TY - CHAP A1 - Köhler, Sebastian A1 - Schreiner, Brian A1 - Ronalter, Steffen A1 - Doll, Konrad A1 - Brunsmann, Ulrich A1 - Zindler, Klaus T1 - Autonomous Evasive Maneuvers Triggered by Infrastructure-Based Detection of Pedestrian Intentions T2 - IEEE Intelligent Vehicles Symposium (IV' 13), Gold Coast, Australien, 23.-26. Juni KW - Evasive Maneuvers KW - Fahrerassistenzsystem KW - Bildverarbeitung Y1 - 2013 U6 - https://doi.org/10.1109/IVS.2013.6629520 SN - 1931-0587 SP - 519 EP - 526 ER - TY - CHAP A1 - Goldhammer, Michael A1 - Strigel, Elias A1 - Meissner, Daniel A1 - Brunsmann, Ulrich A1 - Doll, Konrad A1 - Dietmayer, Klaus T1 - Cooperative Multi Sensor Network for Traffic Safety Applications at Intersections T2 - 15th International IEEE Conference on Intelligent Transportation Systems (ITSC 2012), Anchorage, Alaska, USA. KW - Fahrerassistenzsystem KW - Bildverarbeitung Y1 - 2012 U6 - https://doi.org/10.1109/ITSC.2012.6338672 SP - 1178 EP - 1183 ER - TY - CHAP A1 - Bauer, Sebastian A1 - Köhler, Sebastian A1 - Doll, Konrad A1 - Brunsmann, Ulrich T1 - FPGA-GPU Architecture for Kernel SVM Pedestrian Detection T2 - 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR, San Francisco KW - Field programmable gate array Y1 - 2014 SN - 978-1-4244-7029-7 U6 - https://doi.org/10.1109/CVPRW.2010.5543772 SP - 61 EP - 68 ER - TY - CHAP A1 - Westhofen, Daniel A1 - Gründler, Carolin A1 - Doll, Konrad A1 - Brunsmann, Ulrich A1 - Zecha, Stephan T1 - Transponder- and Camera-Based Advanced Driver Assistance System T2 - IEEE Intelligent Vehicles Symposium (IV' 12), Alcala de Henares, Spain KW - Fahrerassistenzsystem KW - Bildverarbeitung Y1 - 2012 SN - 978-1-4673-2119-8 U6 - https://doi.org/10.1109/IVS.2012.6232140 SN - 1931-0587 SP - 293 EP - 298 ER - TY - CHAP A1 - Berberich, Markus A1 - Doll, Konrad T1 - Highly Flexible FPGA-Architecture of a Support Vector Machine T2 - 45. MPC-Workshop, Albstadt-Sigmaringen KW - Field programmable gate array Y1 - 2014 UR - https://www.mpc-gruppe.de/workshopbaende SN - 1868-9221 IS - 45 SP - 25 EP - 32 ER - TY - CHAP A1 - Fellhauer, Felix A1 - Schmitt, Marc A1 - Doll, Konrad T1 - Echtzeit-BLOB-Analyse mit Lauflängenkodierung und -dekodierung auf einem FPGA T2 - MPC-Workshop, Offenburg, 2012 KW - BLOB-Analyse KW - Field programmable gate array KW - Bildverarbeitung KW - Eingebettetes System Y1 - 2012 UR - https://www.mpc-gruppe.de/workshopbaende SN - 1868-9221 IS - 47 SP - 35 EP - 42 ER - TY - CHAP A1 - Duttine, Thomas A1 - Doll, Konrad T1 - Realisierung eines FPGA-basierten Echtzeitdifferenzbildsensors für Verkehrsassistenzsysteme T2 - 41. MPC-Workshop, Künzelsau, Deutschland KW - Field programmable gate array KW - Eingebettetes System KW - Bildverarbeitung Y1 - 2009 UR - https://www.mpc-gruppe.de/workshopbaende SN - 1862-7102 IS - 41 SP - 51 EP - 60 ER - TY - CHAP A1 - Saxen, Frerk A1 - Doll, Konrad A1 - Brunsmann, Ulrich T1 - Support Vector Pruning with SortedVotes for Large-Scale Datasets T2 - IEEE international conference on intelligent computing and intelligent systems, Guangzhou KW - Vektorquantisierung KW - Maschinelles Lernen Y1 - 2014 VL - 2011 SP - 305 EP - 309 ER - TY - CHAP A1 - Goldhammer, Michael A1 - Hubert, Andreas A1 - Köhler, Sebastian A1 - Zindler, Klaus A1 - Brunsmann, Ulrich A1 - Doll, Konrad A1 - Sick, Bernhard T1 - Analysis on Termination of Pedestrians‘ Gait at Urban Intersections T2 - Intelligent Transportation Systems (ITSC), 2014 IEEE 17th International Conference on KW - Fahrerassistenzsystem KW - Fußgänger Y1 - 2014 U6 - https://doi.org/10.1109/ITSC.2014.6957947 SP - 1758 EP - 1763 PB - IEEE CY - Qingdao, China ER - TY - CHAP A1 - Goldhammer, Michael A1 - Doll, Konrad A1 - Brunsmann, Ulrich A1 - Gensler, Andre A1 - Sick, Bernhard T1 - Pedestrian's Trajectory Forecast in Public Traffic with Artificial Neural Networks T2 - 22nd International Conference on Pattern Recognition (ICPR 2014), Stockholm, Sweden KW - Fahrerassistenzsystem KW - Fußgänger Y1 - 2014 SN - 978-1-4799-5208-3 U6 - https://doi.org/10.1109/ICPR.2014.704 SN - 1051-4651 SP - 4110 EP - 4115 PB - IEEE ER - TY - JOUR A1 - Köhler, Sebastian A1 - Goldhammer, Michael A1 - Bauer, Sebastian A1 - Zecha, Stephan A1 - Doll, Konrad A1 - Brunsmann, Ulrich A1 - Dietmayer, Klaus T1 - Stationary Detection of the Pedestrian's Intention at Intersections JF - IEEE Intelligent Transportation Systems Magazine KW - Fahrerassistenzsystem KW - Fußgänger Y1 - 2013 SN - 1939-1390 VL - 2013 IS - 5 SP - 87 EP - 99 ER - TY - CHAP A1 - Hahn, Stefan A1 - Zindler, Klaus A1 - Doll, Konrad A1 - Jumar, Ulrich T1 - New Control Scheme for a Lane-Keeping Evasive Maneuver Exploiting the Free Space Optimally T2 - Proceedings of the 20th International Conference on Methods and Models in Automation and Robotics,Miedzyzdroje, Poland, 24-27 August, 2015 KW - Fahrerassistenzsystem Y1 - 2015 SP - 856 EP - 861 ER - TY - GEN A1 - Brunsmann, Ulrich A1 - Doll, Konrad A1 - Hellert, Christian A1 - Kempf, Johannes A1 - Köhler, Sebastian A1 - Saxen, Frerk A1 - Weimer, Daniel T1 - Intelligente Verkehrssicherheits- und Informationssysteme T2 - Safety Expo, Aschaffenburg N2 - Poster KW - Verkehrssicherheit Y1 - 2010 N1 - Posterpräsentation und Echtzeitdemonstration ER - TY - GEN A1 - Bauer, Sebastian A1 - Brunsmann, Ulrich A1 - Doll, Konrad A1 - Duttine, Thomas A1 - Schlotterbeck-Macht, Stefan T1 - Kompetenz in Kreuzungsassistenz T2 - Safety Expo, Aschaffenburg N2 - Poster Y1 - 2009 ER - TY - CHAP A1 - Köhler, Sebastian A1 - Doll, Konrad A1 - Kebinger, Sophie A1 - Schmitt, Daniel A1 - Kröhn, Michael A1 - Fried, Maik A1 - Börsig, Rainer T1 - Prozessinnovation: Hochautomatisiert lernendes Assistenzsystem für die manuelle Montage N2 - Trotz hoher Automatisierungsgrade in der produzierenden Industrie, sind manuelle Montageprozesse durch den Menschen, sei es aufgrund der geforderten Flexibilität, insbesondere bei kleinen Losgrößen oder der erforderlichen Präzision, unverzichtbar. Um eine hohe Produktivität und niedrige Ausschussraten zu gewährleisten, ist es sinnvoll, den Menschen in seiner Montagetätigkeit zu unterstützen oder zu entlasten. Intelligente Assistenzsysteme können den Menschen dahingehend unterstützen, dass sie bspw. schwere Tätigkeiten kollaborativ übernehmen, Prozesse gezielt steuern oder Informationen bei Bedarf kontextsensitiv bereitstellen. In diesem Beitrag wird das Konzept eines intelligent hochautomatisiert lernenden Assistenzsystems vorgestellt, dessen Ziel es ist, anhand von bereits gelernten Abläufen an einem manuellen Montagearbeitsplatz fehlerhafte Abläufe zu erkennen oder neue valide Abläufe hochautomatisiert und unüberwacht zu lernen. Manuelle Montageprozesse bestehen aus Abfolgen von Handgriffen. Diese Handgriffe werden vom Assistenzsystem als Gesten erkannt und verarbeitet, sodass der Gesamtablauf in Teilschritte zerlegt werden kann. Weiterhin soll dieses Assistenzsystem Informationen zur Behebung des Fehlers direkt am Arbeitsplatz verfügbar machen. Das Assistenzsystem, dessen Architektur in Abb. 1 dargestellt ist, besteht aus einem zustandsgesteuerten, lernenden Steuersystem mit einem Microsoft Kinect-v2-Sensor, der den Arbeitsplatz aus der Überkopfperspektive erfasst und die Montageschritte erkennt. Da das Grundprinzip des Assistenzsystems in der Langzeitbeobachtung und –unterstützung der Montagetätigkeit liegt, werden die kontinuierlich aggregierten Daten zur Erweiterung und Verbesserung des Assistenzsystems genutzt. Es lernt somit hochautomatisiert neue oder abgewandelte Montageabläufe. Hieraus ergibt sich eine Herausforderung an die Bewertung der Güte eines solchen Systems. Während eine hohe Erkennungsrate der einzelnen Aktivitäten innerhalb eines Montageablaufs unabdingbar ist, wird für das vorgeschlagene System darüber hinaus gefordert, dass komplette Abläufe korrekt, d.h. in der richtigen Reihenfolge ohne einzelne Falschklassifikationen, erkannt werden. Nur hierdurch lassen sich real geänderte Abläufe hochautomatisiert und unüberwacht im Zustandsautomat des Steuersystems online einlernen. T2 - Konferenz für Angewandte Automatisierungstechnik in Lehre und Entwicklung (AALE), 2018 KW - Automatisierungstechnik KW - Montage Y1 - 2018 SN - 978-3-8007-4522-7 SP - 153 EP - 164 CY - Köln ER - TY - CHAP A1 - Hock, Sascha A1 - Hahnle, Michael A1 - Doll, Konrad T1 - Fusion von Fußgängererkennungen auf FPGAs T2 - 55. Workshop der Multiprojekt-Chip-Gruppe Baden-Württemberg N2 - Viele Verfahren zur Erkennung von Objekten, beispielsweise Fußgängern, in Bildern benutzen das Sliding-Window-Prinzip. Dabei wird ein Fenster von links oben nach rechts unten über das Bild verschoben. Für jedes dieser Fenster wird geprüft, ob es ein zu erkennendes Objekt beinhaltet. Ein Klassifikator liefert dann häufig positive Ergebnisse für mehrere benachbarte Fenster, die einem einzelnen Objekt zugeordnet werden können. Durch den Einsatz von unterschiedlichen Skalenstufen wird dieser Effekt weiter verstärkt. Bei der Detektion von Objekten ist daher eine Fusion dieser Mehrfacherkennungen zu einer einzelnen aussagekräftigen Detektion pro Objekt eine entscheidende Komponente. Des Weiteren müssen sporadisch auftauchende Falscherkennungen eliminiert werden. Diese Fusion von Detektionsergebnissen ist in der bildbasierten Objekterkennung ein wichtiger Verarbeitungsschritt und wird häufig auch als Non Maximum Suppression (NMS) bezeichnet. Eine robuste Fusion von Fußgängerdetektionen kann beispielsweise als Grundlage für ein automobiles Fußgängerwarnsystem oder auch für die Absichtserkennung von Personen im Straßenverkehr genutzt werden. Da diese Systeme Echtzeitanforderungen unterliegen, ist hierfür eine schnelle Berechnung erforderlich. In dieser Arbeit wird die erste, den Autoren bekannte, rein FPGA basierte Implementierung vorgestellt. Sie ist in der Lage, die Erkennungsergebnisse mehrerer paralleler Skalenstufen in Echtzeit zu fusionieren. Auf einem Kintex-7 FPGA eines Xilinx Zynq SoCs ist damit eine Verarbeitung von mehr als 100 Bildern pro Sekunde mit einer Auflösung von 1280 x 720 Pixel möglich. Die Genauigkeit der FPGA-Implementierung ist dabei mit der einer auf OpenCV basierenden Softwareanwendung vergleichbar. KW - Field programmable gate array KW - Objekterkennung Y1 - 2016 ER - TY - CHAP A1 - Köhler, Sebastian A1 - Goldhammer, Michael A1 - Zindler, Klaus A1 - Doll, Konrad A1 - Dietmayer, Klaus T1 - Stereo-Vision-Based Pedestrian's Intention Detection in a Moving Vehicle T2 - Intelligent Transportation Systems (ITSC), 2015 IEEE 18th International Conference on N2 - We present a method to detect starting, stopping and bending in intentions of pedestrians from a moving vehicle based on stereo-vision. The method focuses on urban scenarios where these pedestrian movements are common and may result in critical situations. Pedestrian intentions are determined by means of an image-based motion contour histogram of oriented gradient descriptor. It is based on silhouettes gathered from stereo data and does not require any compensation of appearance changes resulting from the ego-motion of a vehicle. Nevertheless, it covers small movements