

Abstract

In this work, an intelligent human-machine interface (HMI) for human worker activity recognition in industrial environments is presented. The interface consists of components for robust and accurate 3D position estimation in workspace environments, the recognition of task-related worker activities and human-computer interaction via gestures. All components of the presented HMI are flexible with respect to applications and can be transferred to other activity recognition problems, as well.

Video-to-Video Face Recognition for Low-Quality Surveillance Data

Author:
Book Series: Karlsruher Schriften zur Anthropomatik / Lehrstuhl für Interaktive Echtzeitsysteme, Karlsruher Institut für Technologie ; Fraunhofer-Inst. für Optronik, Systemtechnik und Bildauswertung IOSB Karlsruhe ISSN: 18636489 ISBN: 9783731507994 Year: Volume: 36 Pages: IX, 153 p. DOI: 10.5445/KSP/1000083168 Language: ENGLISH
Publisher: KIT Scientific Publishing
Subject: Computer Science
Added to DOAB on : 2019-07-28 18:37:01
License:

Loading...
Export citation

Choose an application

Abstract

The availability of video data is an opportunity and a challenge for law enforcement agencies. Face recognition methods can play a key role in the automated search for persons in the data. This work targets efficient representations of low-quality face sequences to enable fast and accurate face search. Novel concepts for multi-scale analysis, dataset augmentation, CNN loss function, and sequence description lead to improvements over state-of-the-art methods on surveillance video footage.

Robust automatic transcription of lectures

Author:
ISBN: 9783866443945 Year: Pages: XXVI, 173 p. DOI: 10.5445/KSP/1000011992 Language: ENGLISH
Publisher: KIT Scientific Publishing
Subject: Computer Science
Added to DOAB on : 2019-07-30 20:02:00
License:

Loading...
Export citation

Choose an application

Abstract

Automatic transcription of lectures is becoming an important task. Possible applications can be found in the fields of automatic translation or summarization, information retrieval, digital libraries, education and communication research. Ideally those systems would operate on distant recordings, freeing the presenter from wearing body-mounted microphones. This task, however, is surpassingly difficult, given that the speech signal is severely degraded by background noise and reverberation.

Begriffliche Situationsanalyse aus Videodaten bei unvollständiger und fehlerhafter Information

Author:
Book Series: Karlsruher Schriften zur Anthropomatik / Lehrstuhl für Interaktive Echtzeitsysteme, Karlsruher Institut für Technologie ; Fraunhofer-Inst. für Optronik, Systemtechnik und Bildauswertung IOSB Karlsruhe ISSN: 18636489 ISBN: 9783731506447 Year: Volume: 32 Pages: XVII, 241 p. DOI: 10.5445/KSP/1000066975 Language: GERMAN
Publisher: KIT Scientific Publishing
Subject: Computer Science
Added to DOAB on : 2019-07-30 20:02:01
License:

Loading...
Export citation

Choose an application

Abstract

This work addresses the automatic detection of complex situations in image sequences in the video surveillance context. There are difficulties when dealing with data from natural environments. This work expands the formalism of FMTHL and SGTs to deal with erroneous, missing, and noisy data and complexity, demonstrates the robustness of situational recognition in natural scenarios, and expands generic applicability beyond discourse boundaries.

Über lernende optische Inspektion am Beispiel der Schüttgutsortierung

Author:
Book Series: Schriftenreihe Automatische Sichtprüfung und Bildverarbeitung ISSN: 18665934 ISBN: 9783731508427 Year: Volume: 13 Pages: XVI, 283 p. DOI: 10.5445/KSP/1000085620 Language: GERMAN
Publisher: KIT Scientific Publishing
Subject: Computer Science
Added to DOAB on : 2019-07-28 18:15:09
License:

Loading...
Export citation

Choose an application

Abstract

Automated visual inspection is an integral part in industrial manufacturing processes, but development and setup of such systems is very costly. Machine learning significantly reduces the effort of and speeds up both tasks. This work develops several machine learning methods suitable for automated visual inspection. The methods augment each other and can be used for a wide range of products.

