arXiv subjects

Klaus Dietmayer

Publications and source records attributed to Klaus Dietmayer.

At least 109 records · Page 6Linked to original sources

arXiv2019

Robust Semantic Segmentation in Adverse Weather Conditions by means of Sensor Data Fusion

A robust and reliable semantic segmentation in adverse weather conditions is very important for autonomous cars, but most state-of-the-art approaches only achieve high accuracy rates in optimal weather conditions. The reason is that they are only optimized for good weather conditions and given noise models. However, most of them fail, if data with unknown disturbances occur, and their performance decrease enormously. 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. Hence, the sensors can complement each other by means of an appropriate sensor data fusion. Nevertheless, the fusion-based approaches are still susceptible to disturbances and fail to classify disturbed image areas correctly. This problem can be solved by means of a special training method, the so called Robust Learning Method (RLM), a method by which the neural network learns to handle unknown noise. In this work, two different sensor fusion architectures for semantic segmentation are compared and evaluated on several datasets. Furthermore, it is shown that the RLM increases the robustness in adverse weather conditions enormously, and achieve good results although no disturbance model has been learned by the neural network.

cs.CV↗

arXiv2019

Leveraging Heteroscedastic Aleatoric Uncertainties for Robust Real-Time LiDAR 3D Object Detection

We present a robust real-time LiDAR 3D object detector that leverages heteroscedastic aleatoric uncertainties to significantly improve its detection performance. A multi-loss function is designed to incorporate uncertainty estimations predicted by auxiliary output layers. Using our proposed method, the network ignores to train from noisy samples, and focuses more on informative ones. We validate our method on the KITTI object detection benchmark. Our method surpasses the baseline method which does not explicitly estimate uncertainties by up to nearly 9% in terms of Average Precision (AP). It also produces state-of-the-art results compared to other methods while running with an inference time of only 72 ms. In addition, we conduct extensive experiments to understand how aleatoric uncertainties behave. Extracting aleatoric uncertainties brings almost no additional computation cost during the deployment, making our method highly desirable for autonomous driving applications.

cs.RO↗

arXiv2019

Deep Active Learning for Efficient Training of a LiDAR 3D Object Detector

Training a deep object detector for autonomous driving requires a huge amount of labeled data. While recording data via on-board sensors such as camera or LiDAR is relatively easy, annotating data is very tedious and time-consuming, especially when dealing with 3D LiDAR points or radar data. Active learning has the potential to minimize human annotation efforts while maximizing the object detector's performance. In this work, we propose an active learning method to train a LiDAR 3D object detector with the least amount of labeled training data necessary. The detector leverages 2D region proposals generated from the RGB images to reduce the search space of objects and speed up the learning process. Experiments show that our proposed method works under different uncertainty estimations and query functions, and can save up to 60% of the labeling efforts while reaching the same network performance.

cs.RO↗

arXiv2019

Semantic Segmentation of Video Sequences with Convolutional LSTMs

Most of the semantic segmentation approaches have been developed for single image segmentation, and hence, video sequences are currently segmented by processing each frame of the video sequence separately. The disadvantage of this is that temporal image information is not considered, which improves the performance of the segmentation approach. One possibility to include temporal information is to use recurrent neural networks. However, there are only a few approaches using recurrent networks for video segmentation so far. These approaches extend the encoder-decoder network architecture of well-known segmentation approaches and place convolutional LSTM layers between encoder and decoder. However, in this paper it is shown that this position is not optimal, and that other positions in the network exhibit better performance. Nowadays, state-of-the-art segmentation approaches rarely use the classical encoder-decoder structure, but use multi-branch architectures. These architectures are more complex, and hence, it is more difficult to place the recurrent units at a proper position. In this work, the multi-branch architectures are extended by convolutional LSTM layers at different positions and evaluated on two different datasets in order to find the best one. It turned out that the proposed approach outperforms the pure CNN-based approach for up to 1.6 percent.

cs.CV↗

arXiv2018

The Adaptive Labeled Multi-Bernoulli Filter

This paper proposes a new multi-Bernoulli filter called the Adaptive Labeled Multi-Bernoulli filter. It combines the relative strengths of the known Delta-Generalized Labeled Multi-Bernoulli and the Labeled Multi-Bernoulli filter. The proposed filter provides a more precise target tracking in critical situations, where the Labeled Multi-Bernoulli filter looses information through the approximation error in the update step. In noncritical situations it inherits the advantage of the Labeled Multi-Bernoulli filter to reduce the computational complexity by using the LMB approximation.

