Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB

Filters

3
Reset filters

Settings
Now showing 1 - 10 of 1743
  • Publication
    Security Fence Inspection at Airports Using Object Detection
    ( 2024)
    Friederich, Nils
    ;
    Specker, Andreas
    ;
    Beyerer, Jürgen
    To ensure the security of airports, it is essential to protect the airside from unauthorized access. For this pur-pose, security fences are commonly used, but they require regular inspection to detect damages. However, due to the growing shortage of human specialists and the large man-ual effort, there is the need for automated methods. The aim is to automatically inspect the fence for damage with the help of an autonomous robot. In this work, we explore object detection methods to address the fence inspection task and localize various types of damages. In addition to evaluating four State-of-the-Art (SOTA) object detection models, we analyze the impact of several design criteria, aiming at adapting to the task-specific challenges. This in-cludes contrast adjustment, optimization of hyperparameters, and utilization of modern backbones. The experimental results indicate that our optimized You Only Look Once v5 (YOLOv5) model achieves the highest accuracy of the four methods with an increase of 6.9% points in Average Precision (AP) compared to the baseline. Moreover, we show the real-time capability of the model. The trained models are published on GitHub: hups://github.com/IN-Friederichlairport_fence_inspection.
  • Publication
    2nd Workshop on Maritime Computer Vision (MaCVi) 2024: Challenge Results
    ( 2024)
    Kiefer, Benjamin
    ;
    Žust, Lojze
    ;
    Kristan, Matej
    ;
    Perš, Janez
    ;
    Teršek, Matija
    ;
    Wiliem, Arnold
    ;
    Messmer, Martin
    ;
    Yang, Cheng
    ;
    Huang, Wei
    ;
    Jiang, Zhongyu
    ;
    Kuo, Cheng-liang
    ;
    Mei, Jie
    ;
    Hwang, Jenq-neng
    ;
    Stadler, Daniel
    ;
    Sommer, Lars Wilko
    ;
    Huang, Kaer
    ;
    Aiguo Zheng
    ;
    Chong, Weitu
    ;
    Lertniphonphan, Kanokphan
    ;
    Xie, Lie-jun
    ;
    Chen, Feng
    ;
    Li, Jian
    ;
    Wang, Zhepeng
    ;
    Zedda, Luca
    ;
    Loddo, Andrea
    ;
    Di Ruberto, Cecilia
    ;
    Vu, Tuan-Anh
    ;
    Hai, Nguyen
    ;
    Ha, Van Sang
    ;
    Tien, Dung Pham
    ;
    Yeung, Kit Ling
    ;
    Feng, Yuan
    ;
    Thien, Nguyen Thanh
    ;
    Tian, Lixin
    ;
    Kuan, Sheng-Yao
    ;
    Ho, Yuan-Hao
    ;
    Bueno Rodriguez, Angel
    ;
    Carrillo-Perez, Borja
    ;
    Klein, Alexander
    ;
    Alex, Antje
    ;
    Steiniger, Yannik
    ;
    Sattler, Felix
    ;
    Solano-carrillo, Edgardo
    ;
    Fabijanić, Matej
    ;
    Šumunec, Magdalena
    ;
    Kapetanović, Nadir
    ;
    Michel, Andreas
    ;
    Groß, Wolfgang
    ;
    Weinmann, Martin
    The 2nd Workshop on Maritime Computer Vision (MaCVi) 2024 addresses maritime computer vision for Unmanned Aerial Vehicles (UAV) and Unmanned Surface Vehicles (USV). Three challenges categories are considered: (i) UAV-based Maritime Object Tracking with Re-ideruification, (ii) USV-based Maritime Obstacle Segmentation and Detection, (iii) USV-based Maritime Boat Tracking. The USV-based Maritime Obstacle Segmentation and Detection features three sub-challenges, including a new embedded challenge addressing efficicent inference on real-world embedded devices. This report offers a comprehensive overview of the findings from the challenges. We provide both statistical and qualitative analyses, evaluating trends from over 195 submissions. All datasets, evaluation code, and the leaderboard are available to the public at https://macvi.org/workshop/macvi24.
  • Publication
    Between Gaming and Microclimate Simulations: Temperature Estimation of an Urban Area
    ( 2024)
    Strauß, Eva
    ;
    Bulatov, Dimitri
    With the rising awareness and interest from researchers, local authorities, and industry in the urban heat island effect, thermal remote sensing data is needed as it allows for identification, tracking, or analysis of land surface temperatures. Yet, the accessibility of appropriate thermal data in both the spatial and temporal domain states an inhibiting factor. Whilst thermal satellite data suffers from both low spatial and temporal resolution, airborne imagery might enable adequate resolutions, however, is not acquired without time and cost consumption. One way to overcome this drawback is the generation of synthetic data, which comprises the simulation of surface temperatures. These rather simplified simulations are either quite fast, as desired in gaming applications, however, highly inaccurate, or rather complex, holistic, time-consuming and computationally intensive, like applied in urban microclimate considerations. In this paper, we present an in-between approach towards the estimation of urban surface temperatures that aims to fill this gap between holistic microclimate simulations and climate maps.