indicating a pedestrian’s intention. A linear support vector machine with probabilistic estimates is used for classification. We evaluated our method on the publicly available Daimler Pedestrian Path Prediction Benchmark Dataset containing detections of a stateof-the-art pedestrian detector. We detect a pedestrian’s stopping intention from 125 ms to 500 ms before standing still within an accuracy range of 80% to 100%. Bending in is detected from 320 ms to 570 ms after a first visible lateral body movement in the same accuracy range. The intention to cross the road from standing still (starting) is detected 250 ms after the first visible motion and, therefore, within the first step with an accuracy of 100%. KW - Image Motion Analysis KW - Stereo Image Processing KW - Pedestrian Safety KW - Bildfolgenanalyse Y1 - 2015 U6 - https://doi.org/10.1109/ITSC.2015.374 SP - 2317 EP - 2322 ER - TY - CHAP A1 - Goldhammer, Michael A1 - Köhler, Sebastian A1 - Doll, Konrad A1 - Sick, Bernhard T1 - Camera Based Pedestrian Path Prediction by Means of Polynomial Least-squares Approximation and Multilayer Perceptron Neural Networks T2 - SAI Intelligent Systems Conference (IntelliSys), 2015 N2 - This paper provides a method to forecast pedestrian trajectories by means of polynomial least-squares approximation and multilayer perceptron artificial neural networks for traffic safety applications. The approach uses camera based head tracking as input data to predict a continuous trajectory for a 2.5 s future time horizon. Training and test is performed using 1075 recorded tracks of uninstructed pedestrians in common public traffic situations, including many challenging scenarios like starting, stopping and bending in. The neural network approach has the ability to handle these scenes by learning a single implicit movement model independent of a specific motion type. The polynomial approximation provides an extraction of the principal information of the underlying time series in the form of the polynomial coefficients, high independence of input data, e.g., sample rate, and additional noise resistance. Our test results show 24% lower prediction errors for starting scenes and 29% for stopping scenes in comparison to a constant velocity Kalman filter. Approaches using MLP without polynomial input and the usage of Support Vector KW - Artificial Neural Networks KW - Polynomial Approximation KW - Path Prediction KW - Intelligent Vehicles KW - Neuronales Netz KW - Polynomapproximation Y1 - 2015 U6 - https://doi.org/10.1109/IntelliSys.2015.7361171 SP - 390 EP - 399 PB - IEEE ER - TY - JOUR A1 - Kröhn, Michael A1 - Eifert, Erik A1 - Reuter, Norbert A1 - Hahnle, Michael A1 - Prochus, Tobias A1 - Doll, Konrad ED - Albers, Thomas ED - Kegel, Gunther ED - Oprzynski, Jörn ED - Otten, Wilhelm ED - Steckenreiter, Thomas T1 - Gestenbasierte Prozessanalyse JF - atp edition N2 - Dieser Beitrag beschreibt ein intelligentes Assistenzsystem, das manuelle Montageprozesse beobachten und Auffälligkeiten im Ablauf identifizieren kann. Die mit der Montage verbundenen Handgriffe werden als eine Abfolge von Gesten erfasst. Aus den Zeitabständen zwischen den Handgriffen lassen sich statistische Aussagen gewinnen. So kann beispielsweise eine große Streuung auf Qualitäts- oder Konzeptprobleme hinweisen. Den Kern des Assistenzsystems bildet die Kinect von Microsoft. Die Autoren stellen das Konzept und erste Ergebnisse des Verfahrens vor. Y1 - 2017 VL - 2016 IS - 12 SP - 26 EP - 33 ER - TY - CHAP A1 - Hahnle, Michael A1 - Saxen, Frerk A1 - Doll, Konrad T1 - Erkennung von Fußgängern in Echtzeit auf FPGAs T2 - 49. MPC-Workshop, Mannheim, Deutschland KW - Fahrerassistenzsystem KW - Fußgänger Y1 - 2013 UR - https://www.mpc-gruppe.de/workshopbaende SN - 1868-9221 SP - 57 EP - 65 ER - TY - GEN A1 - Doll, Konrad A1 - Zindler, Klaus T1 - Hochautomatisiertes Fahren: Sensorik, Sensordatenverarbeitung und Fahrzeugführung T2 - Technologieforum Innovative Sensorik-Anwendungen im Automotive-Bereich N2 - Vortrag KW - Autonomes Fahrzeug KW - Sensortechnik KW - Vortrag Y1 - 2016 VL - 2016 ER - TY - CHAP A1 - Reichert, Hannes A1 - Lang, Lukas A1 - Rosch, Kevin A1 - Bogdoll, Daniel A1 - Doll, Konrad A1 - Sick, Bernhard A1 - Rellss, Hans-Christian A1 - Stiller, Christoph A1 - Zollner, J. Marius T1 - Towards Sensor Data Abstraction of Autonomous Vehicle Perception Systems T2 - 2021 IEEE International Smart Cities Conference (ISC2) KW - Autonomes Fahrzeug Y1 - 2021 U6 - https://doi.org/https://doi.org/10.1109/ISC253183.2021.9562912 SP - 1 EP - 4 PB - IEEE ER - TY - CHAP A1 - Lampert, Pascal A1 - Jung, Janis A1 - Hubert, Andreas A1 - Doll, Konrad T1 - Looping Through Color Space: A Simple Augmentation Method to Improve Biased Object Detection T2 - Lecture Notes in Networks and Systems KW - Objekterkennung Y1 - 2022 SN - 9789811916069 U6 - https://doi.org/10.1007/978-981-19-1607-6_61 SN - 2367-3370 SP - 687 EP - 698 PB - Springer Nature Singapore CY - Singapore ER - TY - CHAP A1 - Schreck, Steven A1 - Reichert, Hannes A1 - Hetzel, Manuel A1 - Doll, Konrad A1 - Sick, Bernhard T1 - Height Change Feature Based Free Space Detection T2 - 2023 11th International Conference on Control, Mechatronics and Automation (ICCMA) KW - Gabelstapler KW - Autonomes Fahrzeug Y1 - 2023 U6 - https://doi.org/https://doi.org/10.1109/ICCMA59762.2023.10374705 SP - 171 EP - 176 PB - IEEE ER - TY - CHAP A1 - Reichert, Hannes A1 - Hetzel, Manuel A1 - Hubert, Andreas A1 - Doll, Konrad A1 - Sick, Bernhard T1 - Sensor Equivariance: A Framework for Semantic