Refine
H-BRS Bibliography
- yes (145) (remove)
Departments, institutes and facilities
- Fachbereich Informatik (77)
- Fachbereich Angewandte Naturwissenschaften (20)
- Fachbereich Ingenieurwissenschaften und Kommunikation (17)
- Fachbereich Wirtschaftswissenschaften (14)
- Institute of Visual Computing (IVC) (14)
- Institut für Technik, Ressourcenschonung und Energieeffizienz (TREE) (11)
- Institut für Verbraucherinformatik (IVI) (7)
- Internationales Zentrum für Nachhaltige Entwicklung (IZNE) (6)
- Institut für Sicherheitsforschung (ISF) (5)
- Fachbereich Sozialpolitik und Soziale Sicherung (4)
Document Type
- Report (145) (remove)
Year of publication
Keywords
- Robotik (5)
- Engineering (4)
- Cutting sticks-Problem (3)
- Teilsummenaufteilung (3)
- Virtuelle Realität (3)
- AAL-Technik (2)
- Deep Learning (2)
- Forschungsbericht (2)
- Gravitation (2)
- Interaktion (2)
The ability of detecting people has become a crucial subtask, especially in robotic systems which aim an application in public or domestic environments. Robots already provide their services e.g. in real home improvement markets and guide people to a desired product. In such a scenario many robot internal tasks would benefit from the knowledge of knowing the number and positions of people in the vicinity. The navigation for example could treat them as dynamical moving objects and also predict their next motion directions in order to compute a much safer path. Or the robot could specifically approach customers and offer its services. This requires to detect a person or even a group of people in a reasonable range in front of the robot. Challenges of such a real-world task are e.g. changing lightning conditions, a dynamic environment and different people shapes. In this thesis a 3D people detection approach based on point cloud data provided by the Microsoft Kinect is implemented and integrated on mobile service robot. A Top-Down/Bottom-Up segmentation is applied to increase the systems flexibility and provided the capability to the detect people even if they are partially occluded. A feature set is proposed to detect people in various pose configurations and motions using a machine learning technique. The system can detect people up to a distance of 5 meters. The experimental evaluation compared different machine learning techniques and showed that standing people can be detected with a rate of 87.29% and sitting people with 74.94% using a Random Forest classifier. Certain objects caused several false detections. To elimante those a verification is proposed which further evaluates the persons shape in the 2D space. The detection component has been implemented as s sequential (frame rate of 10 Hz) and a parallel application (frame rate of 16 Hz). Finally, the component has been embedded into complete people search task which explorates the environment, find all people and approach each detected person.
The objective of this research project is to develop a user-friendly and cost-effective interactive input device that allows intuitive and efficient manipulation of 3D objects (6 DoF) in virtual reality (VR) visualization environments with flat projections walls. During this project, it was planned to develop an extended version of a laser pointer with multiple laser beams arranged in specific patterns. Using stationary cameras observing projections of these patterns from behind the screens, it is planned to develop an algorithm for reconstruction of the emitter’s absolute position and orientation in space. Laser pointer concept is an intuitive way of interaction that would provide user with a familiar, mobile and efficient navigation though a 3D environment. In order to navigate in a 3D world, it is required to know the absolute position (x, y and z position) and orientation (roll, pitch and yaw angles) of the device, a total of 6 degrees of freedom (DoF). Ordinary laser-based pointers when captured on a flat surface with a video camera system and then processed, will only provide x and y coordinates effectively reducing available input to 2 DoF only. In order to overcome this problem, an additional set of multiple (invisible) laser pointers should be used in the pointing device. These laser pointers should be arranged in a way that the projection of their rays will form one fixed dot pattern when intersected with the flat surface of projection screens. Images of such a pattern will be captured via a real-time camera-based system and then processed using mathematical re-projection algorithms. This would allow the reconstruction of the full absolute 3D pose (6 DoF) of the input device. Additionally, multi-user or collaborative work should be supported by the system, would allow several users to interact with a virtual environment at the same time. Possibilities to port processing algorithms into embedded processors or FPGAs will be investigated during this project as well.
A Comparative Study of Uncertainty Estimation Methods in Deep Learning Based Classification Models
(2020)
Deep learning models produce overconfident predictions even for misclassified data. This work aims to improve the safety guarantees of software-intensive systems that use deep learning based classification models for decision making by performing comparative evaluation of different uncertainty estimation methods to identify possible misclassifications.
In this work, uncertainty estimation methods applicable to deep learning models are reviewed and those which can be seamlessly integrated to existing deployed deep learning architectures are selected for evaluation. The different uncertainty estimation methods, deep ensembles, test-time data augmentation and Monte Carlo dropout with its variants, are empirically evaluated on two standard datasets (CIFAR-10 and CIFAR-100) and two custom classification datasets (optical inspection and RoboCup@Work dataset). A relative ranking between the methods is provided by evaluating the deep learning classifiers on various aspects such as uncertainty quality, classifier performance and calibration. Standard metrics like entropy, cross-entropy, mutual information, and variance, combined with a rank histogram based method to identify uncertain predictions by thresholding on these metrics, are used to evaluate uncertainty quality.
