Dr. Marcus Handte

@inproceedings{talako-book-chapter,

title = {Positionierung induktiv geladener Fahrzeuge},

author = {Peter Roch and Bijan Shahbaz Nejad and Marcus Handte and Pedro José Marrón},

editor = {Heike Proff and Markus Clemens and Pedro José Marrón and Benedikt Schmülling},

doi = {10.1007/978-3-658-39979-5_5},

isbn = {978-3-658-39979-5},

year  = {2023},

date = {2023-05-05},

booktitle = {Induktive Taxiladung für den öffentlichen Raum: Technische und betriebswirtschaftliche Aspekte},

pages = {93--142},

abstract = {Ziel des TALAKO Projekts ist es, kabelloses Laden von Elektrofahrzeugen im öffentlichen Raum zu ermöglichen. Induktives Laden erfordert eine präzise Ausrichtung des Fahrzeugs, um einen effizienten Ladevorgang zu gewährleisten. Dabei hat die Ausrichtung des Fahrzeugs direkten Einfluss auf den Wirkungsgrad. Der Positionierungsvorgang kann für den Fahrer herausfordernd sein, da er den Versatz der Ladekomponenten ohne weitere Unterstützung nicht wahrnehmen kann. Daher umfasst die entwickelte Anlage neben der induktiven Ladeinfrastruktur selbst ebenfalls ein kamerabasiertes Fahrerassistenzsystem. Das Fahrerassistenzsystem wird dazu genutzt, anfahrende Fahrzeuge zu erkennen und den Fahrer beim Positionierungsvorgang zu unterstützen. Es besteht aus zwei Komponenten: einem kamerabasierten Positionierungssystem und einer Fahrerleitanwendung. Das Positionierungssystem nutzt Kamerabilder, um die Position von Fahrzeugen mit einer Genauigkeit von 5 cm zu berechnen. Daraus wird der Abstand zwischen Fahrzeug und Ladeplatte abgeleitet. Die Fahrerleitanwendung interpretiert die Positionsinformationen und generiert daraufhin geeignete Anweisungen für den Fahrer. Das Positionierungssystem basiert auf einem neuronalen Netz, welches die Reifen des Fahrzeugs erkennt. Da der Abstand zwischen den Reifen bekannt ist, kann daraus die Position und Rotation des Fahrzeugs errechnet werden. Untersuchungen haben ergeben, dass die Genauigkeit im Bereich von 5 cm liegt. Um das Positionierungssystem unabhängig vom Fahrzeugtyp und Installationsort zu betreiben, muss es entsprechend konfiguriert werden. Dazu muss das neuronale Netz trainiert und die Kameraausrichtung kalibriert werden. Das Training des neuronalen Netzes wird mit synthetisch generierten Bildern ergänzt, welche mit einem eigens entwickelten Bildgenerator produziert werden können. Die Kameraausrichtung wird mit einem speziellen Muster bestimmt, welches an verschiedenen Stellen auf dem Untergrund platziert wird. Da die realen Maße des Musters bekannt sind, lässt sich daraus die Geometrie des Installationsortes ableiten. Im Rahmen einer Nutzerstudie wurde untersucht, welche Bildschirmmodalität für die Fahrerleitanwendung unter den gegebenen Umständen optimal eingesetzt werden kann. Die Studie hat ergeben, dass Nutzer einen im Fahrzeug befindlichen Bildschirm für die Ausgabe von Anweisungen bevorzugen. Daher wurde die Fahrerleitanwendung durch eine mobile Anwendung realisiert. Diese zeigt dem Fahrer die Position des Fahrzeugs in Relation zur Ladestation an. Für die Darstellung der räumlichen Relationen wurden verschiedene Visualisierungen miteinander verglichen. Mit mehreren Visualisierungen sind die Nutzer in der Lage, das Fahrzeug in einem Toleranzbereich von 5 cm zu positionieren. Die meisten Nutzer bevorzugen jedoch eine Darstellung aus der Vogelperspektive. Die Kommunikation der beiden Komponenten wurde mittels Bluetooth Low Energy umgesetzt. Im Gegensatz zu anderen drahtlosen Kommunikationsmöglichkeiten, wie z. B. WLAN, bietet dies den Vorteil, dass Informationen ohne Verzögerung eines Verbindungsaufbaus an die mobile Anwendung gesendet werden können. Dadurch kann der Fahrer unmittelbar nach Ankunft an der Anlage die Positionierung verzögerungsfrei starten. Das Gesamtsystem wurde prototypisch bei einem Taxiunternehmen in Mülheim a. d. R. (Auto Stephany GmbH (2012) Auto Stephany GmbH – Taxi Dienstleistungen. Abgerufen am 04. 08. 2022 von https://taxi-stephany.de/) in Betrieb genommen und über mehrere Monate iterativ optimiert. Während dieser Zeit wurden wertvolle Erfahrungen gesammelt, die dazu beigetragen haben, dass sowohl das Positionierungssystem als auch die Fahrerleitanwendung stetig verbessert wurden. Nach Abschluss der Optimierungen konnte das entwickelte System erfolgreich als Bestandteil der Pilotanlage in Köln mit mehreren Ladeplätzen eingesetzt werden. Da die Pilotanlage in Köln im öffentlichen Raum betrieben wird, müssen die Persönlichkeitsrechte einzelner Personen beachtet werden. Eine explizite Einwilligung in die Datenverarbeitung durch die Betroffenen ist jedoch nicht praktikabel. Daher wurde eine automatisierte Verschleierung eingesetzt, welche personenbezogene Daten wie Kennzeichen und Gesichter aus den Kamerabildern entfernt, um eine Verarbeitung zu vermeiden.

