Abstract We address multi-view pedestrian detection in a setting where labeled data is collected using a multi-camera setup different from the one used for testing. While recent multi-view pedestrian detectors perform well on the camera rig used for training, their performance declines when applied to a different setup. To facilitate seamless deployment across varied camera rigs, we propose an unsupervised domain adaptation (UDA) method that adapts the model to new rigs without requiring additional labeled data. Specifically, we leverage the mean teacher self-training framework with a novel pseudo-labeling technique tailored to multi-view pedestrian detection. This method achieves state-of-the-art performance on multiple benchmarks, including MultiviewX $$\rightarrow $$ Wildtrack. Unlike previous methods, our approach eliminates the need for external labeled monocular datasets, thereby reducing reliance on labeled data. Extensive evaluations demonstrate the effectiveness of our method and validate key design choices. By enabling robust adaptation across camera setups, our work enhances the practicality of multi-view pedestrian detectors and establishes a strong UDA baseline for future research.

Antibiotic Resistance (AR) is a critical global health challenge that necessitates the development of cost-effective, efficient, and accurate diagnostic tools. Given the genetic basis of AR, techniques such as Polymerase Chain Reaction (PCR) that target specific resistance genes offer a promising approach for predictive diagnostics using a limited set of key genes. This study introduces GenoARM, a novel framework that integrates reinforcement learning (RL) with transformer-based models to optimize the selection of PCR gene tests and improve AR predictions, leveraging observed metadata for improved accuracy. In our evaluation, we developed several high-performing baselines and compared them using publicly available datasets derived from real-world bacterial samples representing multiple clinically relevant pathogens. The results show that all evaluated methods achieve strong and reliable performance when metadata is not utilized. When metadata is introduced and the number of selected genes increases, GenoARM demonstrates superior performance due to its capacity to approximate rewards for unseen and sparse combinations. Overall, our framework represents a major advancement in optimizing diagnostic tools for AR in clinical settings.

Ensuring the safety of autonomous robots, such as self-driving vehicles, requires extensive testing across diverse driving scenarios. Simulation is a key ingredient for conducting such testing in a cost-effective and scalable way. Neural rendering methods have gained popularity, as they can build simulation environments from collected logs in a data-driven manner. However, existing neural radiance field (NeRF) methods for sensor-realistic rendering of camera and lidar data suffer from low rendering speeds, limiting their applicability for large-scale testing. While 3D Gaussian Splatting (3DGS) enables real-time rendering, current methods are limited to camera data and are unable to render lidar data essential for autonomous driving. To address these limitations, we propose SplatAD, the first 3DGS-based method for realistic, real-time rendering of dynamic scenes for both camera and lidar data. SplatAD accurately models key sensor-specific phenomena such as rolling shutter effects, lidar intensity, and lidar ray dropouts, using purposebuilt algorithms to optimize rendering efficiency. Evaluation across three autonomous driving datasets demonstrates that SplatAD achieves state-of-the-art rendering quality with up to +2 PSNR for NVS and +3 PSNR for reconstruction while increasing rendering speed over NeRF-based methods by an order of magnitude. See here for our project page.

This paper uses multi-object tracking methods known from the radar tracking community to address the problem of pedestrian tracking using 2D bounding box detections. The standard point-object (SPO) model is adopted, and the posterior density is computed using the Poisson multi-Bernoulli mixture (PMBM) filter. The selection of the model parameters rooted in continuous time is discussed, including the birth and survival probabilities. Some parameters are selected from the first principles, while others are identified from the data, which is, in this case, the publicly available MOT-17 dataset. Although the resulting PMBM algorithm yields promising results, a mismatch between the SPO model and the data is revealed. The model-based approach assumes that modifying the problematic components causing the SPO model-data mismatch will lead to better modelbased algorithms in future developments.

The concept of 6G distributed integrated sensing and communications (DISAC) builds upon the functionality of integrated sensing and communications (ISAC) by integrating distributed architectures, significantly enhancing both sensing and communication coverage and performance. In 6G DISAC systems, tracking target trajectories requires base stations (BSs) to hand over their tracked targets to neighboring BSs. Determining what information to share, where, how, and when is critical to effective handover. This paper addresses the target handover challenge in DISAC systems and introduces a method enabling BSs to share essential target trajectory information at appropriate time steps, facilitating seamless handovers to other BSs. The target tracking problem is tackled using the standard trajectory Poisson multi-Bernoulli mixture (TPMBM) filter, enhanced with the proposed handover algorithm. Simulation results confirm the effectiveness of the implemented tracking solution.