eess.SY↗

arXiv2018

Environment Perception Framework Fusing Multi-Object Tracking, Dynamic Occupancy Grid Maps and Digital Maps

Autonomously driving vehicles require a complete and robust perception of the local environment. A main challenge is to perceive any other road users, where multi-object tracking or occupancy grid maps are commonly used. The presented approach combines both methods to compensate false positives and receive a complementary environment perception. Therefore, an environment perception framework is introduced that defines a common representation, extracts objects from a dynamic occupancy grid map and fuses them with tracks of a Labeled Multi-Bernoulli filter. Finally, a confidence value is developed, that validates object estimates using different constraints regarding physical possibilities, method specific characteristics and contextual information from a digital map. Experimental results with real world data highlight the robustness and significance of the presented fusing approach, utilizing the confidence value in rural and urban scenarios.

cs.RO↗

arXiv2018

Multi-Object Tracking with Interacting Vehicles and Road Map Information

In many applications, tracking of multiple objects is crucial for a perception of the current environment. Most of the present multi-object tracking algorithms assume that objects move independently regarding other dynamic objects as well as the static environment. Since in many traffic situations objects interact with each other and in addition there are restrictions due to drivable areas, the assumption of an independent object motion is not fulfilled. This paper proposes an approach adapting a multi-object tracking system to model interaction between vehicles, and the current road geometry. Therefore, the prediction step of a Labeled Multi-Bernoulli filter is extended to facilitate modeling interaction between objects using the Intelligent Driver Model. Furthermore, to consider road map information, an approximation of a highly precise road map is used. The results show that in scenarios where the assumption of a standard motion model is violated, the tracking system adapted with the proposed method achieves higher accuracy and robustness in its track estimations.

cs.RO↗

arXiv2018

Detecting Traffic Lights by Single Shot Detection

Recent improvements in object detection are driven by the success of convolutional neural networks (CNN). They are able to learn rich features outperforming hand-crafted features. So far, research in traffic light detection mainly focused on hand-crafted features, such as color, shape or brightness of the traffic light bulb. This paper presents a deep learning approach for accurate traffic light detection in adapting a single shot detection (SSD) approach. SSD performs object proposals creation and classification using a single CNN. The original SSD struggles in detecting very small objects, which is essential for traffic light detection. By our adaptations it is possible to detect objects much smaller than ten pixels without increasing the input image size. We present an extensive evaluation on the DriveU Traffic Light Dataset (DTLD). We reach both, high accuracy and low false positive rates. The trained model is real-time capable with ten frames per second on a Nvidia Titan Xp. Code has been made available at https://github.com/julimueller/tl_ssd.

cs.CV↗

arXiv2018

Towards Safe Autonomous Driving: Capture Uncertainty in the Deep Neural Network For Lidar 3D Vehicle Detection

To assure that an autonomous car is driving safely on public roads, its object detection module should not only work correctly, but show its prediction confidence as well. Previous object detectors driven by deep learning do not explicitly model uncertainties in the neural network. We tackle with this problem by presenting practical methods to capture uncertainties in a 3D vehicle detector for Lidar point clouds. The proposed probabilistic detector represents reliable epistemic uncertainty and aleatoric uncertainty in classification and localization tasks. Experimental results show that the epistemic uncertainty is related to the detection accuracy, whereas the aleatoric uncertainty is influenced by vehicle distance and occlusion. The results also show that we can improve the detection performance by 1%-5% by modeling the aleatoric uncertainty.

cs.RO↗

arXiv2018

Disparity Sliding Window: Object Proposals From Disparity Images

Sliding window approaches have been widely used for object recognition tasks in recent years. They guarantee an investigation of the entire input image for the object to be detected and allow a localization of that object. Despite the current trend towards deep neural networks, sliding window methods are still used in combination with convolutional neural networks. The risk of overlooking an object is clearly reduced compared to alternative detection approaches which detect objects based on shape, edges or color. Nevertheless, the sliding window technique strongly increases the computational effort as the classifier has to verify a large number of object candidates. This paper proposes a sliding window approach which also uses depth information from a stereo camera. This leads to a greatly decreased number of object candidates without significantly reducing the detection accuracy. A theoretical investigation of the conventional sliding window approach is presented first. Other publications to date only mentioned rough estimations of the computational cost. A mathematical derivation clarifies the number of object candidates with respect to parameters such as image and object size. Subsequently, the proposed disparity sliding window approach is presented in detail. The approach is evaluated on pedestrian detection with annotations and images from the KITTI object detection benchmark. Furthermore, a comparison with two state-of-the-art methods is made. Code is available in C++ and Python https://github.com/julimueller/ disparity-sliding-window.

