1 code implementation • 24 Apr 2024 • Michael Kösel, Marcel Schreiber, Michael Ulrich, Claudius Gläser, Klaus Dietmayer
LiDAR-based 3D object detection has become an essential part of automated driving due to its ability to localize and classify objects precisely in 3D.
no code implementations • 1 Apr 2024 • Florian Kraus, Nicolas Scheiner, Werner Ritter, Klaus Dietmayer
In this article, we present a dataset with detailed manual annotations for different kinds of ghost detections.
no code implementations • 13 Nov 2023 • Johannes Kopp, Dominik Kellner, Aldi Piroli, Vinzenz Dallabetta, Klaus Dietmayer
The unique properties of radar sensors, such as their robustness to adverse weather conditions, make them an important part of the environment perception system of autonomous vehicles.
no code implementations • 16 Oct 2023 • Mathijs R. van Geerenstein, Felicia Ruppel, Klaus Dietmayer, Dariu M. Gavrila
In experiments, we outperform the state of the art in transformer-based LiDAR object detection on the competitive nuScenes benchmark and showcase the benefits of input-dependent multimodal query initialization, while being more efficient than the available alternatives for LiDAR-camera initialization.
no code implementations • 2 Oct 2023 • Aldi Piroli, Vinzenz Dallabetta, Johannes Kopp, Marc Walessa, Daniel Meissner, Klaus Dietmayer
In this way, the detected objects are less affected by the adverse weather in the scene, resulting in a more accurate perception of the environment.
no code implementations • 2 Oct 2023 • Aldi Piroli, Vinzenz Dallabetta, Johannes Kopp, Marc Walessa, Daniel Meissner, Klaus Dietmayer
LiDAR-based 3D object detectors have achieved unprecedented speed and accuracy in autonomous driving applications.
no code implementations • 28 Aug 2023 • Felicia Ruppel, Florian Faion, Claudius Gläser, Klaus Dietmayer
We show that the proposed method is applicable to many existing transformer based perception approaches and can bring potential benefits.
1 code implementation • 22 Jun 2023 • Adrian Holzbock, Achyut Hegde, Klaus Dietmayer, Vasileios Belagiannis
In particular, the pruned network backbone is trained with synthetically generated images, and our proposed intermediate supervision to mimic the unpruned backbone's output feature map.
1 code implementation • 25 May 2023 • Aldi Piroli, Vinzenz Dallabetta, Johannes Kopp, Marc Walessa, Daniel Meissner, Klaus Dietmayer
Autonomous vehicles rely on LiDAR sensors to perceive the environment.
1 code implementation • 2 May 2023 • Markus Schön, Michael Buchholz, Klaus Dietmayer
Our resulting RT-K-Net sets a new state-of-the-art performance for real-time panoptic segmentation methods on the Cityscapes dataset and shows promising results on the challenging Mapillary Vistas dataset.
no code implementations • 12 Apr 2023 • Julian Schmidt, Pascal Huissel, Julian Wiederer, Julian Jordan, Vasileios Belagiannis, Klaus Dietmayer
It is desirable to predict the behavior of traffic participants conditioned on different planned trajectories of the autonomous vehicle.
1 code implementation • 12 Apr 2023 • Julian Schmidt, Thomas Monninger, Julian Jordan, Klaus Dietmayer
In contrast to the Euclidean Miss Rate, qualitative results show that LMR yields misses for sequences where predictions are located on wrong lanes.
1 code implementation • 16 Mar 2023 • Johannes Kopp, Dominik Kellner, Aldi Piroli, Klaus Dietmayer
Because there is no suitable public data set in which clutter is annotated, we design a method to automatically generate the respective labels.
no code implementations • 20 Feb 2023 • Adrian Holzbock, Nicolai Kern, Christian Waldschmidt, Klaus Dietmayer, Vasileios Belagiannis
We present a joint camera and radar approach to enable autonomous vehicles to understand and react to human gestures in everyday traffic.