Noise-contrastive estimation (NCE) is a popular method for estimating unnormalised probabilistic models, such as energy-based models, which are effective for modelling complex data distributions. Unlike classical maximum likelihood (ML) estimation that relies on importance sampling (resulting in ML-IS) or MCMC (resulting in contrastive divergence, CD), NCE uses a proxy criterion to avoid the need for evaluating an often intractable normalisation constant. Despite apparent conceptual differences, we show that two NCE criteria, ranking NCE (RNCE) and conditional NCE (CNCE), can be viewed as ML estimation methods. Specifically, RNCE is equivalent to ML estimation combined with conditional importance sampling, and both RNCE and CNCE are special cases of CD. These findings bridge the gap between the two method classes and allow us to apply techniques from the ML-IS and CD literature to NCE, offering several advantageous extensions.

Neural radiance fields (NeRFs) have gained popularity in the autonomous driving (AD) community. Recent meth-ods show NeRFs' potential for closed-loop simulation, en-abling testing of AD systems, and as an advanced training data augmentation technique. However, existing meth-ods often require long training times, dense semantic su-pervision, or lack generalizability. This, in turn, hinders the application of NeRFs for AD at scale. In this paper, we propose NeuRAD, a robust novel view synthesis method tailored to dynamic AD data. Our method features simple network design, extensive sensor modeling for both cam-era and lidar - including rolling shutter, beam divergence and ray dropping - and is applicable to multiple datasets out of the box. We verify its performance on five popular AD datasets, achieving state-of-the-art performance across the board. To encourage further development, we openly release the NeuRAD source code.

We consider unsupervised domain adaptation (UDA) for semantic segmentation in which the model is trained on a labeled source dataset and adapted to an unlabeled target dataset. Unfortunately, current self-training methods are susceptible to misclassified pseudo-labels resulting from erroneous predictions. Since certain classes are typically associated with less reliable predictions in UDA, reducing the impact of such pseudo-labels without skewing the training towards some classes is notoriously difficult. To this end, we propose an extensive cut-and-paste strategy (ECAP) to leverage reliable pseudo-labels through data augmentation. Specifically, ECAP maintains a memory bank of pseudo-labeled target samples throughout training and cut-and-pastes the most confident ones onto the current training batch. We implement ECAP on top of the recent method MIC and boost its performance on two synthetic-to-real domain adaptation benchmarks. Notably, MIC+ECAP reaches an unprecedented performance of 69.1 mIoU on the Synthia $\rightarrow$ Cityscapes benchmark. Our code is available at https://github.com/ErikBrorsson/ECAP.

Research connecting text and images has recently seen several breakthroughs, with models like CLIP, DALL•E 2, and Stable Diffusion. However, the connection between text and other visual modalities, such as lidar data, has received less attention, prohibited by the lack of text-lidar datasets. In this work, we propose LidarCLIP, a mapping from automotive point clouds to a pre-existing CLIP embedding space. Using image-lidar pairs, we supervise a point cloud encoder with the image CLIP embeddings, effectively relating text and lidar data with the image domain as an intermediary. We show the effectiveness of Lidar-CLIP by demonstrating that lidar-based retrieval is generally on par with image-based retrieval, but with complementary strengths and weaknesses. By combining image and lidar features, we improve upon both single-modality methods and enable a targeted search for challenging detection scenarios under adverse sensor conditions. We also explore zero-shot classification and show that LidarCLIP outperforms existing attempts to use CLIP for point clouds by a large margin. Finally, we leverage our compatibility with CLIP to explore a range of applications, such as point cloud captioning and lidar-to-image generation, without any additional training. Code and pre-trained models at github.com/atonderski/lidarclip.

Open-set semi-supervised learning (OSSL) embodies a practical scenario within semi-supervised learning, wherein the unlabeled training set encompasses classes absent from the labeled set. Many existing OSSL methods assume that these out-of-distribution data are harmful and put effort into excluding data belonging to unknown classes from the training objective. In contrast, we propose an OSSL framework that facilitates learning from all unlabeled data through self-supervision. Additionally, we utilize an energy-based score to accurately recognize data belonging to the known classes, making our method well-suited for handling uncurated data in deployment. We show through extensive experimental evaluations that our method yields state-of-the-art results on many of the evaluated benchmark problems in terms of closed-set accuracy and open-set recognition when compared with existing methods for OSSL. Our code is available at https://github.com/walline/ssl-tf2-sefoss.

