Related papers: A deep learning approach to multi-track location a…
Most state-of-the-art works in trajectory forecasting for automotive target predicting the pose and orientation of the agents in the scene. This represents a particularly useful problem, for instance in autonomous driving, but it does not…
Millimeter wave channels exhibit structure that allows beam alignment with fewer channel measurements than exhaustive beam search. From a compressed sensing (CS) perspective, the received channel measurements are usually obtained by…
The comprehensive representation and understanding of the driving environment is crucial to improve the safety and reliability of autonomous vehicles. In this paper, we present a new approach to establish an environment model containing a…
Beam training and prediction in millimeter-wave communications are highly challenging due to fast time-varying channels and sensitivity to blockages and mobility. In this context, infrastructure-mounted cameras can capture rich…
We establish a series of deep convolutional neural networks to automatically analyze position averaged convergent beam electron diffraction patterns. The networks first calibrate the zero-order disk size, center position, and rotation…
Object detection and tracking are vital and fundamental tasks for autonomous driving, aiming at identifying and locating objects from those predefined categories in a scene. 3D point cloud learning has been attracting more and more…
Image segmentation aims to partition an image according to the objects in the scene and is a fundamental step in analysing very high spatial-resolution (VHR) remote sensing imagery. Current methods struggle to effectively consider land…
We present our study on the reconstruction of photoelectron tracks in gas pixel detectors used for astrophysical X-ray polarimetry. Our work aims to maximize the performance of convolutional neural networks (CNNs) to predict the impact…
Beam selection for millimeter-wave links in a vehicular scenario is a challenging problem, as an exhaustive search among all candidate beam pairs cannot be assuredly completed within short contact times. We solve this problem via a novel…
Multi-object tracking (MOT) in monocular videos is fundamentally challenged by occlusions and depth ambiguity, issues that conventional tracking-by-detection (TBD) methods struggle to resolve owing to a lack of geometric awareness. To…
This paper proposes a deep learning-based beamforming design framework that directly maps a target beam pattern to optimal beamforming vectors across multiple antenna array architectures, including digital, analog, and hybrid beamforming.…
Due to their radiation hardness, kilohertz frame rates, and high dynamic range, hybrid pixel detectors have recently expanded their application range to electron diffraction and recently also electron imaging. However, these detectors…
Dense image alignment from RGB-D images remains a critical issue for real-world applications, especially under challenging lighting conditions and in a wide baseline setting. In this paper, we propose a new framework to learn a pixel-wise…
Estimating the location and orientation of humans is an essential skill for service and assistive robots. To achieve a reliable estimation in a wide area such as an apartment, multiple RGBD cameras are frequently used. Firstly, these setups…
We propose a novel approach for joint 3D multi-object tracking and reconstruction from RGB-D sequences in indoor environments. To this end, we detect and reconstruct objects in each frame while predicting dense correspondences mappings into…
Millimeter-wave transceivers use large antenna arrays to form narrow high-directional beams and overcome severe attenuation. Narrow beams require large signaling overhead to be aligned if no prior information about beam directions is…
In this paper, we propose first a mmWave channel tracking algorithm based on multidimensional orthogonal matching pursuit algorithm (MOMP) using reduced sparsifying dictionaries, which exploits information from channel estimates in previous…
Determining accurate bird's eye view (BEV) positions of objects and tracks in a scene is vital for various perception tasks including object interactions mapping, scenario extraction etc., however, the level of supervision required to…
Today, most methods for image understanding tasks rely on feed-forward neural networks. While this approach has allowed for empirical accuracy, efficiency, and task adaptation via fine-tuning, it also comes with fundamental disadvantages.…
Visual scene understanding is an important capability that enables robots to purposefully act in their environment. In this paper, we propose a novel approach to object-class segmentation from multiple RGB-D views using deep learning. We…