1.4k citations · 3k across the 64 of their papers we have counts for
11 papers · 1 filter
Group Regression for Query Based Object Detection and Tracking
Felicia Ruppel, Florian Faion, Claudius Gläser +1
Group regression is commonly used in 3D object detection to predict box parameters of similar classes in a joint head, aiming to benefit from similarities while separating highly d…
User Feedback and Sample Weighting for Ill-Conditioned Hand-Eye Calibration
Markus Horn, Thomas Wodtko, Michael Buchholz +1
Hand-eye calibration is an important and extensively researched method for calibrating rigidly coupled sensors, solely based on estimates of their motion. Due to the geometric stru…
Joint Out-of-Distribution Detection and Uncertainty Estimation for Trajectory Prediction
Julian Wiederer, Julian Schmidt, Ulrich Kressel +2
Despite the significant research efforts on trajectory prediction for automated driving, limited work exists on assessing the prediction reliability. To address this limitation we…
Advancing Frame-Dropping in Multi-Object Tracking-by-Detection Systems Through Event-Based Detection Triggering
Matti Henning, Michael Buchholz, Klaus Dietmayer
With rising computational requirements modern automated vehicles (AVs) often consider trade-offs between energy consumption and perception performance, potentially jeopardizing the…
Energy-based Detection of Adverse Weather Effects in LiDAR Data
Aldi Piroli, Vinzenz Dallabetta, Johannes Kopp +3
Autonomous vehicles rely on LiDAR sensors to perceive the environment. Adverse weather conditions like rain, snow, and fog negatively affect these sensors, reducing their reliabili…
Data-Free Backbone Fine-Tuning for Pruned Neural Networks
Adrian Holzbock, Achyut Hegde, Klaus Dietmayer +1
Model compression techniques reduce the computational load and memory consumption of deep neural networks. After the compression operation, e.g. parameter pruning, the model is nor…
RT-K-Net: Revisiting K-Net for Real-Time Panoptic Segmentation
Markus Schön, Michael Buchholz, Klaus Dietmayer
Panoptic segmentation is one of the most challenging scene parsing tasks, combining the tasks of semantic segmentation and instance segmentation. While much progress has been made,…
RESET: Revisiting Trajectory Sets for Conditional Behavior Prediction
Julian Schmidt, Pascal Huissel, Julian Wiederer +3
It is desirable to predict the behavior of traffic participants conditioned on different planned trajectories of the autonomous vehicle. This allows the downstream planner to estim…
The Impact of Frame-Dropping on Performance and Energy Consumption for Multi-Object Tracking
Matti Henning, Michael Buchholz, Klaus Dietmayer
The safety of automated vehicles (AVs) relies on the representation of their environment. Consequently, state-of-the-art AVs employ potent sensor systems to achieve the best possib…
Exploring Navigation Maps for Learning-Based Motion Prediction
Julian Schmidt, Julian Jordan, Franz Gritschneder +2
The prediction of surrounding agents' motion is a key for safe autonomous driving. In this paper, we explore navigation maps as an alternative to the predominant High Definition (H…
SCENE: Reasoning about Traffic Scenes using Heterogeneous Graph Neural Networks
Thomas Monninger, Julian Schmidt, Jan Rupprecht +5
Understanding traffic scenes requires considering heterogeneous information about dynamic agents and the static infrastructure. In this work we propose SCENE, a methodology to enco…