This paper presents an efficient implementation of the trajectory Poisson multi-Bernoulli (PMB) filter for multiple extended object tracking (EOT), which directly estimates a set of object trajectories. The trajectory PMB filter propagates a PMB density on the posterior of sets of trajectories through the filtering recursions over time, where the multi-Bernoulli (MB) mixture in the PMB mixture (PMBM) posterior after each update step is approximated as a single MB. The efficient MB approximation is achieved by first running a blocked Gibbs sampler on the joint posterior of the set of trajectories and the measurement association variables. The single-object measurement model is assumed to be a Poisson point process which enables us to parallelize the sampling across all objects and association variables, respectively. Then, samples of object states are utilized to form the approximate MB density via Kullback-Leibler divergence minimization. Simulation results on EOT with known and constant elliptical shapes show that the TPMB implementation using blocked Gibbs sampling outperforms the state-of-the-art TPMB implementation using loopy belief propagation with significantly reduced runtime.

Millimeter-wave (mmWave) signals provide attractive opportunities for sensing due to their inherent geometrical connections to physical propagation channels. Two common modalities used in mmWave sensing are monostatic and bistatic sensing, which are usually considered separately. By integrating these two modalities, information can be shared between them, leading to improved sensing performance. In this paper, we investigate the integration of monostatic and bistatic sensing in a 5G mmWave scenario, implement the extended Kalman-Poisson multi-Bernoulli sequential filters to solve the sensing problems, and propose a method to periodically fuse user states and maps from two sensing modalities.

The fusion of multiple probability densities has important applications in many fields, including, for example, multi-sensor signal processing, robotics, and smart environments. In this paper, we demonstrate that deep learning based methods can be used to fuse multi-object densities. Given a scenario with several sensors with possibly different field-of-views, tracking is performed locally in each sensor by a tracker, which produces random finite set multi-object densities. To fuse outputs from different trackers, we adapt a recently proposed transformer-based multi-object tracker, where the fusion result is a global multi-object density, describing the set of all alive objects at the current time. We compare the performance of the transformer-based fusion method with a well-performing model-based Bayesian fusion method in several simulated scenarios with different parameter settings using synthetic data. The simulation results show that the transformer-based fusion method outperforms the model-based Bayesian method in our experimental scenarios. The code is available at https://github.com/Lechili/DeepFusion.

Networks in 5G and beyond utilize millimeter wave (mmWave) radio signals, large bandwidths, and large antenna arrays, which bring opportunities in jointly localizing the user equipment and mapping the propagation environment, termed as simultaneous localization and mapping (SLAM). Existing approaches mainly rely on delays and angles, and ignore the Doppler, although it contains geometric information. In this paper, we study the benefits of exploiting Doppler in SLAM through deriving the posterior Cramér-Rao bounds (PCRBs) and formulating the extended Kalman-Poisson multi-Bernoulli sequential filtering solution with Doppler as one of the involved measurements. Both theoretical PCRB analysis and simulation results demonstrate the efficacy of utilizing Doppler.

5G millimeter wave (mmWave) signals have inherent geometric connections to the propagation channel and the propagation environment. Thus, they can be used to jointly localize the receiver and map the propagation environment, which is termed as simultaneous localization and mapping (SLAM). One of the most important tasks in the 5G SLAM is to deal with the nonlinearity of the measurement model. To solve this problem, existing 5G SLAM approaches rely on sigma-point or extended Kalman filters, linearizing the measurement function with respect to the prior probability density function (PDF). In this paper, we study the linearization of the measurement function with respect to the posterior PDF, and implement the iterated posterior linearization filter into the Poisson multi-Bernoulli SLAM filter. Simulation results demonstrate the accuracy and precision improvements of the resulting SLAM filter.

Following the success of supervised learning, semi-supervised learning (SSL) is now becoming increasingly popular. SSL is a family of methods, which in addition to a labeled training set, also use a sizable collection of unlabeled data for fitting a model. Most of the recent successful SSL methods are based on pseudo-labeling approaches: letting confident model predictions act as training labels. While these methods have shown impressive results on many benchmark datasets, a drawback of this approach is that not all unlabeled data are used during training. We propose a new SSL algorithm, DoubleMatch, which combines the pseudo-labeling technique with a self-supervised loss, enabling the model to utilize all unlabeled data in the training process. We show that this method achieves state-of-the-art accuracies on multiple benchmark datasets while also reducing training times compared to existing SSL methods. Code is available at https://github.com/walline/doublematch.

