Search Results for author:
Found 40 papers, 18 papers with code
Table tennis ball spin estimation with an event camera
In table tennis, the combination of high velocity and spin renders traditional low frame rate cameras inadequate for quickly and accurately observing the ball's logo to estimate the spin due to the motion blur.
Can Vehicle Motion Planning Generalize to Realistic Long-tail Scenarios?
We assess existing state-of-the-art planners on our benchmark and show that neither rule-based nor learning-based planners can safely navigate the interPlan scenarios.
Detection of Fast-Moving Objects with Neuromorphic Hardware
Neuromorphic Computing (NC) and Spiking Neural Networks (SNNs) in particular are often viewed as the next generation of Neural Networks (NNs).
Conditional Unscented Autoencoders for Trajectory Prediction
We leverage recent advances in the space of the VAE, the foundation of the CVAE, which show that a simple change in the sampling procedure can greatly benefit performance.
A multi-modal table tennis robot system
Therefore, we introduced a novel, and more accurate spin estimation approach.
eWand: A calibration framework for wide baseline frame-based and event-based camera systems
The standard approach is to use a printed pattern with known geometry to estimate the intrinsic and extrinsic parameters of the cameras.
Hyperspectral Benchmark: Bridging the Gap between HSI Applications through Comprehensive Dataset and Pretraining
This pretraining regimen serves to enhance the stability of training processes for larger models.
Stable Yaw Estimation of Boats from the Viewpoint of UAVs and USVs
In this paper, we propose a method based on HyperPosePDF for predicting the orientation of boats in the 6D space.
SpinDOE: A ball spin estimation method for table tennis robot
Using our algorithm, the ball's orientation can be estimated with a mean error of 2. 4{\deg} and the spin estimation has an relative error lower than 1%.
Memory Maps for Video Object Detection and Tracking on UAVs
This paper introduces a novel approach to video object detection detection and tracking on Unmanned Aerial Vehicles (UAVs).
Fast Region of Interest Proposals on Maritime UAVs
In this work, we consider the problem of finding meaningful region of interest proposals in a video stream on an embedded GPU.
Real-time event simulation with frame-based cameras
However, due to the computational complexity of the simulation, the event streams of existing simulators cannot be generated in real-time but rather have to be pre-calculated from existing video sequences or pre-rendered and then simulated from a virtual 3D scene.
Wavelength-aware 2D Convolutions for Hyperspectral Imaging
Two key challenges are the large channel dimension of the recordings and the incompatibility between cameras of different manufacturers.
Gaze-based Object Detection in the Wild
For this purpose, we explore different sizes of temporal windows, which serve as a basis for the computation of heatmaps, i. e., the spatial distribution of the gaze data.
Comprehensive Analysis of the Object Detection Pipeline on UAVs
We show that not all parameters have an equal impact on detection accuracy and data throughput, and that by using a suitable compromise between parameters we are able to achieve higher detection accuracy for lightweight object detection models, while keeping the same data throughput.
FourierMask: Instance Segmentation using Fourier Mapping in Implicit Neural Networks
We present FourierMask, which employs Fourier series combined with implicit neural representations to generate instance segmentation masks.
Leveraging Synthetic Data in Object Detection on Unmanned Aerial Vehicles
In this work, we explore the potential use of synthetic data in object detection from UAVs across various application environments.
Ranked #1 on
Object Detection
on SeaDronesSee
(using extra training data)
TriStereoNet: A Trinocular Framework for Multi-baseline Disparity Estimation
Stereo vision is an effective technique for depth estimation with broad applicability in autonomous urban and highway driving.
Ranked #1 on
Stereo Depth Estimation
on KITTI2015
(D1-all All metric)
What to expect of hardware metric predictors in NAS
Due to inaccurate predictions, the selected architectures are generally suboptimal, which we quantify as an expected reduction in accuracy and hypervolume.
Seeing Implicit Neural Representations as Fourier Series
Implicit Neural Representations (INR) use multilayer perceptrons to represent high-frequency functions in low-dimensional problem domains.
