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 -