Optical flow estimation is very challenging in situations with transparent or occluded objects. In this work, we address these challenges at the task level by introducing Amodal Optical Flow, which integrates optical flow with amodal perception. Instead of only representing the visible regions, we define amodal optical flow as a multi-layered pixel-level motion field that encompasses both visible and occluded regions of the scene. To facilitate research on this new task, we extend the AmodalSynthDrive dataset to include pixel-level labels for amodal optical flow estimation. We present several strong baselines, along with the Amodal Flow Quality metric to quantify the performance in an interpretable manner. Furthermore, we propose the novel AmodalFlowNet as an initial step toward addressing this task. AmodalFlowNet consists of a transformer-based cost-volume encoder paired with a recurrent transformer decoder which facilitates recurrent hierarchical feature propagation and amodal semantic grounding. We demonstrate the tractability of amodal optical flow in extensive experiments and show its utility for downstream tasks such as panoptic tracking. We make the dataset, code, and trained models publicly available at http://amodal-flow.cs.uni-freiburg.de.

Adversarial attacks refer to an intentional manipulation of the visual input of a deep neural network (DNN). Such a modification can be aligned as an adversarial perturbation able to provoke critical failures of a detection model. Recent research has shown that DNNs are vulnerable against such adversarial attacks, especially in the field of digital attacks. In this work, to demonstrate the threat of adversarial attacks in a non-digital, real-world autonomous driving setting, an optimization pipeline is implemented to generate physical attacks. As the target model, the YOLOv4 algorithm model is chosen to validate the results based on a state-of-the-art object detector. The proposed method improves the success rate of attacks by using an adapted adversarial loss to increase the amount of information during training. In the customized optimization function of this work, several cost terms, including vector distance norms, total-variation loss, and grey-scale loss, are defined to shape the design of the attack. The combination and outbalancing of these terms result in inconspicuous adversarial attacks. Experiments are conducted to validate the approach. The adversarial attacks generated by this approach successfully reduce the confidence by more than 50% in a real indoor and outdoor testing scenes.

Cooperative driving has caught the interest of many research centers around the world as it introduced a solution to many problems in traffic and especially the reduction of accidents. One of the cooperative driving applications is vehicle platooning, which has proven its ability to increase road capacity and decrease fuel consumption. As the platoon has to have a rules of organization to form and split safely, this paper introduces a dynamic platoon model and protocols with different control techniques applied on different sub-systems in the model. Additionally, the basic platooning maneuvers are governed by applying certain protocols to organize the formation of platoon in a safe manner. Several tests on the platooning model and maneuvering controls have been performed from real-life scenarios and using real-vehicle data and a software in the loop to verify the results and evaluate the performance of the proposed approaches. The results prove an acceptable performance of the control techniques applied on the platooning model.