The results indicate that Monte Carlo dropout combined with test-time data augmentation outperforms all other methods by identifying more than 95% of the misclassifications and representing uncertainty in the highest number of samples in the test set. It also yields a better classifier performance and calibration in terms of higher accuracy and lower Expected Calibration Error (ECE), respectively. A python based uncertainty estimation library for training and real-time uncertainty estimation of deep learning based classification models is also developed.
Neuromorphic computing aims to mimic the computational principles of the brain in silico and has motivated research into event-based vision and spiking neural networks (SNNs). Event cameras (ECs) capture local, independent changes in brightness, and offer superior power consumption, response latencies, and dynamic ranges compared to frame-based cameras. SNNs replicate neuronal dynamics observed in biological neurons and propagate information in sparse sequences of ”spikes”. Apart from biological fidelity, SNNs have demonstrated potential as an alternative to conventional artificial neural networks (ANNs), such as in reducing energy expenditure and inference time in visual classification. Although potentially beneficial for robotics, the novel event-driven and spike-based paradigms remain scarcely explored outside the domain of aerial robots.
To investigate the utility of brain-inspired sensing and data processing in a robotics application, we developed a neuromorphic approach to real-time, online obstacle avoidance on a manipulator with an onboard camera. Our approach adapts high-level trajectory plans with reactive maneuvers by processing emulated event data in a convolutional SNN, decoding neural activations into avoidance motions, and adjusting plans in a dynamic motion primitive formulation. We conducted simulated and real experiments with a Kinova Gen3 arm performing simple reaching tasks involving static and dynamic obstacles. Our implementation was systematically tuned, validated, and tested in sets of distinct task scenarios, and compared to a non-adaptive baseline through formalized quantitative metrics and qualitative criteria.
The neuromorphic implementation facilitated reliable avoidance of imminent collisions in most scenarios, with 84% and 92% median success rates in simulated and real experiments, where the baseline consistently failed. Adapted trajectories were qualitatively similar to baseline trajectories, indicating low impacts on safety, predictability and smoothness criteria. Among notable properties of the SNN were the correlation of processing time with the magnitude of perceived motions (captured in events) and robustness to different event emulation methods. Preliminary tests with a DAVIS346 EC showed similar performance, validating our experimental event emulation method. These results motivate future efforts to incorporate SNN learning, utilize neuromorphic processors, and target other robot tasks to further explore this approach.
Abschlussbericht zum BMBF-Fördervorhaben Enabling Infrastructure for HPC-Applications (EI-HPC)
(2020)
Als rohstoffarme und exportorientierte Wirtschaftsnation ist die Bundesrepublik in ho- hem Maß auf die Sicherung und Sicherheit der Logistikketten im grenzüberschreiten- den Verkehr angewiesen. Angesichts der komplexen Transportstrukturen bei grenz- überschreitenden Transporten kommt den eingesetzten Kontroll- und Prüfverfahren besondere Bedeutung zu: Einerseits müssen Kostenbelastungen, Unterbrechungen und Verzögerungen in der Transportkette minimiert, andererseits besonders illegale Einfuhren, Transporte und Substanzen unterbunden werden. Von besonderer Bedeu- tung für Verdachts- bzw. Stichprobenkontrollen ist der Einsatz speziell trainierter Spür- hunde. Als besonders leistungsfähige ‚lebende Sensoren‘ sind sie in der Lage, eine Vielzahl von Stoffen zu detektieren. Der Einsatz von Spürhunden unterliegt allerdings engen Grenzen: Hoher Trainingsaufwand, eng begrenzte Einsatzdauer, begrenzte Verfügbarkeit. Die Entwicklung neuer, optimierter Einsatzverfahren für Spürhunde z. B. mit höheren Durchsatzraten und überprüfbarer Verlässlichkeit durch Einbindung technischer Systeme ist daher ein wichtiger Beitrag für die Sicherung und Sicherheit der Logistikketten.
This report presents the implementation and evaluation of a computer vision problem on a Field Programmable Gate Array (FPGA). This work is based upon [5] where the feasibility of application specific image processing algorithms on a FPGA platform have been evaluated by experimental approaches. The results and conclusions of that previous work builds the starting point for the work, described in this report. The project results show considerable improvement of previous implementations in processing performance and precision. Different algorithms for detecting Binary Large OBjects (BLOBs) more precisely have been implemented. In addition, the set of input devices for acquiring image data has been extended by a Charge-Coupled Device (CCD) camera. The main goal of the designed system is to detect BLOBs in continuous video image material and compute their center points.
This work belongs to the MI6 project from the Computer Vision research group of the University of Applied Sciences Bonn-Rhein-Sieg1 . The intent is the invention of a passive tracking device for an immersive environment to improve user interaction and system usability. Therefore the detection of the users position and orientation in relation to the projection surface is required. For a reliable estimation a robust and fast computation of the BLOB's center-points is necessary. This project has covered the development of a BLOB detection system on an Altera DE2 Development and Education Board with a Cyclone II FPGA. It detects binary spatially extended objects in image material and computes their center points. Two different sources have been applied to provide image material for the processing. First, an analog composite video input, which can be attached to any compatible video device. Second, a five megapixel CCD camera, which is attached to the DE2 board. The results are transmitted on the serial interface of the DE2 board to a PC for validation of their ground truth and further processing. The evaluation compares precision and performance gain dependent on the applied computation methods and the input device, which is providing the image material.