arXiv subjects

Michael Arens

Publications and source records attributed to Michael Arens.

53 records · Page 3Linked to original sources

arXiv2020

A Short Note on Analyzing Sequence Complexity in Trajectory Prediction Benchmarks

The analysis and quantification of sequence complexity is an open problem frequently encountered when defining trajectory prediction benchmarks. In order to enable a more informative assembly of a data basis, an approach for determining a dataset representation in terms of a small set of distinguishable prototypical sub-sequences is proposed. The approach employs a sequence alignment followed by a learning vector quantization (LVQ) stage. A first proof of concept on synthetically generated and real-world datasets shows the viability of the approach.

cs.LG↗

arXiv2020

Image-based OoD-Detector Principles on Graph-based Input Data in Human Action Recognition

Living in a complex world like ours makes it unacceptable that a practical implementation of a machine learning system assumes a closed world. Therefore, it is necessary for such a learning-based system in a real world environment, to be aware of its own capabilities and limits and to be able to distinguish between confident and unconfident results of the inference, especially if the sample cannot be explained by the underlying distribution. This knowledge is particularly essential in safety-critical environments and tasks e.g. self-driving cars or medical applications. Towards this end, we transfer image-based Out-of-Distribution (OoD)-methods to graph-based data and show the applicability in action recognition. The contribution of this work is (i) the examination of the portability of recent image-based OoD-detectors for graph-based input data, (ii) a Metric Learning-based approach to detect OoD-samples, and (iii) the introduction of a novel semi-synthetic action recognition dataset. The evaluation shows that image-based OoD-methods can be applied to graph-based data. Additionally, there is a gap between the performance on intraclass and intradataset results. First methods as the examined baseline or ODIN provide reasonable results. More sophisticated network architectures - in contrast to their image-based application - were surpassed in the intradataset comparison and even lead to less classification accuracy.

cs.CV↗

arXiv2019

Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey

Deep Learning is a state-of-the-art technique to make inference on extensive or complex data. As a black box model due to their multilayer nonlinear structure, Deep Neural Networks are often criticized to be non-transparent and their predictions not traceable by humans. Furthermore, the models learn from artificial datasets, often with bias or contaminated discriminating content. Through their increased distribution, decision-making algorithms can contribute promoting prejudge and unfairness which is not easy to notice due to lack of transparency. Hence, scientists developed several so-called explanators or explainers which try to point out the connection between input and output to represent in a simplified way the inner structure of machine learning black boxes. In this survey we differ the mechanisms and properties of explaining systems for Deep Neural Networks for Computer Vision tasks. We give a comprehensive overview about taxonomy of related studies and compare several survey papers that deal with explainability in general. We work out the drawbacks and gaps and summarize further research ideas.

cs.AI↗

arXiv2019

Modeling continuous-time stochastic processes using $\mathcal{N}$-Curve mixtures

Representations of sequential data are commonly based on the assumption that observed sequences are realizations of an unknown underlying stochastic process, where the learning problem includes determination of the model parameters. In this context the model must be able to capture the multi-modal nature of the data, without blurring between modes. This property is essential for applications like trajectory prediction or human motion modeling. Towards this end, a neural network model for continuous-time stochastic processes usable for sequence prediction is proposed. The model is based on Mixture Density Networks using Bézier curves with Gaussian random variables as control points (abbrev.: $\mathcal{N}$-Curves). Key advantages of the model include the ability of generating smooth multi-mode predictions in a single inference step which reduces the need for Monte Carlo simulation, as required in many multi-step prediction models, based on state-of-the-art neural networks. Essential properties of the proposed approach are illustrated by several toy examples and the task of multi-step sequence prediction. Further, the model performance is evaluated on two real world use-cases, i.e. human trajectory prediction and human motion modeling, outperforming different state-of-the-art models.

stat.ML↗

arXiv2019

An RNN-based IMM Filter Surrogate

The problem of varying dynamics of tracked objects, such as pedestrians, is traditionally tackled with approaches like the Interacting Multiple Model (IMM) filter using a Bayesian formulation. By following the current trend towards using deep neural networks, in this paper an RNN-based IMM filter surrogate is presented. Similar to an IMM filter solution, the presented RNN-based model assigns a probability value to a performed dynamic and, based on them, puts out a multi-modal distribution over future pedestrian trajectories. The evaluation is done on synthetic data, reflecting prototypical pedestrian maneuvers.

cs.CV↗

arXiv2019

Investigation on Combining 3D Convolution of Image Data and Optical Flow to Generate Temporal Action Proposals

