arXiv subjects

Klaus Dietmayer

Publications and source records attributed to Klaus Dietmayer.

At least 91 records · Page 5Linked to original sources

arXiv2020

Seeing Through Fog Without Seeing Fog: Deep Multimodal Sensor Fusion in Unseen Adverse Weather

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. While existing methods exploit redundant information in good environmental conditions, they fail in adverse weather where the sensory streams can be asymmetrically distorted. These rare "edge-case" scenarios are not represented in available datasets, and existing fusion architectures are not designed to handle them. To address this challenge we present a novel multimodal dataset acquired in over 10,000km of driving in northern Europe. Although this dataset is the first large multimodal dataset in adverse weather, with 100k labels for lidar, camera, radar, and gated NIR sensors, it does not facilitate training as extreme weather is rare. To this end, we present a deep fusion network for robust fusion without a large corpus of labeled training data covering all asymmetric distortions. Departing from proposal-level fusion, we propose a single-shot model that adaptively fuses features, driven by measurement entropy. We validate the proposed method, trained on clean data, on our extensive validation dataset. Code and data are available here https://github.com/princeton-computational-imaging/SeeingThroughFog.

cs.CV↗

arXiv2020

Extended Existence Probability Using Digital Maps for Object Verification

A main task for automated vehicles is an accurate and robust environment perception. Especially, an error-free detection and modeling of other traffic participants is of great importance to drive safely in any situation. For this purpose, multi-object tracking algorithms, based on object detections from raw sensor measurements, are commonly used. However, false object hypotheses can occur due to a high density of different traffic participants in complex, arbitrary scenarios. For this reason, the presented approach introduces a probabilistic model to verify the existence of a tracked object. Therefore, an object verification module is introduced, where the influences of multiple digital map elements on a track's existence are evaluated. Finally, a probabilistic model fuses the various influences and estimates an extended existence probability for every track. In addition, a Bayes Net is implemented as directed graphical model to highlight this work's expandability. The presented approach, reduces the number of false positives, while retaining true positives. Real world data is used to evaluate and to highlight the benefits of the presented approach, especially in urban scenarios.

cs.RO↗

arXiv2020

Seeing Around Street Corners: Non-Line-of-Sight Detection and Tracking In-the-Wild Using Doppler Radar

Conventional sensor systems record information about directly visible objects, whereas occluded scene components are considered lost in the measurement process. Non-line-of-sight (NLOS) methods try to recover such hidden objects from their indirect reflections - faint signal components, traditionally treated as measurement noise. Existing NLOS approaches struggle to record these low-signal components outside the lab, and do not scale to large-scale outdoor scenes and high-speed motion, typical in automotive scenarios. In particular, optical NLOS capture is fundamentally limited by the quartic intensity falloff of diffuse indirect reflections. 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. To untangle noisy indirect and direct reflections, we learn from temporal sequences of Doppler velocity and position measurements, which we fuse in a joint NLOS detection and tracking network over time. We validate the approach on in-the-wild automotive scenes, including sequences of parked cars or house facades as relay surfaces, and demonstrate low-cost, real-time NLOS in dynamic automotive environments.

cs.CV↗

arXiv2020

Uncertainty depth estimation with gated images for 3D reconstruction

Gated imaging is an emerging sensor technology for self-driving cars that provides high-contrast images even under adverse weather influence. It has been shown that this technology can even generate high-fidelity dense depth maps with accuracy comparable to scanning LiDAR systems. In this work, we extend the recent Gated2Depth framework with aleatoric uncertainty providing an additional confidence measure for the depth estimates. This confidence can help to filter out uncertain estimations in regions without any illumination. Moreover, we show that training on dense depth maps generated by LiDAR depth completion algorithms can further improve the performance.

eess.IV↗

arXiv2020

Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges

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, Radars), and multiple sensing modalities can be fused to exploit their complementary properties. In this context, many methods have been proposed for deep multi-modal perception problems. However, there is no general guideline for network architecture design, and questions of "what to fuse", "when to fuse", and "how to fuse" remain open. This review paper attempts to systematically summarize methodologies and discuss challenges for deep multi-modal object detection and semantic segmentation in autonomous driving. To this end, we first provide an overview of on-board sensors on test vehicles, open datasets, and background information for object detection and semantic segmentation in autonomous driving research. We then summarize the fusion methodologies and discuss challenges and open questions. In the appendix, we provide tables that summarize topics and methods. We also provide an interactive online platform to navigate each reference: https://boschresearch.github.io/multimodalperception/.

cs.RO↗

arXiv2020

Leveraging Uncertainties for Deep Multi-modal Object Detection in Autonomous Driving

This work presents a probabilistic deep neural network that combines LiDAR point clouds and RGB camera images for robust, accurate 3D object detection. We explicitly model uncertainties in the classification and regression tasks, and leverage uncertainties to train the fusion network via a sampling mechanism. We validate our method on three datasets with challenging real-world driving scenarios. Experimental results show that the predicted uncertainties reflect complex environmental uncertainty like difficulties of a human expert to label objects. The results also show that our method consistently improves the Average Precision by up to 7% compared to the baseline method. When sensors are temporally misaligned, the sampling method improves the Average Precision by up to 20%, showing its high robustness against noisy sensor inputs.