1 code implementation • 13 Feb 2023 • Julian Schmidt, Julian Jordan, Franz Gritschneder, Thomas Monninger, Klaus Dietmayer
Combined with our method for knowledge distillation, we achieve results that are close to the original HD map-reliant models.
1 code implementation • 9 Jan 2023 • Thomas Monninger, Julian Schmidt, Jan Rupprecht, David Raba, Julian Jordan, Daniel Frank, Steffen Staab, Klaus Dietmayer
In this work we propose SCENE, a methodology to encode diverse traffic scenes in heterogeneous graphs and to reason about these graphs using a heterogeneous Graph Neural Network encoder and task-specific decoders.
Ranked #1 on Node Classification on BGS
no code implementations • 26 Oct 2022 • Felicia Ruppel, Florian Faion, Claudius Gläser, Klaus Dietmayer
Transformers have recently been utilized to perform object detection and tracking in the context of autonomous driving.
no code implementations • 30 Sep 2022 • Felicia Ruppel, Florian Faion, Claudius Gläser, Klaus Dietmayer
We present TransLPC, a novel detection model for large point clouds that is based on a transformer architecture.
no code implementations • 11 Jul 2022 • Aldi Piroli, Vinzenz Dallabetta, Marc Walessa, Daniel Meissner, Johannes Kopp, Klaus Dietmayer
We address this problem by presenting a two-step approach for the detection of condensed vehicle gas exhaust.
1 code implementation • 1 Jul 2022 • Arij Bouazizi, Adrian Holzbock, Ulrich Kressel, Klaus Dietmayer, Vasileios Belagiannis
Given a stacked sequence of 3D body poses, a spatial-MLP extracts fine grained spatial dependencies of the body joints.
Ranked #8 on Human Pose Forecasting on Human3.6M
2 code implementations • ICCV 2021 • Markus Schön, Michael Buchholz, Klaus Dietmayer
We define monocular geometric scene understanding as the combination of two known tasks: Panoptic segmentation and self-supervised monocular depth estimation.
no code implementations • 15 Jun 2022 • Thomas Griebel, Johannes Müller, Paul Geisler, Charlotte Hermann, Martin Herrmann, Michael Buchholz, Klaus Dietmayer
Therefore, this work presents a novel method for self-assessment of single-object tracking in clutter based on Kalman filtering and subjective logic.
no code implementations • 10 Jun 2022 • Julian Schmidt, Julian Jordan, David Raba, Tobias Welz, Klaus Dietmayer
Additionally, an analysis of the datasets and an evaluation of the prediction models based on the agent dynamics is provided.
no code implementations • 31 May 2022 • Felicia Ruppel, Florian Faion, Claudius Gläser, Klaus Dietmayer
The model utilizes a cross- and a self-attention mechanism and is applicable to lidar data in an automotive context, as well as other data types, such as radar.
no code implementations • 24 May 2022 • Aldi Piroli, Vinzenz Dallabetta, Marc Walessa, Daniel Meissner, Johannes Kopp, Klaus Dietmayer
Second, we introduce a point cloud augmentation process that can be used to add gas exhaust to datasets recorded in good weather conditions.
1 code implementation • 25 Apr 2022 • Adrian Holzbock, Alexander Tsaregorodtsev, Youssef Dawoud, Klaus Dietmayer, Vasileios Belagiannis
Gesture recognition is essential for the interaction of autonomous vehicles with humans.
Ranked #1 on Skeleton Based Action Recognition on Drive&Act
1 code implementation • 9 Feb 2022 • Julian Schmidt, Julian Jordan, Franz Gritschneder, Klaus Dietmayer
We therefore propose CRAT-Pred, a multi-modal and non-rasterization-based trajectory prediction model, specifically designed to effectively model social interactions between vehicles, without relying on map information.
