@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} }