cs.RO↗

arXiv2019

Learning Super-resolved Depth from Active Gated Imaging

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. In this work, we exploit depth information from an active gated imaging system based on cost-sensitive diode and CMOS technology. Learning a mapping between pixel intensities of three gated slices and depth produces a super-resolved depth map image with respectable relative accuracy of 5% in between 25-80 m. By design, depth information is perfectly aligned with pixel intensity values.

eess.IV↗

arXiv2019

Training a Fast Object Detector for LiDAR Range Images Using Labeled Data from Sensors with Higher Resolution

In this paper, we describe a strategy for training neural networks for object detection in range images obtained from one type of LiDAR sensor using labeled data from a different type of LiDAR sensor. Additionally, an efficient model for object detection in range images for use in self-driving cars is presented. Currently, the highest performing algorithms for object detection from LiDAR measurements are based on neural networks. Training these networks using supervised learning requires large annotated datasets. Therefore, most research using neural networks for object detection from LiDAR point clouds is conducted on a very small number of publicly available datasets. Consequently, only a small number of sensor types are used. 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. This is done by simulating data from the lower resolution LiDAR sensor based on the higher resolution dataset. Furthermore, improvements to models that use LiDAR range images for object detection are presented. The results are validated using both simulated sensor data and data from an actual lower resolution sensor mounted to a research vehicle. It is shown that the model can detect objects from 360° range images in real time.

cs.CV↗

arXiv2019

Fusion of Object Tracking and Dynamic Occupancy Grid Map

Environment modeling in autonomous driving is realized by two fundamental approaches, grid-based and feature-based approach. Both methods interpret the environment differently and show some situation-dependent beneficial realizations. In order to use the advantages of both methods, a combination makes sense. This work presents a fusion, which establishes an association between the representations of environment modeling and then decoupled from this performs a fusion of the information. Thus, there is no need to adapt the environment models. The developed fusion generates new hypotheses, which are closer to reality than a representation alone. This algorithm itself does not use object model assumptions, in effect this fusion can be applied to different object hypotheses. In addition, this combination allows the objects to be tracked over a longer period of time. This is evaluated with a quantitative evaluation on real sequences in real-time.

cs.RO↗

arXiv2019

2D Car Detection in Radar Data with PointNets

For many automated driving functions, a highly accurate perception of the vehicle environment is a crucial prerequisite. Modern high-resolution radar sensors generate multiple radar targets per object, which makes these sensors particularly suitable for the 2D object detection task. This work presents an approach to detect 2D objects solely depending on sparse radar data using PointNets. In literature, only methods are presented so far which perform either object classification or bounding box estimation for objects. In contrast, this method facilitates a classification together with a bounding box estimation of objects using a single radar sensor. 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. The algorithm is evaluated using an automatically created dataset which consist of various realistic driving maneuvers. The results show the great potential of object detection in high-resolution radar data using PointNets.

cs.CV↗

arXiv2019

Gated2Depth: Real-time Dense Lidar from Gated Images

We present an imaging framework which converts three images from a gated camera into high-resolution depth maps with depth accuracy comparable to pulsed lidar measurements. Existing scanning lidar systems achieve low spatial resolution at large ranges due to mechanically-limited angular sampling rates, restricting scene understanding tasks to close-range clusters with dense sampling. Moreover, today's pulsed lidar scanners suffer from high cost, power consumption, large form-factors, and they fail in the presence of strong backscatter. We depart from point scanning and demonstrate that it is possible to turn a low-cost CMOS gated imager into a dense depth camera with at least 80m range - by learning depth from three gated images. The proposed architecture exploits semantic context across gated slices, and is trained on a synthetic discriminator loss without the need of dense depth labels. The proposed replacement for scanning lidar systems is real-time, handles back-scatter and provides dense depth at long ranges. We validate our approach in simulation and on real-world data acquired over 4,000km driving in northern Europe. Data and code are available at https://github.com/gruberto/Gated2Depth.

cs.CV↗

arXiv2019

Tracking Multiple Vehicles Using a Variational Radar Model

High-resolution radar sensors are able to resolve multiple detections per object and therefore provide valuable information for vehicle environment perception. For instance, multiple detections allow to infer the size of an object or to more precisely measure the object's motion. Yet, the increased amount of data raises the demands on tracking modules: measurement models that are able to process multiple detections for an object are necessary and measurement-to-object associations become more complex. This paper presents a new variational radar model for tracking vehicles using radar detections and demonstrates how this model can be incorporated into a Random-Finite-Set-based multi-object filter. The measurement model is learned from actual data using variational Gaussian mixtures and avoids excessive manual engineering. In combination with the multiobject tracker, the entire process chain from the raw measurements to the resulting tracks is formulated probabilistically. The presented approach is evaluated on experimental data and it is demonstrated that the data-driven measurement model outperforms a manually designed model.