Millimeter wave (mmWave) signals are useful for simultaneous localization and mapping (SLAM), due to their inherent geometric connection to the propagation environment and the propagation channel. To solve the SLAM problem, existing approaches rely on sigma-point or particle-based approximations, leading to high computational complexity, precluding real-time execution. We propose a novel low-complexity SLAM filter, based on the Poisson multi-Bernoulli mixture (PMBM) filter. It utilizes the extended Kalman (EK) first-order Taylor series based Gaussian approximation of the filtering distribution, and applies the track-oriented marginal multi-Bernoulli/Poisson (TOMB/P) algorithm to approximate the resulting PMBM as a Poisson multi-Bernoulli (PMB). The filter can account for different landmark types in radio SLAM and multiple data association hypotheses. Hence, it has an adjustable complexity/performance trade-off. Simulation results show that the developed SLAM filter can greatly reduce the computational cost, while it keeps the good performance of mapping and user state estimation.

The state of the art in semantic segmentation is steadily increasing in performance, resulting in more precise and reliable segmentations in many different applications. However, progress is limited by the cost of generating labels for training, which sometimes requires hours of manual labor for a single image. Because of this, semi-supervised methods have been applied to this task, with varying degrees of success. A key challenge is that common augmentations used in semi-supervised classification are less effective for semantic segmentation. We propose a novel data augmentation mechanism called ClassMix, which generates augmentations by mixing unlabelled samples, by leveraging on the network's predictions for respecting object boundaries. We evaluate this augmentation technique on two common semi-supervised semantic segmentation benchmarks, showing that it attains state-of-the-art results. Lastly, we also provide extensive ablation studies comparing different design decisions and training regimes.

Semantic segmentation models based on convolutional neural networks have recently displayed remarkable performance for a multitude of applications. However, these models typically do not generalize well when applied on new domains, especially when going from synthetic to real data. In this paper we address the problem of unsupervised do-main adaptation (UDA), which attempts to train on labelled data from one domain (source domain), and simultaneously learn from unlabelled data in the domain of interest (target domain). Existing methods have seen success by training on pseudo-labels for these unlabelled images. Multiple techniques have been proposed to mitigate low-quality pseudo-labels arising from the domain shift, with varying degrees of success. We propose DACS: Domain Adaptation via Cross-domain mixed Sampling, which mixes images from the two domains along with the corresponding labels and pseudo-labels. These mixed samples are then trained on, in addition to the labelled data itself. We demonstrate the effectiveness of our solution by achieving state-of-the-art results for GTA5 to Cityscapes, a common synthetic-to-real semantic segmentation benchmark for UDA.

Evaluating the performance of multi-object tracking (MOT) methods is not straightforward, and existing performance measures fail to consider all the available uncertainty information in the MOT context. This can lead practitioners to select models which produce uncertainty estimates of lower quality, negatively impacting any downstream systems that rely on them. Additionally, most MOT performance measures have hyperparameters, which makes comparisons of different trackers less straightforward. We propose the use of the negative log-likelihood (NLL) of the multi-object posterior given the set of ground-truth objects as a performance measure. This measure takes into account all available uncertainty information in a sound mathematical manner without hyperparameters. We provide efficient algorithms for approximating the computation of the NLL for several common MOT algorithms, show that in some cases it decomposes and approximates the widely-used GOSPA metric, and provide several illustrative examples highlighting the advantages of the NLL in comparison to other MOT performance measures.

In this paper we propose a method for accurate localization of a multi-layer LiDAR sensor in a pre-recorded map, given a coarse initialization pose. The foundation of the algorithm is the usage of neural network optical flow predictions. We train a network to encode representations of the sensor measurement and the map, and then regress flow vectors at each spatial position in the sensor feature map. The flow regression network is straight-forward to train, and the resulting flow field can be used with standard techniques for computing sensor pose from sensor-to-map correspondences. Additionally, the network can regress flow at different spatial scales, which means that it is able to handle both position recovery and high accuracy localization. We demonstrate average localization accuracy of $\lt 0.04{\mathrm {m}}$ position and $\lt 0.1^{\circ}$ heading angle for a vehicle driving application with simulated LiDAR measurements, which is similar to point-to-point iterative closest point (ICP). The algorithm typically manages to recover position with prior error of more than 20m and is significantly more robust to scenes with non-salient or repetitive structure than the baselines used for comparison.