cs.CV↗

arXiv2018

Fast Trajectory Planning for Automated Vehicles using Gradient-based Nonlinear Model Predictive Control

Motion trajectory planning is one crucial aspect for automated vehicles, as it governs the own future behavior in a dynamically changing environment. A good utilization of a vehicle's characteristics requires the consideration of the nonlinear system dynamics within the optimization problem to be solved. In particular, real-time feasibility is essential for automated driving, in order to account for the fast changing surrounding, e.g. for moving objects. The key contributions of this paper are the presentation of a fast optimization algorithm for trajectory planning including the nonlinear system model. Further, a new concurrent operation scheme for two optimization algorithms is derived and investigated. The proposed algorithm operates in the submillisecond range on a standard PC. As an exemplary scenario, the task of driving along a challenging reference course is demonstrated.

math.OC↗

arXiv2018

Optimal Sensor Data Fusion Architecture for Object Detection in Adverse Weather Conditions

A good and robust sensor data fusion in diverse weather conditions is a quite challenging task. There are several fusion architectures in the literature, e.g. the sensor data can be fused right at the beginning (Early Fusion), or they can be first processed separately and then concatenated later (Late Fusion). In this work, different fusion architectures are compared and evaluated by means of object detection tasks, in which the goal is to recognize and localize predefined objects in a stream of data. Usually, state-of-the-art object detectors based on neural networks are highly optimized for good weather conditions, since the well-known benchmarks only consist of sensor data recorded in optimal weather conditions. Therefore, the performance of these approaches decreases enormously or even fails in adverse weather conditions. 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. A new training strategy is also introduced such that the performance of the object detector is greatly enhanced in adverse weather scenarios or if a sensor fails. Furthermore, the paper responds to the question if the detection accuracy can be increased further by providing the neural network with a-priori knowledge such as the spatial calibration of the sensors.

cs.CV↗

arXiv2018

Deep Object Tracking on Dynamic Occupancy Grid Maps Using RNNs

The comprehensive representation and understanding of the driving environment is crucial to improve the safety and reliability of autonomous vehicles. In this paper, we present a new approach to establish an environment model containing a segmentation between static and dynamic background and parametric modeled objects with shape, position and orientation. Multiple laser scanners are fused into a dynamic occupancy grid map resulting in a 360° perception of the environment. A single-stage deep convolutional neural network is combined with a recurrent neural network, which takes a time series of the occupancy grid map as input and tracks cell states and its corresponding object hypotheses. The labels for training are created unsupervised with an automatic label generation algorithm. The proposed methods are evaluated in real-world experiments in complex inner city scenarios using the aforementioned 360° laser perception. The results show a better object detection accuracy in comparison with our old approach as well as an AUC score of 0.946 for the dynamic and static segmentation. Furthermore, we gain an improved detection for occluded objects and a more consistent size estimation due to the usage of time series as input and the memory about previous states introduced by the recurrent neural network.

cs.RO↗

arXiv2018

Offline Object Extraction from Dynamic Occupancy Grid Map Sequences

A dynamic occupancy grid map (DOGMa) allows a fast, robust, and complete environment representation for automated vehicles. Dynamic objects in a DOGMa, however, are commonly represented as independent cells while modeled objects with shape and pose are favorable. The evaluation of algorithms for object extraction or the training and validation of learning algorithms rely on labeled ground truth data. Manually annotating objects in a DOGMa to obtain ground truth data is a time consuming and expensive process. Additionally the quality of labeled data depend strongly on the variation of filtered input data. The presented work introduces an automatic labeling process, where a full sequence is used to extract the best possible object pose and shape in terms of temporal consistency. A two direction temporal search is executed to trace single objects over a sequence, where the best estimate of its extent and pose is refined in every time step. Furthermore, the presented algorithm only uses statistical constraints of the cell clusters for the object extraction instead of fixed heuristic parameters. Experimental results show a well-performing automatic labeling algorithm with real sensor data even at challenging scenarios.

cs.CV↗

arXiv2018

Intentions of Vulnerable Road Users - Detection and Forecasting by Means of Machine Learning