In this paper, several variants of two-stream architectures for temporal action proposal generation in long, untrimmed videos are presented. Inspired by the recent advances in the field of human action recognition utilizing 3D convolutions in combination with two-stream networks and based on the Single-Stream Temporal Action Proposals (SST) architecture, four different two-stream architectures utilizing sequences of images on one stream and sequences of images of optical flow on the other stream are subsequently investigated. The four architectures fuse the two separate streams at different depths in the model; for each of them, a broad range of parameters is investigated systematically as well as an optimal parametrization is empirically determined. The experiments on the THUMOS'14 dataset show that all four two-stream architectures are able to outperform the original single-stream SST and achieve state of the art results. Additional experiments revealed that the improvements are not restricted to a single method of calculating optical flow by exchanging the formerly used method of Brox with FlowNet2 and still achieving improvements.

cs.CV↗

arXiv2019

Fusion of time of arrival and time difference of arrival for ultra-wideband indoor localization

This article presents a new approach for the wireless clock synchronization of Decawave ultra-wideband transceivers based on the time difference of arrival. The presented techniques combine the time-of-arrival and time-difference-of-arrival measurements without losing the advantages of each approach. The precision and accuracy of the distances measured by the Decawave devices depends on three effects: signal power, clock drift, and uncertainty in the hardware delay. This article shows how all three effects may be compensated with both measurement techniques.

eess.SP↗

arXiv2018

Learning and Tracking the 3D Body Shape of Freely Moving Infants from RGB-D sequences

Statistical models of the human body surface are generally learned from thousands of high-quality 3D scans in predefined poses to cover the wide variety of human body shapes and articulations. Acquisition of such data requires expensive equipment, calibration procedures, and is limited to cooperative subjects who can understand and follow instructions, such as adults. We present a method for learning a statistical 3D Skinned Multi-Infant Linear body model (SMIL) from incomplete, low-quality RGB-D sequences of freely moving infants. Quantitative experiments show that SMIL faithfully represents the RGB-D data and properly factorizes the shape and pose of the infants. To demonstrate the applicability of SMIL, we fit the model to RGB-D sequences of freely moving infants and show, with a case study, that our method captures enough motion detail for General Movements Assessment (GMA), a method used in clinical practice for early detection of neurodevelopmental disorders in infants. SMIL provides a new tool for analyzing infant shape and movement and is a step towards an automated system for GMA.

cs.CV↗

arXiv2018

Particle-based pedestrian path prediction using LSTM-MDL models

Recurrent neural networks are able to learn complex long-term relationships from sequential data and output a pdf over the state space. Therefore, recurrent models are a natural choice to address path prediction tasks, where a trained model is used to generate future expectations from past observations. When applied to security applications, like predicting the path of pedestrians for risk assessment, a point-wise greedy (ML) evaluation of the output pdf is not feasible, since the environment often allows multiple choices. Therefore, a robust risk assessment has to take all options into account, even if they are overall not very likely. Towards this end, a combination of particle filter sampling strategies and a LSTM-MDL model is proposed to address a multi-modal path prediction task. The capabilities and viability of the proposed approach are evaluated on several synthetic test conditions, yielding the counter-intuitive result that the simplest approach performs best. Further, the feasibility of the proposed approach is illustrated on several real world scenes.

cs.CV↗

arXiv2018

Stereo 3D Object Trajectory Reconstruction

We present a method to reconstruct the three-dimensional trajectory of a moving instance of a known object category using stereo video data. We track the two-dimensional shape of objects on pixel level exploiting instance-aware semantic segmentation techniques and optical flow cues. We apply Structure from Motion (SfM) techniques to object and background images to determine for each frame initial camera poses relative to object instances and background structures. We refine the initial SfM results by integrating stereo camera constraints exploiting factor graphs. We compute the object trajectory by combining object and background camera pose information. In contrast to stereo matching methods, our approach leverages temporal adjacent views for object point triangulation. As opposed to monocular trajectory reconstruction approaches, our method shows no degenerated cases. We evaluate our approach using publicly available video data of vehicles in urban scenes.

cs.CV↗

arXiv2018

An Evaluation of Trajectory Prediction Approaches and Notes on the TrajNet Benchmark

In recent years, there is a shift from modeling the tracking problem based on Bayesian formulation towards using deep neural networks. Towards this end, in this paper the effectiveness of various deep neural networks for predicting future pedestrian paths are evaluated. The analyzed deep networks solely rely, like in the traditional approaches, on observed tracklets without human-human interaction information. The evaluation is done on the publicly available TrajNet benchmark dataset, which builds up a repository of considerable and popular datasets for trajectory-based activity forecasting. We show that a Recurrent-Encoder with a Dense layer stacked on top, referred to as RED-predictor, is able to achieve sophisticated results compared to elaborated models in such scenarios. Further, we investigate failure cases and give explanations for observed phenomena and give some recommendations for overcoming demonstrated shortcomings.