},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{mosavat2023experience,

title = {Experience: ARISTOTLE: wAke-up ReceIver-based, STar tOpology baTteryLEss sensor network},

author = {Sayedsepehr Mosavat and Matteo Zella and Marcus Handte and Alexander Julian Golkowski and Pedro José Marrón},

doi = {10.1145/3583120.3586961},

isbn = {979-8-4007-0118-4},

year  = {2023},

date = {2023-05-09},

booktitle = {Proceedings of the 22nd International Conference on Information Processing in Sensor Networks},

publisher = {ACM Digital Library},

abstract = {A truly ubiquitous, planet-wide Internet of Things requires ultra-low-power, long-lasting sensor nodes at its core so that it can be practically utilized in real-world scenarios without prohibitively high maintenance efforts. Recent advances in energy harvesting and low-power electronics have provided a solid foundation for the design of such sensor nodes. However, the issue of reliable two-way communication among such devices is still an active research undertaking due to the high energy footprint of traditional wireless transceivers. Although approaches such as radio duty cycling have proved beneficial for reducing the overall energy consumption of wireless sensor nodes, they come with trade-offs such as increased communication latency and complex protocols. To address these limitations, we propose ARISTOTLE, an ultra-low-power, wake-up receiver-based sensor node design employing a star network topology. We have deployed ARISTOTLE in two different venues for carrying out the task of weather data collection. In addition to reporting the results of the two deployments, we also evaluate several performance aspects of our proposed solution. ARISTOTLE has a mean power consumption of 236.67 uW while it is in sleep mode and monitoring the radio channel for incoming wake-up signals. Utilizing various sizes of supercapacitors, ARISTOTLE was able to reach system availabilities between 47.83% and 97.36% during our real-world deployments.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{10.1145/3608143.3608147,

title = {A Low-Cost Binaural Hearing Support System for Mobile Robots},

author = {Alexander Julian Golkowski and Marcus Handte and Pedro Jose Marron and Alexander Wedemeyer and Jakob Robert},

url = {https://doi.org/10.1145/3608143.3608147},

doi = {10.1145/3608143.3608147},

isbn = {9798400707742},

year  = {2023},

date = {2023-01-01},

urldate = {2023-01-01},

booktitle = {Proceedings of the 2023 International Conference on Robotics, Control and Vision Engineering},