Avoiding collisions with vulnerable road users (VRUs) using sensor-based early recognition of critical situations is one of the manifold opportunities provided by the current development in the field of intelligent vehicles. As especially pedestrians and cyclists are very agile and have a variety of movement options, modeling their behavior in traffic scenes is a challenging task. In this article we propose movement models based on machine learning methods, in particular artificial neural networks, in order to classify the current motion state and to predict the future trajectory of VRUs. Both model types are also combined to enable the application of specifically trained motion predictors based on a continuously updated pseudo probabilistic state classification. Furthermore, the architecture is used to evaluate motion-specific physical models for starting and stopping and video-based pedestrian motion classification. A comprehensive dataset consisting of 1068 pedestrian and 494 cyclist scenes acquired at an urban intersection is used for optimization, training, and evaluation of the different models. The results show substantial higher classification rates and the ability to earlier recognize motion state changes with the machine learning approaches compared to interacting multiple model (IMM) Kalman Filtering. The trajectory prediction quality is also improved for all kinds of test scenes, especially when starting and stopping motions are included. Here, 37\% and 41\% lower position errors were achieved on average, respectively.

cs.CV↗

arXiv2018

Object Detection on Dynamic Occupancy Grid Maps Using Deep Learning and Automatic Label Generation

We tackle the problem of object detection and pose estimation in a shared space downtown environment. For perception multiple laser scanners with 360° coverage were fused in a dynamic occupancy grid map (DOGMa). A single-stage deep convolutional neural network is trained to provide object hypotheses comprising of shape, position, orientation and an existence score from a single input DOGMa. Furthermore, an algorithm for offline object extraction was developed to automatically label several hours of training data. The algorithm is based on a two-pass trajectory extraction, forward and backward in time. Typical for engineered algorithms, the automatic label generation suffers from misdetections, which makes hard negative mining impractical. Therefore, we propose a loss function counteracting the high imbalance between mostly static background and extremely rare dynamic grid cells. Experiments indicate, that the trained network has good generalization capabilities since it detects objects occasionally lost by the label algorithm. Evaluation reaches an average precision (AP) of 75.9%

cs.CV↗

arXiv2017

Dynamic Occupancy Grid Prediction for Urban Autonomous Driving: A Deep Learning Approach with Fully Automatic Labeling

Long-term situation prediction plays a crucial role in the development of intelligent vehicles. A major challenge still to overcome is the prediction of complex downtown scenarios with multiple road users, e.g., pedestrians, bikes, and motor vehicles, interacting with each other. This contribution tackles this challenge by combining a Bayesian filtering technique for environment representation, and machine learning as long-term predictor. More specifically, a dynamic occupancy grid map is utilized as input to a deep convolutional neural network. This yields the advantage of using spatially distributed velocity estimates from a single time step for prediction, rather than a raw data sequence, alleviating common problems dealing with input time series of multiple sensors. Furthermore, convolutional neural networks have the inherent characteristic of using context information, enabling the implicit modeling of road user interaction. Pixel-wise balancing is applied in the loss function counteracting the extreme imbalance between static and dynamic cells. One of the major advantages is the unsupervised learning character due to fully automatic label generation. The presented algorithm is trained and evaluated on multiple hours of recorded sensor data and compared to Monte-Carlo simulation.

cs.RO↗

arXiv2016

A Random Finite Set Approach for Dynamic Occupancy Grid Maps with Real-Time Application

Grid mapping is a well established approach for environment perception in robotic and automotive applications. Early work suggests estimating the occupancy state of each grid cell in a robot's environment using a Bayesian filter to recursively combine new measurements with the current posterior state estimate of each grid cell. This filter is often referred to as binary Bayes filter (BBF). A basic assumption of classical occupancy grid maps is a stationary environment. Recent publications describe bottom-up approaches using particles to represent the dynamic state of a grid cell and outline prediction-update recursions in a heuristic manner. This paper defines the state of multiple grid cells as a random finite set, which allows to model the environment as a stochastic, dynamic system with multiple obstacles, observed by a stochastic measurement system. It motivates an original filter called the probability hypothesis density / multi-instance Bernoulli (PHD/MIB) filter in a top-down manner. The paper presents a real-time application serving as a fusion layer for laser and radar sensor data and describes in detail a highly efficient parallel particle filter implementation. A quantitative evaluation shows that parameters of the stochastic process model affect the filter results as theoretically expected and that appropriate process and observation models provide consistent state estimation results.

cs.RO↗