Segmentation with Diverse Camera Models T2 - 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) KW - Bildverarbeitung KW - Sensor Y1 - 2024 U6 - https://doi.org/https://doi.org/10.1109/CVPRW63382.2024.00132 SP - 1254 EP - 1261 PB - IEEE ER - TY - JOUR A1 - Zindler, Klaus A1 - Doll, Konrad A1 - Huber, Bertold ED - WILEY-VCH, Verlag T1 - Sicher unterwegs - Fortschritte beim aktiven Fußgängerschutz JF - messtec drives Automation KW - aktiver Fußgängerschutz, automatische Brems- und Ausweichmanöver KW - Fahrerassistenzsystem KW - Fußgänger Y1 - 2017 UR - https://www.wileyindustrynews.com/restricted-files/161702 VL - 25 IS - 03 SP - 82 EP - 82 ER - TY - CHAP A1 - Köhler, Sebastian A1 - Doll, Konrad A1 - Kebinger, Sophie A1 - Schmitt, Daniel A1 - Kröhn, Michael A1 - Fried, Maik A1 - Börsig, Rainer T1 - Gestenerkennung in einem hochautomatisiert lernenden Assistenzsystem für manuelle Montageprozesse T2 - AUTOMATION 2018, VDI-Berichte 2330 KW - Assistenzsystem KW - Montage Y1 - 2018 SN - 978-3-18-092330-7 SP - 145 EP - 156 CY - Baden-Baden ER - TY - CHAP A1 - Bieshaar, Maarten A1 - Reitberger, Günther A1 - Zernetsch, Stefan A1 - Sick, Bernhard A1 - Fuchs, Erich A1 - Doll, Konrad T1 - Detecting intentions of vulnerable road users based on collective intelligence T2 - AAET – Automatisiertes und vernetztes Fahren N2 - Vulnerable road users (VRUs, i.e. cyclists and pedestrians) will play an important role in future traffic. To avoid accidents and achieve a highly efficient traffic flow, it is important to detect VRUs and to predict their intentions. In this article a holistic approach for detecting intentions of VRUs by cooperative methods is presented. The intention detection consists of basic movement primitive prediction, e.g. standing, moving, turning, and a forecast of the future trajectory. Vehicles equipped with sensors, data processing systems and communication abilities, referred to as intelligent vehicles, acquire and maintain a local model of their surrounding traffic environment, e.g. crossing cyclists. Heterogeneous, open sets of agents (cooperating and interacting vehicles, infrastructure, e.g. cameras and laser scanners, and VRUs equipped with smart devices and body-worn sensors) exchange information forming a multi-modal sensor system with the goal to reliably and robustly detect VRUs and their intentions under consideration of real time requirements and uncertainties. The resulting model allows to extend the perceptual horizon of the individual agent beyond their own sensory capabilities, enabling a longer forecast horizon. Concealments, implausibilities and inconsistencies are resolved by the collective intelligence of cooperating agents. Novel techniques of signal processing and modelling in combination with analytical and learning based approaches of pattern and activity recognition are used for detection, as well as intention prediction of VRUs. Cooperation, by means of probabilistic sensor and knowledge fusion, takes place on the level of perception and intention recognition. Based on the requirements of the cooperative approach for the communication a new strategy for an ad hoc network is proposed. The evaluation is done using real data gathered with a research vehicle, a research intersection with public traffic and mobile devices. KW - Verkehrsverhalten Y1 - 2017 SP - 67 EP - 87 ER - TY - CHAP A1 - Kreß, Viktor A1 - Jung, Janis A1 - Zernetsch, Stefan A1 - Doll, Konrad A1 - Sick, Bernhard T1 - Pose Based Start Intention Detection of Cyclists N2 - In this work, we present a new approach for start intention detection of cyclists based on 3D human pose estimation to increase their safety in road traffic. Start intention detection is realized using sequences of frame-wise estimated 3D poses. The poses were obtained by image sequences recorded by a stereo camera mounted behind the windshield of a moving vehicle. For training and evaluation, a dataset with 206 starting cyclists was created in real traffic. We demonstrate the advantages of this approach by comparing it to an existing, solely head trajectory based method. In particular, we investigate the performance for different observed time horizons ranging from 0.12 s up to 1.0 s as inputs for the two methods. This is of special importance for the protection of cyclists in road traffic, as they often only become visible to approaching vehicles shortly before dangerous situations occur. With an input length of 1.0 s the solely head trajectory based approach detects starting motions on average 0.834 s after the first motion of the bicycle with an F1-score of 97.5 %. The pose based approach outperforms these results by achieving the same F1-score 0.135 s earlier. The advantages of the pose based method become even more obvious with shorter input lengths. With an input length of 0.12 s, the head based approach achieves an F1-score of 93.5 % after 2.37 s, while the same score is reached after 0.668 s using poses. KW - Fahrerassistenzsystem KW - Fahrrad Y1 - 2019 U6 - https://doi.org/10.1109/ITSC.2019.8917215 SP - 2381 EP - 2386 PB - IEEE CY - Auckland ER - TY - CHAP A1 - Kreß, Viktor A1 - Jung, Janis A1 - Zernetsch, Stefan A1 - Doll, Konrad A1 - Sick, Bernhard ED - Draude, Claude ED - Lange, Martin ED - Sick, Bernhard T1 - Start Intention Detection of Cyclists using an LSTM Network T2 - INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik – Informatik für Gesellschaft (Workshop-Beiträge) N2 - In this article, we present an approach for start intention detection of cyclists based on their