Using a one dimensional parabolic model of the full-batch loss to estimate learning rates during training
In the experiments conducted, our approach is on par with SGD with Momentum tuned with a piece-wise constant learning rate schedule and often outperforms other line search approaches for Deep Learning across models, datasets, and batch sizes on validation and test accuracy.
Separable Convolutions for Optimizing 3D Stereo Networks
In this work first, we show that these 3D convolutions in stereo networks consume up to 94% of overall network operations and act as a major bottleneck.
MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matching
Depending on the dimension of cost volume, we design a 2D and a 3D model with encoder-decoders built from 2D and 3D convolutions, respectively.
Ranked #1 on
Stereo Depth Estimation
on sceneflow
Score refinement for confidence-based 3D multi-object tracking
We show that manipulating the scores depending on time consistency while terminating the tracklets depending on the tracklet score improves tracking results.
Object detection and Autoencoder-based 6D pose estimation for highly cluttered Bin Picking
Bin picking is a core problem in industrial environments and robotics, with its main module as 6D pose estimation.
Tackling the Background Bias in Sparse Object Detection via Cropped Windows
Object detection on Unmanned Aerial Vehicles (UAVs) is still a challenging task.
SeaDronesSee: A Maritime Benchmark for Detecting Humans in Open Water
Therefore, this paper introduces a large-scaled visual object detection and tracking benchmark (SeaDronesSee) aiming to bridge the gap from land-based vision systems to sea-based ones.
Ranked #1 on
Object Tracking
on SeaDronesSee
Inter-choice dependent super-network weights
The automatic design of architectures for neural networks, Neural Architecture Search, has gained a lot of attention over the recent years, as the thereby created networks repeatedly broke state-of-the-art results for several disciplines.
Measuring the Ripeness of Fruit with Hyperspectral Imaging and Deep Learning
We present a system to measure the ripeness of fruit with a hyperspectral camera and a suitable deep neural network architecture.
Empirically explaining SGD from a line search perspective
Optimization in Deep Learning is mainly guided by vague intuitions and strong assumptions, with a limited understanding how and why these work in practice.
Diminishing Domain Bias by Leveraging Domain Labels in Object Detection on UAVs
Object detection from Unmanned Aerial Vehicles (UAVs) is of great importance in many aerial vision-based applications.
Gaining Scale Invariance in UAV Bird's Eye View Object Detection by Adaptive Resizing
This work introduces a new preprocessing step for object detection applicable to UAV bird's eye view imagery, which we call Adaptive Resizing.
Exploring single-path Architecture Search ranking correlations
Recently presented benchmarks for Neural Architecture Search (NAS) provide the results of training thousands of different architectures in a specific search space, thus enabling the fair and rapid comparison of different methods.
Sample-efficient Reinforcement Learning in Robotic Table Tennis
In this paper we present a sample-efficient RL algorithm applied to the example of a table tennis robot.
A straightforward line search approach on the expected empirical loss for stochastic deep learning problems
In traditional optimization, line searches are used to determine good step sizes, however, in deep learning, it is too costly to search for good step sizes on the expected empirical loss due to noisy losses.
FourierNet: Compact mask representation for instance segmentation using differentiable shape decoders
Code is available at: github. com/cogsys-tuebingen/FourierNet.
Prune and Replace NAS
While recent NAS algorithms are thousands of times faster than the pioneering works, it is often overlooked that they use fewer candidate operations, resulting in a significantly smaller search space.
Spin Detection in Robotic Table Tennis
Our robot successfully copes with different spin types in a real table tennis rally against a human opponent.
Parabolic Approximation Line Search for DNNs
The optimal step size is closely related to the shape of the loss in the update step direction.
ShuffleNASNets: Efficient CNN models through modified Efficient Neural Architecture Search
Neural network architectures found by sophistic search algorithms achieve strikingly good test performance, surpassing most human-crafted network models by significant margins.
