@inproceedings{KressJungZernetschetal.2018, author = {Kreß, Viktor and Jung, Janis and Zernetsch, Stefan and Doll, Konrad and Sick, Bernhard}, title = {Human Pose Estimation in Real Traffic Scenes}, series = {2018 IEEE Symposium Series on Computational Intelligence (SSCI)}, booktitle = {2018 IEEE Symposium Series on Computational Intelligence (SSCI)}, publisher = {IEEE}, address = {Bangalore, India}, doi = {10.1109/SSCI.2018.8628660}, pages = {518 -- 523}, year = {2018}, subject = {Autonomes Fahrzeug}, language = {en} } @inproceedings{KressZernetschDolletal.2019, author = {Kreß, Viktor and Zernetsch, Stefan and Doll, Konrad and Sick, Bernhard}, title = {Pose Based Trajectory Forecast of Vulnerable Road Users}, series = {IEEE Symposium Series on Computational Intelligence (SSCI)}, volume = {2019}, booktitle = {IEEE Symposium Series on Computational Intelligence (SSCI)}, publisher = {IEEE}, address = {Xiamen, China}, doi = {10.1109/SSCI44817.2019.9003023}, pages = {1200 -- 1207}, year = {2019}, abstract = {In this article, we investigate the use of 3D human poses for trajectory forecasting of vulnerable road users (VRUs), such as pedestrians and cyclists, in road traffic. The forecast is based on past movements of the respective VRU and an important aspect in driver assistance systems and autonomous driving, which both could increase VRU safety. The 3D poses represent the entire body posture of the VRUs and can therefore provide important indicators for trajectory forecasting. In particular, we investigate the influence of different joint combinations and input sequence lengths of past movements on the accuracy of trajectory forecasts for pedestrians and cyclists. In addition, we divide VRU movements into the motion types wait, start, move, and stop and evaluate the results separately for each of them. Comparing it to an existing, solely head based trajectory forecast, we show the advantages of using 3D poses. With an input sequence length of 1.0 s, the forecasting error is reduced by 17.9 \% for starting, 8.18 \% for moving, and 11.0 \% for stopping cyclists. For pedestrians, the error is reduced by 6.93 \%, 2.73 \%, and 5.02 \%, respectively. With shorter input sequences, the improvements over the solely head based method remain for cyclists and even increase for pedestrians.}, subject = {Fahrerassistenzsystem}, language = {en} } @inproceedings{ZernetschKressSicketal.2018, author = {Zernetsch, Stefan and Kreß, Viktor and Sick, Bernhard and Doll, Konrad}, title = {Early Start Intention Detection of Cyclists Using Motion History Images and a Deep Residual Network}, series = {2018 IEEE Intelligent Vehicles Symposium (IV)}, booktitle = {2018 IEEE Intelligent Vehicles Symposium (IV)}, publisher = {IEEE}, address = {Changshu, China}, doi = {10.1109/IVS.2018.8500428}, year = {2018}, abstract = {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.}, subject = {Fahrerassistenzsystem}, language = {en} } @inproceedings{ZernetschReichertKressetal.2019, author = {Zernetsch, Stefan and Reichert, Hannes and Kreß, Viktor and Doll, Konrad and Sick, Bernhard}, title = {Trajectory Forecasts with Uncertainties of Vulnerable Road Users by Means of Neural Networks}, series = {2019 IEEE Intelligent Vehicles Symposium (IV)}, booktitle = {2019 IEEE Intelligent Vehicles Symposium (IV)}, publisher = {IEEE}, address = {Paris, France}, doi = {10.1109/IVS.2019.8814258}, year = {2019}, abstract = {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.}, subject = {Fahrerassistenzsystem}, language = {en} } @inproceedings{KressJungZernetschetal.2019, author = {Kreß, Viktor and Jung, Janis and Zernetsch, Stefan and Doll, Konrad and Sick, Bernhard}, title = {Start Intention Detection of Cyclists using an LSTM Network}, series = {INFORMATIK 2019: 50 Jahre Gesellschaft f{\"u}r Informatik - Informatik f{\"u}r Gesellschaft (Workshop-Beitr{\"a}ge)}, booktitle = {INFORMATIK 2019: 50 Jahre Gesellschaft f{\"u}r Informatik - Informatik f{\"u}r Gesellschaft (Workshop-Beitr{\"a}ge)}, editor = {Draude, Claude and Lange, Martin and Sick, Bernhard}, publisher = {Gesellschaft f{\"u}r Informatik e.V.