Ranked #174 on Motion Forecasting on Argoverse CVPR 2020
1 code implementation • 12 Jan 2022 • Thomas Wodtko, Markus Horn, Michael Buchholz, Klaus Dietmayer
In this work, we present an approach for monocular hand-eye calibration from per-sensor ego-motion based on dual quaternions.
no code implementations • 20 Sep 2021 • Thomas Griebel, Dominik Authaler, Markus Horn, Matti Henning, Michael Buchholz, Klaus Dietmayer
On the one hand, radar offers a direct measurement of the radial velocity of targets in the environment.
no code implementations • 27 Aug 2021 • Johannes Kopp, Dominik Kellner, Aldi Piroli, Klaus Dietmayer
Each of these effects is described both theoretically and regarding a method for identifying the corresponding clutter detections.
1 code implementation • 19 Jul 2021 • Carsten Ditzel, Klaus Dietmayer
Autonomous systems require a continuous and dependable environment perception for navigation and decision-making, which is best achieved by combining different sensor types.
no code implementations • 16 Jul 2021 • Nico Engel, Vasileios Belagiannis, Klaus Dietmayer
We present a vehicle self-localization method using point-based deep neural networks.
no code implementations • 3 Mar 2021 • Markus Horn, Ole Schumann, Markus Hahn, Jürgen Dickmann, Klaus Dietmayer
A complete overview of the surrounding vehicle environment is important for driver assistance systems and highly autonomous driving.
1 code implementation • 27 Jan 2021 • Markus Horn, Thomas Wodtko, Michael Buchholz, Klaus Dietmayer
Further, our online calibration approach is tested on the KITTI odometry dataset, which provides data of a lidar and two stereo camera systems mounted on a vehicle.
Robotics
no code implementations • 18 Dec 2020 • Di Feng, Zining Wang, Yiyang Zhou, Lars Rosenbaum, Fabian Timm, Klaus Dietmayer, Masayoshi Tomizuka, Wei Zhan
As a result, an in-depth evaluation among different object detection methods remains challenging, and the training process of object detectors is sub-optimal, especially in probabilistic object detection.
no code implementations • 7 Dec 2020 • Maximilian Graf, Oliver Speidel, Jona Ruof, Klaus Dietmayer
It is well known that motion planning is a key technology for autonomous driving.
Autonomous Driving Motion Planning Robotics
1 code implementation • 20 Nov 2020 • Di Feng, Ali Harakeh, Steven Waslander, Klaus Dietmayer
Next, we present a strict comparative study for probabilistic object detection based on an image detector and three public autonomous driving datasets.
2 code implementations • 2 Nov 2020 • Nico Engel, Vasileios Belagiannis, Klaus Dietmayer
In this work, we present Point Transformer, a deep neural network that operates directly on unordered and unstructured point sets.
Ranked #35 on 3D Part Segmentation on ShapeNet-Part
no code implementations • 10 Aug 2020 • Di Feng, Lars Rosenbaum, Fabian Timm, Klaus Dietmayer
Reliable uncertainty estimation is crucial for robust object detection in autonomous driving.
1 code implementation • 22 Jul 2020 • Markus Horn, Nico Engel, Vasileios Belagiannis, Michael Buchholz, Klaus Dietmayer
This work addresses the problem of point cloud registration using deep neural networks.
no code implementations • 10 Jul 2020 • Florian Kraus, Nicolas Scheiner, Werner Ritter, Klaus Dietmayer
We show that we can use a state-of-the-art automotive radar classifier in order to detect ghost objects alongside real objects.