  • Publication
    Robust Human-Centered Assembly Line Scheduling with Reinforcement Learning
    ( 2024)
    Grumbach, Felix
    ;
    Müller, Arthur
    ;
    Vollenkemper, Lukas
    This study set out to develop a Reinforcement Learning (RL) agent for solving an extended Permutation Flow Shop Scheduling Problem (PFSSP). From the domain perspective, we see a lack of realistic constraints for synchronized, human-centered assembly lines. Moreover, objective functions must be provided to enable stress-reducing as well as robust planning under uncertainty. From a methodical perspective, RL has received more and more attention for problems of this type. However, we cannot identify applicable RL concepts for our extended PFSSP with multicriteria objectives. We propose a generic RL agent, which operates on an abstract representation of the schedule and with an objective-independent reward function. Our numerical experiments demonstrate that the agent successfully generalizes a policy and achieves better scores than a Simulated Annealing (SA) metaheuristic.
  • Publication
    12.2 W ZGP OPO pumped by a Q-Switched Tm3+:Ho3+-codoped fiber laser
    ( 2024)
    Forster, Patrick
    ;
    Lautenschläger, Jan
    ;
    Lorenz, Dominik
    ;
    Schneider, Julian
    ;
    Panitzek, Dieter
    ;
    Romano, Clément
    ;
    Eichhorn, Marc
    ;
    Kieleck, Christelle
    We present our latest results in power scaling of Midwave-Infrared (MWIR) Optical Parametric Oscillators (OPOs) based on a Zinc Germanium Phosphide (ZGP) crystal, utilizing a single oscillator fiber laser as pump source. To obtain a compact and complexity-reduced pump source emitting at ≥ 2.09 μm, a Q-switched Tm3+:Ho3+- codoped fiber laser was developed. Based on this pump source at an emission wavelength of 2.1 μm, we achieved an MWIR output power of 12.2W with pulse energies of up to 270 μJ and a conversion efficiency exceeding 43 %. This result exceeds the published power records of ZGP-based OPOs pumped by 2 μm Q-switched fiber lasers by 50 % and sets a new benchmark for average power scaling and pulse energy of Q-switched pump sources.
  • Publication
    Knowledge-Distillation-Based Label Smoothing for Fine-Grained Open-Set Vehicle Recognition
    ( 2024)
    Wolf, Stefan
    ;
    Loran, Dennis
    ;
    Beyerer, Jürgen
    Fine-grained vehicle classification describes the task of estimating the make and the model of a vehicle based on an image. It provides a useful tool for security authorities to find suspects in surveillance cameras. However, most research about fine-grained vehicle classification is only focused on a closed-set scenario which considers all possible classes to be included in the training. This is not realistic for real-world surveillance applications where the images fed into the classifier can be of arbitrary vehicle models and the large number of commercially available vehicle models renders learning all models impossible. Thus, we investigate fine-grained vehicle classification in an open-set recognition scenario which includes unknown vehicle models in the test set and expects these samples to be rejected. Our experiments highlight the importance of label smoothing for open-set recognition performance. Nonetheless, it lacks recognizing the different semantic distances between vehicle models which result in largely different confusion probabilities. Thus, we propose a knowledge-distillation-based label smoothing approach which considers these different semantic similarities and thus, improves the closed-set classification as well as the open-set recognition performance.
  • Publication
    Enhancing Skeleton-Based Action Recognition in Real-World Scenarios Through Realistic Data Augmentation
    ( 2024)
    Cormier, Mickael
    ;
    Schmid, Yannik
    ;
    Beyerer, Jürgen
    Skeleton-based action recognition is a prominent research area that provides a concise representation of human motion. However, real-world scenarios pose challenges to the reliability of human pose estimation, which is fundamental to such recognition. The existing literature mainly focuses on laboratory experiments with near-perfect skeletons, and fails to address the complexities of the real world. To address this, we propose simple yet highly effective data augmentation techniques based on the observation of erroneous human pose estimation, which enhance state-of-the-art methods for real-world skeleton-based action recognition. These techniques yield significant improvements (up to +4.63 accuracy) on the widely used UAV Human Dataset, a benchmark for evaluating real-world action recognition. Experimental results demonstrate the effectiveness of our augmentation techniques in compensating for erroneous and noisy pose estimation, leading to significant improvements in action recognition accuracy. By bridging the gap between laboratory experiments and real-world scenarios, our work paves the way for more reliable and practical skeleton-based action recognition systems. To facilitate reproducibility and further development, the Skelbumentations library is released at https://github.com/MickaelCormier/Skelbumentations. This library provides the code implementation of our augmentation techniques, enabling researchers and practitioners to easily augment skeleton sequences and improve the performance of skeleton-based action recognition models in real-world applications.