pages = {18–24},

publisher = {Association for Computing Machinery},

address = {Tokyo, Japan},

series = {RCVE '23},

abstract = {The ability to quickly obtain a comprehensive picture of the environment is an important prerequisite for the realization of robust and safe autonomous navigation with mobile robots. Due to their comparatively low computational requirements and cost, as well as their ability to provide omnidirectional perception, audio systems can be an excellent complement to more sophisticated or expensive sensing systems such as cameras or lidars. In this paper, we describe the development of a low-cost binaural audio system capable of interpreting the acoustic information present in an environment to assist a lidar system in making decisions that need to be made by a mobile robot. By taking advantage of the robot’s mobility, the system can resolve the uncertainties inherent in consciously choosing two off-the-shelf microphones and effectively realize 360-degree coverage. This opens up new possibilities, for example, to make room monitoring much more reliable.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{fod_wc,

title = {Visual Foreign Object Detection for Wireless Charging of Electric Vehicles},

author = {Bijan Shahbaz Nejad and Peter Roch and Marcus Handte and Pedro José Marrón},

year  = {2023},

date = {2023-10-16},

urldate = {2023-10-16},

booktitle = {Advances in Visual Computing},

volume = {18},

abstract = {Wireless charging of electric vehicles can be achieved by installing a transmitter coil into the ground and a receiver coil at the underbody of a vehicle. In order to charge efficiently, accurate alignment of the charging components must be accomplished, which can be achieved with a camera-based positioning system. Due to an air gap between both charging components, foreign objects can interfere with the charging process and pose potential hazards to the environment. Various foreign object detection systems have been developed with the motivation to increase the safety of wireless charging. In this paper, we propose an object-type independent foreign object detection technique which utilizes the existing camera of an embedded positioning system. To evaluate our approach, we conduct two experiments by analyzing images from a dataset of a wireless charging surface and from a publicly available dataset depicting foreign objects in an airport environment. Our technique outperforms two background subtraction algorithms and reaches accuracy scores that are comparable to the accuracy achieved by a state-of-the-art neural network (~97%). While acknowledging the superior accuracy results of the neural network, we observe that our approach requires significantly less resources, which makes it more suitable for embedded devices. The dataset of the first experiment is published alongside this paper and consists of 3652 labeled images recorded by a positioning camera of an operating wireless charging station in an outdoor environment.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{limit_pnp,

title = {Optimizing PnP-Algorithms for Limited Point Correspondences Using Spatial Constraints},

author = {Peter Roch and Bijan Shahbaz Nejad and Marcus Handte and Pedro José Marrón},

year  = {2023},

date = {2023-10-16},

urldate = {2023-10-16},

booktitle = {Advances in Visual Computing},

volume = {18},

abstract = {Pose Estimation is an important component of many real-world computer vision systems. Most existing pose estimation algorithms need a large number of point correspondences to accurately determine the pose of an object. Since the number of point correspondences depends on the object’s appearance, lighting and other external conditions, detecting many points may not be feasible. In many real-world applications, movement of objects is limited due to gravity. Hence, detecting objects with only three degrees of freedom is usually sufficient. This allows us to improve the accuracy of pose estimation by changing the underlying equation of the perspective-n-point problem to allow only three variables instead of six. By using the improved equations, our algorithm is more robust against detection errors with limited point correspondences. In this paper, we specify two scenarios where such constraints apply. The first one is about parking a vehicle on a specific spot, while the second scenario describes a camera observing objects from a bird’s-eye view. In both scenarios, objects can only move in the ground plane and rotate around the vertical axis. Experiments with synthetic data and real-world photographs have shown that our algorithm outperforms state-of-the-art pose estimation algorithms. Depending on the scenario, our algorithm usually achieves 50% better accuracy, while being equally fast.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{nokey,

title = {Simplifying the Control of Mobile Robots through Image-based Behaviors},

author = {Alexander Julian Golkowski and Marcus Handte and Leon Alexander Marold and Pedro José Marrón},

doi = {10.1109/ICCCR54399.2022.9790104},

year  = {2022},

date = {2022-06-14},

booktitle = {2022 2nd International Conference on Computer, Control and Robotics (ICCCR)},

