arXiv subjects

Klaus Dietmayer

Publications and source records attributed to Klaus Dietmayer.

At least 73 records · Page 4Linked to original sources

arXiv2021

Anomaly Detection in Radar Data Using PointNets

For autonomous driving, radar is an important sensor type. On the one hand, radar offers a direct measurement of the radial velocity of targets in the environment. On the other hand, in literature, radar sensors are known for their robustness against several kinds of adverse weather conditions. However, on the downside, radar is susceptible to ghost targets or clutter which can be caused by several different causes, e.g., reflective surfaces in the environment. Ghost targets, for instance, can result in erroneous object detections. To this end, it is desirable to identify anomalous targets as early as possible in radar data. In this work, we present an approach based on PointNets to detect anomalous radar targets. Modifying the PointNet-architecture driven by our task, we developed a novel grouping variant which contributes to a multi-form grouping module. Our method is evaluated on a real-world dataset in urban scenarios and shows promising results for the detection of anomalous radar targets.

cs.CV↗

arXiv2021

Fast Rule-Based Clutter Detection in Automotive Radar Data

Automotive radar sensors output a lot of unwanted clutter or ghost detections, whose position and velocity do not correspond to any real object in the sensor's field of view. This poses a substantial challenge for environment perception methods like object detection or tracking. Especially problematic are clutter detections that occur in groups or at similar locations in multiple consecutive measurements. In this paper, a new algorithm for identifying such erroneous detections is presented. It is mainly based on the modeling of specific commonly occurring wave propagation paths that lead to clutter. In particular, the three effects explicitly covered are reflections at the underbody of a car or truck, signals traveling back and forth between the vehicle on which the sensor is mounted and another object, and multipath propagation via specular reflection. The latter often occurs near guardrails, concrete walls or similar reflective surfaces. Each of these effects is described both theoretically and regarding a method for identifying the corresponding clutter detections. Identification is done by analyzing detections generated from a single sensor measurement only. The final algorithm is evaluated on recordings of real extra-urban traffic. For labeling, a semi-automatic process is employed. The results are promising, both in terms of performance and regarding the very low execution time. Typically, a large part of clutter is found, while only a small ratio of detections corresponding to real objects are falsely classified by the algorithm.

cs.CV↗

arXiv2021

GenRadar: Self-supervised Probabilistic Camera Synthesis based on Radar Frequencies

Autonomous systems require a continuous and dependable environment perception for navigation and decision-making, which is best achieved by combining different sensor types. Radar continues to function robustly in compromised circumstances in which cameras become impaired, guaranteeing a steady inflow of information. Yet, camera images provide a more intuitive and readily applicable impression of the world. This work combines the complementary strengths of both sensor types in a unique self-learning fusion approach for a probabilistic scene reconstruction in adverse surrounding conditions. After reducing the memory requirements of both high-dimensional measurements through a decoupled stochastic self-supervised compression technique, the proposed algorithm exploits similarities and establishes correspondences between both domains at different feature levels during training. Then, at inference time, relying exclusively on radio frequencies, the model successively predicts camera constituents in an autoregressive and self-contained process. These discrete tokens are finally transformed back into an instructive view of the respective surrounding, allowing to visually perceive potential dangers for important tasks downstream.

cs.CV↗

arXiv2021

Attention-based Vehicle Self-Localization with HD Feature Maps

We present a vehicle self-localization method using point-based deep neural networks. Our approach processes measurements and point features, i.e. landmarks, from a high-definition digital map to infer the vehicle's pose. To learn the best association and incorporate local information between the point sets, we propose an attention mechanism that matches the measurements to the corresponding landmarks. Finally, we use this representation for the point-cloud registration and the subsequent pose regression task. Furthermore, we introduce a training simulation framework that artificially generates measurements and landmarks to facilitate the deployment process and reduce the cost of creating extensive datasets from real-world data. We evaluate our method on our dataset, as well as an adapted version of the Kitti odometry dataset, where we achieve superior performance compared to related approaches; and additionally show dominant generalization capabilities.