head trajectories. Therefore, we are using a network architecture based on Long Short-Term Memory (LSTM) cells, which is able to handle input sequences of different lengths. This is important because, for example, due to occlusions, cyclists often only become visible to approaching vehicles shortly before dangerous situations occur. Hence, the dependency of the results on the input sequence length is investigated. We use a dataset with 206 situations where cyclists were transitioning from waiting to moving that was recorded from a moving vehicle in inner-city traffic.With an input sequence length of 1.0 s we achieve an F1-score of 96.2% on average 0.680 s after the first movement of the bicycle. We obtain similar results for sequence lengths down to 0.2 s. For shorter sequences, the results regarding the F1-score and the mean detection time deteriorate considerably. KW - Fahrerassistenzsystem KW - Fahrrad Y1 - 2019 SN - 978-3-88579-689-3 U6 - https://doi.org/10.18420/inf2019_ws25 SN - 1617-5468 SP - 219 EP - 228 PB - Gesellschaft für Informatik e.V. CY - Bonn ER - TY - CHAP A1 - Reitberger, Günther A1 - Bieshaar, Maarten A1 - Zernetsch, Stefan A1 - Doll, Konrad A1 - Sick, Bernhard A1 - Fuchs, Erich T1 - Cooperative Tracking of Cyclists Based on Smart Devices and Infrastructure T2 - 21st International Conference on Intelligent Transportation Systems (ITSC) 2018 N2 - In future traffic scenarios, vehicles and other traffic participants will be interconnected and equipped with various types of sensors, allowing for cooperation based on data or information exchange. This article presents an approach to cooperative tracking of cyclists using smart devices and infrastructure-based sensors. A smart device is carried by the cyclists and an intersection is equipped with a wide angle stereo camera system. Two tracking models are presented and compared. The first model is based on the stereo camera system detections only, whereas the second model cooperatively combines the camera based detections with velocity and yaw rate data provided by the smart device. Our aim is to overcome limitations of tracking approaches based on single data sources. We show in numerical evaluations on scenes where cyclists are starting or turning right that the cooperation leads to an improvement in both the ability to keep track of a cyclist and the accuracy of the track particularly when it comes to occlusions in the visual system. We, therefore, contribute to the safety of vulnerable road users in future traffic. KW - Fahrerassistenzsystem KW - Fahrrad KW - Sensortechnik Y1 - 2018 U6 - https://doi.org/10.1109/ITSC.2018.8569267 PB - IEEE CY - Maui, HI, USA ER - TY - CHAP A1 - Zernetsch, Stefan A1 - Kohnen, Sascha A1 - Goldhammer, Michael A1 - Doll, Konrad A1 - Sick, Bernhard T1 - Trajectory prediction of cyclists using a physical model and an artificial neural network T2 - Intelligent Vehicles Symposium (IV), 2016 N2 - This article presents two methods for predicting the trajectories of cyclists at an intersection and compares them to a Kalman Filter (KF) approach. The first method uses a physical model of cyclists to predict their future position. The second method is based on a polynomial least-squares approximation in combination with a multilayer perceptron artificial neural network and is able to predict the future position of cyclists independent of their motion type such as “Starting”, “Stopping”, “Waiting” or “Passing”. To evaluate the performance of the methods, 566 tracks (394 for training, 172 for testing) of uninstructed cyclists were recorded at a public intersection using a wide angle stereo camera system and laser scanners. Using the tracks as input data, the future trajectory was predicted for a time horizon of 2.5 s. For starting motions the prediction using the physical model leads to 27% more accurate positions than the KF approach for a forecast horizon of 2.5 s. The neural network shows a 34% more accurate result for starting and stopping motions and a similar result for waiting and passing motions. KW - Kalman-Filter KW - Prognose Y1 - 2016 U6 - https://doi.org/10.1109/IVS.2016.7535484 SP - 833 EP - 838 ER - TY - CHAP A1 - Goldhammer, Michael A1 - Gerhard, Matthias A1 - Zernetsch, Stefan A1 - Doll, Konrad A1 - Brunsmann, Ulrich T1 - Early Prediction of a Pedestrian's Trajectory at Intersections T2 - 16th International IEEE Conference on Intelligent Transportation Systems - (ITSC 2013), The Hague, The Netherlands KW - Fahrerassistenzsystem KW - Fußgänger Y1 - 2013 SN - 978-1-4799-2914-6 U6 - https://doi.org/10.1109/ITSC.2013.6728239 SP - 237 EP - 242 PB - IEEE ER - TY - CHAP A1 - Kreß, Viktor A1 - Jung, Janis A1 - Zernetsch, Stefan A1 - Doll, Konrad A1 - Sick, Bernhard T1 - Human Pose Estimation in Real Traffic Scenes T2 - 2018 IEEE Symposium Series on Computational Intelligence (SSCI) KW - Autonomes Fahrzeug KW - Fahrerassistenzsystem KW - Fußgänger KW - Radfahrer Y1 - 2018 U6 - https://doi.org/10.1109/SSCI.2018.8628660 SP - 518 EP - 523 PB - IEEE CY - Bangalore, India ER - TY - CHAP A1 - Zernetsch, Stefan A1 - Kreß, Viktor A1 - Sick, Bernhard A1 - Doll, Konrad T1 - Early Start Intention Detection of Cyclists Using Motion History Images and a Deep Residual Network T2 - 2018 IEEE Intelligent Vehicles Symposium (IV) N2 - In this article, we present a novel approach to detect starting motions of cyclists in real world traffic scenarios based on Motion History Images (MHIs). The method uses a deep Convolutional Neural Network (CNN) with a residual network architecture (ResNet), which is commonly used in image classification and detection tasks. By combining MHIs with a ResNet classifier and performing a frame by frame classification of the MHIs, we are able to detect starting motions in image sequences. The detection is performed using a wide angle stereo camera system at an urban intersection. We compare our algorithm to an existing method to detect movement transitions of pedestrians that uses MHIs in combination with a Histograms of Oriented Gradients (HOG) like descriptor and a Support Vector Machine (SVM), which we adapted to cyclists. To train and evaluate the methods a dataset containing MHIs of 394 cyclist starting motions was created. The results show that both methods can be used to detect starting motions of cyclists. Using the SVM approach, we were able to safely detect starting motions 0.506 s on average after the bicycle starts moving with an F 1 -score of 97.7%. The ResNet approach achieved an F 1- score of 100% at an average detection time of 0.144 s. The ResNet approach outperformed the SVM approach in both robustness against false positive detections and detection time. KW - Fahrerassistenzsystem KW - Radfahrer KW - Fußgänger Y1 - 2018 U6 - https://doi.org/10.1109/IVS.2018.8500428 PB - IEEE CY - Changshu, China ER - TY - CHAP A1 - Zernetsch, Stefan A1 - Reichert, Hannes A1 - Kreß, Viktor A1 - Doll, Konrad A1 - Sick, Bernhard T1 - Trajectory Forecasts with Uncertainties of Vulnerable Road Users by Means of Neural Networks T2 - 2019 IEEE Intelligent Vehicles Symposium (IV) N2 - In this article, we present an approach to forecast trajectories of vulnerable road users (VRUs) including a numerical quantification of the uncertainty of the forecast. The uncertainty estimates are modeled as normal distributions by means of neural networks. Additionally, we present a method to evaluate the reliability of the forecasted uncertainty estimates, where we utilize quantile-quantile (Q-Q) plots, a graphical method to compare two distributions widely used in statistics. The positional accuracy is evaluated using Euclidean distances, in specific we use the average Euclidean error (AEE) and the average specific AEE (ASAEE). The model is trained and tested using a large dataset of 1311 cyclist trajectories, recorded at an urban intersection in real world traffic. Using this method, we achieve a similar positional accuracy compared to our previous work, where only positions are forecasted. The method is able to produce reliable uncertainty estimates for the motion types start, stop, turn left, and turn rightand produces underconfident uncertainty estimates for the motion types waitand move straight. Since uncertainties are not underestimated, the method can be used as a basis for trajectory planing in automated vehicles. KW - Fahrerassistenzsystem KW - Fahrrad KW - Autonomes Fahrzeug Y1 - 2019 U6 - https://doi.org/10.1109/IVS.2019.8814258 PB - IEEE CY - Paris, France ER - TY - JOUR A1 - Bieshaar, Maarten A1 - Zernetsch, Stefan A1 - Hubert, Andreas A1 - Sick, Bernhard A1 - Doll, Konrad T1 - Cooperative Starting Movement Detection of Cyclists Using Convolutional Neural Networks and a Boosted Stacking Ensemble JF - IEEE Transactions on Intelligent Vehicles N2 - In the future, vehicles and other traffic participants will be interconnected and equipped with various types of sensors, allowing for cooperation on different levels, such as situation prediction or intention detection. In this paper, we present a cooperative approach for starting movement detection of cyclists using a boosted stacking ensemble approach realizing feature- and decision-level cooperation. We introduce a novel method based on a three-dimensional convolutional neural network (CNN) to detect starting motions on image sequences by learning spatio-temporal features. The CNN is complemented by a smart device based starting movement detection originating from smart devices carried by the cyclist. Both model outputs are combined in a stacking ensemble approach using an extreme gradient boosting classifier resulting in a fast and yet robust cooperative starting movement detector. We evaluate our cooperative approach on real-world data originating from experiments with 49 test subjects consisting of 84 starting motions. KW - Fahrerassistenzsystem KW - Fahrrad KW - Sensortechnik Y1 - 2018 VL - 3 IS - 4 SP - 534 EP - 544 ER - TY - CHAP A1 - Eilbrecht, Jan A1 - Bieshaar, Maarten A1 - Zernetsch, Stefan A1 - Doll, Konrad A1 - Sick, Bernhard A1 - Stursberg, Olaf T1 - Model-predictive planning for autonomous vehicles anticipating intentions of vulnerable road users by artificial neural networks T2 - 2017 IEEE Symposium Series on Computational Intelligence (SSCI) KW - Fahrerassistenzsystem KW - Fußgänger KW - Radfahrer KW - Autonomes Fahrzeug Y1 - 2017 U6 - https://doi.org/10.1109/SSCI.2017.8285249 SP - 1 EP - 8 PB - IEEE CY - Honolulu, HI, USA ER - TY - JOUR A1 - Goldhammer, Michael A1 - Köhler, Sebastian A1 - Zernetsch, Stefan A1 - Doll, Konrad A1 - Sick, Bernhard A1 - Dietmayer, Klaus T1 - Intentions of Vulnerable Road Users – Detection and Forecasting by Means of Machine Learning JF - IEEE Transactions on Intelligent Transportation Systems KW - Fahrerassistenzsystem KW - Fußgänger KW - Radfahrer Y1 - 2019 UR - https://doi.org/10.1109/TITS.2019.2923319 U6 - https://doi.org/10.1109/TITS.2019.2923319 VL - 2020 IS - 21 / 7 SP - 3035 EP - 3045 ER - TY - CHAP A1 - Bieshaar, Maarten A1 - Zernetsch, Stefan A1 - Depping, Malte A1 - Sick, Bernhard A1 - Doll, Konrad