185 citations · 286 across the 34 of their papers we have counts for
17 papers · 1 filter
Leveraging Synthetic Data in Object Detection on Unmanned Aerial Vehicles
Benjamin Kiefer, David Ott, Andreas Zell
Acquiring data to train deep learning-based object detectors on Unmanned Aerial Vehicles (UAVs) is expensive, time-consuming and may even be prohibited by law in specific environme…
FourierMask: Instance Segmentation using Fourier Mapping in Implicit Neural Networks
Hamd ul Moqeet Riaz, Nuri Benbarka, Timon Hoefer +1
We present FourierMask, which employs Fourier series combined with implicit neural representations to generate instance segmentation masks. We apply a Fourier mapping (FM) to the c…
Optimal Stroke Learning with Policy Gradient Approach for Robotic Table Tennis
Yapeng Gao, Jonas Tebbe, Andreas Zell
Learning to play table tennis is a challenging task for robots, as a wide variety of strokes required. Recent advances have shown that deep Reinforcement Learning (RL) is able to s…
TriStereoNet: A Trinocular Framework for Multi-baseline Disparity Estimation
Faranak Shamsafar, Andreas Zell
Stereo vision is an effective technique for depth estimation with broad applicability in autonomous urban and highway driving. While various deep learning-based approaches have bee…
Seeing Implicit Neural Representations as Fourier Series
Nuri Benbarka, Timon Höfer, Hamd ul-moqeet Riaz +1
Implicit Neural Representations (INR) use multilayer perceptrons to represent high-frequency functions in low-dimensional problem domains. Recently these representations achieved s…
Separable Convolutions for Optimizing 3D Stereo Networks
Rafia Rahim, Faranak Shamsafar, Andreas Zell
Deep learning based 3D stereo networks give superior performance compared to 2D networks and conventional stereo methods. However, this improvement in the performance comes at the…
MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matching
Faranak Shamsafar, Samuel Woerz, Rafia Rahim +1
Recent methods in stereo matching have continuously improved the accuracy using deep models. This gain, however, is attained with a high increase in computation cost, such that the…
Using a one dimensional parabolic model of the full-batch loss to estimate learning rates during training
Maximus Mutschler, Kevin Laube, Andreas Zell
A fundamental challenge in Deep Learning is to find optimal step sizes for stochastic gradient descent automatically. In traditional optimization, line searches are a commonly used…
Score refinement for confidence-based 3D multi-object tracking
Nuri Benbarka, Jona Schröder, Andreas Zell
Multi-object tracking is a critical component in autonomous navigation, as it provides valuable information for decision-making. Many researchers tackled the 3D multi-object tracki…
Object detection and Autoencoder-based 6D pose estimation for highly cluttered Bin Picking
Timon Höfer, Faranak Shamsafar, Nuri Benbarka +1
Bin picking is a core problem in industrial environments and robotics, with its main module as 6D pose estimation. However, industrial depth sensors have a lack of accuracy when it…
Tackling the Background Bias in Sparse Object Detection via Cropped Windows
Leon Amadeus Varga, Andreas Zell
Object detection on Unmanned Aerial Vehicles (UAVs) is still a challenging task. The recordings are mostly sparse and contain only small objects. In this work, we propose a simple…
SeaDronesSee: A Maritime Benchmark for Detecting Humans in Open Water
Leon Amadeus Varga, Benjamin Kiefer, Martin Messmer +1
Unmanned Aerial Vehicles (UAVs) are of crucial importance in search and rescue missions in maritime environments due to their flexible and fast operation capabilities. Modern compu…
Measuring the Ripeness of Fruit with Hyperspectral Imaging and Deep Learning
Leon Amadeus Varga, Jan Makowski, Andreas Zell
We present a system to measure the ripeness of fruit with a hyperspectral camera and a suitable deep neural network architecture. This architecture did outperform competitive basel…
Conditional super-network weights
Kevin Alexander Laube, Andreas Zell
Modern Neural Architecture Search methods have repeatedly broken state-of-the-art results for several disciplines. The super-network, a central component of many such methods, enab…
Empirically explaining SGD from a line search perspective
Maximus Mutschler, Andreas Zell
Optimization in Deep Learning is mainly guided by vague intuitions and strong assumptions, with a limited understanding how and why these work in practice. To shed more light on th…
Gaining Scale Invariance in UAV Bird's Eye View Object Detection by Adaptive Resizing
Martin Messmer, Benjamin Kiefer, Andreas Zell
This work introduces a new preprocessing step for object detection applicable to UAV bird's eye view imagery, which we call Adaptive Resizing. By design, it helps alleviate the cha…
Diminishing Domain Bias by Leveraging Domain Labels in Object Detection on UAVs
Benjamin Kiefer, Martin Messmer, Andreas Zell
Object detection from Unmanned Aerial Vehicles (UAVs) is of great importance in many aerial vision-based applications. Despite the great success of generic object detection methods…