cs.CV↗

arXiv2021

A Review and Comparative Study on Probabilistic Object Detection in Autonomous Driving

Capturing uncertainty in object detection is indispensable for safe autonomous driving. In recent years, deep learning has become the de-facto approach for object detection, and many probabilistic object detectors have been proposed. However, there is no summary on uncertainty estimation in deep object detection, and existing methods are not only built with different network architectures and uncertainty estimation methods, but also evaluated on different datasets with a wide range of evaluation metrics. As a result, a comparison among methods remains challenging, as does the selection of a model that best suits a particular application. This paper aims to alleviate this problem by providing a review and comparative study on existing probabilistic object detection methods for autonomous driving applications. First, we provide an overview of generic uncertainty estimation in deep learning, and then systematically survey existing methods and evaluation metrics for probabilistic object detection. Next, we present a strict comparative study for probabilistic object detection based on an image detector and three public autonomous driving datasets. Finally, we present a discussion of the remaining challenges and future works. Code has been made available at https://github.com/asharakeh/pod_compare.git

cs.CV↗

arXiv2021

On-Road Motion Planning for Automated Vehicles at Ulm University

The Institute of Measurement, Control and Microtechnology at Ulm University investigates advanced driver assistance systems for decades and concentrates in large parts on autonomous driving. It is well known that motion planning is a key technology for autonomous driving. It is first and foremost responsible for the safety of the vehicle passengers as well as of all surrounding traffic participants. However, a further task consists in providing a smooth and comfortable driving behavior. In Ulm, we have the grateful opportunity to test our algorithms under real conditions in public traffic and diversified scenarios. In this paper, we would like to give the readers an insight of our work, about the vehicle, the test track, as well as of the related problems, challenges and solutions. Therefore, we will describe the motion planning system and explain the implemented functionalities. Furthermore, we will show how our vehicle moves through public road traffic and how it deals with challenging scenarios like e.g. driving through roundabouts and intersections.

cs.RO↗

arXiv2021

Motion Classification and Height Estimation of Pedestrians Using Sparse Radar Data

A complete overview of the surrounding vehicle environment is important for driver assistance systems and highly autonomous driving. Fusing results of multiple sensor types like camera, radar and lidar is crucial for increasing the robustness. The detection and classification of objects like cars, bicycles or pedestrians has been analyzed in the past for many sensor types. Beyond that, it is also helpful to refine these classes and distinguish for example between different pedestrian types or activities. This task is usually performed on camera data, though recent developments are based on radar spectrograms. However, for most automotive radar systems, it is only possible to obtain radar targets instead of the original spectrograms. This work demonstrates that it is possible to estimate the body height of walking pedestrians using 2D radar targets. Furthermore, different pedestrian motion types are classified.

cs.CV↗

arXiv2021

Online Extrinsic Calibration based on Per-Sensor Ego-Motion Using Dual Quaternions

In this work, we propose an approach for extrinsic sensor calibration from per-sensor ego-motion estimates. Our problem formulation is based on dual quaternions, enabling two different online capable solving approaches. We provide a certifiable globally optimal and a fast local approach along with a method to verify the globality of the local approach. Additionally, means for integrating previous knowledge, for example, a common ground plane for planar sensor motion, are described. Our algorithms are evaluated on simulated data and on a publicly available dataset containing RGB-D camera images. 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. Our evaluation confirms the short run time, state-of-the-art accuracy, as well as online capability of our approach while retaining the global optimality of the solution at any time.

cs.RO↗

arXiv2021

Graph-based Motion Planning for Automated Vehicles using Multi-model Branching and Admissible Heuristics

Automated driving in urban scenarios requires efficient planning algorithms able to handle complex situations in real-time. A popular approach is to use graph-based planning methods in order to obtain a rough trajectory which is subsequently optimized. A key aspect is the generation of trajectories implementing comfortable and safe behavior already during graph-search while keeping computation times low. To capture this aspect, on the one hand, a branching strategy is presented in this work that leads to better performance in terms of quality of resulting trajectories and runtime. On the other hand, admissible heuristics are shown which guide the graph-search efficiently, where the solution remains optimal.