1 code implementation • 1 Jul 2020 • Andreas Pfeuffer, Klaus Dietmayer
Computer vision tasks such as semantic segmentation perform very well in good weather conditions, but if the weather turns bad, they have problems to achieve this performance in these conditions.
no code implementations • 1 Jul 2020 • Thomas Griebel, Johannes Müller, Michael Buchholz, Klaus Dietmayer
Thus, by embedding classical Kalman filtering into subjective logic, our method additionally features an explicit measure for statistical uncertainty in the self-assessment.
no code implementations • 11 Mar 2020 • Stefanie Walz, Tobias Gruber, Werner Ritter, Klaus Dietmayer
Gated imaging is an emerging sensor technology for self-driving cars that provides high-contrast images even under adverse weather influence.
no code implementations • 7 Mar 2020 • Zining Wang, Di Feng, Yiyang Zhou, Lars Rosenbaum, Fabian Timm, Klaus Dietmayer, Masayoshi Tomizuka, Wei Zhan
Based on the spatial distribution, we further propose an extension of IoU, called the Jaccard IoU (JIoU), as a new evaluation metric that incorporates label uncertainty.
no code implementations • 1 Feb 2020 • Di Feng, Yifan Cao, Lars Rosenbaum, Fabian Timm, Klaus Dietmayer
This work presents a probabilistic deep neural network that combines LiDAR point clouds and RGB camera images for robust, accurate 3D object detection.
1 code implementation • CVPR 2020 • Nicolas Scheiner, Florian Kraus, Fangyin Wei, Buu Phan, Fahim Mannan, Nils Appenrodt, Werner Ritter, Jürgen Dickmann, Klaus Dietmayer, Bernhard Sick, Felix Heide
In this work, we depart from visible-wavelength approaches and demonstrate detection, classification, and tracking of hidden objects in large-scale dynamic environments using Doppler radars that can be manufactured at low-cost in series production.
no code implementations • 5 Dec 2019 • Tobias Gruber, Mariia Kokhova, Werner Ritter, Norbert Haala, Klaus Dietmayer
Environment perception for autonomous driving is doomed by the trade-off between range-accuracy and resolution: current sensors that deliver very precise depth information are usually restricted to low resolution because of technology or cost limitations.
no code implementations • 26 Sep 2019 • Di Feng, Lars Rosenbaum, Claudius Glaeser, Fabian Timm, Klaus Dietmayer
Reliable uncertainty estimation is crucial for perception systems in safe autonomous driving.
1 code implementation • 16 Jul 2019 • Andreas Pfeuffer, Klaus Dietmayer
The advantage of video segmentation approaches compared to single image segmentation is that temporal image information is considered, and their performance increases due to this.
1 code implementation • 21 Jun 2019 • Tobias Gruber, Mario Bijelic, Felix Heide, Werner Ritter, Klaus Dietmayer
This work introduces an evaluation benchmark for depth estimation and completion using high-resolution depth measurements with angular resolution of up to 25" (arcsecond), akin to a 50 megapixel camera with per-pixel depth available.
1 code implementation • 24 May 2019 • Florian Kraus, Klaus Dietmayer
Environment perception is the task for intelligent vehicles on which all subsequent steps rely.
no code implementations • 24 May 2019 • Andreas Pfeuffer, Klaus Dietmayer
One possibility to still obtain reliable results is to observe the environment with different sensor types, such as camera and lidar, and to fuse the sensor data by means of neural networks, since different sensors behave differently in diverse weather conditions.
no code implementations • 8 May 2019 • Manuel Herzog, Klaus Dietmayer
We use an existing annotated dataset to train a neural network that can be used with a LiDAR sensor that has a lower resolution than the one used for recording the annotated dataset.
1 code implementation • 3 May 2019 • Andreas Pfeuffer, Karina Schulz, Klaus Dietmayer
The disadvantage of this is that temporal image information is not considered, which improves the performance of the segmentation approach.
no code implementations • 18 Apr 2019 • Nico Engel, Stefan Hoermann, Markus Horn, Vasileios Belagiannis, Klaus Dietmayer
The map is generated off-line by extracting landmarks from the vehicle's field of view, while the measurements are collected similarly on the fly.
no code implementations • 17 Apr 2019 • Andreas Danzer, Thomas Griebel, Martin Bach, Klaus Dietmayer
To this end, PointNets are adjusted for radar data performing 2D object classification with segmentation, and 2D bounding box regression in order to estimate an amodal 2D bounding box.
