Claudius Gläser
YOU?
Author Swipe
Multi-Scale Neighborhood Occupancy Masked Autoencoder for Self-Supervised Learning in LiDAR Point Clouds Open
Masked autoencoders (MAE) have shown tremendous potential for self-supervised learning (SSL) in vision and beyond. However, point clouds from LiDARs used in automated driving are particularly challenging for MAEs since large areas of the 3…
View article: Bosch Street Dataset: A Multi-Modal Dataset with Imaging Radar for Automated Driving
Bosch Street Dataset: A Multi-Modal Dataset with Imaging Radar for Automated Driving Open
This paper introduces the Bosch street dataset (BSD), a novel multi-modal large-scale dataset aimed at promoting highly automated driving (HAD) and advanced driver-assistance systems (ADAS) research. Unlike existing datasets, BSD offers a …
Revisiting Out-of-Distribution Detection in LiDAR-based 3D Object Detection Open
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. However, object detectors face a critical challenge when dealing with unknown foreground…
Group Regression for Query Based Object Detection and Tracking Open
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 dissimilar classes. For query-based perception methods, this…
Can Transformer Attention Spread Give Insights Into Uncertainty of Detected and Tracked Objects? Open
Transformers have recently been utilized to perform object detection and tracking in the context of autonomous driving. One unique characteristic of these models is that attention weights are computed in each forward pass, giving insights …
Sensor Visibility Estimation: Metrics and Methods for Systematic Performance Evaluation and Improvement Open
Sensor visibility is crucial for safety-critical applications in automotive,\nrobotics, smart infrastructure and others: In addition to object detection and\noccupancy mapping, visibility describes where a sensor can potentially measure\no…
Transformers for Object Detection in Large Point Clouds Open
We present TransLPC, a novel detection model for large point clouds that is based on a transformer architecture. While object detection with transformers has been an active field of research, it has proved difficult to apply such models to…
DeepFusion: A Robust and Modular 3D Object Detector for Lidars, Cameras and Radars Open
We propose DeepFusion, a modular multi-modal architecture to fuse lidars, cameras and radars in different combinations for 3D object detection. Specialized feature extractors take advantage of each modality and can be exchanged easily, mak…
Transformers for Multi-Object Tracking on Point Clouds Open
We present TransMOT, a novel transformer-based end-to-end trainable online tracker and detector for point cloud data. The model utilizes a cross- and a self-attention mechanism and is applicable to lidar data in an automotive context, as w…
Self-Supervised Velocity Estimation for Automotive Radar Object Detection Networks Open
This paper presents a method to learn the Cartesian velocity of objects using\nan object detection network on automotive radar data. The proposed method is\nself-supervised in terms of generating its own training signal for the\nvelocities…
Improved Orientation Estimation and Detection with Hybrid Object Detection Networks for Automotive Radar Open
This paper presents novel hybrid architectures that combine grid- and point-based processing to improve the detection performance and orientation estimation of radar-based object detection networks. Purely grid-based detection models opera…
A Multi-Task Recurrent Neural Network for End-to-End Dynamic Occupancy Grid Mapping Open
A common approach for modeling the environment of an autonomous vehicle are dynamic occupancy grid maps, in which the surrounding is divided into cells, each containing the occupancy and velocity state of its location. Despite the advantag…
Where can I drive? A System Approach: Deep Ego Corridor Estimation for Robust Automated Driving Open
Lane detection is an essential part of the perception sub-architecture of any automated driving (AD) or advanced driver assistance system (ADAS). When focusing on low-cost, large scale products for automated driving, model-driven approache…
Dynamic Occupancy Grid Mapping with Recurrent Neural Networks Open
Modeling and understanding the environment is an essential task for autonomous driving. In addition to the detection of objects, in complex traffic scenarios the motion of other road participants is of special interest. Therefore, we propo…
DeepReflecs: Deep Learning for Automotive Object Classification with Radar Reflections Open
This paper presents an novel object type classification method for automotive applications which uses deep learning with radar reflections. The method provides object class information such as pedestrian, cyclist, car, or non-obstacle. The…
Pedestrian Behavior Prediction for Automated Driving: Requirements, Metrics, and Relevant Features Open
Automated vehicles require a comprehensive understanding of traffic situations to ensure safe and anticipatory driving. In this context, the prediction of pedestrians is particularly challenging as pedestrian behavior can be influenced by …
Where can I drive? A System Approach: Deep Ego Corridor Estimation for\n Robust Automated Driving Open
Lane detection is an essential part of the perception sub-architecture of any\nautomated driving (AD) or advanced driver assistance system (ADAS). When\nfocusing on low-cost, large scale products for automated driving, model-driven\napproa…
Where can I drive? Deep Ego-Corridor Estimation for Robust Automated Driving. Open
Lane detection is an essential part of the perception module of any automated driving (AD) or advanced driver assistance system (ADAS). So far, model-driven approaches for the detection of lane markings proved sufficient. More recently, ho…
View article: Deep Multi-Modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges
Deep Multi-Modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges Open
Recent advancements in perception for autonomous driving are driven by deep learning. In order to achieve robust and accurate scene understanding, autonomous vehicles are usually equipped with different sensors (e.g. cameras, LiDARs, Radar…
Can We Trust You? On Calibration of a Probabilistic Object Detector for Autonomous Driving Open
Reliable uncertainty estimation is crucial for perception systems in safe autonomous driving. Recently, many methods have been proposed to model uncertainties in deep learning based object detectors. However, the estimated probabilities ar…
Motion Estimation in Occupancy Grid Maps in Stationary Settings Using Recurrent Neural Networks Open
In this work, we tackle the problem of modeling the vehicle environment as dynamic occupancy grid map in complex urban scenarios using recurrent neural networks. Dynamic occupancy grid maps represent the scene in a bird's eye view, where e…