}, address = {Bonn}, isbn = {978-3-88579-689-3}, issn = {1617-5468}, doi = {10.18420/inf2019_ws25}, pages = {219 -- 228}, year = {2019}, abstract = {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.}, subject = {Fahrerassistenzsystem}, language = {en} } @inproceedings{KressJungZernetschetal.2019, author = {Kreß, Viktor and Jung, Janis and Zernetsch, Stefan and Doll, Konrad and Sick, Bernhard}, title = {Pose Based Start Intention Detection of Cyclists}, publisher = {IEEE}, address = {Auckland}, doi = {10.1109/ITSC.2019.8917215}, pages = {2381 -- 2386}, year = {2019}, abstract = {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.}, subject = {Fahrerassistenzsystem}, language = {en} } @inproceedings{BieshaarReitbergerKressetal.2017, author = {Bieshaar, Maarten and Reitberger, G{\"u}nther and Kreß, Viktor and Zernetsch, Stefan and Doll, Konrad and Fuchs, Erich and Sick, Bernhard}, title = {Highly Automated Learning for Improved Active Safety of Vulnerable Road Users}, series = {ACM Chapters Computer Science in Cars Symposium (CSCS-17)}, volume = {2017}, booktitle = {ACM Chapters Computer Science in Cars Symposium (CSCS-17)}, address = {M{\"u}nchen}, year = {2017}, subject = {Fahrerassistenzsystem}, language = {en} } @inproceedings{KressZernetschDolletal.2020, author = {Kreß, Viktor and Zernetsch, Stefan and Doll, Konrad and Sick, Bernhard}, title = {Pose Based Trajectory Forecast of Vulnerable Road Users Using Recurrent Neural Networks}, series = {ICPR 2021: Pattern Recognition. ICPR International Workshops and Challenges}, booktitle = {ICPR 2021: Pattern Recognition. ICPR International Workshops and Challenges}, publisher = {Springer International Publishing}, address = {Cham}, isbn = {978-3-030-68763-2}, doi = {https://doi.org/10.1007/978-3-030-68763-2_5}, pages = {57 -- 71}, year = {2020}, abstract = {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.}, subject = {Fahrerassistenzsystem}, language = {en} } @inproceedings{KressSchreckZernetschetal.2020, author = {Kress, Viktor and Schreck, Steven and Zernetsch, Stefan and Doll, Konrad and Sick, Bernhard}, title = {Pose Based Action Recognition of Vulnerable Road Users Using Recurrent Neural Networks}, series = {2020 IEEE Symposium Series on Computational Intelligence (SSCI)}, booktitle = {2020 IEEE Symposium Series on Computational Intelligence (SSCI)}, publisher = {IEEE}, address = {Canberra, Australia}, isbn = {978-1-7281-2548-0}, doi = {10.1109/SSCI47803.2020.9308462}, pages = {2723 -- 2730}, year = {2020}, abstract = {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.}, subject = {Fahrerassistenzsystem}, language = {en} } @inproceedings{ZernetschSchreckKressetal.2020, author = {Zernetsch, Stefan and Schreck, Steven and Kress, Viktor and Doll, Konrad and Sick, Bernhard}, title = {Image Sequence Based Cyclist Action Recognition Using Multi-Stream 3D Convolution}, series = {2020 25th International Conference on Pattern Recognition (ICPR)}, booktitle = {2020 25th International Conference on Pattern Recognition (ICPR)}, year = {2020}, abstract = {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.}, subject = {Fahrerassistenzsystem}, language = {en} } @phdthesis{Kress2022, author = {Kreß, Viktor}, title = {Posenbasierte Intentionserkennung von ungesch{\"u}tzten Verkehrsteilnehmern aus einem Fahrzeug}, school = {Technische Hochschule Aschaffenburg}, year = {2022}, subject = {Fahrerassistenzsystem}, language = {de} } @inproceedings{FischerKressRieder2016, author = {Fischer, Peter and Kreß, Viktor and Rieder, Maximilian}, title = {Universelle Softwarearchitektur f{\"u}r die autonome Exploration mit mobilen Robotern am Beispiel des ROS-basierten EtaBot}, series = {Tagungsband AALE 2016: 13. Fachkonferenz}, booktitle = {Tagungsband AALE 2016: 13. Fachkonferenz}, publisher = {DIV Deutscher Industrieverlag}, address = {L{\"u}beck}, pages = {85 -- 94}, year = {2016}, subject = {Robotik}, language = {de} }