1 code implementation • CVPR 2020 • Mario Bijelic, Tobias Gruber, Fahim Mannan, Florian Kraus, Werner Ritter, Klaus Dietmayer, Felix Heide
The fusion of multimodal sensor streams, such as camera, lidar, and radar measurements, plays a critical role in object detection for autonomous vehicles, which base their decision making on these inputs.
Ranked #2 on 2D Object Detection on Clear Weather
1 code implementation • 21 Feb 2019 • Di Feng, Christian Haase-Schuetz, Lars Rosenbaum, Heinz Hertlein, Claudius Glaeser, Fabian Timm, Werner Wiesbeck, Klaus Dietmayer
This review paper attempts to systematically summarize methodologies and discuss challenges for deep multi-modal object detection and semantic segmentation in autonomous driving.
Robotics
2 code implementations • ICCV 2019 • Tobias Gruber, Frank Julca-Aguilar, Mario Bijelic, Werner Ritter, Klaus Dietmayer, Felix Heide
The proposed replacement for scanning lidar systems is real-time, handles back-scatter and provides dense depth at long ranges.
no code implementations • 29 Jan 2019 • Di Feng, Xiao Wei, Lars Rosenbaum, Atsuto Maki, Klaus Dietmayer
Training a deep object detector for autonomous driving requires a huge amount of labeled data.
no code implementations • 14 Sep 2018 • Di Feng, Lars Rosenbaum, Fabian Timm, Klaus Dietmayer
We validate our method on the KITTI object detection benchmark.
Robotics
no code implementations • 11 Sep 2018 • Marcel Schreiber, Stefan Hoermann, Klaus Dietmayer
We tackle the long-term prediction of scene evolution in a complex downtown scenario for automated driving based on Lidar grid fusion and recurrent neural networks (RNNs).
no code implementations • 6 Jul 2018 • Andreas Pfeuffer, Klaus Dietmayer
In this work, different sensor fusion architectures are compared for good and adverse weather conditions for finding the optimal fusion architecture for diverse weather situations.
1 code implementation • 17 May 2018 • Julian Müller, Andreas Fregin, Klaus Dietmayer
A mathematical derivation clarifies the number of object candidates with respect to parameters such as image and object size.
2 code implementations • 7 May 2018 • Julian Müller, Klaus Dietmayer
So far, research in traffic light detection mainly focused on hand-crafted features, such as color, shape or brightness of the traffic light bulb.
no code implementations • 13 Apr 2018 • Di Feng, Lars Rosenbaum, Klaus Dietmayer
Experimental results show that the epistemic uncertainty is related to the detection accuracy, whereas the aleatoric uncertainty is influenced by vehicle distance and occlusion.
no code implementations • 11 Apr 2018 • Daniel Stumper, Fabian Gies, Stefan Hoermann, Klaus Dietmayer
The evaluation of algorithms for object extraction or the training and validation of learning algorithms rely on labeled ground truth data.
no code implementations • 9 Mar 2018 • Michael Goldhammer, Sebastian Köhler, Stefan Zernetsch, Konrad Doll, Bernhard Sick, Klaus Dietmayer
Furthermore, the architecture is used to evaluate motion-specific physical models for starting and stopping and video-based pedestrian motion classification.
no code implementations • 30 Jan 2018 • Stefan Hoermann, Philipp Henzler, Martin Bach, Klaus Dietmayer
We tackle the problem of object detection and pose estimation in a shared space downtown environment.
1 code implementation • 10 Nov 2017 • Alexander Scheel, Klaus Dietmayer
Yet, the increased amount of data raises the demands on tracking modules: measurement models that are able to process multiple measurements for an object are necessary and measurement-to-object associations become more complex.
Signal Processing Robotics Computation
no code implementations • 24 May 2017 • Stefan Hoermann, Martin Bach, Klaus Dietmayer
Long-term situation prediction plays a crucial role in the development of intelligent vehicles.
Robotics