  • Publication
    Particle-Specific Deflection Windows for Optical Sorting by Uncertainty Quantification
    ( 2024)
    Reith-Braun, Marcel
    ;
    Liang, Kevin
    ;
    Pfaff, Florian
    ;
    Maier, Georg
    ;
    Gruna, Robin
    ;
    Bauer, Albert
    ;
    Kruggel-Emden, Harald
    ;
    Längle, Thomas
    ;
    Beyerer, Jürgen
    ;
    Hanebeck, Uwe D.
    In current state of the art sensor-based sorting systems, the length of the deflection windows, i.e., the period of nozzle activation and the number of nozzles to be activated, is commonly determined solely by the size of the particles. However, this comes at the cost of the sorting process not accounting for model discrepancies between actual and presumed particle motion, as well as for situations where the available information does not allow for precise determination of nozzle activations. To achieve a desired sorting accuracy, in practice, one is therefore usually forced to enlarge the deflection window to a certain degree, which increases the number of falsely co-deflected particles and compressed air consumption. In this paper, we propose incorporating the uncertainty of the prediction of particle motion of each individual particle into the determination of the deflection windows. The method is based on the predictive tracking approach for optical sorting, which tracks the particles while they move toward the nozzle array based on images of an area-scan camera. Given the extracted motion information from the tracking, we propose an approximation for the distribution of arrival time and location of the particle at the nozzle array assuming nearly constant-velocity or nearly constantacceleration particle motion behavior. By evaluating the quantile function of both distributions, we obtain a confidence interval for the arrival time and location based on prediction uncertainty, which we then combine with the particle size to form the final deflection window. We apply our method to a real sorting task using a pilot-scale chute sorter. Our results obtained from extensive sorting trials show that sorting accuracies can be remarkably improved compared with state-of-the-art industrial sorters and enhanced even further compared with predictive tracking while having the potential to reduce compressed air consumption.
  • Publication
    Unsupervised 3D Skeleton-Based Action Recognition using Cross-Attention with Conditioned Generation Capabilities
    ( 2024)
    Lerch, David
    ;
    Zhong, Zeyun
    ;
    Martin, Manuel
    ;
    Voit, Michael
    ;
    Beyerer, Jürgen
    Human action recognition plays a pivotal role in various real-world applications, including surveillance systems, robotics, and occupant monitoring in the car interior. With such a diverse range of domains, the demand for generalization becomes increasingly crucial. In this work, we propose a cross-attention-based encoder-decoder approach for unsupervised 3D skeleton-based action recognition. Specifically, our model takes a skeleton sequence as input for the encoder and further applies masking and noise to the original sequence for the decoder. By training the model to reconstruct the original skeleton sequence, it simultaneously learns to capture the underlying patterns of actions. Extensive experiments on NTU and NW-UCLA datasets demonstrate the state-of-the-art performance as well as the impressive generalizability of our proposed approach. Moreover, our experiments reveal that our approach is capable of generating conditioned skeleton sequences, offering the potential to enhance small datasets or generate samples of under-represented classes in imbalanced datasets. Our code will be published on GitHub.
  • Publication
    High-pulse-energy actively Q-switched Tm3+-doped photonic crystal fiber laser operating at 2050 nm with narrow linewidth
    ( 2024)
    Schneider, Julian
    ;
    Lassiette, Hugo
    ;
    Lorenz, Dominik
    ;
    Forster, Patrick
    ;
    Lautenschläger, Jan
    ;
    Panitzek, Dieter
    ;
    Romano, Clément
    ;
    Eichhorn, Marc
    ;
    Kieleck, Christelle
    An actively Q-switched diode-pumped Tm3+-doped fiber laser (TDFL) operating at 2050 nm is reported based on a flexible Photonic Crystal Fiber (PCF) with a core diamter of 50 μm. Using a fiber length of 3 m, the TDFL delivers gaussian shaped pulses with a maximum pulse energy of 1.5 mJ, corresponding to a peak power of 16 kW and a pulse width of 88 ns. The measured output spectrum shows a single peak at 2050 nm with a 3-dB-linewidth of 100 pm and 10-dB-linewidth of 270 pm. For a longer fiber length of 7 m, the effective gain is redshifted by reabsorbtion, increasing the achievable pulse energy up to 1.9 mJ. The average output power of the pulsed TDFL can be scaled to more than 100 W with a slope efficiency of 46 %. In all configurations the TDFL delivers nearly diffraction limited beam quality (M2 ⪅1.3).