Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB

Filters

Reset filters

Settings
Now showing 1 - 10 of 52
  • Publication
    Utilizing Dataset Affinity Prediction in Object Detection to Assess Training Data
    ( 2024)
    Becker, Stefan
    ;
    Bayer, Jens
    ;
    Hug, Ronny
    ;
    Hübner, Wolfgang
    ;
    Arens, Michael
    Data pooling offers various advantages, such as increasing the sample size, improving generalization, reducing sampling bias, and addressing data sparsity and quality, but it is not straightforward and may even be counterproductive. Assessing the effectiveness of pooling datasets in a principled manner is challenging due to the difficulty in estimating the overall information content of individual datasets. Towards this end, we propose incorporating a data source prediction module into standard object detection pipelines. The module runs with minimal overhead during inference time, providing additional information about the data source assigned to individual detections. We show the benefits of the so-called dataset affinity score by automatically selecting samples from a heterogeneous pool of vehicle datasets. The results show that object detectors can be trained on a significantly sparser set of training samples without losing detection accuracy. T
  • Publication
    Center point-based feature representation for tracking
    ( 2023)
    Becker, Stefan
    ;
    Hug, Ronny
    ;
    Hübner, Wolfgang
    ;
    Arens, Michael
    Center points are commonly the results of anchor-free object detectors. Starting from this initial representation, a regression scheme is utilized to determine a target point set to capture object properties such as enclosing bounding boxes and further attributes such as class labels. When only trained for the detection tasks, the encoded center point feature representations are not well suited for tracking objects since the embedded features are not stable over time. To tackle this problem, we present an approach of joint detection and feature embedding for multiple object tracking. The proposed approach applies an anchor-free detection model to pairs of images to extract single-point feature representations. To generate temporal stable features which are suitable for track association across short time intervals, auxiliary losses are applied to reduce the distance of tracked identities in the embedded feature space. The abilities of the presented approach are demonstrated on real-world data reflecting prototypical object tracking scenarios.
  • Publication
    Bézier Curve Gaussian Processes
    ( 2022-11-18)
    Hug, Ronny
    ;
    Becker, Stefan
    ;
    Hübner, Wolfgang
    ;
    Arens, Michael
    ;
    Beyerer, Jürgen
    Probabilistic models for sequential data are the basis for a variety of applications concerned with processing timely ordered information. The predominant approach in this domain is given by recurrent neural networks, implementing either an approximate Bayesian approach (e.g. Variational Autoencoders or Generative Adversarial Networks) or a regression-based approach, i.e. variations of Mixture Density networks (MDN). In this paper, we focus on the N-MDN variant, which parameterizes (mixtures of) probabilistic Bézier curves (N-Curves) for modeling stochastic processes. While in favor in terms of computational cost and stability, MDNs generally fall behind approximate Bayesian approaches in terms of expressiveness. Towards this end, we present an approach for closing this gap by enabling full Bayesian inference on top of N-MDNs. For this, we show that N-Curves are a special case of Gaussian processes (denoted as N-GP) and then derive corresponding mean and kernel functions for different modalities. Following this, we propose the use of the N-MDN as a data-dependent generator for N-GP prior distributions. We show the advantages granted by this combined model in an application context, using human trajectory prediction as an example.
  • Publication
    Generating Versatile Training Samples for UAV Trajectory Prediction
    ( 2022)
    Becker, Stefan
    ;
    Hug, Ronny
    ;
    Hübner, Wolfgang
    ;
    Arens, Michael
    ;
    Morris, Brendan T.
    Following the success of deep learning-based models in various sequence processing tasks, these models are increasingly utilized in object tracking applications for motion prediction as a replacement of traditional approaches. On the one hand, these models can capture complex object dynamics while requiring less modeling, but on the other hand, they depend on a large amount of training data for parameter tuning. Towards this end, an approach for generating synthetic trajectory data of unmanned-aerial-vehicles (UAVs) in image space is presented in this paper. Since UAVs are dynamical systems, they are bound to strict physical constraints and inputs for controlling. Thus, they cannot move along arbitrary trajectories. To generate executable trajectories, it is possible to apply solutions from trajectory planning for our desired purpose of generating realistic UAV trajectory data. Accordingly, with the prerequisite that UAV trajectories fulfill a smoothness criterion corresponding to a minimal change of higher-order motion, planning methods enabling aggressive quadrotor flights are applied to generate optimal trajectories through a sequence of 3D waypoints. By projecting these maneuver trajectories to image space, a versatile trajectory data set is realized. To demonstrate the applicability of the synthetic trajectory data, we show that deep learning-based prediction models solely trained on the synthetically generated data can outperform traditional reference models on a real-world UAV tracking dataset. The evaluation is done on the publicly available ANTI-UAV dataset.
  • Publication
    Quantifying the Complexity of Standard Benchmarking Datasets for Long-Term Human Trajectory Prediction
    ( 2021)
    Hug, Ronny
    ;
    Becker, Stefan
    ;
    Hübner, Wolfgang
    ;
    Arens, Michael