cs.RO↗

arXiv2021

DeepCLR: Correspondence-Less Architecture for Deep End-to-End Point Cloud Registration

This work addresses the problem of point cloud registration using deep neural networks. We propose an approach to predict the alignment between two point clouds with overlapping data content, but displaced origins. Such point clouds originate, for example, from consecutive measurements of a LiDAR mounted on a moving platform. The main difficulty in deep registration of raw point clouds is the fusion of template and source point cloud. Our proposed architecture applies flow embedding to tackle this problem, which generates features that describe the motion of each template point. These features are then used to predict the alignment in an end-to-end fashion without extracting explicit point correspondences between both input clouds. We rely on the KITTI odometry and ModelNet40 datasets for evaluating our method on various point distributions. Our approach achieves state-of-the-art accuracy and the lowest run-time of the compared methods.

cs.CV↗

arXiv2020

Labels Are Not Perfect: Inferring Spatial Uncertainty in Object Detection

The availability of many real-world driving datasets is a key reason behind the recent progress of object detection algorithms in autonomous driving. However, there exist ambiguity or even failures in object labels due to error-prone annotation process or sensor observation noise. Current public object detection datasets only provide deterministic object labels without considering their inherent uncertainty, as does the common training process or evaluation metrics for object detectors. 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. In this work, we infer the uncertainty in bounding box labels from LiDAR point clouds based on a generative model, and define a new representation of the probabilistic bounding box through a spatial uncertainty distribution. Comprehensive experiments show that the proposed model reflects complex environmental noises in LiDAR perception and the label quality. Furthermore, we propose Jaccard IoU (JIoU) as a new evaluation metric that extends IoU by incorporating label uncertainty. We conduct an in-depth comparison among several LiDAR-based object detectors using the JIoU metric. Finally, we incorporate the proposed label uncertainty in a loss function to train a probabilistic object detector and to improve its detection accuracy. We verify our proposed methods on two public datasets (KITTI, Waymo), as well as on simulation data. Code is released at https://bit.ly/2W534yo.

cs.CV↗

arXiv2020

Trajectory Planning for Automated Driving in Intersection Scenarios using Driver Models

Efficient trajectory planning for urban intersections is currently one of the most challenging tasks for an Autonomous Vehicle (AV). Courteous behavior towards other traffic participants, the AV's comfort and its progression in the environment are the key aspects that determine the performance of trajectory planning algorithms. To capture these aspects, we propose a novel trajectory planning framework that ensures social compliance and simultaneously optimizes the AV's comfort subject to kinematic constraints. The framework combines a local continuous optimization approach and an efficient driver model to ensure fast behavior prediction, maneuver generation and decision making over long horizons. The proposed framework is evaluated in different scenarios to demonstrate its capabilities in terms of the resulting trajectories and runtime.

cs.RO↗

arXiv2020

Labels Are Not Perfect: Improving Probabilistic Object Detection via Label Uncertainty

Reliable uncertainty estimation is crucial for robust object detection in autonomous driving. However, previous works on probabilistic object detection either learn predictive probability for bounding box regression in an un-supervised manner, or use simple heuristics to do uncertainty regularization. This leads to unstable training or suboptimal detection performance. In this work, we leverage our previously proposed method for estimating uncertainty inherent in ground truth bounding box parameters (which we call label uncertainty) to improve the detection accuracy of a probabilistic LiDAR-based object detector. Experimental results on the KITTI dataset show that our method surpasses both the baseline model and the models based on simple heuristics by up to 3.6% in terms of Average Precision.

cs.CV↗

arXiv2020

Inferring Spatial Uncertainty in Object Detection

The availability of real-world datasets is the prerequisite for developing object detection methods for autonomous driving. While ambiguity exists in object labels due to error-prone annotation process or sensor observation noises, current object detection datasets only provide deterministic annotations without considering their uncertainty. This precludes an in-depth evaluation among different object detection methods, especially for those that explicitly model predictive probability. In this work, we propose a generative model to estimate bounding box label uncertainties from LiDAR point clouds, and define a new representation of the probabilistic bounding box through spatial distribution. Comprehensive experiments show that the proposed model represents uncertainties commonly seen in driving scenarios. 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. Experiments on the KITTI and the Waymo Open Datasets show that JIoU is superior to IoU when evaluating probabilistic object detectors.