eess.SP↗

arXiv2019

Can We Trust You? On Calibration of a Probabilistic Object Detector for Autonomous Driving

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 are often uncalibrated, which may lead to severe problems in safety critical scenarios. In this work, we identify such uncertainty miscalibration problems in a probabilistic LiDAR 3D object detection network, and propose three practical methods to significantly reduce errors in uncertainty calibration. Extensive experiments on several datasets show that our methods produce well-calibrated uncertainties, and generalize well between different datasets.

cs.RO↗

arXiv2019

Pixel-Accurate Depth Evaluation in Realistic Driving Scenarios

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. Existing datasets, such as the KITTI benchmark, provide only sparse reference measurements with an order of magnitude lower angular resolution - these sparse measurements are treated as ground truth by existing depth estimation methods. We propose an evaluation methodology in four characteristic automotive scenarios recorded in varying weather conditions (day, night, fog, rain). As a result, our benchmark allows us to evaluate the robustness of depth sensing methods in adverse weather and different driving conditions. Using the proposed evaluation data, we demonstrate that current stereo approaches provide significantly more stable depth estimates than monocular methods and lidar completion in adverse weather. Data and code are available at https://github.com/gruberto/PixelAccurateDepthBenchmark.git.

cs.CV↗

arXiv2019

Towards Courteous Behavior and Trajectory Planning for Automated Driving

Efficient behavior and trajectory planning is one of the major challenges for automated driving. Especially intersection scenarios are very demanding due to their complexity arising from the variety of maneuver possibilities and other traffic participants. A key challenge is to generate behaviors which optimize the comfort and progress of the ego vehicle but at the same time are not too aggressive towards other traffic participants. In order to maintain real time capability for courteous behavior and trajectory planning, an efficient formulation of the optimal control problem and corresponding solving algorithms are required. Consequently, a novel planning framework is presented which considers comfort and progress as well as the courtesy of actions in a graph-based behavior planning module. Utilizing the low level trajectory generation, the behavior result can be further optimized for driving comfort while satisfying constraints over the whole planning horizon. According experiments show the practicability and real time capability of the framework.

cs.RO↗

arXiv2019

DeepLocalization: Landmark-based Self-Localization with Deep Neural Networks

We address the problem of vehicle self-localization from multi-modal sensor information and a reference map. 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. Our goal is to determine the autonomous vehicle's pose from the landmark measurements and map landmarks. To learn this mapping, we propose DeepLocalization, a deep neural network that regresses the vehicle's translation and rotation parameters from unordered and dynamic input landmarks. The proposed network architecture is robust to changes of the dynamic environment and can cope with a small number of extracted landmarks. During the training process we rely on synthetically generated ground-truth. In our experiments, we evaluate two inference approaches in real-world scenarios. We show that DeepLocalization can be combined with regular GPS signals and filtering algorithms such as the extended Kalman filter. Our approach achieves state-of-the-art accuracy and is about ten times faster than the related work.

cs.RO↗

arXiv2019

Separable Convolutional LSTMs for Faster Video Segmentation

Semantic Segmentation is an important module for autonomous robots such as self-driving cars. 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. Hence, single image segmentation approaches are extended by recurrent units such as convolutional LSTM (convLSTM) cells, which are placed at suitable positions in the basic network architecture. However, a major critique of video segmentation approaches based on recurrent neural networks is their large parameter count and their computational complexity, and so, their inference time of one video frame takes up to 66 percent longer than their basic version. Inspired by the success of the spatial and depthwise separable convolutional neural networks, we generalize these techniques for convLSTMs in this work, so that the number of parameters and the required FLOPs are reduced significantly. Experiments on different datasets show that the segmentation approaches using the proposed, modified convLSTM cells achieve similar or slightly worse accuracy, but are up to 15 percent faster on a GPU than the ones using the standard convLSTM cells. Furthermore, a new evaluation metric is introduced, which measures the amount of flickering pixels in the segmented video sequence.

cs.CV↗

arXiv2019

Long-Term Occupancy Grid Prediction Using Recurrent Neural Networks

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). A bird's eye view of the scene, including occupancy and velocity, is fed as a sequence to a RNN which is trained to predict future occupancy. The nature of prediction allows generation of multiple hours of training data without the need of manual labeling. Thus, the training strategy and loss function is designed for long sequences of real-world data (unbalanced, continuously changing situations, false labels, etc.). The deep CNN architecture comprises convolutional long short-term memories (ConvLSTMs) to separate static from dynamic regions and to predict dynamic objects in future frames. Novel recurrent skip connections show the ability to predict small occluded objects, i.e. pedestrians, and occluded static regions. Spatio-temporal correlations between grid cells are exploited to predict multimodal future paths and interactions between objects. Experiments also quantify improvements to our previous network, a Monte Carlo approach, and literature.

cs.CV↗