cs.CV↗

arXiv2018

Improved Time of Arrival measurement model for non-convex optimization with noisy data

The quadratic system provided by the Time of Arrival technique can be solved analytical or by optimization algorithms. In real environments the measurements are always corrupted by noise. This measurement noise effects the analytical solution more than non-linear optimization algorithms. On the other hand it is also true that local optimization tends to find the local minimum, instead of the global minimum. This article presents an approach how this risk can be significantly reduced in noisy environments. The main idea of our approach is to transform the local minimum to a saddle point, by increasing the number of dimensions.

eess.SP↗

arXiv2018

Multilateration of the Local Position Measurement

The Local Position Measurement system (LPM) is one of the most precise systems for 3D position estimation. It is able to operate in- and outdoor and updates at a rate up to 1000 measurements per second. Previous scientific publications focused on the time of arrival equation (TOA) provided by the LPM and filtering after the numerical position estimation. This paper investigates the advantages of the TOA over the time difference of arrival equation transformation (TDOA) and the signal smoothing prior to its fitting. The LPM was designed under the general assumption that the position of the base station and position of the reference station are known. The information resulting from this research can prove vital for the systems self-calibration, providing data aiding in locating the relative position of the base station without prior knowledge of the transponder and reference station positions.

eess.SP↗

arXiv2018

Improved Time of Arrival measurement model for non-convex optimization

The quadratic system provided by the Time of Arrival technique can be solved analytically or by optimization algorithms. In practice, a combination of both methods is used. An important problem in quadratic optimization is the possible convergence to a local minimum, instead of the global minimum. This article presents an approach how this risk can be significantly reduced. The main idea of our approach is to transform the local minimum to a saddle point, by increasing the number of dimensions. In contrast to similar methods such as, dimension lifting does our problem remains non-convex.

math.OC↗

arXiv2018

Improved linear direct solution for asynchronous radio network localization (RNL)

In the field of localization the linear least square solution is frequently used. This solution is compared to nonlinear solvers more effected by noise, but able to provide a position estimation without the knowledge of any starting condition. The linear least square solution is able to minimize Gaussian noise by solving an overdetermined equation with the MoorePenrose pseudoinverse. Unfortunately this solution fails if it comes to non Gaussian noise. This publication presents a direct solution which is able to use prefiltered data for the LPM (RNL) equation. The used input for the linear position estimation will not be the raw data but over the time filtered data, for this reason this solution will be called direct solution. It will be shown that the presented symmetrical direct solution is superior to non symmetrical direct solution and especially to the not prefiltered linear least square solution.

eess.SP↗

arXiv2017

3D Trajectory Reconstruction of Dynamic Objects Using Planarity Constraints

We present a method to reconstruct the three-dimensional trajectory of a moving instance of a known object category in monocular video data. We track the two-dimensional shape of objects on pixel level exploiting instance-aware semantic segmentation techniques and optical flow cues. We apply Structure from Motion techniques to object and background images to determine for each frame camera poses relative to object instances and background structures. By combining object and background camera pose information, we restrict the object trajectory to a one-parameter family of possible solutions. We compute a ground representation by fusing background structures and corresponding semantic segmentations. This allows us to determine an object trajectory consistent to image observations and reconstructed environment model. Our method is robust to occlusion and handles temporarily stationary objects. We show qualitative results using drone imagery. Due to the lack of suitable benchmark datasets we present a new dataset to evaluate the quality of reconstructed three-dimensional object trajectories. The video sequences contain vehicles in urban areas and are rendered using the path-tracing render engine Cycles to achieve realistic results. We perform a quantitative evaluation of the presented approach using this dataset. Our algorithm achieves an average reconstruction-to-ground-truth distance of 0.31 meter.

cs.CV↗

arXiv2017

Instance Flow Based Online Multiple Object Tracking

We present a method to perform online Multiple Object Tracking (MOT) of known object categories in monocular video data. Current Tracking-by-Detection MOT approaches build on top of 2D bounding box detections. In contrast, we exploit state-of-the-art instance aware semantic segmentation techniques to compute 2D shape representations of target objects in each frame. We predict position and shape of segmented instances in subsequent frames by exploiting optical flow cues. We define an affinity matrix between instances of subsequent frames which reflects locality and visual similarity. The instance association is solved by applying the Hungarian method. We evaluate different configurations of our algorithm using the MOT 2D 2015 train dataset. The evaluation shows that our tracking approach is able to track objects with high relative motions. In addition, we provide results of our approach on the MOT 2D 2015 test set for comparison with previous works. We achieve a MOTA score of 32.1.

cs.CV↗