This paper presents two multi-Bernoulli filters on sets of trajectories for multiple target tracking. The first filter provides a multi-Bernoulli approximation of the posterior density over the set of alive trajectories at the current time step. The second filter provides a multi-Bernoulli approximation of the posterior density over the set of all trajectories (alive and dead) up to the current time. We also explain the Gaussian implementation of the filters and compare them with other multiple target tracking algorithms in a simulated scenario.

In this paper we introduce spatiotemporal constraints for trajectories, i.e., restrictions that the trajectory must be in some part of the state space (spatial constraint) at some point in time (temporal constraint). Spatiotemporal contraints on trajectories can be used to answer a range of important questions, including, e.g., “where did the person that were in area A at time t, go afterwards?”. We discuss how multiple constraints can be combined into sets of constraints, and we then apply sets of constraints to set of trajectories densities, specifically Poisson Multi-Bernoulli Mixture (PMBM) densities. For Poisson target birth, the exact posterior density is PMBM for both point targets and extended targets. In the paper we show that if the unconstrained set of trajectories density is PMBM, then the constrained density is also PMBM. Examples of constrained trajectory densities motivate and illustrate the key results.

This paper presents a solution for recovering full trajectory information, via the calculation of the posterior of the set of trajectories, from a sequence of multitarget (unlabelled) filtering densities and the multitarget dynamic model. Importantly, the proposed solution opens an avenue of trajectory estimation possibilities for multitarget filters that do not explicitly estimate trajectories. In this paper, we first derive a general multitrajectory forward-backward smoothing equation based on sets of trajectories and the random finite set framework. Then we show how to sample sets of trajectories using backward simulation when the multitarget filtering densities are multi-Bernoulli processes. The proposed approach is demonstrated in a simulation study.

5G millimeter wave (mmWave) signals can be used to jointly localize the receiver and map the propagation environment in vehicular networks, which is a typical simultaneous localization and mapping (SLAM) problem. Mapping the environment is challenging, due to measurements comprising both specular and diffuse multipath components, where diffuse multipath is usually considered as a perturbation. We here propose a novel method to utilize all available multipath signals from each landmark for mapping and incorporate this into a Poisson multi-Bernoulli mixture for the 5G SLAM problem. Simulation results demonstrate the efficacy of the proposed scheme.

The aim of this article is to present Levenberg-Marquardt and line-search extensions of the classical iterated extended Kalman smoother (IEKS) which has previously been shown to be equivalent to the Gauss-Newton method. The algorithms are derived by rewriting the algorithm's steps in forms that can be efficiently implemented using modified EKS iterations. The resulting algorithms are experimentally shown to have superior convergence properties over the classical IEKS.

This paper presents the probability hypothesis density (PHD) filter for sets of trajectories: the trajectory probability density (TPHD) filter. The TPHD filter is capable of estimating trajectories in a principled way without requiring to evaluate all measurement-to-target association hypotheses. The TPHD filter is based on recursively obtaining the best Poisson approximation to the multitrajectory filtering density in the sense of minimising the Kullback-Leibler divergence. We also propose a Gaussian mixture implementation of the TPHD recursion. Finally, we include simulation results to show the performance of the proposed algorithm.

The Poisson multi-Bernoulli mixture (PMBM) is an unlabelled multi-target distribution for which the prediction and update are closed. It has a Poisson birth process, and new Bernoulli components are generated on each new measurement as a part of the Bayesian measurement update. The PMBM filter is similar to the multiple hypothesis tracker (MHT), but seemingly does not provide explicit continuity between time steps. This paper considers a recently developed formulation of the multi-target tracking problem as a random finite set (RFS) of trajectories, and derives two trajectory RFS filters, called PMBM trackers. The PMBM trackers efficiently estimate the set of trajectories, and share hypothesis structure with the PMBM filter. By showing that the prediction and update in the PMBM filter can be viewed as an efficient method for calculating the time marginals of the RFS of trajectories, continuity in the same sense as MHT is established for the PMBM filter.