pages = {52-57},

abstract = {The development and commissioning of mobile robots is usually a time-consuming and cost-intensive undertaking. Today, systems are realized primarily through the use of complex software and hardware architectures, which only partially meet modern requirements for mobile robots. The core discipline that a mobile robot must fulfill is the correct perception of its environment. To achieve this, various technologies are used that are useful for detecting obstacles or navigating targets. An increasingly attractive technology in this domain are artificial neural networks. Existing literature focuses on either improving the performance of existing systems or on training for very specialized applications. In the field of mobile robotics, the focus is usually on realizing a specific task, while little attention is paid to generalizability, cost and energy constraints. To fill this gap, this paper investigates the possibility of reducing the setup for a mobile robot application to a minimum while still enabling complex behaviors. For the implementation, we take a biological inspired approach and investigate the usability of artificial neural networks, in this case YOLOv4, in a mobile robot application. In particular, we examine whether the currently available technologies meet todays requirements.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{epic,

title = {Enhancing Privacy in Computer Vision Applications: An Emotion Preserving Approach to Obfuscate Faces},

author = {Bijan Shahbaz Nejad and Peter Roch and Marcus Handte and Pedro José Marrón},

editor = {George Bebis and Bo Li and Angela Yao and Yang Liu and Ye Duan and Manfred Lau and Rajiv Khadka and Ana Crisan and Remco Chang},

doi = {10.1007/978-3-031-20716-7_7},

isbn = {978-3-031-20716-7},

year  = {2022},

date = {2022-10-04},

urldate = {2022-10-04},

booktitle = {Advances in Visual Computing},

volume = {17},

pages = {80--90},

publisher = {Springer Nature Switzerland},

abstract = {Computer vision offers many techniques to facilitate the extraction of semantic information from images. If the images include persons, preservation of privacy in computer vision applications is challenging, but undoubtedly desired. A common technique to prevent exposure of identities is to cover peoples' faces with, for example, a black bar. Although emotions are crucial for reasoning in many applications, facial expressions may be covered, which hinders the recognition of actual emotions. Thus, recorded images containing obfuscated faces may be useless for further analysis and investigation. We introduce an approach that enables automatic detection and obfuscation of faces. To avoid privacy conflicts, we use synthetically generated faces for obfuscation. Furthermore, we reconstruct the facial expressions of the original face, adjust the color of the new face and seamlessly clone it to the original location. To evaluate our approach experimentally, we obfuscate faces from various datasets by applying blurring, pixelation and the proposed technique. To determine the success of obfuscation, we verify whether the original and the resulting face represent the same person using a state-of-the-art matching tool. Our approach successfully obfuscates faces in more than 97{%} of the cases. This performance is comparable to blurring, which scores around 96{%}, and even better than pixelation (76{%}). Moreover, we analyze how effectively emotions can be preserved when obfuscating the faces. For this, we utilize emotion recognizers to recognize the depicted emotions before and after obfuscation. Regardless of the recognizer, our approach preserves emotions more effectively than the other techniques while preserving a convincingly natural appearance.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{guild,

title = {GUILD - A Generator for Usable Images in Large-Scale Datasets},

author = {Peter Roch and Bijan Shahbaz Nejad and Marcus Handte and Pedro José Marrón},

editor = {George Bebis and Bo Li and Angela Yao and Yang Liu and Ye Duan and Manfred Lau and Rajiv Khadka and Ana Crisan and Remco Chang},

doi = {10.1007/978-3-031-20716-7_19},

isbn = {978-3-031-20716-7},

year  = {2022},

date = {2022-10-04},

urldate = {2022-10-04},

booktitle = {Advances in Visual Computing},

volume = {17},

pages = {245--258},

publisher = {Springer Nature Switzerland},

abstract = {Large image datasets are important for many different aspects of computer vision. However, creating datasets containing thousands or millions of labeled images is time consuming. Instead of manual collection of a large dataset, we propose a framework for generating large-scale datasets synthetically. Our framework is capable of generating realistic looking images with varying environmental conditions, while automatically creating labels. To evaluate usefulness of such a dataset, we generate two datasets containing vehicle images. Afterwards, we use these images to train a neural network. We then compare detection accuracy to the same neural network trained with images of existing datasets. The experiments show that our generated datasets are well-suited to train neural networks and achieve comparable accuracy to existing datasets containing real photographs, while they are much faster to create.

},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}