cs.CV↗

arXiv2020

Uncertainty Estimation in One-Stage Object Detection

Environment perception is the task for intelligent vehicles on which all subsequent steps rely. A key part of perception is to safely detect other road users such as vehicles, pedestrians, and cyclists. With modern deep learning techniques huge progress was made over the last years in this field. However such deep learning based object detection models cannot predict how certain they are in their predictions, potentially hampering the performance of later steps such as tracking or sensor fusion. We present a viable approaches to estimate uncertainty in an one-stage object detector, while improving the detection performance of the baseline approach. The proposed model is evaluated on a large scale automotive pedestrian dataset. Experimental results show that the uncertainty outputted by our system is coupled with detection accuracy and the occlusion level of pedestrians.

cs.CV↗

arXiv2020

Using Machine Learning to Detect Ghost Images in Automotive Radar

Radar sensors are an important part of driver assistance systems and intelligent vehicles due to their robustness against all kinds of adverse conditions, e.g., fog, snow, rain, or even direct sunlight. This robustness is achieved by a substantially larger wavelength compared to light-based sensors such as cameras or lidars. As a side effect, many surfaces act like mirrors at this wavelength, resulting in unwanted ghost detections. In this article, we present a novel approach to detect these ghost objects by applying data-driven machine learning algorithms. For this purpose, we use a large-scale automotive data set with annotated ghost objects. We show that we can use a state-of-the-art automotive radar classifier in order to detect ghost objects alongside real objects. Furthermore, we are able to reduce the amount of false positive detections caused by ghost images in some settings.

cs.CV↗

arXiv2020

Robust Semantic Segmentation in Adverse Weather Conditions by means of Fast Video-Sequence Segmentation

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. One possibility to obtain more robust and reliable results in adverse weather conditions is to use video-segmentation approaches instead of commonly used single-image segmentation methods. Video-segmentation approaches capture temporal information of the previous video-frames in addition to current image information, and hence, they are more robust against disturbances, especially if they occur in only a few frames of the video-sequence. However, video-segmentation approaches, which are often based on recurrent neural networks, cannot be applied in real-time applications anymore, since their recurrent structures in the network are computational expensive. For instance, the inference time of the LSTM-ICNet, in which recurrent units are placed at proper positions in the single-segmentation approach ICNet, increases up to 61 percent compared to the basic ICNet. Hence, in this work, the LSTM-ICNet is sped up by modifying the recurrent units of the network so that it becomes real-time capable again. Experiments on different datasets and various weather conditions show that the inference time can be decreased by about 23 percent by these modifications, while they achieve similar performance than the LSTM-ICNet and outperform the single-segmentation approach enormously in adverse weather conditions.

cs.CV↗

arXiv2020

Kalman Filter Meets Subjective Logic: A Self-Assessing Kalman Filter Using Subjective Logic

Self-assessment is a key to safety and robustness in automated driving. In order to design safer and more robust automated driving functions, the goal is to self-assess the performance of each module in a whole automated driving system. One crucial component in automated driving systems is the tracking of surrounding objects, where the Kalman filter is the most fundamental tracking algorithm. For Kalman filters, some classical online consistency measures exist for self-assessment, which are based on classical probability theory. However, these classical approaches lack the ability to measure the explicit statistical uncertainty within the self-assessment, which is an important quality measure, particularly, if only a small number of samples is available for the self-assessment. In this work, we propose a novel online self-assessment method using subjective logic, which is a modern extension of probabilistic logic that explicitly models the statistical uncertainty. Thus, by embedding classical Kalman filtering into subjective logic, our method additionally features an explicit measure for statistical uncertainty in the self-assessment.

eess.SY↗