This paper proposes an efficient implementation of the Poisson multi-Bernoulli mixture (PMBM) trajectory filter. The proposed implementation performs track-oriented N-scan pruning to limit complexity, and uses dual decomposition to solve the involved multi-frame assignment problem. In contrast to the existing PMBM filter for sets of targets, the PMBM trajectory filter is based on sets of trajectories which ensures that track continuity is formally maintained. The resulting filter is an efficient and scalable approximation to a Bayes optimal multi-target tracking algorithm, and its performance is compared, in a simulation study, to the PMBM target filter, and the delta generalized labelled multi-Bernoulli filter, in terms of state/trajectory estimation error and computational time.

In this letter, we propose an iterative Kalman type algorithm based on posterior linearization. The proposed algorithm uses a nested loop structure to optimize the mean of the estimate in the inner loop and update the covariance, which is a computationally more expensive operation, only in the outer loop. The optimization of the mean update is done using a damped algorithm to avoid divergence. Our simulations show that the proposed algorithm is more accurate than existing iterative Kalman filters.

This paper presents the generalized optimal sub-pattern assignment (GOSPA) metric on the space of finite sets of targets. Compared to the well-established optimal sub-pattern assignment (OSPA) metric, GOSPA is not normalised by the cardinality of the largest set and it penalizes cardinality errors differently, which enables us to express it as an optimisation over assignments instead of permutations. An important consequence of this is that GOSPA allows us to penalize localization errors for detected targets and the errors due to missed and false targets, as indicated by traditional multiple target tracking (MTT) performance measures, in a sound manner. In addition, we extend the GOSPA metric to the space of random finite sets, which is important to evaluate MTT algorithms via simulations in a rigorous way.

In this paper, we evaluate the performance of labelled and unlabelled multi-Bernoulli conjugate priors for multi-target filtering. Filters are compared in two different scenarios with performance assessed using the generalised optimal sub-pattern assignment (GOSPA) metric. The first scenario under consideration is tracking of well-spaced targets. The second scenario is more challenging and considers targets in close proximity, for which filters may suffer from coalescence. We analyse various aspects of the filters in these two scenarios. Though all filters have pros and cons, the Poisson multi-Bernoulli filters arguably provide the best overall performance concerning GOSPA and computational time.

In this work, a deep learning approach has been developed to carry out road detection using only LIDAR data. Starting from an unstructured point cloud, top-view images encoding several basic statistics such as mean elevation and density are generated. By considering a top-view representation, road detection is reduced to a single-scale problem that can be addressed with a simple and fast fully convolutional neural network (FCN). The FCN is specifically designed for the task of pixel-wise semantic segmentation by combining a large receptive field with high-resolution feature maps. The proposed system achieved excellent performance and it is among the top-performing algorithms on the KITTI road benchmark. Its fast inference makes it particularly suitable for real-time applications.

Environment perception is a key enabling technology in autonomous vehicles, and multiple object tracking is an important part of this. High resolution sensors, such as automotive radar and lidar, leads to the so called extended target tracking problem, in which there are multiple detections per tracked object. For computationally feasible multiple extended target tracking, the data association problem must be handled. Previous work has relied on the use of clustering algorithms, together with assignment algorithms, to achieve this. In this paper we present a stochastic optimisation method that directly maximises the desired likelihood function, and solves the problem in a single step, rather than two steps (clustering+assignment). The proposed method is evaluated against previous work in an experiment where Velodyne data is used to track pedestrians, and the results clearly show that the proposed method achieves the best performance, especially in challenging scenarios.

This paper presents an algorithm for estimating the shape of the road ahead of a host vehicle equipped with the following onboard sensors: a camera, a radar, and vehicle internal sensors. The aim is to accurately describe the road geometry up to 200 m ahead in highway scenarios. This purpose is accomplished by deriving a precise clothoid-based road model for which we design a Bayesian fusion framework. Using this framework, the road geometry is estimated using sensor observations on the shape of the lane markings, the heading of leading vehicles, and the position of roadside radar reflectors. The evaluation on sensor data shows that the proposed algorithm is capable of capturing the shape of the road well, even in challenging mountainous highways.

We propose the infinite factorial dynamic model (iFDM), a general Bayesian nonparametric model for source separation. Our model builds on the Markov Indian buffet process to consider a potentially unbounded number of hidden Markov chains (sources) that evolve independently according to some dynamics, in which the state space can be either discrete or continuous. For posterior inference, we develop an algorithm based on particle Gibbs with ancestor sampling that can be efficiently applied to a wide range of source separation problems. We evaluate the performance of our iFDM on four well-known applications: multitarget tracking, cocktail party, power disaggregation, and multiuser detection. Our experimental results show that our approach for source separation does not only outperform previous approaches, but it can also handle problems that were computationally intractable for existing approaches.