Learning Dynamic Systems for Intention Recognition in Human-Robot-Cooperation

Author:
Book Series: Karlsruhe Series on Intelligent Sensor-Actuator-Systems / Karlsruher Institut für Technologie, Intelligent Sensor-Actuator-Systems Laboratory ISSN: 18673813 ISBN: 9783866449527 Year: Volume: 11 Pages: XIV, 210 p. DOI: 10.5445/KSP/1000031356 Language: ENGLISH
Publisher: KIT Scientific Publishing
Subject: Computer Science
Added to DOAB on : 2019-07-30 20:01:58
License:

Loading...
Export citation

Choose an application

Abstract

This thesis is concerned with intention recognition for a humanoid robot and investigates how the challenges of uncertain and incomplete observations, a high degree of detail of the used models, and real-time inference may be addressed by modeling the human rationale as hybrid, dynamic Bayesian networks and performing inference with these models. The key focus lies on the automatic identification of the employed nonlinear stochastic dependencies and the situation-specific inference.

Human Pose Estimation with Implicit Shape Models

Author:
Book Series: Schriftenreihe Automatische Sichtprüfung und Bildverarbeitung ISSN: 18665934 ISBN: 9783731501848 Year: Volume: 6 Pages: XVIII, 264 p. DOI: 10.5445/KSP/1000039083 Language: ENGLISH
Publisher: KIT Scientific Publishing
Subject: Computer Science
Added to DOAB on : 2019-07-30 20:01:58
License:

Loading...
Export citation

Choose an application

Abstract

This work presents a new approach for estimating 3D human poses based on monocular camera information only. For this, the Implicit Shape Model is augmented by new voting strategies that allow to localize 2D anatomical landmarks in the image. The actual 3D pose estimation is then formulated as a Particle Swarm Optimization (PSO) where projected 3D pose hypotheses are compared with the generated landmark vote distributions.

Advancing Electromyographic Continuous Speech Recognition: Signal Preprocessing and Modeling

Author:
ISBN: 9783731502111 Year: Pages: XVIII, 226 p. DOI: 10.5445/KSP/1000040667 Language: ENGLISH
Publisher: KIT Scientific Publishing
Subject: Computer Science
Added to DOAB on : 2019-07-30 20:02:00
License:

Loading...
Export citation

Choose an application

Abstract

Speech is the natural medium of human communication, but audible speech can be overheard by bystanders and excludes speech-disabled people. This work presents a speech recognizer based on surface electromyography, where electric potentials of the facial muscles are captured by surface electrodes, allowing speech to be processed nonacoustically. A system which was state-of-the-art at the beginning of this book is substantially improved in terms of accuracy, flexibility, and robustness.

Analysis and recognition of human actions with flow features and temporal models

Author:
ISBN: 9783731502821 Year: Pages: XV, 183 p. DOI: 10.5445/KSP/1000043583 Language: ENGLISH
Publisher: KIT Scientific Publishing
Subject: Computer Science
Added to DOAB on : 2019-07-30 20:02:01
License:

Loading...
Export citation

Choose an application

Abstract

This work focuses the recognition of complex human activities in video data. A combination of new features and techniques from speech recognition is used to realize a recognition of action units and their combinations in video sequences. The presented approach shows how motion information gained from video data can be used to interpret the underlying structural information of actions and how higher level models allow an abstraction of different motion categories beyond simple classification.

Probabilistic Maneuver Recognition in Traffic Scenarios

Author:
Book Series: Schriftenreihe / Institut für Mess- und Regelungstechnik, Karlsruher Institut für Technologie ISSN: 16134214 ISBN: 9783731502876 Year: Volume: 031 Pages: VI, 150 p. DOI: 10.5445/KSP/1000043680 Language: ENGLISH
Publisher: KIT Scientific Publishing
Subject: Technology (General)
Added to DOAB on : 2019-07-30 20:02:02
License:

Loading...
Export citation

Choose an application

Abstract

In this work an approach is presented to model and recognize traffic maneuvers in terms of interactions between different traffic participants on extra urban roads. Results of the recognition concept are presented and evaluated using different sensor setups and its benefit is outlined by an integration into a software framework in the field of Car-to-Car (C2C) communications. Furthermore, recognition results are used in this work to robustly predict vehicle’s trajectories while driving dynamic

Listing 1 - 10 of 10
Sort by
Narrow your search

Publisher

KIT Scientific Publishing (10)


License

CC by-sa (7)

CC by-nc-nd (3)


Language

english (8)

german (2)


Year
From To Submit

2018 (2)

2017 (1)

2014 (4)

2013 (1)

2011 (1)

2009 (1)