T1 - Cooperative Starting Intention Detection of Cyclists based on Smart Devices and Infrastructure T2 - 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC) KW - Fahrerassistenzsystem KW - Radfahrer Y1 - 2017 U6 - https://doi.org/10.1109/ITSC.2017.8317691 SP - 1 EP - 8 PB - IEEE CY - Yokohama, Japan ER - TY - CHAP A1 - Bieshaar, Maarten A1 - Reitberger, Günther A1 - Kreß, Viktor A1 - Zernetsch, Stefan A1 - Doll, Konrad A1 - Fuchs, Erich A1 - Sick, Bernhard T1 - Highly Automated Learning for Improved Active Safety of Vulnerable Road Users T2 - ACM Chapters Computer Science in Cars Symposium (CSCS-17) KW - Fahrerassistenzsystem Y1 - 2017 VL - 2017 CY - München ER - TY - CHAP A1 - Kress, Viktor A1 - Schreck, Steven A1 - Zernetsch, Stefan A1 - Doll, Konrad A1 - Sick, Bernhard T1 - Pose Based Action Recognition of Vulnerable Road Users Using Recurrent Neural Networks T2 - 2020 IEEE Symposium Series on Computational Intelligence (SSCI) N2 - This work investigates the use of knowledge about three dimensional (3D) poses and Recurrent Neural Networks (RNNs) for detection of basic movements, such as wait, start, move, stop, turn left, turn right, and no turn, of pedestrians and cyclists in road traffic. The 3D poses model the posture of individual body parts of these vulnerable road users (VRUs). Fields of application for this technology are, for example, driver assistance systems or autonomous driving functions of vehicles. In road traffic, VRUs are often occluded and only become visible in the immediate vicinity of the vehicle. Hence, our proposed approach is able to classify basic movements after different and especially short observation periods. The classification will then be successively improved in case of a longer observation. This allows countermeasures, such as emergency braking, to be initiated early if necessary. The benefits of using 3D poses are evaluated by a comparison with a method based solely on the head trajectory. We also investigate the effects of different observation periods. Overall, knowledge about 3D poses improves the basic movement detection, in particular for short observation periods. The greatest improvements are achieved for the basic movements start, stop, turn left, and turn right. KW - Fahrerassistenzsystem KW - Autonomes Fahrzeug KW - Fußgänger KW - Fahrrad Y1 - 2020 SN - 978-1-7281-2548-0 U6 - https://doi.org/10.1109/SSCI47803.2020.9308462 SP - 2723 EP - 2730 PB - IEEE CY - Canberra, Australia ER - TY - CHAP A1 - Zernetsch, Stefan A1 - Schreck, Steven A1 - Kress, Viktor A1 - Doll, Konrad A1 - Sick, Bernhard T1 - Image Sequence Based Cyclist Action Recognition Using Multi-Stream 3D Convolution T2 - 2020 25th International Conference on Pattern Recognition (ICPR) N2 - In this article, we present an approach to detect basic movements of cyclists in real world traffic situations based on image sequences, optical flow (OF) sequences, and past positions using a multi-stream 3D convolutional neural network (3D-ConvNet) architecture. To resolve occlusions of cyclists by other traffic participants or road structures, we use a wide angle stereo camera system mounted at a heavily frequented public intersection. We created a large dataset consisting of 1,639 video sequences containing cyclists, recorded in real world traffic, resulting in over 1.1 million samples. Through modeling the cyclists' behavior by a state machine of basic cyclist movements, our approach takes every situation into account and is not limited to certain scenarios. We compare our method to an approach solely based on position sequences. Both methods are evaluated taking into account frame wise and scene wise classification results of basic movements, and detection times of basic movement transitions, where our approach outperforms the position based approach by producing more reliable detections with shorter detection times. Our code and parts of our dataset are made publicly available. KW - Fahrerassistenzsystem KW - Radfahrer Y1 - 2020 UR - https://ieeexplore.ieee.org/document/9413233 ER - TY - CHAP A1 - Kreß, Viktor A1 - Zernetsch, Stefan A1 - Doll, Konrad A1 - Sick, Bernhard T1 - Pose Based Trajectory Forecast of Vulnerable Road Users Using Recurrent Neural Networks T2 - ICPR 2021: Pattern Recognition. ICPR International Workshops and Challenges N2 - In this work, we use Recurrent Neural Networks (RNNs) in form of Gated Recurrent Unit (GRU) networks to forecast trajectories of vulnerable road users (VRUs), such as pedestrians and cyclists, in road traffic utilizing the past trajectory and 3D poses as input. The 3D poses represent the postures and movements of limbs and torso and contain early indicators for the transition between motion types, e.g. wait, start, move, and stop. VRUs often only become visible from the perspective of an approaching vehicle shortly before dangerous situations occur. Therefore, a network architecture is required which is able to forecast trajectories after short time periods and is able to improve the forecasts in case of longer observations. This motivates us to use GRU networks, which are able to use time series of varying duration as inputs, and to investigate the effects of different observation periods on the forecasting results. Our approach is able to make reasonable forecasts even for short observation periods. The use of poses improves the forecasting accuracy, especially for short observation periods compared to a solely head trajectory based approach. Different motion types benefit to different extent from the