In the research on autonomous vehicles, self-localization is an important problem to solve. In this paper we present a localization algorithm based on a map and a set of off-the-shelf sensors, with the purpose of evaluating this low-cost solution with respect to localization performance. The used test vehicle is equipped with a Global Positioning System receiver, a gyroscope, wheel speed sensors, a camera providing information about lane markings, and a radar detecting landmarks along the road. Evaluation shows that the localization result is within or close to the requirements for autonomous driving when lane markers and good radar landmarks are present. However, it also indicates that the solution is not robust enough to handle situations when one of these information sources is absent.

A marginal version of the enumeration Bayesian Cramér-Rao Bound (EBCRB) for jump Markov systems is proposed. It is shown that the proposed bound is at least as tight as EBCRB and the improvement stems from better handling of the nonlinearities. The new bound is illustrated to yield tighter results than BCRB and EBCRB on a benchmark example.

This paper describes an algorithm for estimating the road ahead of a host vehicle based on the measurements from several onboard sensors: a camera, a radar, wheel speed sensors, and an inertial measurement unit. We propose a novel road model that is able to describe the road ahead with higher accuracy than the usual polynomial model. We also develop a Bayesian fusion system that uses the following information from the surroundings: lane marking measurements obtained by the camera and leading vehicle and stationary object measurements obtained by a radar-camera fusion system. The performance of our fusion algorithm is evaluated in several drive tests. As expected, the more information we use, the better the performance is.

In this work, we introduce the particle PHD forward filter - backward simulator (PHD-FFBSi) capable of dealing with uncertainties in the labeling of tracks that appear when tracking two targets in close proximity with measurements that do not discriminate between them. The Forward Filter Backward Simulator is a smoothing technique based on rejection sampling for the calculation of the probabilities of association between targets and tracks. The forward filter is a particle implementation of the Probability Hypothesis Density (PHD) filter that presents advantages over an SIR filter. Difficulties that arise due to the presence of target birth and death processes are addressed through modifications to the fast FFBSi. Simulations show the new particle filter of asymptotically linear complexity in the number of particles calculates correct target label probabilities at varying levels of measurement noise.

Particle smoothing is useful for offline state inference and parameter learning in nonlinear/non-Gaussian state-space models. However, many particle smoothers, such as the popular forward filter/backward simulator (FFBS), are plagued by a quadratic computational complexity in the number of particles. One approach to tackle this issue is to use rejection-sampling-based FFBS (RS-FFBS), which asymptotically reaches linear complexity. In practice, however, the constants can be quite large and the actual gain in computational time limited. In this contribution, we develop a hybrid method, governed by an adaptive stopping rule, in order to exploit the benefits, but avoid the drawbacks, of RS-FFBS. The resulting particle smoother is shown in a simulation study to be considerably more computationally efficient than both FFBS and RS-FFBS.

The optimal homotopy filter is a nonlinear filtering approximation which seeks an optimal parameterisation for the posterior. The search for an optimal parameterisation is performed by constructing a homotopy between the prior and posterior and solving the resulting ordinary differential equation. Here the optimal homotopy filter is applied to the problem of bearings-only tracking. A simulation analysis shows that the performance of the optimal homotopy filter compares favourably to established algorithms.

A novel approach to estimate (inverse) complex covariance matrices is proposed. By considering the class of unitary invariant estimators, the main challenge lies in estimating the underlying eigenvalues from sampled versions. By exploiting that the distribution of the sample eigenvalues can be derived in closed form, a Maximum A Posteriori (MAP) based scheme is then derived. The performance of the derived estimator is simulated and results indicate that the proposed scheme shows performance similar to one of the best estimators known to date. The main advantage lies in that the proposed solution only requires numerical optimization over a P-dimensional space where P is the size of the covariance matrix.

In this work, the problem of receiver design for phase noise estimation and data detection in the presence of oscillator phase noise in a point-to-point multiple-input multiple-output (MIMO) system is addressed. First, we discuss some interesting and challenging aspects in receiver design for MIMO systems in the presence of Wiener phase noise. Then, using the variational Bayesian (VB) framework, a joint iterative phase noise estimator and symbol detector are developed based on inverse Gibbs or variational free energy maximization. Further, the symbol error probability (SEP) of the newly proposed iterative scheme is compared with the optimal maximum likelihood (ML) detector with perfect phase information for 16-phase shift keying (PSK) and 16-quadrature amplitude modulation (QAM) schemes.