    Methods to quantify the complexity of trajectory datasets are still a missing piece in benchmarking human trajectory prediction models. In order to gain a better understanding of the complexity of trajectory prediction tasks and following the intuition, that more complex datasets contain more information, an approach for quantifying the amount of information contained in a dataset from a prototype-based dataset representation is proposed. The dataset representation is obtained by first employing a non-trivial spatial sequence alignment, which enables a subsequent learning vector quantization (LVQ) stage. A large-scale complexity analysis is conducted on several human trajectory prediction benchmarking datasets, followed by a brief discussion on indications for human trajectory prediction and benchmarking.
  • Publication
    Grundlagen des Maschinellen Lernens
    ( 2021)
    Bauckhage, Christian
    ;
    Hübner, Wolfgang
    ;
    Hug, Ronny
    ;
    Paaß, Gerhard
    ;
    Rüping, Stefan
    Zu definieren, was die menschliche Intelligenz sowie intelligentes Handeln – und da­mit auch die Künstliche Intelligenz – ausmacht, ist außerordentlich schwer und be­schäftigt Philosophen und Psychologen seit Jahrtausenden. Allgemein anerkannt istaber, dass die Fähigkeit zu lernen ein zentrales Merkmal vonIntelligenzist. So ist auchdas Forschungsgebiet desMaschinellen Lernens(engl.machine learning, ML) ein zen­traler Teil der Künstlichen Intelligenz, das hinter vielen aktuellen Erfolgen von KI-Sys­temen steckt.
  • Publication
    Generating Synthetic Training Data for Deep Learning-Based UAV Trajectory Prediction
    ( 2021)
    Becker, Stefan
    ;
    Hug, Ronny
    ;
    Hübner, Wolfgang
    ;
    Arens, Michael
    ;
    Morris, Brendan T.
    Deep learning-based models, such as recurrent neural networks (RNNs), have been applied to various sequence learning tasks with great success. Following this, these models are increasingly replacing classic approaches in object tracking applications for motion prediction. On the one hand, these models can capture complex object dynamics with less modeling required, but on the other hand, they depend on a large amount of training data for parameter tuning. Towards this end, we present an approach for generating synthetic trajectory data of unmanned-aerial-vehicles (UAVs) in image space. Since UAVs, or rather quadrotors are dynamical systems, they can not follow arbitrary trajectories. With the prerequisite that UAV trajectories fulfill a smoothness criterion corresponding to a minimal change of higher-order motion, methods for planning aggressive quadrotors flights can be utilized to generate optimal trajectories through a sequence of 3D waypoints. By projecting these maneuver trajectories, which are suitable for controlling quadrotors, to image space, a versatile trajectory data set is realized. To demonstrate the applicability of the synthetic trajectory data, we show that an RNN-based prediction model solely trained on the generated data can outperform classic reference models on a real-world UAV tracking dataset. The evaluation is done on the publicly available ANTI-UAV dataset.
  • Publication
    MissFormer: (In-)Attention-Based Handling of Missing Observations for Trajectory Filtering and Prediction
    ( 2021)
    Becker, Stefan
    ;
    Hug, Ronny
    ;
    Hübner, Wolfgang
    ;
    Arens, Michael
    ;
    Morris, Brendan Tran
    In applications such as object tracking, time-series data inevitably carry missing observations. Following the success of deep learning-based models for various sequence learning tasks, these models increasingly replace classic approaches in object tracking applications for inferring the objects' motion states. While traditional tracking approaches can deal with missing observations, most of their deep counterparts are, by default, not suited for this. Towards this end, this paper introduces a transformer-based approach for handling missing observations in variable input length trajectory data. The model is formed indirectly by successively increasing the complexity of the demanded inference tasks. Starting from reproducing noise-free trajectories, the model then learns to infer trajectories from noisy inputs. By providing missing tokens, binary-encoded missing events, the model learns to in-attend to missing data and infers a complete trajectory conditioned on the remaining inputs. In the case of a sequence of successive missing events, the model then acts as a pure prediction model. The abilities of the approach are demonstrated on synthetic data and real-world data reflecting prototypical object tracking scenarios.
  • Publication
    Handling Missing Observations with an RNN-based Prediction-Update Cycle
    ( 2021)
    Becker, Stefan
    ;
    Hug, Ronny
    ;
    Hübner, Wolfgang
    ;
    Arens, Michael
    ;
    Morris, Brendan T.
    In tasks such as tracking, time-series data inevitably carry missing observations. While traditional tracking approaches can handle missing observations, recurrent neural networks (RNNs) are designed to receive input data in every step. Furthermore, current solutions for RNNs, like omitting the missing data or data imputation, are not sufficient to account for the resulting increased uncertainty. Towards this end, this paper introduces an RNN-based approach that provides a full temporal filtering cycle for motion state estimation. The Kalman filter inspired approach enables to deal with missing observations and outliers. For providing a full temporal filtering cycle, a basic RNN is extended to take observations and the associated belief about its accuracy into account for updating the current state. An RNN prediction model, which generates a parametrized distribution to capture the predicted states, is combined with an RNN update model, which relies on the prediction model output and the current observation. By providing the model with masking information, binary-encoded missing events, the model can overcome limitations of standard techniques for dealing with missing input values. The model abilities are demonstrated on synthetic data reflecting prototypical pedestrian tracking scenarios.