use of poses and longer observation periods. KW - 3D human trajectory forecast KW - Vulnerable road users KW - 3D body pose KW - Fahrerassistenzsystem KW - Fußgänger KW - Radfahrer Y1 - 2020 SN - 978-3-030-68763-2 U6 - https://doi.org/https://doi.org/10.1007/978-3-030-68763-2_5 SP - 57 EP - 71 PB - Springer International Publishing CY - Cham ER - TY - GEN A1 - Doll, Konrad A1 - Köhler, Sebastian A1 - Goldhammer, Michael A1 - Brunsmann, Ulrich T1 - Pedestrian Movement Modelling and Trajectory Prediction at Urban Intersections T2 - International IEEE Conference on Intelligent Transportation Systems (ITSC 2015) N2 - Vortrag KW - Fahrerassistenzsystem KW - Fußgänger Y1 - 2015 CY - Las Palmas de Gran Canaria, Spain ER - TY - CHAP A1 - Hubert, Andreas A1 - Zernetsch, Stefan A1 - Doll, Konrad A1 - Sick, Bernhard T1 - Cyclists starting behavior at intersections T2 - 2017 IEEE Intelligent Vehicles Symposium (IV) KW - Fahrerassistenzsystem KW - Radfahrer Y1 - 2017 U6 - https://doi.org/10.1109/IVS.2017.7995856 SP - 1071 EP - 1077 PB - IEEE CY - Los Angeles, CA, USA ER - TY - JOUR A1 - Kröhn, Michael A1 - Reuter, Norbert A1 - Hahnle, Michael A1 - Prochus, Tobias A1 - Doll, Konrad T1 - Gestengesteuerte Prozessanalyse JF - atp edition - Automatisierungstechnische Praxis KW - Prozessanalyse Y1 - 2016 VL - 58 IS - 12 SP - 26 EP - 33 ER - TY - CHAP A1 - Zernetsch, Stefan A1 - Reichert, Hannes A1 - Kress, Viktor A1 - Doll, Konrad A1 - Sick, Bernhard T1 - A Holistic View on Probabilistic Trajectory Forecasting – Case Study. Cyclist Intention Detection T2 - 2022 IEEE Intelligent Vehicles Symposium (IV) KW - Autonomes Fahrzeug KW - Radfahrer Y1 - 2022 U6 - https://doi.org/https://doi.org/10.1109/IV51971.2022.9827220 SP - 265 EP - 272 PB - IEEE ER - TY - CHAP A1 - Bieshaar, Maarten A1 - Zernetsch, Stefan A1 - Riepe, Katharina A1 - Doll, Konrad A1 - Sick, Bernhard T1 - Cyclist Motion State Forecasting - Going beyond Detection T2 - 2021 IEEE Symposium Series on Computational Intelligence (SSCI) KW - Autonomes Fahrzeug KW - Radfahrer Y1 - 2021 U6 - https://doi.org/10.1109/SSCI50451.2021.9660151 SP - 1 EP - 8 PB - IEEE ER - TY - CHAP A1 - Schneegans, Jan A1 - Eilbrecht, Jan A1 - Zernetsch, Stefan A1 - Bieshaar, Maarten A1 - Doll, Konrad A1 - Stursberg, Olaf A1 - Sick, Bernhard T1 - Probabilistic VRU Trajectory Forecasting for Model-Predictive Planning A Case Study: Overtaking Cyclists T2 - 2021 IEEE Intelligent Vehicles Symposium Workshops (IV Workshops) KW - Fahrerassistenzsystem KW - Radfahrer KW - Autonomes Fahrzeug Y1 - 2021 U6 - https://doi.org/10.1109/IVWorkshops54471.2021.9669208 SP - 272 EP - 279 PB - IEEE ER - TY - JOUR A1 - Kress, Viktor A1 - Jeske, Fabian A1 - Zernetsch, Stefan A1 - Doll, Konrad A1 - Sick, Bernhard T1 - Pose and Semantic Map Based Probabilistic Forecast of Vulnerable Road Users’ Trajectories JF - IEEE Transactions on Intelligent Vehicles KW - Fahrerassistenzsystem KW - Autonomes Fahrzeug Y1 - 2023 U6 - https://doi.org/10.1109/TIV.2022.3149624 SN - 2379-8904 VL - 8 IS - 3 SP - 2592 EP - 2603 PB - Institute of Electrical and Electronics Engineers (IEEE) ER - TY - CHAP A1 - Zernetsch, Stefan A1 - Trupp, Oliver A1 - Kress, Viktor A1 - Doll, Konrad A1 - Sick, Bernhard T1 - Cyclist Trajectory Forecasts by Incorporation of Multi-View Video Information T2 - 2021 IEEE International Smart Cities Conference (ISC2) KW - Autonomes Fahrzeug KW - Radfahrer Y1 - 2021 U6 - https://doi.org/10.1109/ISC253183.2021.9562857 SP - 1 EP - 7 PB - IEEE ER - TY - CHAP A1 - Jung, Janis A1 - Hubert, Andreas A1 - Doll, Konrad A1 - Kröhn, Michael A1 - Stadler, Jochen T1 - Prozessinnovation T2 - Wissenstransfer im Spannungsfeld von Autonomisierung und Fachkräftemangel, Tagungsband, 18. AALE-Konferenz, Pforzheim, 09.03.-11.03.2022 N2 - Manuelle Montageprozesse sind nach wie vor unverzichtbar in vielen Bereichen der produzierenden Industrie. Vor allem die Qualitätskontrolle, sowie das Einlernen neuer Mitarbeitenden stellen Betriebe durch die voranschreitende Digitalisierung vor neue Herausforderungen. Assistenzsysteme können hier helfen, die Lücke zwischen Anforderungen und Qualifikation zu überbrücken. Wir stellen einen Ansatz zur intelligenten Assistenz vor, welcher auf einer kamerabasierten Erkennung von Arbeitsabläufen mit Hilfe von Methoden des maschinellen Lernens beruht. Das Assistenzsystem erzeugt automatisiert Hilfsmaterial zur Unterstützung der Werkenden. Zusätzlich zur Darstellung der technischen Aspekte, werden psychologische Aspekte, wie Akzeptanz und Motivation untersucht. KW - Assistenzsystem KW - Montage KW - Maschinelles Lernen Y1 - 2022 U6 - https://doi.org/10.33968/2022.20 PB - Hochschule für Technik, Wirtschaft und Kultur Leipzig ER - TY - CHAP A1 - Serfling, Benjamin A1 - Reichert, Hannes A1 - Bayerlein, Lorenzo A1 - Doll, Konrad A1 - Radkhah-Lens, Kati T1 - LiDAR Based Semantic Perception for Forklifts in Outdoor Environments T2 - 2025 IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI) KW - Gabelstapler KW - Autonomes Fahrzeug Y1 - 2025 U6 - https://doi.org/https://doi.org/10.1109/SOLI66289.2025.11396313 SP - 40 EP - 45 PB - IEEE ER - TY - CHAP A1 - Hubert, Andreas A1 - Guo, Chenxi A1 - Doll, Konrad A1 - Sick, Bernhard T1 - Improving Fast 6D Pose Estimation with Adaptive Model Fusion T2 - 2025 5th International Conference on Machine Learning and Intelligent Systems Engineering (MLISE) KW - Maschinelles Lernen KW - Deep Learning KW - Montagezelle Y1 - 2025 U6 - https://doi.org/https://doi.org/10.1109/MLISE66443.2025.11100239 SP - 58 EP - 63 PB - IEEE ER -