In this paper, we present the Cooperative Adaptive Cruise Control (CACC) architecture, which was proposed and implemented by the team from Chalmers University of Technology, Göteborg, Sweden, that joined the Grand Cooperative Driving Challenge (GCDC) in 2011. The proposed CACC architecture consists of the following three main components, which are described in detail: 1) communication; 2) sensor fusion; and 3) control. Both simulation and experimental results are provided, demonstrating that the proposed CACC system can drive within a vehicle platoon while minimizing the inter-vehicle spacing within the allowed range of safety distances, tracking a desired speed profile, and attenuating acceleration shockwaves.

Optimizing over a variant of the Mean Optimal Subpattern Assignment (MOSPA) metric is equivalent to optimizing over the track accuracy statistic often used in target tracking benchmarks. Past work has shown how obtaining a Minimum MOSPA (MMOSPA) estimate for target locations from a Probability Density Function (PDF) outperforms more traditional methods (e.g. maximum likelihood (ML) or Minimum Mean Squared Error (MMSE) estimates) with regard to track accuracy metrics. In this paper, we derive an approximation to the MMOSPA estimator in the two-target case, which is generally very complicated, based on minimizing a Bhattacharyya-like bound. It has a particularly nice form for Gaussian mixtures. We thence compare the new estimator to that obtained from using the MMSE and the optimal MMOSPA estimators.

In this paper, we describe a minimal mean square error (MMSE) optimal interpolation filter for discrete random signals. We explicitly derive the interpolation filter for a first-order autoregressive process (AR(1)), and show that the filter depends only on the two adjacent points. The result is extended by developing an algorithm called local AR approximation (LARA), where a random signal is locally estimated as an AR(1) process. Experimental evaluation illustrates that LARA interpolation yields a lower mean square error than other common interpolation techniques, including linear, spline and local polynomial approximation (LPA).

Reliable and accurate vehicle motion models are of vital importance for automotive active safety systems for a number of reasons. First of all, these models are necessary in tracking algorithms that provide the safety system with information. Second, the motion model is often used by the safety application to make long-term predictions about the future traffic situation. These predictions are then part of the basic data used by the system to determine if, when, and how to intervene. In this paper, we suggest a framework for designing accurate vehicle motion models. The resulting models differ from conventional models in that the expected control input from the driver is included. By also providing a methodology for a formal treatment of the uncertainties, a model structure well suited, e.g., in a tracking algorithm, is obtained. To utilize the framework in an application will require careful design and validation of submodels to calculate the expected driver control input. We illustrate the potential of the framework by examining the performance for a specific model example using real measurements. The properties are compared with those of a constant acceleration model. Evaluations indicate that the proposed model yields better predictions and that it has an ability to estimate the prediction uncertainties.

The interacting multiple model filter has long been the preferred method to handle multiple models in target tracking. The filter finds a suboptimal solution to a problem, which implicitly assumes that immediate model shifts have the highest probability. We argue that this model-shift property does not capture the typical nature of maneuvering targets, namely that changes in target dynamics persist for some time. In this paper, we propose an adjusted switch time assumption that forces the dynamic models to remain fixed for a specified time. The modified filtering problem has lower complexity, and we derive a state estimation algorithm that is close to optimal in many scenarios. From Monte Carlo simulations, the new filter is found to yield a 20% decrease in root mean square position error, compared to the interacting multiple model filter in situations where the switch-time conditions are fulfilled.

The main purpose of the paper is to show that significant improvements in infrared land mine detectors can be achieved, by also considering visual wavelength images. A Bayesian approach, based on dual-band data, is presented that incorporates prior knowledge regarding external parameters such as recent weather, burial depth and soil moisture. By noting that most relevant backgrounds render rotationally invariant statistics, a low dimensional parameterization of the noise space is derived. Simulations show the performance of three different detectors; first the standard detector used, the matched filter which correlates the infrared image with the known mine shape; secondly a detector which models the spatial statistics of the infrared background while neglecting the visual wavelength data, and thirdly the proposed detector that exploits the full dual-band space. The second detector outperforms the matched filter, and is significantly improved by also utilizing the visual wavelength image.